Merge remote-tracking branch 'upstream/master' into feature/panneau-pocket-upstream

This commit is contained in:
Florent VIOLLEAU 2024-12-08 16:04:33 +01:00
commit 705ee2d051
330 changed files with 12069 additions and 11569 deletions

2
.gitattributes vendored
View File

@ -47,8 +47,6 @@ phpcs.xml export-ignore
phpcompatibility.xml export-ignore
tests/ export-ignore
cache/.gitkeep export-ignore
bridges/DemoBridge.php export-ignore
bridges/FeedExpanderExampleBridge.php export-ignore
## Composer
#

1
.github/.gitignore vendored
View File

@ -4,3 +4,4 @@
# Generated files
comment*.md
comment*.txt
*.html

89
.github/prtester.py vendored
View File

@ -4,7 +4,9 @@ import re
from bs4 import BeautifulSoup
from datetime import datetime
from typing import Iterable
import os.path
import os
import glob
import urllib
# This script is specifically written to be used in automation for https://github.com/RSS-Bridge/rss-bridge
#
@ -13,18 +15,33 @@ import os.path
# It also add a <base> tag with the url of em's public instance, so viewing
# the HTML file locally will actually work as designed.
ARTIFACT_FILE_EXTENSION = '.html'
class Instance:
name = ''
url = ''
def main(instances: Iterable[Instance], with_upload: bool, with_reduced_upload: bool, title: str, output_file: str):
start_date = datetime.now()
prid = os.getenv('PR')
artifact_base_url = f'https://rss-bridge.github.io/rss-bridge-tests/prs/{prid}'
artifact_directory = os.getcwd()
for file in glob.glob(f'*{ARTIFACT_FILE_EXTENSION}', root_dir=artifact_directory):
os.remove(file)
table_rows = []
for instance in instances:
page = requests.get(instance.url) # Use python requests to grab the rss-bridge main page
soup = BeautifulSoup(page.content, "html.parser") # use bs4 to turn the page into soup
bridge_cards = soup.select('.bridge-card') # get a soup-formatted list of all bridges on the rss-bridge page
table_rows += testBridges(instance, bridge_cards, with_upload, with_reduced_upload) # run the main scraping code with the list of bridges
table_rows += testBridges(
instance=instance,
bridge_cards=bridge_cards,
with_upload=with_upload,
with_reduced_upload=with_reduced_upload,
artifact_directory=artifact_directory,
artifact_base_url=artifact_base_url) # run the main scraping code with the list of bridges
with open(file=output_file, mode='w+', encoding='utf-8') as file:
table_rows_value = '\n'.join(sorted(table_rows))
file.write(f'''
@ -36,7 +53,7 @@ def main(instances: Iterable[Instance], with_upload: bool, with_reduced_upload:
*last change: {start_date.strftime("%A %Y-%m-%d %H:%M:%S")}*
'''.strip())
def testBridges(instance: Instance, bridge_cards: Iterable, with_upload: bool, with_reduced_upload: bool) -> Iterable:
def testBridges(instance: Instance, bridge_cards: Iterable, with_upload: bool, with_reduced_upload: bool, artifact_directory: str, artifact_base_url: str) -> Iterable:
instance_suffix = ''
if instance.name:
instance_suffix = f' ({instance.name})'
@ -45,15 +62,14 @@ def testBridges(instance: Instance, bridge_cards: Iterable, with_upload: bool, w
bridgeid = bridge_card.get('id')
bridgeid = bridgeid.split('-')[1] # this extracts a readable bridge name from the bridge metadata
print(f'{bridgeid}{instance_suffix}')
bridgestring = '/?action=display&bridge=' + bridgeid + '&format=Html'
bridge_name = bridgeid.replace('Bridge', '')
context_forms = bridge_card.find_all("form")
form_number = 1
for context_form in context_forms:
# a bridge can have multiple contexts, named 'forms' in html
# this code will produce a fully working formstring that should create a working feed when called
# this code will produce a fully working url that should create a working feed when called
# this will create an example feed for every single context, to test them all
formstring = ''
context_parameters = {}
error_messages = []
context_name = '*untitled*'
context_name_element = context_form.find_previous_sibling('h5')
@ -62,32 +78,33 @@ def testBridges(instance: Instance, bridge_cards: Iterable, with_upload: bool, w
parameters = context_form.find_all("input")
lists = context_form.find_all("select")
# this for/if mess cycles through all available input parameters, checks if it required, then pulls
# the default or examplevalue and then combines it all together into the formstring
# the default or examplevalue and then combines it all together into the url parameters
# if an example or default value is missing for a required attribute, it will throw an error
# any non-required fields are not tested!!!
for parameter in parameters:
if parameter.get('type') == 'hidden' and parameter.get('name') == 'context':
cleanvalue = parameter.get('value').replace(" ","+")
formstring = formstring + '&' + parameter.get('name') + '=' + cleanvalue
if parameter.get('type') == 'number' or parameter.get('type') == 'text':
parameter_type = parameter.get('type')
parameter_name = parameter.get('name')
if parameter_type == 'hidden':
context_parameters[parameter_name] = parameter.get('value')
if parameter_type == 'number' or parameter_type == 'text':
if parameter.has_attr('required'):
if parameter.get('placeholder') == '':
if parameter.get('value') == '':
name_value = parameter.get('name')
error_messages.append(f'Missing example or default value for parameter "{name_value}"')
error_messages.append(f'Missing example or default value for parameter "{parameter_name}"')
else:
formstring = formstring + '&' + parameter.get('name') + '=' + parameter.get('value')
context_parameters[parameter_name] = parameter.get('value')
else:
formstring = formstring + '&' + parameter.get('name') + '=' + parameter.get('placeholder')
# same thing, just for checkboxes. If a checkbox is checked per default, it gets added to the formstring
if parameter.get('type') == 'checkbox':
context_parameters[parameter_name] = parameter.get('placeholder')
# same thing, just for checkboxes. If a checkbox is checked per default, it gets added to the url parameters
if parameter_type == 'checkbox':
if parameter.has_attr('checked'):
formstring = formstring + '&' + parameter.get('name') + '=on'
context_parameters[parameter_name] = 'on'
for listing in lists:
selectionvalue = ''
listname = listing.get('name')
cleanlist = []
for option in listing.contents:
options = listing.find_all('option')
for option in options:
if 'optgroup' in option.name:
cleanlist.extend(option)
else:
@ -101,15 +118,21 @@ def testBridges(instance: Instance, bridge_cards: Iterable, with_upload: bool, w
if 'selected' in selectionentry.attrs:
selectionvalue = selectionentry.get('value')
break
formstring = formstring + '&' + listname + '=' + selectionvalue
termpad_url = 'about:blank'
context_parameters[listname] = selectionvalue
artifact_url = 'about:blank'
if error_messages:
status = '<br>'.join(map(lambda m: f'❌ `{m}`', error_messages))
else:
# if all example/default values are present, form the full request string, run the request, add a <base> tag with
# if all example/default values are present, form the full request url, run the request, add a <base> tag with
# the url of em's public instance to the response text (so that relative paths work, e.g. to the static css file) and
# then upload it to termpad.com, a pastebin-like-site.
response = requests.get(instance.url + bridgestring + formstring)
# then save it to a html file.
context_parameters.update({
'action': 'display',
'bridge': bridgeid,
'format': 'Html',
})
request_url = f'{instance.url}/?{urllib.parse.urlencode(context_parameters)}'
response = requests.get(request_url)
page_text = response.text.replace('<head>','<head><base href="https://rss-bridge.org/bridge01/" target="_blank">')
page_text = page_text.encode("utf_8")
soup = BeautifulSoup(page_text, "html.parser")
@ -133,16 +156,18 @@ def testBridges(instance: Instance, bridge_cards: Iterable, with_upload: bool, w
if status_is_ok:
status = '✔️'
if with_upload and (not with_reduced_upload or not status_is_ok):
termpad = requests.post(url="https://termpad.com/", data=page_text)
termpad_url = termpad.text.strip()
termpad_url = termpad_url.replace('termpad.com/','termpad.com/raw/')
table_rows.append(f'| {bridge_name} | [{form_number} {context_name}{instance_suffix}]({termpad_url}) | {status} |')
filename = f'{bridge_name} {form_number}{instance_suffix}{ARTIFACT_FILE_EXTENSION}'
filename = re.sub(r'[^a-z0-9 \_\-\.]', '', filename, flags=re.I).replace(' ', '_')
with open(file=f'{artifact_directory}/{filename}', mode='wb') as file:
file.write(page_text)
artifact_url = f'{artifact_base_url}/{filename}'
table_rows.append(f'| {bridge_name} | [{form_number} {context_name}{instance_suffix}]({artifact_url}) | {status} |')
form_number += 1
return table_rows
def getFirstLine(value: str) -> str:
# trim whitespace and remove text that can break the table or is simply unnecessary
clean_value = re.sub('^\[[^\]]+\]\s*rssbridge\.|[\|`]', '', value.strip())
clean_value = re.sub(r'^\[[^\]]+\]\s*rssbridge\.|[\|`]', '', value.strip())
first_line = next(iter(clean_value.splitlines()), '')
max_length = 250
if (len(first_line) > max_length):
@ -162,8 +187,8 @@ if __name__ == '__main__':
for instance_arg in args.instances:
instance_arg_parts = instance_arg.split('::')
instance = Instance()
instance.name = instance_arg_parts[1] if len(instance_arg_parts) >= 2 else ''
instance.url = instance_arg_parts[0]
instance.name = instance_arg_parts[1].strip() if len(instance_arg_parts) >= 2 else ''
instance.url = instance_arg_parts[0].strip().rstrip("/")
instances.append(instance)
else:
instance = Instance()
@ -180,4 +205,4 @@ if __name__ == '__main__':
with_reduced_upload=args.reduced_upload and not args.no_upload,
title=args.title,
output_file=args.output_file
);
);

View File

@ -21,7 +21,7 @@ jobs:
-
name: Docker meta
id: docker_meta
uses: docker/metadata-action@v4
uses: docker/metadata-action@v5
with:
images: |
${{ env.DOCKERHUB_SLUG }}
@ -33,26 +33,26 @@ jobs:
type=raw,value=stable,enable=${{ startsWith(github.ref, 'refs/tags/20') }}
-
name: Set up QEMU
uses: docker/setup-qemu-action@v2
uses: docker/setup-qemu-action@v3
-
name: Set up Docker Buildx
uses: docker/setup-buildx-action@v2
uses: docker/setup-buildx-action@v3
-
name: Login to DockerHub
uses: docker/login-action@v2
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
-
name: Login to GitHub Container Registry
uses: docker/login-action@v2
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
-
name: Build and push
uses: docker/bake-action@v2
uses: docker/bake-action@v5
with:
files: |
./docker-bake.hcl

View File

@ -9,7 +9,7 @@ jobs:
documentation:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- uses: actions/checkout@v4
with:
persist-credentials: false
- name: Setup PHP

View File

@ -13,7 +13,7 @@ jobs:
matrix:
php-versions: ['7.4']
steps:
- uses: actions/checkout@v3
- uses: actions/checkout@v4
- uses: shivammathur/setup-php@v2
with:
php-version: ${{ matrix.php-versions }}
@ -26,7 +26,7 @@ jobs:
matrix:
php-versions: ['7.4']
steps:
- uses: actions/checkout@v3
- uses: actions/checkout@v4
- uses: shivammathur/setup-php@v2
with:
php-version: ${{ matrix.php-versions }}
@ -38,7 +38,7 @@ jobs:
executable_php_files_check:
runs-on: ubuntu-20.04
steps:
- uses: actions/checkout@v3
- uses: actions/checkout@v4
- run: |
if find -name "*.php" -executable -type f -print -exec false {} +
then

View File

@ -5,15 +5,30 @@ on:
branches: [ master ]
jobs:
check-bridges:
name: Check if bridges were changed
runs-on: ubuntu-latest
outputs:
BRIDGES: ${{ steps.check1.outputs.BRIDGES }}
steps:
- name: Check number of bridges
id: check1
run: |
PR=${{github.event.number}};
wget https://patch-diff.githubusercontent.com/raw/$GITHUB_REPOSITORY/pull/$PR.patch;
bridgeamount=$(cat $PR.patch | grep "\bbridges/[A-Za-z0-9]*Bridge\.php\b" | sed "s=.*\bbridges/\([A-Za-z0-9]*\)Bridge\.php\b.*=\1=g" | sort | uniq | wc -l);
echo "BRIDGES=$bridgeamount" >> "$GITHUB_OUTPUT"
test-pr:
name: Generate HTML
runs-on: ubuntu-latest
needs: check-bridges
if: needs.check-bridges.outputs.BRIDGES > 0
env:
PYTHONUNBUFFERED: 1
# Needs additional permissions https://github.com/actions/first-interaction/issues/10#issuecomment-1041402989
steps:
- name: Check out self
uses: actions/checkout@v3
uses: actions/checkout@v4
with:
ref: ${{github.event.pull_request.head.ref}}
repository: ${{github.event.pull_request.head.repo.full_name}}
@ -33,9 +48,9 @@ jobs:
docker build -t prbuild .;
docker run -d -v $GITHUB_WORKSPACE/whitelist.txt:/app/whitelist.txt -v $GITHUB_WORKSPACE/DEBUG:/app/DEBUG -p 3001:80 prbuild
- name: Setup python
uses: actions/setup-python@v4
uses: actions/setup-python@v5
with:
python-version: '3.7'
python-version: '3.13'
cache: 'pip'
- name: Install requirements
run: |
@ -51,9 +66,17 @@ jobs:
body="${body//$'\n'/'%0A'}";
body="${body//$'\r'/'%0D'}";
echo "bodylength=${#body}" >> $GITHUB_OUTPUT
env:
PR: ${{ github.event.number }}
- name: Upload generated tests
uses: actions/upload-artifact@v4
id: upload-generated-tests
with:
name: tests
path: '*.html'
- name: Find Comment
if: ${{ steps.testrun.outputs.bodylength > 130 }}
uses: peter-evans/find-comment@v2
uses: peter-evans/find-comment@v3
id: fc
with:
issue-number: ${{ github.event.pull_request.number }}
@ -61,9 +84,43 @@ jobs:
body-includes: Pull request artifacts
- name: Create or update comment
if: ${{ steps.testrun.outputs.bodylength > 130 }}
uses: peter-evans/create-or-update-comment@v2
uses: peter-evans/create-or-update-comment@v4
with:
comment-id: ${{ steps.fc.outputs.comment-id }}
issue-number: ${{ github.event.pull_request.number }}
body-file: comment.txt
edit-mode: replace
upload_tests:
name: Upload tests
runs-on: ubuntu-latest
needs: test-pr
steps:
- uses: actions/checkout@v4
with:
repository: 'RSS-Bridge/rss-bridge-tests'
ref: 'main'
token: ${{ secrets.RSSTESTER_ACTION }}
- name: Setup git config
run: |
git config --global user.name "GitHub Actions"
git config --global user.email "<>"
- name: Download tests
uses: actions/download-artifact@v4
with:
name: tests
- name: Move tests
run: |
cd prs
mkdir -p ${{github.event.number}}
cd ${{github.event.number}}
mv -f $GITHUB_WORKSPACE/*.html .
- name: Commit and push generated tests
run: |
export COMMIT_MESSAGE="Added tests for PR ${{github.event.number}}"
git add .
git commit -m "$COMMIT_MESSAGE"
git push

View File

@ -13,9 +13,11 @@ jobs:
matrix:
php-versions: ['7.4', '8.0', '8.1']
steps:
- uses: actions/checkout@v3
- uses: actions/checkout@v4
- uses: shivammathur/setup-php@v2
with:
php-version: ${{ matrix.php-versions }}
env:
update: true
- run: composer install
- run: composer test

1
.gitignore vendored
View File

@ -6,7 +6,6 @@ data/
*.pydevproject
.project
.metadata
bin/
tmp/
*.tmp
*.bak

View File

@ -144,6 +144,7 @@
* [Niehztog](https://github.com/Niehztog)
* [NikNikYkt](https://github.com/NikNikYkt)
* [Nono-m0le](https://github.com/Nono-m0le)
* [NotsoanoNimus](https://github.com/NotsoanoNimus)
* [obsiwitch](https://github.com/obsiwitch)
* [Ololbu](https://github.com/Ololbu)
* [ORelio](https://github.com/ORelio)

View File

@ -1,5 +1,3 @@
FROM lwthiker/curl-impersonate:0.5-ff-slim-buster AS curlimpersonate
FROM debian:12-slim AS rssbridge
LABEL description="RSS-Bridge is a PHP project capable of generating RSS and Atom feeds for websites that don't have one."
@ -7,7 +5,8 @@ LABEL repository="https://github.com/RSS-Bridge/rss-bridge"
LABEL website="https://github.com/RSS-Bridge/rss-bridge"
ARG DEBIAN_FRONTEND=noninteractive
RUN apt-get update && \
RUN set -xe && \
apt-get update && \
apt-get install --yes --no-install-recommends \
ca-certificates \
nginx \
@ -24,21 +23,47 @@ RUN apt-get update && \
php-xml \
php-zip \
# php-zlib is enabled by default with PHP 8.2 in Debian 12
# for downloading libcurl-impersonate
curl \
&& \
# install curl-impersonate library
curlimpersonate_version=0.6.0 && \
{ \
{ \
[ $(arch) = 'aarch64' ] && \
archive="libcurl-impersonate-v${curlimpersonate_version}.aarch64-linux-gnu.tar.gz" && \
sha512sum="d04b1eabe71f3af06aa1ce99b39a49c5e1d33b636acedcd9fad163bc58156af5c3eb3f75aa706f335515791f7b9c7a6c40ffdfa47430796483ecef929abd905d" \
; } \
|| { \
[ $(arch) = 'armv7l' ] && \
archive="libcurl-impersonate-v${curlimpersonate_version}.arm-linux-gnueabihf.tar.gz" && \
sha512sum="05906b4efa1a6ed8f3b716fd83d476b6eea6bfc68e3dbc5212d65a2962dcaa7bd1f938c9096a7535252b11d1d08fb93adccc633585ff8cb8cec5e58bfe969bc9" \
; } \
|| { \
[ $(arch) = 'x86_64' ] && \
archive="libcurl-impersonate-v${curlimpersonate_version}.x86_64-linux-gnu.tar.gz" && \
sha512sum="480bbe9452cd9aff2c0daaaf91f1057b3a96385f79011628a9237223757a9b0d090c59cb5982dc54ea0d07191657299ea91ca170a25ced3d7d410fcdff130ace" \
; } \
} && \
curl -LO "https://github.com/lwthiker/curl-impersonate/releases/download/v${curlimpersonate_version}/${archive}" && \
echo "$sha512sum $archive" | sha512sum -c - && \
mkdir -p /usr/local/lib/curl-impersonate && \
tar xaf "$archive" -C /usr/local/lib/curl-impersonate --wildcards 'libcurl-impersonate-ff.so*' && \
rm "$archive" && \
apt-get purge --assume-yes curl && \
rm -rf /var/lib/apt/lists/*
ENV LD_PRELOAD /usr/local/lib/curl-impersonate/libcurl-impersonate-ff.so
ENV CURL_IMPERSONATE ff91esr
# logs should go to stdout / stderr
RUN ln -sfT /dev/stderr /var/log/nginx/error.log; \
ln -sfT /dev/stdout /var/log/nginx/access.log; \
chown -R --no-dereference www-data:adm /var/log/nginx/
COPY --from=curlimpersonate /usr/local/lib/libcurl-impersonate-ff.so /usr/local/lib/curl-impersonate/
ENV LD_PRELOAD /usr/local/lib/curl-impersonate/libcurl-impersonate-ff.so
ENV CURL_IMPERSONATE ff91esr
COPY ./config/nginx.conf /etc/nginx/sites-available/default
COPY ./config/php-fpm.conf /etc/php/8.2/fpm/pool.d/rss-bridge.conf
COPY ./config/php.ini /etc/php/8.2/fpm/conf.d/90-rss-bridge.conf
COPY ./config/php.ini /etc/php/8.2/fpm/conf.d/90-rss-bridge.ini
COPY --chown=www-data:www-data ./ /app/

296
README.md
View File

@ -2,16 +2,25 @@
![RSS-Bridge](static/logo_600px.png)
RSS-Bridge is a web application.
RSS-Bridge is a PHP web application.
It generates web feeds for websites that don't have one.
Officially hosted instance: https://rss-bridge.org/bridge01/
IRC channel #rssbridge at https://libera.chat/
[Full documentation](https://rss-bridge.github.io/rss-bridge/index.html)
Alternatively find another
[public instance](https://rss-bridge.github.io/rss-bridge/General/Public_Hosts.html).
Requires minimum PHP 7.4.
[![LICENSE](https://img.shields.io/badge/license-UNLICENSE-blue.svg)](UNLICENSE)
[![GitHub release](https://img.shields.io/github/release/rss-bridge/rss-bridge.svg?logo=github)](https://github.com/rss-bridge/rss-bridge/releases/latest)
[![irc.libera.chat](https://img.shields.io/badge/irc.libera.chat-%23rssbridge-blue.svg)](https://web.libera.chat/#rssbridge)
[![Chat on Matrix](https://matrix.to/img/matrix-badge.svg)](https://matrix.to/#/#rssbridge:libera.chat)
[![Actions Status](https://img.shields.io/github/actions/workflow/status/RSS-Bridge/rss-bridge/tests.yml?branch=master&label=GitHub%20Actions&logo=github)](https://github.com/RSS-Bridge/rss-bridge/actions)
|||
@ -19,9 +28,8 @@ Officially hosted instance: https://rss-bridge.org/bridge01/
|![Screenshot #1](/static/screenshot-1.png?raw=true)|![Screenshot #2](/static/screenshot-2.png?raw=true)|
|![Screenshot #3](/static/screenshot-3.png?raw=true)|![Screenshot #4](/static/screenshot-4.png?raw=true)|
|![Screenshot #5](/static/screenshot-5.png?raw=true)|![Screenshot #6](/static/screenshot-6.png?raw=true)|
|![Screenshot #7](/static/twitter-form.png?raw=true)|![Screenshot #8](/static/twitter-rasmus.png?raw=true)|
## A subset of bridges (17/412)
## A subset of bridges (16/447)
* `CssSelectorBridge`: [Scrape out a feed using CSS selectors](https://rss-bridge.org/bridge01/#bridge-CssSelectorBridge)
* `FeedMergeBridge`: [Combine multiple feeds into one](https://rss-bridge.org/bridge01/#bridge-FeedMergeBridge)
@ -36,75 +44,171 @@ Officially hosted instance: https://rss-bridge.org/bridge01/
* `ThePirateBayBridge:` [Fetches torrents by search/user/category](https://rss-bridge.org/bridge01/#bridge-ThePirateBayBridge)
* `TikTokBridge`: [Fetches posts by username](https://rss-bridge.org/bridge01/#bridge-TikTokBridge)
* `TwitchBridge`: [Fetches videos from channel](https://rss-bridge.org/bridge01/#bridge-TwitchBridge)
* `TwitterBridge`: [Fetches tweets](https://rss-bridge.org/bridge01/#bridge-TwitterBridge)
* `VkBridge`: [Fetches posts from user/group](https://rss-bridge.org/bridge01/#bridge-VkBridge)
* `XPathBridge`: [Scrape out a feed using XPath expressions](https://rss-bridge.org/bridge01/#bridge-XPathBridge)
* `YoutubeBridge`: [Fetches videos by username/channel/playlist/search](https://rss-bridge.org/bridge01/#bridge-YoutubeBridge)
* `YouTubeCommunityTabBridge`: [Fetches posts from a channel's community tab](https://rss-bridge.org/bridge01/#bridge-YouTubeCommunityTabBridge)
[Full documentation](https://rss-bridge.github.io/rss-bridge/index.html)
Check out RSS-Bridge right now on https://rss-bridge.org/bridge01/
Alternatively find another
[public instance](https://rss-bridge.github.io/rss-bridge/General/Public_Hosts.html).
## Tutorial
### Install with composer or git
### How to install on traditional shared web hosting
Requires minimum PHP 7.4.
RSS-Bridge can basically be unzipped into a web folder. Should be working instantly.
Latest zip:
https://github.com/RSS-Bridge/rss-bridge/archive/refs/heads/master.zip (2MB)
### How to install on Debian 12 (nginx + php-fpm)
These instructions have been tested on a fresh Debian 12 VM from Digital Ocean (1vcpu-512mb-10gb, 5 USD/month).
```shell
apt install nginx php-fpm php-mbstring php-simplexml php-curl
```
timedatectl set-timezone Europe/Oslo
apt install git nginx php8.2-fpm php-mbstring php-simplexml php-curl php-intl
# Create a user account
useradd --shell /bin/bash --create-home rss-bridge
```shell
cd /var/www
composer create-project -v --no-dev rss-bridge/rss-bridge
# Create folder and change ownership
mkdir rss-bridge && chown rss-bridge:rss-bridge rss-bridge/
# Become user
su rss-bridge
# Fetch latest master
git clone https://github.com/RSS-Bridge/rss-bridge.git rss-bridge/
cd rss-bridge
# Copy over the default config
cp -v config.default.ini.php config.ini.php
# Give full permissions only to owner (rss-bridge)
chmod 700 -R ./
# Give read and execute to others (nginx and php-fpm)
chmod o+rx ./ ./static
# Give read to others (nginx)
chmod o+r -R ./static
```
```shell
cd /var/www
git clone https://github.com/RSS-Bridge/rss-bridge.git
```
Config:
```shell
# Give the http user write permission to the cache folder
chown www-data:www-data /var/www/rss-bridge/cache
# Optionally copy over the default config file
cp config.default.ini.php config.ini.php
```
Example config for nginx:
Nginx config:
```nginx
# /etc/nginx/sites-enabled/rssbridge
# /etc/nginx/sites-enabled/rss-bridge.conf
server {
listen 80;
server_name example.com;
root /var/www/rss-bridge;
index index.php;
location ~ \.php$ {
# TODO: change to your own server name
server_name example.com;
access_log /var/log/nginx/rss-bridge.access.log;
error_log /var/log/nginx/rss-bridge.error.log;
log_not_found off;
# Intentionally not setting a root folder here
# autoindex is off by default but feels good to explicitly turn off
autoindex off;
# Static content only served here
location /static/ {
alias /var/www/rss-bridge/static/;
}
# Pass off to php-fpm when location is exactly /
location = / {
root /var/www/rss-bridge/;
include snippets/fastcgi-php.conf;
fastcgi_read_timeout 60s;
fastcgi_pass unix:/run/php/php-fpm.sock;
fastcgi_read_timeout 45s;
fastcgi_pass unix:/run/php/rss-bridge.sock;
}
# Reduce spam
location = /favicon.ico {
access_log off;
}
# Reduce spam
location = /robots.txt {
access_log off;
}
}
```
PHP FPM pool config:
```ini
; /etc/php/8.2/fpm/pool.d/rss-bridge.conf
[rss-bridge]
user = rss-bridge
group = rss-bridge
listen = /run/php/rss-bridge.sock
listen.owner = www-data
listen.group = www-data
# Create 10 workers standing by to serve requests
pm = static
pm.max_children = 10
# Respawn worker after 500 requests (workaround for memory leaks etc.)
pm.max_requests = 500
```
PHP ini config:
```ini
; /etc/php/8.2/fpm/conf.d/30-rss-bridge.ini
max_execution_time = 15
memory_limit = 64M
```
Restart fpm and nginx:
```shell
# Lint and restart php-fpm
php-fpm8.2 -t && systemctl restart php8.2-fpm
# Lint and restart nginx
nginx -t && systemctl restart nginx
```
### How to install from Composer
Install the latest release.
```shell
cd /var/www
composer create-project -v --no-dev --no-scripts rss-bridge/rss-bridge
```
### How to install with Caddy
TODO. See https://github.com/RSS-Bridge/rss-bridge/issues/3785
### Install from Docker Hub:
Install by downloading the docker image from Docker Hub:
```bash
# Create container
docker create --name=rss-bridge --publish 3000:80 rssbridge/rss-bridge
docker create --name=rss-bridge --publish 3000:80 --volume $(pwd)/config:/config rssbridge/rss-bridge
```
You can put custom `config.ini.php` and bridges into `./config`.
**You must restart container for custom changes to take effect.**
See `docker-entrypoint.sh` for details.
```bash
# Start container
docker start rss-bridge
```
@ -118,30 +222,29 @@ Browse http://localhost:3000/
docker build -t rss-bridge .
# Create container
docker create --name rss-bridge --publish 3000:80 rss-bridge
docker create --name rss-bridge --publish 3000:80 --volume $(pwd)/config:/config rss-bridge
```
You can put custom `config.ini.php` and bridges into `./config`.
**You must restart container for custom changes to take effect.**
See `docker-entrypoint.sh` for details.
```bash
# Start container
docker start rss-bridge
```
Browse http://localhost:3000/
### Install with docker-compose
### Install with docker-compose (using Docker Hub)
Create a `docker-compose.yml` file locally with with the following content:
```yml
version: '2'
services:
rss-bridge:
image: rssbridge/rss-bridge:latest
volumes:
- </local/custom/path>:/config
ports:
- 3000:80
restart: unless-stopped
```
You can put custom `config.ini.php` and bridges into `./config`.
Then launch with `docker-compose`:
**You must restart container for custom changes to take effect.**
See `docker-entrypoint.sh` for details.
```bash
docker-compose up
@ -156,7 +259,7 @@ Browse http://localhost:3000/
[![Deploy to Cloudron](https://cloudron.io/img/button.svg)](https://www.cloudron.io/store/com.rssbridgeapp.cloudronapp.html)
[![Run on PikaPods](https://www.pikapods.com/static/run-button.svg)](https://www.pikapods.com/pods?run=rssbridge)
The Heroku quick deploy currently does not work. It might possibly work if you fork this repo and
The Heroku quick deploy currently does not work. It might work if you fork this repo and
modify the `repository` in `scalingo.json`. See https://github.com/RSS-Bridge/rss-bridge/issues/2688
Learn more in
@ -164,6 +267,64 @@ Learn more in
## How-to
### How to fix "Access denied."
Output is from php-fpm. It is unable to read index.php.
chown rss-bridge:rss-bridge /var/www/rss-bridge/index.php
### How to password-protect the instance (token)
Modify `config.ini.php`:
[authentication]
token = "hunter2"
### How to remove all cache items
As current user:
bin/cache-clear
As user rss-bridge:
sudo -u rss-bridge bin/cache-clear
As root:
sudo bin/cache-clear
### How to remove all expired cache items
bin/cache-prune
### How to fix "PHP Fatal error: Uncaught Exception: The FileCache path is not writable"
```shell
# Give rss-bridge ownership
chown rss-bridge:rss-bridge -R /var/www/rss-bridge/cache
# Or, give www-data ownership
chown www-data:www-data -R /var/www/rss-bridge/cache
# Or, give everyone write permission
chmod 777 -R /var/www/rss-bridge/cache
# Or last ditch effort (CAREFUL)
rm -rf /var/www/rss-bridge/cache/ && mkdir /var/www/rss-bridge/cache/
```
### How to fix "attempt to write a readonly database"
The sqlite files (db, wal and shm) are not writeable.
chown -v rss-bridge:rss-bridge cache/*
### How to fix "Unable to prepare statement: 1, no such table: storage"
rm cache/*
### How to create a new bridge from scratch
Create the new bridge in e.g. `bridges/BearBlogBridge.php`:
@ -193,8 +354,6 @@ Learn more in [bridge api](https://rss-bridge.github.io/rss-bridge/Bridge_API/in
### How to enable all bridges
Modify `config.ini.php`:
enabled_bridges[] = *
### How to enable some bridges
@ -251,9 +410,7 @@ Modify `report_limit` so that an error must occur 3 times before it is reported.
The report count is reset to 0 each day.
### How to password-protect the instance
HTTP basic access authentication:
### How to password-protect the instance (HTTP Basic Auth)
[authentication]
@ -275,9 +432,20 @@ See `formats/PlaintextFormat.php` for an example.
These commands require that you have installed the dev dependencies in `composer.json`.
Run all tests:
./vendor/bin/phpunit
Run a single test class:
./vendor/bin/phpunit --filter UrlTest
Run linter:
./vendor/bin/phpcs --standard=phpcs.xml --warning-severity=0 --extensions=php -p ./
https://github.com/squizlabs/PHP_CodeSniffer/wiki
### How to spawn a minimal development environment
php -S 127.0.0.1:9001
@ -301,7 +469,7 @@ Cached files are deleted automatically after 24 hours.
RSS-Bridge allows you to take full control over which bridges are displayed to the user.
That way you can host your own RSS-Bridge service with your favorite collection of bridges!
Current maintainers (as of 2023): @dvikan and @Mynacol #2519
Current maintainers (as of 2024): @dvikan and @Mynacol #2519
## Reference

View File

@ -14,20 +14,21 @@ class ConnectivityAction implements ActionInterface
{
private BridgeFactory $bridgeFactory;
public function __construct()
{
$this->bridgeFactory = new BridgeFactory();
public function __construct(
BridgeFactory $bridgeFactory
) {
$this->bridgeFactory = $bridgeFactory;
}
public function execute(array $request)
public function __invoke(Request $request): Response
{
if (!Debug::isEnabled()) {
return new Response('This action is only available in debug mode!', 403);
}
$bridgeName = $request['bridge'] ?? null;
$bridgeName = $request->get('bridge');
if (!$bridgeName) {
return render_template('connectivity.html.php');
return new Response(render_template('connectivity.html.php'));
}
$bridgeClassName = $this->bridgeFactory->createBridgeClassName($bridgeName);
if (!$bridgeClassName) {
@ -54,8 +55,8 @@ class ConnectivityAction implements ActionInterface
];
try {
$response = getContents($bridge::URI, [], $curl_opts, true);
$result['http_code'] = $response['code'];
if (in_array($response['code'], [200])) {
$result['http_code'] = $response->getCode();
if (in_array($result['http_code'], [200])) {
$result['successful'] = true;
}
} catch (\Exception $e) {

View File

@ -2,40 +2,50 @@
class DetectAction implements ActionInterface
{
public function execute(array $request)
{
$targetURL = $request['url'] ?? null;
$format = $request['format'] ?? null;
private BridgeFactory $bridgeFactory;
if (!$targetURL) {
throw new \Exception('You must specify a url!');
public function __construct(
BridgeFactory $bridgeFactory
) {
$this->bridgeFactory = $bridgeFactory;
}
public function __invoke(Request $request): Response
{
$url = $request->get('url');
$format = $request->get('format');
if (!$url) {
return new Response(render(__DIR__ . '/../templates/error.html.php', ['message' => 'You must specify a url']));
}
if (!$format) {
throw new \Exception('You must specify a format!');
return new Response(render(__DIR__ . '/../templates/error.html.php', ['message' => 'You must specify a format']));
}
$bridgeFactory = new BridgeFactory();
foreach ($bridgeFactory->getBridgeClassNames() as $bridgeClassName) {
if (!$bridgeFactory->isEnabled($bridgeClassName)) {
foreach ($this->bridgeFactory->getBridgeClassNames() as $bridgeClassName) {
if (!$this->bridgeFactory->isEnabled($bridgeClassName)) {
continue;
}
$bridge = $bridgeFactory->create($bridgeClassName);
$bridge = $this->bridgeFactory->create($bridgeClassName);
$bridgeParams = $bridge->detectParameters($targetURL);
$bridgeParams = $bridge->detectParameters($url);
if (is_null($bridgeParams)) {
if (!$bridgeParams) {
continue;
}
$bridgeParams['bridge'] = $bridgeClassName;
$bridgeParams['format'] = $format;
$url = '?action=display&' . http_build_query($bridgeParams);
return new Response('', 301, ['location' => $url]);
$query = [
'action' => 'display',
'bridge' => $bridgeClassName,
'format' => $format,
];
$query = array_merge($query, $bridgeParams);
return new Response('', 301, ['location' => '?' . http_build_query($query)]);
}
throw new \Exception('No bridge found for given URL: ' . $targetURL);
return new Response(render(__DIR__ . '/../templates/error.html.php', [
'message' => 'No bridge found for given URL: ' . $url,
]));
}
}

View File

@ -4,58 +4,40 @@ class DisplayAction implements ActionInterface
{
private CacheInterface $cache;
private Logger $logger;
private BridgeFactory $bridgeFactory;
public function __construct()
{
$this->cache = RssBridge::getCache();
$this->logger = RssBridge::getLogger();
public function __construct(
CacheInterface $cache,
Logger $logger,
BridgeFactory $bridgeFactory
) {
$this->cache = $cache;
$this->logger = $logger;
$this->bridgeFactory = $bridgeFactory;
}
public function execute(array $request)
public function __invoke(Request $request): Response
{
if (Configuration::getConfig('system', 'enable_maintenance_mode')) {
return new Response(render(__DIR__ . '/../templates/error.html.php', [
'title' => '503 Service Unavailable',
'message' => 'RSS-Bridge is down for maintenance.',
]), 503);
}
$bridgeName = $request->get('bridge');
$format = $request->get('format');
$noproxy = $request->get('_noproxy');
$cacheKey = 'http_' . json_encode($request);
/** @var Response $cachedResponse */
$cachedResponse = $this->cache->get($cacheKey);
if ($cachedResponse) {
$ifModifiedSince = $_SERVER['HTTP_IF_MODIFIED_SINCE'] ?? null;
$lastModified = $cachedResponse->getHeader('last-modified');
if ($ifModifiedSince && $lastModified) {
$lastModified = new \DateTimeImmutable($lastModified);
$lastModifiedTimestamp = $lastModified->getTimestamp();
$modifiedSince = strtotime($ifModifiedSince);
if ($lastModifiedTimestamp <= $modifiedSince) {
$modificationTimeGMT = gmdate('D, d M Y H:i:s ', $lastModifiedTimestamp);
return new Response('', 304, ['last-modified' => $modificationTimeGMT . 'GMT']);
}
}
return $cachedResponse;
}
$bridgeName = $request['bridge'] ?? null;
if (!$bridgeName) {
return new Response(render(__DIR__ . '/../templates/error.html.php', ['message' => 'Missing bridge parameter']), 400);
}
$bridgeFactory = new BridgeFactory();
$bridgeClassName = $bridgeFactory->createBridgeClassName($bridgeName);
$bridgeClassName = $this->bridgeFactory->createBridgeClassName($bridgeName);
if (!$bridgeClassName) {
return new Response(render(__DIR__ . '/../templates/error.html.php', ['message' => 'Bridge not found']), 404);
}
$format = $request['format'] ?? null;
if (!$format) {
return new Response(render(__DIR__ . '/../templates/error.html.php', ['message' => 'You must specify a format']), 400);
}
if (!$bridgeFactory->isEnabled($bridgeClassName)) {
if (!$this->bridgeFactory->isEnabled($bridgeClassName)) {
return new Response(render(__DIR__ . '/../templates/error.html.php', ['message' => 'This bridge is not whitelisted']), 400);
}
$noproxy = $request['_noproxy'] ?? null;
// Disable proxy (if enabled and per user's request)
if (
Configuration::getConfig('proxy', 'url')
&& Configuration::getConfig('proxy', 'by_bridge')
@ -65,14 +47,14 @@ class DisplayAction implements ActionInterface
define('NOPROXY', true);
}
$bridge = $bridgeFactory->create($bridgeClassName);
$formatFactory = new FormatFactory();
$format = $formatFactory->create($format);
$cacheKey = 'http_' . json_encode($request->toArray());
$bridge = $this->bridgeFactory->create($bridgeClassName);
$response = $this->createResponse($request, $bridge, $format);
if ($response->getCode() === 200) {
$ttl = $request['_cache_timeout'] ?? null;
$ttl = $request->get('_cache_timeout');
if (Configuration::getConfig('cache', 'custom_timeout') && $ttl) {
$ttl = (int) $ttl;
} else {
@ -81,60 +63,48 @@ class DisplayAction implements ActionInterface
$this->cache->set($cacheKey, $response, $ttl);
}
if (in_array($response->getCode(), [403, 429, 503])) {
// Cache these responses for about ~20 mins on average
$this->cache->set($cacheKey, $response, 60 * 15 + rand(1, 60 * 10));
}
if ($response->getCode() === 500) {
$this->cache->set($cacheKey, $response, 60 * 15);
}
if (rand(1, 100) === 2) {
$this->cache->prune();
}
return $response;
}
private function createResponse(array $request, BridgeAbstract $bridge, FormatAbstract $format)
private function createResponse(Request $request, BridgeAbstract $bridge, string $format)
{
$items = [];
$infos = [];
try {
$bridge->loadConfiguration();
// Remove parameters that don't concern bridges
$input = array_diff_key($request, array_fill_keys(['action', 'bridge', 'format', '_noproxy', '_cache_timeout', '_error_time'], ''));
$remove = [
'token',
'action',
'bridge',
'format',
'_noproxy',
'_cache_timeout',
'_error_time',
'_', // Some RSS readers add a cache-busting parameter (_=<timestamp>) to feed URLs, detect and ignore them.
];
$requestArray = $request->toArray();
$input = array_diff_key($requestArray, array_fill_keys($remove, ''));
$bridge->setInput($input);
$bridge->collectData();
$items = $bridge->getItems();
if (isset($items[0]) && is_array($items[0])) {
$feedItems = [];
foreach ($items as $item) {
$feedItems[] = FeedItem::fromArray($item);
}
$items = $feedItems;
} catch (\Throwable $e) {
if ($e instanceof RateLimitException) {
// These are internally generated by bridges
$this->logger->info(sprintf('RateLimitException in DisplayAction(%s): %s', $bridge->getShortName(), create_sane_exception_message($e)));
return new Response(render(__DIR__ . '/../templates/exception.html.php', ['e' => $e]), 429);
}
$infos = [
'name' => $bridge->getName(),
'uri' => $bridge->getURI(),
'donationUri' => $bridge->getDonationURI(),
'icon' => $bridge->getIcon()
];
} catch (\Exception $e) {
if ($e instanceof HttpException) {
// Reproduce (and log) these responses regardless of error output and report limit
if ($e->getCode() === 429) {
$this->logger->info(sprintf('Exception in DisplayAction(%s): %s', $bridge->getShortName(), create_sane_exception_message($e)));
return new Response(render(__DIR__ . '/../templates/exception.html.php', ['e' => $e]), 429);
}
if ($e->getCode() === 503) {
$this->logger->info(sprintf('Exception in DisplayAction(%s): %s', $bridge->getShortName(), create_sane_exception_message($e)));
return new Response(render(__DIR__ . '/../templates/exception.html.php', ['e' => $e]), 503);
if (in_array($e->getCode(), [429, 503])) {
// Log with debug, immediately reproduce and return
$this->logger->debug(sprintf('Exception in DisplayAction(%s): %s', $bridge->getShortName(), create_sane_exception_message($e)));
return new Response(render(__DIR__ . '/../templates/exception.html.php', ['e' => $e]), $e->getCode());
}
// Some other status code which we let fail normally (but don't log it)
} else {
// Log error if it's not an HttpException
$this->logger->error(sprintf('Exception in DisplayAction(%s)', $bridge->getShortName()), ['e' => $e]);
}
$this->logger->error(sprintf('Exception in DisplayAction(%s)', $bridge->getShortName()), ['e' => $e]);
$errorOutput = Configuration::getConfig('error', 'output');
$reportLimit = Configuration::getConfig('error', 'report_limit');
$errorCount = 1;
@ -145,7 +115,7 @@ class DisplayAction implements ActionInterface
if ($errorCount >= $reportLimit) {
if ($errorOutput === 'feed') {
// Render the exception as a feed item
$items[] = $this->createFeedItemFromException($e, $bridge);
$items = [$this->createFeedItemFromException($e, $bridge)];
} elseif ($errorOutput === 'http') {
return new Response(render(__DIR__ . '/../templates/exception.html.php', ['e' => $e]), 500);
} elseif ($errorOutput === 'none') {
@ -154,38 +124,49 @@ class DisplayAction implements ActionInterface
}
}
$formatFactory = new FormatFactory();
$format = $formatFactory->create($format);
$format->setItems($items);
$format->setExtraInfos($infos);
$format->setFeed($bridge->getFeed());
$now = time();
$format->setLastModified($now);
$headers = [
'last-modified' => gmdate('D, d M Y H:i:s ', $now) . 'GMT',
'content-type' => $format->getMimeType() . '; charset=' . $format->getCharset(),
'content-type' => $format->getMimeType() . '; charset=UTF-8',
];
return new Response($format->stringify(), 200, $headers);
$body = $format->render();
// This is supposed to remove non-utf8 byte sequences, but I'm unsure if it works
ini_set('mbstring.substitute_character', 'none');
$body = mb_convert_encoding($body, 'UTF-8', 'UTF-8');
return new Response($body, 200, $headers);
}
private function createFeedItemFromException($e, BridgeAbstract $bridge): FeedItem
private function createFeedItemFromException($e, BridgeAbstract $bridge): array
{
$item = new FeedItem();
$item = [];
// Create a unique identifier every 24 hours
$uniqueIdentifier = urlencode((int)(time() / 86400));
$title = sprintf('Bridge returned error %s! (%s)', $e->getCode(), $uniqueIdentifier);
$item->setTitle($title);
$item->setURI(get_current_url());
$item->setTimestamp(time());
$item['title'] = $title;
$item['uri'] = get_current_url();
$item['timestamp'] = time();
// Create an item identifier for feed readers e.g. "staysafetv twitch videos_19389"
$item->setUid($bridge->getName() . '_' . $uniqueIdentifier);
$item['uid'] = $bridge->getName() . '_' . $uniqueIdentifier;
$content = render_template(__DIR__ . '/../templates/bridge-error.html.php', [
'error' => render_template(__DIR__ . '/../templates/exception.html.php', ['e' => $e]),
'searchUrl' => self::createGithubSearchUrl($bridge),
'issueUrl' => self::createGithubIssueUrl($bridge, $e, create_sane_exception_message($e)),
'issueUrl' => self::createGithubIssueUrl($bridge, $e),
'maintainer' => $bridge->getMaintainer(),
]);
$item->setContent($content);
$item['content'] = $content;
return $item;
}
@ -210,22 +191,34 @@ class DisplayAction implements ActionInterface
return $report['count'];
}
private static function createGithubIssueUrl($bridge, $e, string $message): string
private static function createGithubIssueUrl(BridgeAbstract $bridge, \Throwable $e): string
{
return sprintf('https://github.com/RSS-Bridge/rss-bridge/issues/new?%s', http_build_query([
'title' => sprintf('%s failed with error %s', $bridge->getName(), $e->getCode()),
$maintainer = $bridge->getMaintainer();
if (str_contains($maintainer, ',')) {
$maintainers = explode(',', $maintainer);
} else {
$maintainers = [$maintainer];
}
$maintainers = array_map('trim', $maintainers);
$queryString = $_SERVER['QUERY_STRING'] ?? '';
$query = [
'title' => $bridge->getName() . ' failed with: ' . $e->getMessage(),
'body' => sprintf(
"```\n%s\n\n%s\n\nQuery string: %s\nVersion: %s\nOs: %s\nPHP version: %s\n```",
$message,
"```\n%s\n\n%s\n\nQuery string: %s\nVersion: %s\nOs: %s\nPHP version: %s\n```\nMaintainer: @%s",
create_sane_exception_message($e),
implode("\n", trace_to_call_points(trace_from_exception($e))),
$_SERVER['QUERY_STRING'] ?? '',
$queryString,
Configuration::getVersion(),
PHP_OS_FAMILY,
phpversion() ?: 'Unknown'
phpversion() ?: 'Unknown',
implode(', @', $maintainers),
),
'labels' => 'Bridge-Broken',
'assignee' => $bridge->getMaintainer(),
]));
'assignee' => $maintainer[0],
];
return 'https://github.com/RSS-Bridge/rss-bridge/issues/new?' . http_build_query($query);
}
private static function createGithubSearchUrl($bridge): string

View File

@ -7,29 +7,35 @@
*/
class FindfeedAction implements ActionInterface
{
public function execute(array $request)
{
$targetURL = $request['url'] ?? null;
$format = $request['format'] ?? null;
private BridgeFactory $bridgeFactory;
if (!$targetURL) {
public function __construct(
BridgeFactory $bridgeFactory
) {
$this->bridgeFactory = $bridgeFactory;
}
public function __invoke(Request $request): Response
{
$url = $request->get('url');
$format = $request->get('format');
if (!$url) {
return new Response('You must specify a url', 400);
}
if (!$format) {
return new Response('You must specify a format', 400);
}
$bridgeFactory = new BridgeFactory();
$results = [];
foreach ($bridgeFactory->getBridgeClassNames() as $bridgeClassName) {
if (!$bridgeFactory->isEnabled($bridgeClassName)) {
foreach ($this->bridgeFactory->getBridgeClassNames() as $bridgeClassName) {
if (!$this->bridgeFactory->isEnabled($bridgeClassName)) {
continue;
}
$bridge = $bridgeFactory->create($bridgeClassName);
$bridge = $this->bridgeFactory->create($bridgeClassName);
$bridgeParams = $bridge->detectParameters($targetURL);
$bridgeParams = $bridge->detectParameters($url);
if ($bridgeParams === null) {
continue;

View File

@ -2,44 +2,48 @@
final class FrontpageAction implements ActionInterface
{
public function execute(array $request)
private BridgeFactory $bridgeFactory;
public function __construct(
BridgeFactory $bridgeFactory
) {
$this->bridgeFactory = $bridgeFactory;
}
public function __invoke(Request $request): Response
{
$token = $request->attribute('token');
$messages = [];
$showInactive = (bool) ($request['show_inactive'] ?? null);
$activeBridges = 0;
$bridgeFactory = new BridgeFactory();
$bridgeClassNames = $bridgeFactory->getBridgeClassNames();
$bridgeClassNames = $this->bridgeFactory->getBridgeClassNames();
foreach ($bridgeFactory->getMissingEnabledBridges() as $missingEnabledBridge) {
foreach ($this->bridgeFactory->getMissingEnabledBridges() as $missingEnabledBridge) {
$messages[] = [
'body' => sprintf('Warning : Bridge "%s" not found', $missingEnabledBridge),
'level' => 'warning'
];
}
$formatFactory = new FormatFactory();
$formats = $formatFactory->getFormatNames();
$body = '';
foreach ($bridgeClassNames as $bridgeClassName) {
if ($bridgeFactory->isEnabled($bridgeClassName)) {
$body .= BridgeCard::displayBridgeCard($bridgeClassName, $formats);
if ($this->bridgeFactory->isEnabled($bridgeClassName)) {
$body .= BridgeCard::render($this->bridgeFactory, $bridgeClassName, $token);
$activeBridges++;
} elseif ($showInactive) {
$body .= BridgeCard::displayBridgeCard($bridgeClassName, $formats, false) . PHP_EOL;
}
}
// todo: cache this renderered template
return render(__DIR__ . '/../templates/frontpage.html.php', [
'messages' => $messages,
'admin_email' => Configuration::getConfig('admin', 'email'),
'admin_telegram' => Configuration::getConfig('admin', 'telegram'),
'bridges' => $body,
'active_bridges' => $activeBridges,
'total_bridges' => count($bridgeClassNames),
'show_inactive' => $showInactive,
]);
$response = new Response(render(__DIR__ . '/../templates/frontpage.html.php', [
'messages' => $messages,
'admin_email' => Configuration::getConfig('admin', 'email'),
'admin_telegram' => Configuration::getConfig('admin', 'telegram'),
'bridges' => $body,
'active_bridges' => $activeBridges,
'total_bridges' => count($bridgeClassNames),
]));
// TODO: The rendered template could be cached, but beware config changes that changes the html
return $response;
}
}

View File

@ -4,7 +4,7 @@ declare(strict_types=1);
class HealthAction implements ActionInterface
{
public function execute(array $request)
public function __invoke(Request $request): Response
{
$response = [
'code' => 200,

View File

@ -2,19 +2,25 @@
class ListAction implements ActionInterface
{
public function execute(array $request)
private BridgeFactory $bridgeFactory;
public function __construct(
BridgeFactory $bridgeFactory
) {
$this->bridgeFactory = $bridgeFactory;
}
public function __invoke(Request $request): Response
{
$list = new \stdClass();
$list->bridges = [];
$list->total = 0;
$bridgeFactory = new BridgeFactory();
foreach ($bridgeFactory->getBridgeClassNames() as $bridgeClassName) {
$bridge = $bridgeFactory->create($bridgeClassName);
foreach ($this->bridgeFactory->getBridgeClassNames() as $bridgeClassName) {
$bridge = $this->bridgeFactory->create($bridgeClassName);
$list->bridges[$bridgeClassName] = [
'status' => $bridgeFactory->isEnabled($bridgeClassName) ? 'active' : 'inactive',
'status' => $this->bridgeFactory->isEnabled($bridgeClassName) ? 'active' : 'inactive',
'uri' => $bridge->getURI(),
'donationUri' => $bridge->getDonationURI(),
'name' => $bridge->getName(),

View File

@ -1,46 +0,0 @@
<?php
class SetBridgeCacheAction implements ActionInterface
{
private CacheInterface $cache;
public function __construct()
{
$this->cache = RssBridge::getCache();
}
public function execute(array $request)
{
$authenticationMiddleware = new ApiAuthenticationMiddleware();
$authenticationMiddleware($request);
$key = $request['key'] ?? null;
if (!$key) {
returnClientError('You must specify key!');
}
$bridgeFactory = new BridgeFactory();
$bridgeName = $request['bridge'] ?? null;
$bridgeClassName = $bridgeFactory->createBridgeClassName($bridgeName);
if (!$bridgeClassName) {
throw new \Exception(sprintf('Bridge not found: %s', $bridgeName));
}
// whitelist control
if (!$bridgeFactory->isEnabled($bridgeClassName)) {
throw new \Exception('This bridge is not whitelisted', 401);
}
$bridge = $bridgeFactory->create($bridgeClassName);
$bridge->loadConfiguration();
$value = $request['value'];
$cacheKey = get_class($bridge) . '_' . $key;
$ttl = 86400 * 3;
$this->cache->set($cacheKey, $value, $ttl);
header('Content-Type: text/plain');
echo 'done';
}
}

16
bin/cache-clear Executable file
View File

@ -0,0 +1,16 @@
#!/usr/bin/env php
<?php
/**
* Remove all items from the cache
*/
require __DIR__ . '/../lib/bootstrap.php';
require __DIR__ . '/../lib/config.php';
$container = require __DIR__ . '/../lib/dependencies.php';
/** @var CacheInterface $cache */
$cache = $container['cache'];
$cache->clear();

24
bin/cache-prune Executable file
View File

@ -0,0 +1,24 @@
#!/usr/bin/env php
<?php
/**
* Remove all expired items from the cache
*/
require __DIR__ . '/../lib/bootstrap.php';
require __DIR__ . '/../lib/config.php';
$container = require __DIR__ . '/../lib/dependencies.php';
if (
Configuration::getConfig('cache', 'type') === 'file'
&& !Configuration::getConfig('FileCache', 'enable_purge')
) {
// Override enable_purge for this particular execution
Configuration::setConfig('FileCache', 'enable_purge', true);
}
/** @var CacheInterface $cache */
$cache = $container['cache'];
$cache->prune();

20
bin/test Executable file
View File

@ -0,0 +1,20 @@
#!/usr/bin/env php
<?php
/**
* Add log records to all three levels (for testing purposes)
*/
require __DIR__ . '/../lib/bootstrap.php';
require __DIR__ . '/../lib/config.php';
$container = require __DIR__ . '/../lib/dependencies.php';
/** @var Logger $logger */
$logger = $container['logger'];
$logger->debug('This is a test debug message');
$logger->info('This is a test info message');
$logger->error('This is a test error message');

View File

@ -31,17 +31,17 @@ class ABCNewsBridge extends BridgeAbstract
{
$url = sprintf('https://www.abc.net.au/news/%s', $this->getInput('topic'));
$dom = getSimpleHTMLDOM($url);
$dom = $dom->find('div[data-component="CardList"]', 0);
$dom = $dom->find('div[data-component="PaginationList"]', 0);
if (!$dom) {
throw new \Exception(sprintf('Unable to find css selector on `%s`', $url));
}
$dom = defaultLinkTo($dom, $this->getURI());
foreach ($dom->find('div[data-component="GenericCard"]') as $article) {
foreach ($dom->find('article[data-component="DetailCard"]') as $article) {
$a = $article->find('a', 0);
$this->items[] = [
'title' => $a->plaintext,
'uri' => $a->href,
'content' => $article->find('[data-component="CardDescription"]', 0)->plaintext,
'content' => $article->find('p', 0)->plaintext,
'timestamp' => strtotime($article->find('time', 0)->datetime),
];
}

View File

@ -12,9 +12,22 @@ class AO3Bridge extends BridgeAbstract
'url' => [
'name' => 'url',
'required' => true,
// Example: F/F tag, complete works only
'exampleValue' => 'https://archiveofourown.org/works?work_search[complete]=T&tag_id=F*s*F',
// Example: F/F tag
'exampleValue' => 'https://archiveofourown.org/tags/F*s*F/works',
],
'range' => [
'name' => 'Chapter Content',
'title' => 'Chapter(s) to include in each work\'s feed entry',
'defaultValue' => null,
'type' => 'list',
'values' => [
'None' => null,
'First' => 'first',
'Latest' => 'last',
'Entire work' => 'all',
],
],
'limit' => self::LIMIT,
],
'Bookmarks' => [
'user' => [
@ -39,18 +52,13 @@ class AO3Bridge extends BridgeAbstract
{
switch ($this->queriedContext) {
case 'Bookmarks':
$user = $this->getInput('user');
$this->title = $user;
$url = self::URI
. '/users/' . $user
. '/bookmarks?bookmark_search[sort_column]=bookmarkable_date';
$this->collectList($url);
$this->collectList($this->getURI());
break;
case 'List':
$this->collectList($this->getInput('url'));
$this->collectList($this->getURI());
break;
case 'Work':
$this->collectWork($this->getInput('id'));
$this->collectWork($this->getURI());
break;
}
}
@ -61,9 +69,24 @@ class AO3Bridge extends BridgeAbstract
*/
private function collectList($url)
{
$html = getSimpleHTMLDOM($url);
$version = 'v0.0.1';
$headers = [
"useragent: rss-bridge $version (https://github.com/RSS-Bridge/rss-bridge)"
];
$response = getContents($url, $headers);
$html = \str_get_html($response);
$html = defaultLinkTo($html, self::URI);
// Get list title. Will include page range + count in some cases
$heading = ($html->find('#main h2', 0));
if ($heading->find('a.tag')) {
$heading = $heading->find('a.tag', 0);
}
$this->title = $heading->plaintext;
$limit = $this->getInput('limit') ?? 3;
$count = 0;
foreach ($html->find('.index.group > li') as $element) {
$item = [];
@ -72,17 +95,66 @@ class AO3Bridge extends BridgeAbstract
continue; // discard deleted works
}
$item['title'] = $title->plaintext;
$item['content'] = $element;
$item['uri'] = $title->href;
$strdate = $element->find('div p.datetime', 0)->plaintext;
$item['timestamp'] = strtotime($strdate);
// detach from rest of page because remove() is buggy
$element = str_get_html($element->outertext());
$tags = $element->find('ul.required-tags', 0);
foreach ($tags->childNodes() as $tag) {
$item['categories'][] = html_entity_decode($tag->plaintext);
}
$tags->remove();
$tags = $element->find('ul.tags', 0);
foreach ($tags->childNodes() as $tag) {
$item['categories'][] = html_entity_decode($tag->plaintext);
}
$tags->remove();
$item['content'] = implode('', $element->childNodes());
$chapters = $element->find('dl dd.chapters', 0);
// bookmarked series and external works do not have a chapters count
$chapters = (isset($chapters) ? $chapters->plaintext : 0);
$item['uid'] = $item['uri'] . "/$strdate/$chapters";
// Fetch workskin of desired chapter(s) in list
if ($this->getInput('range') && ($limit == 0 || $count++ < $limit)) {
$url = $item['uri'];
switch ($this->getInput('range')) {
case ('all'):
$url .= '?view_full_work=true';
break;
case ('first'):
break;
case ('last'):
// only way to get this is using the navigate page unfortunately
$url .= '/navigate';
$response = getContents($url, $headers);
$html = \str_get_html($response);
$html = defaultLinkTo($html, self::URI);
$url = $html->find('ol.index.group > li > a', -1)->href;
break;
}
$response = getContents($url, $headers);
$html = \str_get_html($response);
$html = defaultLinkTo($html, self::URI);
// remove duplicate fic summary
if ($ficsum = $html->find('#workskin > .preface > .summary', 0)) {
$ficsum->remove();
}
$item['content'] .= $html->find('#workskin', 0);
}
// Use predictability of download links to generate enclosures
$wid = explode('/', $item['uri'])[4];
foreach (['azw3', 'epub', 'mobi', 'pdf', 'html'] as $ext) {
$item['enclosures'][] = 'https://archiveofourown.org/downloads/' . $wid . '/work.' . $ext;
}
$this->items[] = $item;
}
}
@ -90,26 +162,31 @@ class AO3Bridge extends BridgeAbstract
/**
* Feed for recent chapters of a specific work.
*/
private function collectWork($id)
private function collectWork($url)
{
$url = self::URI . "/works/$id/navigate";
$httpClient = RssBridge::getHttpClient();
$version = 'v0.0.1';
$response = $httpClient->request($url, [
'useragent' => "rss-bridge $version (https://github.com/RSS-Bridge/rss-bridge)",
]);
$headers = [
"useragent: rss-bridge $version (https://github.com/RSS-Bridge/rss-bridge)"
];
$response = getContents($url . '/navigate', $headers);
$html = \str_get_html($response->getBody());
$html = \str_get_html($response);
$html = defaultLinkTo($html, self::URI);
$response = getContents($url . '?view_full_work=true', $headers);
$workhtml = \str_get_html($response);
$workhtml = defaultLinkTo($workhtml, self::URI);
$this->title = $html->find('h2 a', 0)->plaintext;
foreach ($html->find('ol.index.group > li') as $element) {
$nav = $html->find('ol.index.group > li');
for ($i = 0; $i < count($nav); $i++) {
$item = [];
$element = $nav[$i];
$item['title'] = $element->find('a', 0)->plaintext;
$item['content'] = $element;
$item['content'] = $workhtml->find('#chapter-' . ($i + 1), 0);
$item['uri'] = $element->find('a', 0)->href;
$strdate = $element->find('span.datetime', 0)->plaintext;
@ -138,4 +215,24 @@ class AO3Bridge extends BridgeAbstract
{
return self::URI . '/favicon.ico';
}
public function getURI()
{
$url = parent::getURI();
switch ($this->queriedContext) {
case 'Bookmarks':
$user = $this->getInput('user');
$url = self::URI
. '/users/' . $user
. '/bookmarks?bookmark_search[sort_column]=bookmarkable_date';
break;
case 'List':
$url = $this->getInput('url');
break;
case 'Work':
$url = self::URI . '/works/' . $this->getInput('id');
break;
}
return $url;
}
}

View File

@ -63,11 +63,13 @@ class ARDAudiothekBridge extends BridgeAbstract
public function collectData()
{
$oldTz = date_default_timezone_get();
$path = $this->getInput('path');
$limit = $this->getInput('limit');
$oldTz = date_default_timezone_get();
date_default_timezone_set('Europe/Berlin');
$pathComponents = explode('/', $this->getInput('path'));
$pathComponents = explode('/', $path);
if (empty($pathComponents)) {
returnClientError('Path may not be empty');
}
@ -82,17 +84,21 @@ class ARDAudiothekBridge extends BridgeAbstract
}
$url = self::APIENDPOINT . 'programsets/' . $showID . '/';
$rawJSON = getContents($url);
$processedJSON = json_decode($rawJSON)->data->programSet;
$json1 = getContents($url);
$data1 = Json::decode($json1, false);
$processedJSON = $data1->data->programSet;
if (!$processedJSON) {
throw new \Exception('Unable to find show id: ' . $showID);
}
$limit = $this->getInput('limit');
$answerLength = 1;
$offset = 0;
$numberOfElements = 1;
while ($answerLength != 0 && $offset < $numberOfElements && (is_null($limit) || $offset < $limit)) {
$rawJSON = getContents($url . '?offset=' . $offset);
$processedJSON = json_decode($rawJSON)->data->programSet;
$json2 = getContents($url . '?offset=' . $offset);
$data2 = Json::decode($json2, false);
$processedJSON = $data2->data->programSet;
$answerLength = count($processedJSON->items->nodes);
$offset = $offset + $answerLength;
@ -119,6 +125,10 @@ class ARDAudiothekBridge extends BridgeAbstract
$item['categories'] = [$category];
}
$item['itunes'] = [
'duration' => $audio->duration,
];
$this->items[] = $item;
}
}

View File

@ -40,6 +40,11 @@ class ARDMediathekBridge extends BridgeAbstract
* @const IMAGEWIDTHPLACEHOLDER
*/
const IMAGEWIDTHPLACEHOLDER = '{width}';
/**
* Title of the current show
* @var string
*/
private $title;
const PARAMETERS = [
[
@ -72,7 +77,7 @@ class ARDMediathekBridge extends BridgeAbstract
}
}
$url = self::APIENDPOINT . $showID . '/?pageSize=' . self::PAGESIZE;
$url = self::APIENDPOINT . $showID . '?pageSize=' . self::PAGESIZE;
$rawJSON = getContents($url);
$processedJSON = json_decode($rawJSON);
@ -93,6 +98,17 @@ class ARDMediathekBridge extends BridgeAbstract
$this->items[] = $item;
}
$this->title = $processedJSON->title;
date_default_timezone_set($oldTz);
}
/** {@inheritdoc} */
public function getName()
{
if (!empty($this->title)) {
return $this->title;
}
return parent::getName();
}
}

View File

@ -0,0 +1,45 @@
<?php
class ActivisionResearchBridge extends BridgeAbstract
{
const NAME = 'Activision Research Blog';
const URI = 'https://research.activision.com';
const DESCRIPTION = 'Posts from the Activision Research blog';
const MAINTAINER = 'thefranke';
const CACHE_TIMEOUT = 86400; // 24h
public function collectData()
{
$dom = getSimpleHTMLDOM(static::URI);
$dom = $dom->find('div[id="home-blog-feed"]', 0);
if (!$dom) {
throw new \Exception(sprintf('Unable to find css selector on `%s`', $url));
}
$dom = defaultLinkTo($dom, $this->getURI());
foreach ($dom->find('div[class="blog-entry"]') as $article) {
$a = $article->find('a', 0);
$blogimg = extractFromDelimiters($article->find('div[class="blog-img"]', 0)->style, 'url(', ')');
$title = htmlspecialchars_decode($article->find('div[class="title"]', 0)->plaintext);
$author = htmlspecialchars_decode($article->find('div[class="author]', 0)->plaintext);
$date = $article->find('div[class="pubdate"]', 0)->plaintext;
$entry = getSimpleHTMLDOMCached($a->href, static::CACHE_TIMEOUT * 7 * 4);
$entry = defaultLinkTo($entry, $this->getURI());
$content = $entry->find('div[class="blog-body"]', 0);
$tagsremove = ['script', 'iframe', 'input', 'form'];
$content = sanitize($content, $tagsremove);
$content = '<img src="' . static::URI . $blogimg . '" alt="">' . $content;
$this->items[] = [
'title' => $title,
'author' => $author,
'uri' => $a->href,
'content' => $content,
'timestamp' => strtotime($date),
];
}
}
}

View File

@ -13,12 +13,9 @@ class AllegroBridge extends BridgeAbstract
'exampleValue' => 'https://allegro.pl/kategoria/swieze-warzywa-cebula-318660',
'required' => true,
],
'sessioncookie' => [
'name' => 'The \'wdctx\' session cookie',
'title' => 'Paste the value of the \'wdctx\' cookie from your browser if you want to prevent Allegro imposing rate limits',
'pattern' => '^.{70,};?$',
// phpcs:ignore
'exampleValue' => 'v4.1-oCrmXTMqv2ppC21GTUCKLmUwRPP1ssQVALKuqwsZ1VXjcKgL2vO5TTRM5xMxS9GiyqxF1gAeyc-63dl0coUoBKXCXi_nAmr95yyqGpq2RAFoneZ4L399E8n6iYyemcuGARjAoSfjvLHJCEwvvHHynSgaxlFBu7hUnKfuy39zo9sSQdyTUjotJg3CAZ53q9v2raAnPCyGOAR4ytRILd9p24EJnxp7_oR0XbVPIo1hDa4WmjXFOxph8rHaO5tWd',
'cookie' => [
'name' => 'The complete cookie value',
'title' => 'Paste the value of the cookie value from your browser if you want to prevent Allegro imposing rate limits',
'required' => false,
],
'includeSponsoredOffers' => [
@ -35,10 +32,23 @@ class AllegroBridge extends BridgeAbstract
public function getName()
{
parse_str(parse_url($this->getInput('url'), PHP_URL_QUERY), $fields);
$url = $this->getInput('url');
if (!$url) {
return parent::getName();
}
$parsedUrl = parse_url($url, PHP_URL_QUERY);
if (!$parsedUrl) {
return parent::getName();
}
parse_str($parsedUrl, $fields);
if ($query = array_key_exists('string', $fields) ? urldecode($fields['string']) : false) {
return $query;
if (array_key_exists('string', $fields)) {
$f = urldecode($fields['string']);
} else {
$f = false;
}
if ($f) {
return $f;
}
return parent::getName();
@ -57,9 +67,9 @@ class AllegroBridge extends BridgeAbstract
$opts = [];
// If a session cookie is provided
if ($sessioncookie = $this->getInput('sessioncookie')) {
$opts[CURLOPT_COOKIE] = 'wdctx=' . $sessioncookie;
// If a cookie is provided
if ($cookie = $this->getInput('cookie')) {
$opts[CURLOPT_COOKIE] = $cookie;
}
$html = getSimpleHTMLDOM($url, [], $opts);
@ -71,11 +81,11 @@ class AllegroBridge extends BridgeAbstract
$results = $html->find('article[data-analytics-view-custom-context="REGULAR"]');
if (!$this->getInput('includeSponsoredOffers')) {
if ($this->getInput('includeSponsoredOffers')) {
$results = array_merge($results, $html->find('article[data-analytics-view-custom-context="SPONSORED"]'));
}
if (!$this->getInput('includePromotedOffers')) {
if ($this->getInput('includePromotedOffers')) {
$results = array_merge($results, $html->find('article[data-analytics-view-custom-context="PROMOTED"]'));
}

278
bridges/AnfrBridge.php Normal file
View File

@ -0,0 +1,278 @@
<?php
class AnfrBridge extends BridgeAbstract
{
const NAME = 'ANFR';
const URI = 'https://data.anfr.fr/';
const DESCRIPTION = 'Fetches data from the French administration "Agence Nationale des Fréquences".';
const CACHE_TIMEOUT = 604800; // 7d
const MAINTAINER = 'quent1';
const PARAMETERS = [
'Données sur les réseaux mobiles' => [
'departement' => [
'name' => 'Département',
'type' => 'list',
'values' => [
'Tous' => null,
'Ain' => '001',
'Aisne' => '002',
'Allier' => '003',
'Alpes-de-Haute-Provence' => '004',
'Hautes-Alpes' => '005',
'Alpes-Maritimes' => '006',
'Ardèche' => '007',
'Ardennes' => '008',
'Ariège' => '009',
'Aube' => '010',
'Aude' => '011',
'Aveyron' => '012',
'Bouches-du-Rhône' => '013',
'Calvados' => '014',
'Cantal' => '015',
'Charente' => '016',
'Charente-Maritime' => '017',
'Cher' => '018',
'Corrèze' => '019',
'Corse-du-Sud' => '02A',
'Haute-Corse' => '02B',
'Côte-d\'Or' => '021',
'Côtes-d\'Armor' => '022',
'Creuse' => '023',
'Dordogne' => '024',
'Doubs' => '025',
'Drôme' => '026',
'Eure' => '027',
'Eure-et-Loir' => '028',
'Finistère' => '029',
'Gard' => '030',
'Haute-Garonne' => '031',
'Gers' => '032',
'Gironde' => '033',
'Hérault' => '034',
'Ille-et-Vilaine' => '035',
'Indre' => '036',
'Indre-et-Loire' => '037',
'Isère' => '038',
'Jura' => '039',
'Landes' => '040',
'Loir-et-Cher' => '041',
'Loire' => '042',
'Haute-Loire' => '043',
'Loire-Atlantique' => '044',
'Loiret' => '045',
'Lot' => '046',
'Lot-et-Garonne' => '047',
'Lozère' => '048',
'Maine-et-Loire' => '049',
'Manche' => '050',
'Marne' => '051',
'Haute-Marne' => '052',
'Mayenne' => '053',
'Meurthe-et-Moselle' => '054',
'Meuse' => '055',
'Morbihan' => '056',
'Moselle' => '057',
'Nièvre' => '058',
'Nord' => '059',
'Oise' => '060',
'Orne' => '061',
'Pas-de-Calais' => '062',
'Puy-de-Dôme' => '063',
'Pyrénées-Atlantiques' => '064',
'Hautes-Pyrénées' => '065',
'Pyrénées-Orientales' => '066',
'Bas-Rhin' => '067',
'Haut-Rhin' => '068',
'Rhône' => '069',
'Haute-Saône' => '070',
'Saône-et-Loire' => '071',
'Sarthe' => '072',
'Savoie' => '073',
'Haute-Savoie' => '074',
'Paris' => '075',
'Seine-Maritime' => '076',
'Seine-et-Marne' => '077',
'Yvelines' => '078',
'Deux-Sèvres' => '079',
'Somme' => '080',
'Tarn' => '081',
'Tarn-et-Garonne' => '082',
'Var' => '083',
'Vaucluse' => '084',
'Vendée' => '085',
'Vienne' => '086',
'Haute-Vienne' => '087',
'Vosges' => '088',
'Yonne' => '089',
'Territoire de Belfort' => '090',
'Essonne' => '091',
'Hauts-de-Seine' => '092',
'Seine-Saint-Denis' => '093',
'Val-de-Marne' => '094',
'Val-d\'Oise' => '095',
'Guadeloupe' => '971',
'Martinique' => '972',
'Guyane' => '973',
'La Réunion' => '974',
'Saint-Pierre-et-Miquelon' => '975',
'Mayotte' => '976',
'Saint-Barthélemy' => '977',
'Saint-Martin' => '978',
'Terres australes et antarctiques françaises' => '984',
'Wallis-et-Futuna' => '986',
'Polynésie française' => '987',
'Nouvelle-Calédonie' => '988',
'Île de Clipperton' => '989'
]
],
'generation' => [
'name' => 'Génération',
'type' => 'list',
'values' => [
'Tous' => null,
'2G' => '2G',
'3G' => '3G',
'4G' => '4G',
'5G' => '5G',
]
],
'operateur' => [
'name' => 'Opérateur',
'type' => 'list',
'values' => [
'Tous' => null,
'Bouygues Télécom' => 'BOUYGUES TELECOM',
'Dauphin Télécom' => 'DAUPHIN TELECOM',
'Digiciel' => 'DIGICEL',
'Free Caraïbes' => 'FREE CARAIBES',
'Free Mobile' => 'FREE MOBILE',
'GLOBALTEL' => 'GLOBALTEL',
'Office des postes et télécommunications de Nouvelle Calédonie' => 'Gouv Nelle Calédonie (OPT)',
'Maore Mobile' => 'MAORE MOBILE',
'ONATi' => 'ONATI',
'Orange' => 'ORANGE',
'Outremer Telecom' => 'OUTREMER TELECOM',
'Vodafone polynésie' => 'PMT/VODAPHONE',
'SFR' => 'SFR',
'SPM Télécom' => 'SPM TELECOM',
'Service des Postes et Télécommunications de Polynésie Française' => 'Gouv Nelle Calédonie (OPT)',
'SRR' => 'SRR',
'Station étrangère' => 'Station étrangère',
'Telco OI' => 'TELCO IO',
'United Telecommunication Services Caraïbes' => 'UTS Caraibes',
'Ora Mobile' => 'VITI SAS',
'Zeop' => 'ZEOP'
]
],
'statut' => [
'name' => 'Statut',
'type' => 'list',
'values' => [
'Tous' => null,
'En service' => 'En service',
'Projet approuvé' => 'Projet approuvé',
'Techniquement opérationnel' => 'Techniquement opérationnel',
]
]
]
];
public function collectData()
{
$urlParts = [
'id' => 'observatoire_2g_3g_4g',
'resource_id' => '88ef0887-6b0f-4d3f-8545-6d64c8f597da',
'fields' => 'id,adm_lb_nom,sta_nm_dpt,emr_lb_systeme,generation,date_maj,sta_nm_anfr,adr_lb_lieu,adr_lb_add1,adr_lb_add2,adr_lb_add3,adr_nm_cp,statut',
'rows' => 10000
];
if (!empty($this->getInput('departement'))) {
$urlParts['refine.sta_nm_dpt'] = urlencode($this->getInput('departement'));
}
if (!empty($this->getInput('generation'))) {
$urlParts['refine.generation'] = $this->getInput('generation');
}
if (!empty($this->getInput('operateur'))) {
// http_build_query() already does urlencoding so this call is redundant
$urlParts['refine.adm_lb_nom'] = urlencode($this->getInput('operateur'));
}
if (!empty($this->getInput('statut'))) {
$urlParts['refine.statut'] = urlencode($this->getInput('statut'));
}
// API seems to not play well with urlencoded data
$url = urljoin(static::URI, '/d4c/api/records/1.0/download/?' . urldecode(http_build_query($urlParts)));
$json = getContents($url);
$data = Json::decode($json, false);
$records = $data->records;
$frequenciesByStation = [];
foreach ($records as $record) {
if (!isset($frequenciesByStation[$record->fields->sta_nm_anfr])) {
$street = sprintf(
'%s %s %s',
$record->fields->adr_lb_add1 ?? '',
$record->fields->adr_lb_add2 ?? '',
$record->fields->adr_lb_add3 ?? ''
);
$frequenciesByStation[$record->fields->sta_nm_anfr] = [
'id' => $record->fields->sta_nm_anfr,
'operator' => $record->fields->adm_lb_nom,
'frequencies' => [],
'lastUpdate' => 0,
'address' => [
'street' => trim($street),
'postCode' => $record->fields->adr_nm_cp,
'city' => $record->fields->adr_lb_lieu
]
];
}
$frequenciesByStation[$record->fields->sta_nm_anfr]['frequencies'][] = [
'generation' => $record->fields->generation,
'frequency' => $record->fields->emr_lb_systeme,
'status' => $record->fields->statut,
'updatedAt' => strtotime($record->fields->date_maj),
];
$frequenciesByStation[$record->fields->sta_nm_anfr]['lastUpdate'] = max(
$frequenciesByStation[$record->fields->sta_nm_anfr]['lastUpdate'],
strtotime($record->fields->date_maj)
);
}
usort($frequenciesByStation, static fn ($a, $b) => $b['lastUpdate'] <=> $a['lastUpdate']);
foreach ($frequenciesByStation as $station) {
$title = sprintf(
'[%s] Mise à jour de la station n°%s à %s (%s)',
$station['operator'],
$station['id'],
$station['address']['city'],
$station['address']['postCode']
);
$array_reduce = array_reduce($station['frequencies'], static function ($carry, $frequency) {
return sprintf('%s<li>%s : %s</li>', $carry, $frequency['frequency'], $frequency['status']);
}, '');
$content = sprintf(
'<h1>Adresse complète</h1><p>%s<br>%s<br>%s</p><h1>Fréquences</h1><p><ul>%s</ul></p>',
$station['address']['street'],
$station['address']['postCode'],
$station['address']['city'],
$array_reduce
);
$this->items[] = [
'uid' => $station['id'],
'timestamp' => $station['lastUpdate'],
'title' => $title,
'content' => $content,
];
}
}
}

View File

@ -0,0 +1,87 @@
<?php
class AnisearchBridge extends BridgeAbstract
{
const MAINTAINER = 'Tone866';
const NAME = 'Anisearch';
const URI = 'https://www.anisearch.de';
const CACHE_TIMEOUT = 1800; // 30min
const DESCRIPTION = 'Feed for Anisearch';
const PARAMETERS = [[
'category' => [
'name' => 'Dub',
'type' => 'list',
'values' => [
'DE'
=> 'https://www.anisearch.de/anime/index/page-1?char=all&synchro=de&sort=date&order=desc&view=4',
'EN'
=> 'https://www.anisearch.de/anime/index/page-1?char=all&synchro=en&sort=date&order=desc&view=4',
'JP'
=> 'https://www.anisearch.de/anime/index/page-1?char=all&synchro=ja&sort=date&order=desc&view=4'
]
],
'trailers' => [
'name' => 'Trailers',
'type' => 'checkbox',
'title' => 'Will include trailes',
'defaultValue' => false
]
]];
public function collectData()
{
$baseurl = 'https://www.anisearch.de/';
$trailers = false;
$trailers = $this->getInput('trailers');
$limit = 10;
if ($trailers) {
$limit = 5;
}
$dom = getSimpleHTMLDOM($this->getInput('category'));
foreach ($dom->find('li.btype0') as $key => $li) {
if ($key >= $limit) {
break;
}
$a = $li->find('a', 0);
$title = $a->find('span.title', 0);
$url = $baseurl . $a->href;
//get article
$domarticle = getSimpleHTMLDOM($url);
$content = $domarticle->find('div.details-text', 0);
//get header-image and set absolute src
$headerimage = $domarticle->find('img#details-cover', 0);
$src = $headerimage->src;
foreach ($content->find('.hidden') as $element) {
$element->remove();
}
//get trailer
$ytlink = '';
if ($trailers) {
$trailerlink = $domarticle->find('section#trailers > div > div.swiper > ul.swiper-wrapper > li.swiper-slide > a', 0);
if (isset($trailerlink)) {
$trailersite = getSimpleHTMLDOM($baseurl . $trailerlink->href);
$trailer = $trailersite->find('div#player > iframe', 0);
$trailer = $trailer->{'data-xsrc'};
$ytlink = <<<EOT
<br /><iframe width="560" height="315" src="$trailer" title="YouTube video player"
frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share"
referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
EOT;
}
}
$this->items[] = [
'title' => $title->plaintext,
'uri' => $url,
'content' => $headerimage . '<br />' . $content . $ytlink
];
}
}
}

View File

@ -0,0 +1,183 @@
<?php
class AnnasArchiveBridge extends BridgeAbstract
{
const NAME = 'Anna\'s Archive';
const MAINTAINER = 'phantop';
const URI = 'https://annas-archive.org/';
const DESCRIPTION = 'Returns books from Anna\'s Archive';
const PARAMETERS = [
[
'q' => [
'name' => 'Query',
'exampleValue' => 'apothecary diaries',
'required' => true,
],
'ext' => [
'name' => 'Extension',
'type' => 'list',
'values' => [
'Any' => null,
'azw3' => 'azw3',
'cbr' => 'cbr',
'cbz' => 'cbz',
'djvu' => 'djvu',
'epub' => 'epub',
'fb2' => 'fb2',
'fb2.zip' => 'fb2.zip',
'mobi' => 'mobi',
'pdf' => 'pdf',
]
],
'lang' => [
'name' => 'Language',
'type' => 'list',
'values' => [
'Any' => null,
'Afrikaans [af]' => 'af',
'Arabic [ar]' => 'ar',
'Bangla [bn]' => 'bn',
'Belarusian [be]' => 'be',
'Bulgarian [bg]' => 'bg',
'Catalan [ca]' => 'ca',
'Chinese [zh]' => 'zh',
'Church Slavic [cu]' => 'cu',
'Croatian [hr]' => 'hr',
'Czech [cs]' => 'cs',
'Danish [da]' => 'da',
'Dongxiang [sce]' => 'sce',
'Dutch [nl]' => 'nl',
'English [en]' => 'en',
'French [fr]' => 'fr',
'German [de]' => 'de',
'Greek [el]' => 'el',
'Hebrew [he]' => 'he',
'Hindi [hi]' => 'hi',
'Hungarian [hu]' => 'hu',
'Indonesian [id]' => 'id',
'Irish [ga]' => 'ga',
'Italian [it]' => 'it',
'Japanese [ja]' => 'ja',
'Kazakh [kk]' => 'kk',
'Korean [ko]' => 'ko',
'Latin [la]' => 'la',
'Latvian [lv]' => 'lv',
'Lithuanian [lt]' => 'lt',
'Luxembourgish [lb]' => 'lb',
'Ndolo [ndl]' => 'ndl',
'Norwegian [no]' => 'no',
'Persian [fa]' => 'fa',
'Polish [pl]' => 'pl',
'Portuguese [pt]' => 'pt',
'Romanian [ro]' => 'ro',
'Russian [ru]' => 'ru',
'Serbian [sr]' => 'sr',
'Spanish [es]' => 'es',
'Swedish [sv]' => 'sv',
'Tamil [ta]' => 'ta',
'Traditional Chinese [zhHant]' => 'zhHant',
'Turkish [tr]' => 'tr',
'Ukrainian [uk]' => 'uk',
'Unknown language' => '_empty',
'Unknown language [und]' => 'und',
'Unknown language [urdu]' => 'urdu',
'Urdu [ur]' => 'ur',
'Vietnamese [vi]' => 'vi',
'Welsh [cy]' => 'cy',
]
],
'content' => [
'name' => 'Type',
'type' => 'list',
'values' => [
'Any' => null,
'Book (fiction)' => 'book_fiction',
'Book (nonfiction)' => 'book_nonfiction',
'Book (unknown)' => 'book_unknown',
'Comic book' => 'book_comic',
'Journal article' => 'journal_article',
'Magazine' => 'magazine',
'Standards document' => 'standards_document',
]
],
'src' => [
'name' => 'Source',
'type' => 'list',
'values' => [
'Any' => null,
'Internet Archive' => 'ia',
'Libgen.li' => 'lgli',
'Libgen.rs' => 'lgrs',
'SciHub' => 'scihub',
'ZLibrary' => 'zlib',
]
],
]
];
public function collectData()
{
$url = $this->getURI();
$list = getSimpleHTMLDOMCached($url);
$list = defaultLinkTo($list, self::URI);
// Don't attempt to do anything if not found message is given
if ($list->find('.js-not-found-additional')) {
return;
}
$elements = $list->find('.w-full > .mb-4 > div');
foreach ($elements as $element) {
// stop added entries once partial match list starts
if (str_contains($element->innertext, 'partial match')) {
break;
}
if ($element = $element->find('a', 0)) {
$item = [];
$item['title'] = $element->find('h3', 0)->plaintext;
$item['author'] = $element->find('div.italic', 0)->plaintext;
$item['uri'] = $element->href;
$item['content'] = $element->plaintext;
$item['uid'] = $item['uri'];
$item_html = getSimpleHTMLDOMCached($item['uri'], 86400 * 20);
if ($item_html) {
$item_html = defaultLinkTo($item_html, self::URI);
$item['content'] .= $item_html->find('main img', 0);
$item['content'] .= $item_html->find('main .mt-4', 0); // Summary
foreach ($item_html->find('main ul.mb-4 > li > a.js-download-link') as $file) {
if (!str_contains($file->href, 'fast_download')) {
$item['enclosures'][] = $file->href;
}
}
// Remove bulk torrents from enclosures list
$item['enclosures'] = array_diff($item['enclosures'], [self::URI . 'datasets']);
}
$this->items[] = $item;
}
}
}
public function getName()
{
$name = parent::getName();
if ($this->getInput('q') != null) {
$name .= ' - ' . $this->getInput('q');
}
return $name;
}
public function getURI()
{
$params = array_filter([ // Filter to remove non-provided parameters
'q' => $this->getInput('q'),
'ext' => $this->getInput('ext'),
'lang' => $this->getInput('lang'),
'src' => $this->getInput('src'),
'content' => $this->getInput('content'),
]);
$url = parent::getURI() . 'search?sort=newest&' . http_build_query($params);
return $url;
}
}

View File

@ -18,9 +18,45 @@ class AppleMusicBridge extends BridgeAbstract
'required' => true,
],
]];
const CACHE_TIMEOUT = 21600; // 6 hours
const CACHE_TIMEOUT = 60 * 60 * 6; // 6 hours
private $title;
public function collectData()
{
$items = $this->getJson();
$artist = $this->getArtist($items);
$this->title = $artist->artistName;
foreach ($items as $item) {
if ($item->wrapperType === 'collection') {
$copyright = $item->copyright ?? '';
$artworkUrl500 = str_replace('/100x100', '/500x500', $item->artworkUrl100);
$artworkUrl2000 = str_replace('/100x100', '/2000x2000', $item->artworkUrl100);
$escapedCollectionName = htmlspecialchars($item->collectionName);
$this->items[] = [
'title' => $item->collectionName,
'uri' => $item->collectionViewUrl,
'timestamp' => $item->releaseDate,
'enclosures' => $artworkUrl500,
'author' => $item->artistName,
'content' => "<figure>
<img srcset=\"$item->artworkUrl60 60w, $item->artworkUrl100 100w, $artworkUrl500 500w, $artworkUrl2000 2000w\"
sizes=\"100%\" src=\"$artworkUrl2000\"
alt=\"Cover of $escapedCollectionName\"
style=\"display: block; margin: 0 auto;\" />
<figcaption>
from <a href=\"$artist->artistLinkUrl\">$item->artistName</a><br />$copyright
</figcaption>
</figure>",
];
}
}
}
private function getJson()
{
# Limit the amount of releases to 50
if ($this->getInput('limit') > 50) {
@ -29,31 +65,53 @@ class AppleMusicBridge extends BridgeAbstract
$limit = $this->getInput('limit');
}
$url = 'https://itunes.apple.com/lookup?id='
. $this->getInput('artist')
. '&entity=album&limit='
. $limit .
'&sort=recent';
$url = 'https://itunes.apple.com/lookup?id=' . $this->getInput('artist') . '&entity=album&limit=' . $limit . '&sort=recent';
$html = getSimpleHTMLDOM($url);
$json = json_decode($html);
$result = $json->results;
foreach ($json->results as $obj) {
if ($obj->wrapperType === 'collection') {
$copyright = $obj->copyright ?? '';
$this->items[] = [
'title' => $obj->artistName . ' - ' . $obj->collectionName,
'uri' => $obj->collectionViewUrl,
'timestamp' => $obj->releaseDate,
'enclosures' => $obj->artworkUrl100,
'content' => '<a href=' . $obj->collectionViewUrl
. '><img src="' . $obj->artworkUrl100 . '" /></a><br><br>'
. $obj->artistName . ' - ' . $obj->collectionName
. '<br>'
. $copyright,
];
}
if (!is_array($result) || count($result) == 0) {
returnServerError('There is no artist with id "' . $this->getInput('artist') . '".');
}
return $result;
}
private function getArtist($json)
{
$nameArray = array_filter($json, function ($obj) {
return $obj->wrapperType == 'artist';
});
if (count($nameArray) === 1) {
return $nameArray[0];
}
return parent::getName();
}
public function getName()
{
if (isset($this->title)) {
return $this->title;
}
return parent::getName();
}
public function getIcon()
{
if (empty($this->getInput('artist'))) {
return parent::getIcon();
}
// it isn't necessary to set the correct artist name into the url
$url = 'https://music.apple.com/us/artist/jon-bellion/' . $this->getInput('artist');
$html = getSimpleHTMLDOMCached($url);
$image = $html->find('meta[property="og:image"]', 0)->content;
$imageUpdatedSize = preg_replace('/\/\d*x\d*cw/i', '/144x144-999', $image);
return $imageUpdatedSize;
}
}

View File

@ -35,42 +35,84 @@ class ArsTechnicaBridge extends FeedExpander
protected function parseItem(array $item)
{
$item_html = getSimpleHTMLDOMCached($item['uri'] . '&amp');
$item_html = getSimpleHTMLDOMCached($item['uri']);
$item_html = defaultLinkTo($item_html, self::URI);
$item_content = $item_html->find('.article-content.post-page', 0);
if (!$item_content) {
// The dom selector probably broke. Let's just return the item as-is
return $item;
$content = '';
$header = $item_html->find('article header', 0);
$leading = $header->find('p[class*=leading]', 0);
if ($leading != null) {
$content .= '<p>' . $leading->innertext . '</p>';
}
$intro_image = $header->find('img.intro-image', 0);
if ($intro_image != null) {
$content .= '<figure>' . $intro_image;
$image_caption = $header->find('.caption .caption-content', 0);
if ($image_caption != null) {
$content .= '<figcaption>' . $image_caption->innertext . '</figcaption>';
}
$content .= '</figure>';
}
$item['content'] = $item_content;
foreach ($item_html->find('.post-content') as $content_tag) {
$content .= $content_tag->innertext;
}
$item['content'] = str_get_html($content);
$parsely = $item_html->find('[name="parsely-page"]', 0);
$parsely_json = json_decode(html_entity_decode($parsely->content), true);
$item['categories'] = $parsely_json['tags'];
// Some lightboxes are nested in figures. I'd guess that's a
// bug in the website
foreach ($item['content']->find('figure div div.ars-lightbox') as $weird_lightbox) {
$weird_lightbox->parent->parent->outertext = $weird_lightbox;
}
// It's easier to reconstruct the whole thing than remove
// duplicate reactive tags
foreach ($item['content']->find('.ars-lightbox') as $lightbox) {
$lightbox_content = '';
foreach ($lightbox->find('.ars-lightbox-item') as $lightbox_item) {
$img = $lightbox_item->find('img', 0);
if ($img != null) {
$lightbox_content .= '<figure>' . $img;
$caption = $lightbox_item->find('div.pswp-caption-content', 0);
if ($caption != null) {
$credit = $lightbox_item->find('div.ars-gallery-caption-credit', 0);
if ($credit != null) {
$credit->innertext = 'Credit: ' . $credit->innertext;
}
$lightbox_content .= '<figcaption>' . $caption->innertext . '</figcaption>';
}
$lightbox_content .= '</figure>';
}
}
$lightbox->innertext = $lightbox_content;
}
// remove various ars advertising
$item['content']->find('#social-left', 0)->remove();
foreach ($item['content']->find('.ars-component-buy-box') as $ad) {
foreach ($item['content']->find('.ars-interlude-container') as $ad) {
$ad->remove();
}
foreach ($item['content']->find('i-amphtml-sizer') as $ad) {
$ad->remove();
}
foreach ($item['content']->find('.sidebar') as $ad) {
$ad->remove();
foreach ($item['content']->find('.toc-container') as $toc) {
$toc->remove();
}
foreach ($item['content']->find('a') as $link) { //remove amp redirect links
$url = $link->getAttribute('href');
if (str_contains($url, 'go.redirectingat.com')) {
$url = extractFromDelimiters($url, 'url=', '&amp');
$url = urldecode($url);
$link->setAttribute('href', $url);
}
// Mostly YouTube videos
$iframes = $item['content']->find('iframe');
foreach ($iframes as $iframe) {
$iframe->outertext = '<a href="' . $iframe->src . '">' . $iframe->src . '</a>';
}
// This fixed padding around the former iframes and actual inline videos
foreach ($item['content']->find('div[style*=aspect-ratio]') as $styled) {
$styled->removeAttribute('style');
}
$item['content'] = backgroundToImg(str_replace('data-amp-original-style="background-image', 'style="background-image', $item['content']));
$item['uid'] = explode('=', $item['uri'])[1];
$item['content'] = backgroundToImg($item['content']);
$item['uid'] = strval($parsely_json['post_id']);
return $item;
}
}

View File

@ -45,7 +45,6 @@ class AsahiShimbunAJWBridge extends BridgeAbstract
foreach ($html->find('#MainInner li a') as $element) {
if ($element->parent()->class == 'HeadlineTopImage-S') {
Debug::log('Skip Headline, it is repeated below');
continue;
}
$item = [];

View File

@ -0,0 +1,254 @@
<?php
class BMDSystemhausBlogBridge extends BridgeAbstract
{
const MAINTAINER = 'cn-tools';
const NAME = 'BMD SYSTEMHAUS GesmbH';
const CACHE_TIMEOUT = 21600; //6h
const URI = 'https://www.bmd.com';
const DONATION_URI = 'https://paypal.me/cntools';
const DESCRIPTION = 'BMD Systemhaus - We make business easy';
const BMD_FAV_ICON = 'https://www.bmd.com/favicon.ico';
const ITEMSTYLE = [
'ilcr' => '<table width="100%"><tr><td style="vertical-align: top;">{data_img}</td><td style="vertical-align: top;">{data_content}</td></tr></table>',
'clir' => '<table width="100%"><tr><td style="vertical-align: top;">{data_content}</td><td style="vertical-align: top;">{data_img}</td></tr></table>',
'itcb' => '<div>{data_img}<br />{data_content}</div>',
'ctib' => '<div>{data_content}<br />{data_img}</div>',
'co' => '{data_content}',
'io' => '{data_img}'
];
const PARAMETERS = [
'Blog' => [
'country' => [
'name' => 'Country',
'type' => 'list',
'values' => [
'Österreich' => 'at',
'Deutschland' => 'de',
'Schweiz' => 'ch',
'Slovensko' => 'sk',
'Cesko' => 'cz',
'Hungary' => 'hu',
],
'defaultValue' => 'at',
],
'style' => [
'name' => 'Style',
'type' => 'list',
'values' => [
'Image left, content right' => 'ilcr',
'Content left, image right' => 'clir',
'Image top, content bottom' => 'itcb',
'Content top, image bottom' => 'ctib',
'Content only' => 'co',
'Image only' => 'io',
],
'defaultValue' => 'ilcr',
]
]
];
//-----------------------------------------------------
public function collectData()
{
// get website content
$html = getSimpleHTMLDOM($this->getURI());
// Convert relative links in HTML into absolute links
$html = defaultLinkTo($html, self::URI);
// Convert lazy-loading images and frames (video embeds) into static elements
$html = convertLazyLoading($html);
foreach ($html->find('div#bmdNewsList div#bmdNewsList-Item') as $element) {
$itemScope = $element->find('div[itemscope=itemscope]', 0);
$item = [];
// set base article data
$item['title'] = $this->getMetaItemPropContent($itemScope, 'headline');
$item['timestamp'] = strtotime($this->getMetaItemPropContent($itemScope, 'datePublished'));
$item['author'] = $this->getMetaItemPropContent($itemScope->find('div[itemprop=author]', 0), 'name');
// find article image
$imageTag = '';
$image = $element->find('div.mediaelement.mediaelement-image img', 0);
if ((!is_null($image)) and ($image->src != '')) {
$item['enclosures'] = [$image->src];
$imageTag = '<img src="' . $image->src . '"/>';
}
// begin with right style
$content = self::ITEMSTYLE[$this->getInput('style')];
// render placeholder
$content = str_replace('{data_content}', $this->getMetaItemPropContent($itemScope, 'description'), $content);
$content = str_replace('{data_img}', $imageTag, $content);
// set finished content
$item['content'] = $content;
// get link to article
$link = $element->find('div#bmdNewsList-Text div#bmdNewsList-Title a', 0);
if (!is_null($link)) {
$item['uri'] = $link->href;
}
// init categories
$categories = [];
$tmpOne = [];
$tmpTwo = [];
// search first categorie span
$catElem = $element->find('div#bmdNewsList-Text div#bmdNewsList-Category span.news-list-category', 0);
$txt = trim($catElem->innertext);
$tmpOne = explode('/', $txt);
// split by 2 spaces
foreach ($tmpOne as $tmpElem) {
$tmpElem = trim($tmpElem);
$tmpData = preg_split('/ /', $tmpElem);
$tmpTwo = array_merge($tmpTwo, $tmpData);
}
// split by tabulator
foreach ($tmpTwo as $tmpElem) {
$tmpElem = trim($tmpElem);
$tmpData = preg_split('/\t+/', $tmpElem);
$categories = array_merge($categories, $tmpData);
}
// trim each categorie entries
$categories = array_map('trim', $categories);
// remove empty entries
$categories = array_filter($categories, function ($value) {
return !is_null($value) && $value !== '';
});
// set categories
if (count($categories) > 0) {
$item['categories'] = $categories;
}
// add item
if (($item['title'] != '') and ($item['content'] != '') and ($item['uri'] != '')) {
$this->items[] = $item;
}
}
}
//-----------------------------------------------------
public function detectParameters($url)
{
try {
$parsedUrl = Url::fromString($url);
} catch (UrlException $e) {
return null;
}
if (!in_array($parsedUrl->getHost(), ['www.bmd.com', 'bmd.com'])) {
return null;
}
$lang = '';
// extract language from url
$path = explode('/', $parsedUrl->getPath());
if (count($path) > 1) {
$lang = $path[1];
// validate data
if ($this->getURIbyCountry($lang) == '') {
$lang = '';
}
}
// if no country available, find language by browser
if ($lang == '') {
$srvLanguages = explode(';', $_SERVER['HTTP_ACCEPT_LANGUAGE']);
if (count($srvLanguages) > 0) {
$languages = explode(',', $srvLanguages[0]);
if (count($languages) > 0) {
for ($i = 0; $i < count($languages); $i++) {
$langDetails = explode('-', $languages[$i]);
if (count($langDetails) > 1) {
$lang = $langDetails[1];
} else {
$lang = substr($srvLanguages[0], 0, 2);
}
// validate data
if ($this->getURIbyCountry($lang) == '') {
$lang = '';
}
if ($lang != '') {
break;
}
}
}
}
}
// if no URL found by language, use AT as default
if ($this->getURIbyCountry($lang) == '') {
$lang = 'at';
}
$params = [];
$params['country'] = strtolower($lang);
return $params;
}
//-----------------------------------------------------
public function getURI()
{
$country = $this->getInput('country') ?? '';
$lURI = $this->getURIbyCountry($country);
return $lURI != '' ? $lURI : parent::getURI();
}
//-----------------------------------------------------
public function getIcon()
{
return self::BMD_FAV_ICON;
}
//-----------------------------------------------------
private function getMetaItemPropContent($elem, $key)
{
if (($key != '') and (!is_null($elem))) {
$metaElem = $elem->find('meta[itemprop=' . $key . ']', 0);
if (!is_null($metaElem)) {
return $metaElem->getAttribute('content');
}
}
return '';
}
//-----------------------------------------------------
private function getURIbyCountry($country)
{
switch (strtolower($country)) {
case 'at':
return 'https://www.bmd.com/at/ueber-bmd/blog-ohne-filter.html';
case 'de':
return 'https://www.bmd.com/de/das-ist-bmd/blog.html';
case 'ch':
return 'https://www.bmd.com/ch/das-ist-bmd/blog.html';
case 'sk':
return 'https://www.bmd.com/sk/firma/blog.html';
case 'cz':
return 'https://www.bmd.com/cz/firma/news-blog.html';
case 'hu':
return 'https://www.bmd.com/hu/rolunk/hirek.html';
default:
return '';
}
}
}

View File

@ -284,8 +284,7 @@ class BadDragonBridge extends BridgeAbstract
case 'Clearance':
$toyData = json_decode(getContents($this->inputToURL(true)));
$productList = json_decode(getContents(self::URI
. 'api/inventory-toy/product-list'));
$productList = json_decode(getContents(self::URI . 'api/inventory-toy/product-list'));
foreach ($toyData->toys as $toy) {
$item = [];

View File

@ -111,12 +111,12 @@ class BandcampBridge extends BridgeAbstract
$url = self::URI . 'api/hub/1/dig_deeper';
$data = $this->buildRequestJson();
$header = [
'Content-Type: application/json',
'Content-Length: ' . strlen($data)
'Content-Type: application/json',
'Content-Length: ' . strlen($data),
];
$opts = [
CURLOPT_CUSTOMREQUEST => 'POST',
CURLOPT_POSTFIELDS => $data
CURLOPT_CUSTOMREQUEST => 'POST',
CURLOPT_POSTFIELDS => $data,
];
$content = getContents($url, $header, $opts);
@ -314,7 +314,8 @@ class BandcampBridge extends BridgeAbstract
{
$url = self::URI . 'api/' . $endpoint . '?' . http_build_query($query_data);
// todo: 429 Too Many Requests happens a lot
$data = json_decode(getContents($url));
$response = getContents($url);
$data = json_decode($response);
return $data;
}

View File

@ -37,7 +37,7 @@ class BlizzardNewsBridge extends XPathAbstract
const XPATH_EXPRESSION_ITEM = '/html/body/div/div[4]/div[2]/div[2]/div/div/section/ol/li/article';
const XPATH_EXPRESSION_ITEM_TITLE = './/div/div[2]/h2';
const XPATH_EXPRESSION_ITEM_CONTENT = './/div[@class="ArticleListItem-description"]/div[@class="h6"]';
const XPATH_EXPRESSION_ITEM_CONTENT = './/div[@class="ArticleListItem-description"]/div[@class="h6"]/text()';
const XPATH_EXPRESSION_ITEM_URI = './/a[@class="ArticleLink ArticleLink"]/@href';
const XPATH_EXPRESSION_ITEM_AUTHOR = '';
const XPATH_EXPRESSION_ITEM_TIMESTAMP = './/time[@class="ArticleListItem-footerTimestamp"]/@timestamp';
@ -57,4 +57,11 @@ class BlizzardNewsBridge extends XPathAbstract
}
return 'https://news.blizzard.com/' . $locale;
}
public function getIcon()
{
return <<<icon
https://blznews.akamaized.net/images/favicon-cb34a003c6f2f637ee8f4f7b406f3b9b120b918c04cabec7f03a760e708977ea9689a1c638f4396def8dce7b202cd007eae91946cc3c4a578aa8b5694226cfc6.ico
icon;
}
}

230
bridges/BlueskyBridge.php Normal file
View File

@ -0,0 +1,230 @@
<?php
class BlueskyBridge extends BridgeAbstract
{
const NAME = 'Bluesky';
const URI = 'https://bsky.app';
const DESCRIPTION = 'Fetches posts from Bluesky';
const MAINTAINER = 'Code modified from rsshub (TonyRL https://github.com/TonyRL) and expanded';
const PARAMETERS = [
[
'data_source' => [
'name' => 'Bluesky Data Source',
'type' => 'list',
'defaultValue' => 'Profile',
'values' => [
'Profile' => 'getAuthorFeed',
],
'title' => 'Select the type of data source to fetch from Bluesky.'
],
'handle' => [
'name' => 'User Handle',
'type' => 'text',
'required' => true,
'exampleValue' => 'jackdodo.bsky.social',
'title' => 'Handle found in URL'
],
'filter' => [
'name' => 'Filter',
'type' => 'list',
'defaultValue' => 'posts_and_author_threads',
'values' => [
'posts_and_author_threads' => 'posts_and_author_threads',
'posts_with_replies' => 'posts_with_replies',
'posts_no_replies' => 'posts_no_replies',
'posts_with_media' => 'posts_with_media',
],
'title' => 'Combinations of post/repost types to include in response.'
]
]
];
private $profile;
public function getName()
{
if (isset($this->profile)) {
return sprintf('%s (@%s) - Bluesky', $this->profile['displayName'], $this->profile['handle']);
}
return parent::getName();
}
public function getURI()
{
if (isset($this->profile)) {
return self::URI . '/profile/' . $this->profile['handle'];
}
return parent::getURI();
}
public function getIcon()
{
if (isset($this->profile)) {
return $this->profile['avatar'];
}
return parent::getIcon();
}
public function getDescription()
{
if (isset($this->profile)) {
return $this->profile['description'];
}
return parent::getDescription();
}
private function parseExternal($external, $did)
{
$description = '';
$externalUri = $external['uri'];
$externalTitle = htmlspecialchars($external['title'], ENT_QUOTES, 'UTF-8');
$externalDescription = htmlspecialchars($external['description'], ENT_QUOTES, 'UTF-8');
$thumb = $external['thumb'] ?? null;
if (preg_match('/youtube\.com\/watch\?v=([^\&\?\/]+)/', $externalUri, $id) || preg_match('/youtu\.be\/([^\&\?\/]+)/', $externalUri, $id)) {
$videoId = $id[1];
$description .= "<p>External Link: <a href=\"$externalUri\">$externalTitle</a></p>";
$description .= "<iframe width=\"560\" height=\"315\" src=\"https://www.youtube.com/embed/$videoId\" frameborder=\"0\" allowfullscreen></iframe>";
} else {
$description .= "<p>External Link: <a href=\"$externalUri\">$externalTitle</a></p>";
$description .= "<p>$externalDescription</p>";
if ($thumb) {
$thumbUrl = 'https://cdn.bsky.app/img/feed_thumbnail/plain/' . $did . '/' . $thumb['ref']['$link'] . '@jpeg';
$description .= "<p><a href=\"$externalUri\"><img src=\"$thumbUrl\" alt=\"External Thumbnail\" /></a></p>";
}
}
return $description;
}
private function textToDescription($text)
{
$text = nl2br(htmlspecialchars($text, ENT_QUOTES, 'UTF-8'));
$text = preg_replace('/(https?:\/\/[^\s]+)/i', '<a href="$1">$1</a>', $text);
return $text;
}
public function collectData()
{
$handle = $this->getInput('handle');
$filter = $this->getInput('filter') ?: 'posts_and_author_threads';
$did = $this->resolveHandle($handle);
$this->profile = $this->getProfile($did);
$authorFeed = $this->getAuthorFeed($did, $filter);
foreach ($authorFeed['feed'] as $post) {
$item = [];
$item['uri'] = self::URI . '/profile/' . $post['post']['author']['handle'] . '/post/' . explode('app.bsky.feed.post/', $post['post']['uri'])[1];
$item['title'] = strtok($post['post']['record']['text'], "\n");
$item['timestamp'] = strtotime($post['post']['record']['createdAt']);
$item['author'] = $this->profile['displayName'];
$description = $this->textToDescription($post['post']['record']['text']);
// Retrieve DID for constructing image URLs
$authorDid = $post['post']['author']['did'];
if (isset($post['post']['record']['embed']['$type']) && $post['post']['record']['embed']['$type'] === 'app.bsky.embed.external') {
$description .= $this->parseExternal($post['post']['record']['embed']['external'], $authorDid);
}
if (isset($post['post']['record']['embed']['$type']) && $post['post']['record']['embed']['$type'] === 'app.bsky.embed.video') {
$thumbnail = $post['post']['embed']['thumbnail'] ?? null;
if ($thumbnail) {
$itemUri = self::URI . '/profile/' . $post['post']['author']['handle'] . '/post/' . explode('app.bsky.feed.post/', $post['post']['uri'])[1];
$description .= "<p><a href=\"$itemUri\"><img src=\"$thumbnail\" alt=\"Video Thumbnail\" /></a></p>";
}
}
if (isset($post['post']['record']['embed']['$type']) && $post['post']['record']['embed']['$type'] === 'app.bsky.embed.recordWithMedia#view') {
$thumbnail = $post['post']['embed']['media']['thumbnail'] ?? null;
$playlist = $post['post']['embed']['media']['playlist'] ?? null;
if ($thumbnail) {
$description .= "<p><video controls poster=\"$thumbnail\">";
$description .= "<source src=\"$playlist\" type=\"application/x-mpegURL\">";
$description .= 'Video source not supported</video></p>';
}
}
if (!empty($post['post']['record']['embed']['images'])) {
foreach ($post['post']['record']['embed']['images'] as $image) {
$linkRef = $image['image']['ref']['$link'];
$thumbnailUrl = $this->resolveThumbnailUrl($authorDid, $linkRef);
$fullsizeUrl = $this->resolveFullsizeUrl($authorDid, $linkRef);
$description .= "<br /><br /><a href=\"$fullsizeUrl\"><img src=\"$thumbnailUrl\" alt=\"Image\"></a>";
}
}
// Enhanced handling for quote posts with images
if (isset($post['post']['record']['embed']) && $post['post']['record']['embed']['$type'] === 'app.bsky.embed.record') {
$quotedRecord = $post['post']['record']['embed']['record'];
$quotedAuthor = $post['post']['embed']['record']['author']['handle'] ?? null;
$quotedDisplayName = $post['post']['embed']['record']['author']['displayName'] ?? null;
$quotedText = $post['post']['embed']['record']['value']['text'] ?? null;
if ($quotedAuthor && isset($quotedRecord['uri'])) {
$parts = explode('/', $quotedRecord['uri']);
$quotedPostId = end($parts);
$quotedPostUri = self::URI . '/profile/' . $quotedAuthor . '/post/' . $quotedPostId;
}
if ($quotedText) {
$description .= '<hr /><strong>Quote from ' . htmlspecialchars($quotedDisplayName) . ' (@ ' . htmlspecialchars($quotedAuthor) . '):</strong><br />';
$description .= $this->textToDescription($quotedText);
if (isset($quotedPostUri)) {
$description .= "<p><a href=\"$quotedPostUri\">View original quote post</a></p>";
}
}
}
if (isset($post['post']['embed']['record']['value']['embed']['images'])) {
$quotedImages = $post['post']['embed']['record']['value']['embed']['images'];
foreach ($quotedImages as $image) {
$linkRef = $image['image']['ref']['$link'] ?? null;
if ($linkRef) {
$quotedAuthorDid = $post['post']['embed']['record']['author']['did'] ?? null;
$thumbnailUrl = $this->resolveThumbnailUrl($quotedAuthorDid, $linkRef);
$fullsizeUrl = $this->resolveFullsizeUrl($quotedAuthorDid, $linkRef);
$description .= "<br /><br /><a href=\"$fullsizeUrl\"><img src=\"$thumbnailUrl\" alt=\"Quoted Image\"></a>";
}
}
}
$item['content'] = $description;
$this->items[] = $item;
}
}
private function resolveHandle($handle)
{
$uri = 'https://public.api.bsky.app/xrpc/com.atproto.identity.resolveHandle?handle=' . urlencode($handle);
$response = json_decode(getContents($uri), true);
return $response['did'];
}
private function getProfile($did)
{
$uri = 'https://public.api.bsky.app/xrpc/app.bsky.actor.getProfile?actor=' . urlencode($did);
$response = json_decode(getContents($uri), true);
return $response;
}
private function getAuthorFeed($did, $filter)
{
$uri = 'https://public.api.bsky.app/xrpc/app.bsky.feed.getAuthorFeed?actor=' . urlencode($did) . '&filter=' . urlencode($filter) . '&limit=30';
$response = json_decode(getContents($uri), true);
return $response;
}
private function resolveThumbnailUrl($authorDid, $linkRef)
{
return 'https://cdn.bsky.app/img/feed_thumbnail/plain/' . $authorDid . '/' . $linkRef . '@jpeg';
}
private function resolveFullsizeUrl($authorDid, $linkRef)
{
return 'https://cdn.bsky.app/img/feed_fullsize/plain/' . $authorDid . '/' . $linkRef . '@jpeg';
}
}

218
bridges/BodaccBridge.php Normal file
View File

@ -0,0 +1,218 @@
<?php
class BodaccBridge extends BridgeAbstract
{
const NAME = 'BODACC';
const URI = 'https://bodacc-datadila.opendatasoft.com/';
const DESCRIPTION = 'Fetches announces from the French Government "Bulletin Officiel Des Annonces Civiles et Commerciales".';
const CACHE_TIMEOUT = 86400;
const MAINTAINER = 'quent1';
const PARAMETERS = [
'Annonces commerciales' => [
'departement' => [
'name' => 'Département',
'type' => 'list',
'values' => [
'Tous' => null,
'Ain' => '01',
'Aisne' => '02',
'Allier' => '03',
'Alpes-de-Haute-Provence' => '04',
'Hautes-Alpes' => '05',
'Alpes-Maritimes' => '06',
'Ardèche' => '07',
'Ardennes' => '08',
'Ariège' => '09',
'Aube' => '10',
'Aude' => '11',
'Aveyron' => '12',
'Bouches-du-Rhône' => '13',
'Calvados' => '14',
'Cantal' => '15',
'Charente' => '16',
'Charente-Maritime' => '17',
'Cher' => '18',
'Corrèze' => '19',
'Corse-du-Sud' => '2A',
'Haute-Corse' => '2B',
'Côte-d\'Or' => '21',
'Côtes-d\'Armor' => '22',
'Creuse' => '23',
'Dordogne' => '24',
'Doubs' => '25',
'Drôme' => '26',
'Eure' => '27',
'Eure-et-Loir' => '28',
'Finistère' => '29',
'Gard' => '30',
'Haute-Garonne' => '31',
'Gers' => '32',
'Gironde' => '33',
'Hérault' => '34',
'Ille-et-Vilaine' => '35',
'Indre' => '36',
'Indre-et-Loire' => '37',
'Isère' => '38',
'Jura' => '39',
'Landes' => '40',
'Loir-et-Cher' => '41',
'Loire' => '42',
'Haute-Loire' => '43',
'Loire-Atlantique' => '44',
'Loiret' => '45',
'Lot' => '46',
'Lot-et-Garonne' => '47',
'Lozère' => '48',
'Maine-et-Loire' => '49',
'Manche' => '50',
'Marne' => '51',
'Haute-Marne' => '52',
'Mayenne' => '53',
'Meurthe-et-Moselle' => '54',
'Meuse' => '55',
'Morbihan' => '56',
'Moselle' => '57',
'Nièvre' => '58',
'Nord' => '59',
'Oise' => '60',
'Orne' => '61',
'Pas-de-Calais' => '62',
'Puy-de-Dôme' => '63',
'Pyrénées-Atlantiques' => '64',
'Hautes-Pyrénées' => '65',
'Pyrénées-Orientales' => '66',
'Bas-Rhin' => '67',
'Haut-Rhin' => '68',
'Rhône' => '69',
'Haute-Saône' => '70',
'Saône-et-Loire' => '71',
'Sarthe' => '72',
'Savoie' => '73',
'Haute-Savoie' => '74',
'Paris' => '75',
'Seine-Maritime' => '76',
'Seine-et-Marne' => '77',
'Yvelines' => '78',
'Deux-Sèvres' => '79',
'Somme' => '80',
'Tarn' => '81',
'Tarn-et-Garonne' => '82',
'Var' => '83',
'Vaucluse' => '84',
'Vendée' => '85',
'Vienne' => '86',
'Haute-Vienne' => '87',
'Vosges' => '88',
'Yonne' => '89',
'Territoire de Belfort' => '90',
'Essonne' => '91',
'Hauts-de-Seine' => '92',
'Seine-Saint-Denis' => '93',
'Val-de-Marne' => '94',
'Val-d\'Oise' => '95',
'Guadeloupe' => '971',
'Martinique' => '972',
'Guyane' => '973',
'La Réunion' => '974',
'Saint-Pierre-et-Miquelon' => '975',
'Mayotte' => '976',
'Saint-Barthélemy' => '977',
'Saint-Martin' => '978',
'Terres australes et antarctiques françaises' => '984',
'Wallis-et-Futuna' => '986',
'Polynésie française' => '987',
'Nouvelle-Calédonie' => '988',
'Île de Clipperton' => '989'
]
],
'famille' => [
'name' => 'Famille',
'type' => 'list',
'values' => [
'Toutes' => null,
'Annonces diverses' => 'divers',
'Créations' => 'creation',
'Dépôts des comptes' => 'dpc',
'Immatriculations' => 'immatriculation',
'Modifications diverses' => 'modification',
'Procédures collectives' => 'collective',
'Procédures de conciliation' => 'conciliation',
'Procédures de rétablissement professionnel' => 'retablissement_professionnel',
'Radiations' => 'radiation',
'Ventes et cessions' => 'vente'
]
],
'type' => [
'name' => 'Type',
'type' => 'list',
'values' => [
'Tous' => null,
'Avis initial' => 'annonce',
'Avis d\'annulation' => 'annulation',
'Avis rectificatif' => 'rectificatif'
]
]
]
];
public function collectData()
{
$parameters = [
'select' => 'id,dateparution,typeavis_lib,familleavis_lib,commercant,ville,cp',
'order_by' => 'id desc',
'limit' => 50,
];
$where = [];
if (!empty($this->getInput('departement'))) {
$where[] = 'numerodepartement="' . $this->getInput('departement') . '"';
}
if (!empty($this->getInput('famille'))) {
$where[] = 'familleavis="' . $this->getInput('famille') . '"';
}
if (!empty($this->getInput('type'))) {
$where[] = 'typeavis="' . $this->getInput('type') . '"';
}
if ($where !== []) {
$parameters['where'] = implode(' and ', $where);
}
$url = urljoin(self::URI, '/api/explore/v2.1/catalog/datasets/annonces-commerciales/records?' . http_build_query($parameters));
$data = Json::decode(getContents($url), false);
foreach ($data->results as $result) {
if (
!isset(
$result->id,
$result->dateparution,
$result->typeavis_lib,
$result->familleavis_lib,
$result->commercant,
$result->ville,
$result->cp
)
) {
continue;
}
$title = sprintf(
'[%s] %s - %s à %s (%s)',
$result->typeavis_lib,
$result->familleavis_lib,
$result->commercant,
$result->ville,
$result->cp
);
$this->items[] = [
'uid' => $result->id,
'timestamp' => strtotime($result->dateparution),
'title' => $title,
];
}
}
}

View File

@ -1218,14 +1218,15 @@ EOT;
$table = $this->generateEventDetailsTable($event);
$imgsrc = $event['BannerURL'];
$FShareURL = $event['FShareURL'];
return <<<EOT
<img title="Event Banner URL" src="$imgsrc"></img>
<br>
$table
<br>
More Details are available on the <a href="${event['FShareURL']}">BookMyShow website</a>.
EOT;
<img title="Event Banner URL" src="$imgsrc">
<br>
$table
<br>
More Details are available on the <a href="$FShareURL">BookMyShow website</a>.
EOT;
}
/**
@ -1292,14 +1293,15 @@ EOT;
$synopsis = preg_replace(self::SYNOPSIS_REGEX, '', $data['EventSynopsis']);
$eventTrailerURL = $data['EventTrailerURL'];
return <<<EOT
<img title="Movie Poster" src="$imgsrc"></img>
<div>$table</div>
<p>$innerHtml</p>
<p>${synopsis}</p>
More Details are available on the <a href="$url">BookMyShow website</a> and a trailer is available
<a href="${data['EventTrailerURL']}" title="Trailer URL">here</a>
EOT;
<img title="Movie Poster" src="$imgsrc"></img>
<div>$table</div>
<p>$innerHtml</p>
<p>$synopsis</p>
More Details are available on the <a href="$url">BookMyShow website</a> and a trailer is available
<a href="$eventTrailerURL" title="Trailer URL">here</a>
EOT;
}
/**

View File

@ -164,7 +164,7 @@ class BugzillaBridge extends BridgeAbstract
}
$cache = $this->loadCacheValue($this->instance . $user);
if (!is_null($cache)) {
if ($cache) {
return $cache;
}

View File

@ -0,0 +1,28 @@
<?php
class BundesverbandFuerFreieKammernBridge extends XPathAbstract
{
const NAME = 'Bundesverband für freie Kammern e.V.';
const URI = 'https://www.bffk.de/aktuelles/aktuelle-nachrichten.html';
const DESCRIPTION = 'Aktuelle Nachrichten';
const MAINTAINER = 'hleskien';
const FEED_SOURCE_URL = 'https://www.bffk.de/aktuelles/aktuelle-nachrichten.html';
//const XPATH_EXPRESSION_FEED_ICON = './/link[@rel="icon"]/@href';
const XPATH_EXPRESSION_ITEM = '//ul[@class="article-list"]/li';
const XPATH_EXPRESSION_ITEM_TITLE = './/a/text()';
const XPATH_EXPRESSION_ITEM_CONTENT = './/a/text()';
const XPATH_EXPRESSION_ITEM_URI = './/a/@href';
//const XPATH_EXPRESSION_ITEM_AUTHOR = './/';
const XPATH_EXPRESSION_ITEM_TIMESTAMP = './/span/i';
//const XPATH_EXPRESSION_ITEM_ENCLOSURES = './';
//const XPATH_EXPRESSION_ITEM_CATEGORIES = './/';
protected function formatItemTimestamp($value)
{
$value = trim($value, '()');
$dti = DateTimeImmutable::createFromFormat('d.m.Y', $value);
$dti = $dti->setTime(0, 0, 0);
return $dti->getTimestamp();
}
}

View File

@ -56,7 +56,7 @@ class CNETBridge extends SitemapBridge
foreach ($links as $article_uri) {
$article_dom = convertLazyLoading(getSimpleHTMLDOMCached($article_uri));
$title = trim($article_dom->find('h1', 0)->plaintext);
$author = $article_dom->find('span.c-assetAuthor_name', 0)->plaintext;
$author = $article_dom->find('span.c-assetAuthor_name', 0);
$headline = $article_dom->find('p.c-contentHeader_description', 0);
$content = $article_dom->find('div.c-pageArticle_content, div.single-article__content, div.article-main-body', 0);
$date = null;
@ -97,7 +97,11 @@ class CNETBridge extends SitemapBridge
$item = [];
$item['uri'] = $article_uri;
$item['title'] = $title;
$item['author'] = $author;
if ($author) {
$item['author'] = $author->plaintext;
}
$item['content'] = $content;
if (!is_null($date)) {

View File

@ -42,45 +42,23 @@ class CVEDetailsBridge extends BridgeAbstract
$this->fetchContent();
}
foreach ($this->html->find('#searchresults > .row') as $i => $tr) {
// There are some optional vulnerability types, which will be
// added to the categories as well as the CWE number -- which is
// always given.
$categories = [$this->vendor];
$enclosures = [];
$detailLink = $tr->find('h3 > a', 0);
$detailHtml = getSimpleHTMLDOM($detailLink->href);
// The CVE number itself
$var = $this->html->find('#searchresults > div > div.row');
foreach ($var as $i => $tr) {
$uri = $tr->find('h3 > a', 0)->href ?? null;
$title = $tr->find('h3 > a', 0)->innertext;
$content = $tr->find('.cvesummarylong', 0)->innertext;
$cweList = $detailHtml->find('h2', 2)->next_sibling();
foreach ($cweList->find('li') as $li) {
$cweWithDescription = $li->find('a', 0)->innertext ?? '';
if (preg_match('/CWE-(\d+)/', $cweWithDescription, $cwe)) {
$categories[] = 'CWE-' . $cwe[1];
$enclosures[] = 'https://cwe.mitre.org/data/definitions/' . $cwe[1] . '.html';
}
}
if ($this->product != '') {
$categories[] = $this->product;
}
$content = $tr->find('.cvesummarylong', 0)->innertext ?? '';
$timestamp = $tr->find('[data-tsvfield="publishDate"]', 0)->innertext ?? 0;
$this->items[] = [
'uri' => 'https://cvedetails.com/' . $detailHtml->find('h1 > a', 0)->href,
'uri' => $uri,
'title' => $title,
'timestamp' => $tr->find('[data-tsvfield="publishDate"]', 0)->innertext,
'timestamp' => $timestamp,
'content' => $content,
'categories' => $categories,
'enclosures' => $enclosures,
'categories' => [$this->vendor],
'enclosures' => [],
'uid' => $title,
];
// We only want to fetch the latest 10 CVEs
if (count($this->items) >= 10) {
if (count($this->items) >= 30) {
break;
}
}

View File

@ -6,48 +6,113 @@ class CarThrottleBridge extends BridgeAbstract
const URI = 'https://www.carthrottle.com/';
const DESCRIPTION = 'Get the latest car-related news from Car Throttle.';
const MAINTAINER = 't0stiman';
const DONATION_URI = 'https://ko-fi.com/tostiman';
const PARAMETERS = [
'Show articles from these categories:' => [
'news' => [
'name' => 'news',
'type' => 'checkbox'
],
'reviews' => [
'name' => 'reviews',
'type' => 'checkbox'
],
'features' => [
'name' => 'features',
'type' => 'checkbox'
],
'videos' => [
'name' => 'videos',
'type' => 'checkbox'
],
'gaming' => [
'name' => 'gaming',
'type' => 'checkbox'
]
]
];
public function collectData()
{
$news = getSimpleHTMLDOMCached(self::URI . 'news')
or returnServerError('could not retrieve page');
$this->items = [];
$this->items[] = [];
$this->handleCategory('news');
$this->handleCategory('reviews');
$this->handleCategory('features');
$this->handleCategory2('videos', 'video');
$this->handleCategory('gaming');
}
private function handleCategory($category)
{
if ($this->getInput($category)) {
$this->getArticles($category);
}
}
private function handleCategory2($categoryParameter, $categoryURLname)
{
if ($this->getInput($categoryParameter)) {
$this->getArticles($categoryURLname);
}
}
private function getArticles($category)
{
$categoryPage = getSimpleHTMLDOMCached(self::URI . $category);
//for each post
foreach ($news->find('div.cmg-card') as $post) {
foreach ($categoryPage->find('div.cmg-card') as $post) {
$item = [];
$titleElement = $post->find('div.title a.cmg-link')[0];
$item['uri'] = self::URI . $titleElement->getAttribute('href');
$titleElement = $post->find('div.title a')[0];
$post_uri = self::URI . $titleElement->getAttribute('href');
if (!isset($post_uri) || $post_uri == '') {
continue;
}
$item['uri'] = $post_uri;
$item['title'] = $titleElement->innertext;
$articlePage = getSimpleHTMLDOMCached($item['uri'])
or returnServerError('could not retrieve page');
$articlePage = getSimpleHTMLDOMCached($item['uri']);
$authorDiv = $articlePage->find('div.author div');
if ($authorDiv) {
$item['author'] = $authorDiv[1]->innertext;
}
$item['author'] = $this->parseAuthor($articlePage);
$articleImage = $articlePage->find('div.block-layout-field-image')[0];
$article = $articlePage->find('div.block-layout-body')[1];
$dinges = $articlePage->find('div.main-body')[0] ?? null;
//remove ads
if ($dinges) {
foreach ($dinges->find('aside') as $ad) {
$ad->outertext = '';
$dinges->save();
}
foreach ($article->find('aside') as $ad) {
$ad->outertext = '';
}
$var = $articlePage->find('div.summary')[0] ?? '';
$var1 = $articlePage->find('figure.main-image')[0] ?? '';
$dinges1 = $dinges ?? '';
$summary = $articlePage->find('div.summary')[0];
$item['content'] = $var .
$var1 .
$dinges1;
//these are supposed to be hidden
foreach ($article->find('.visually-hidden') as $found) {
$found->outertext = '';
}
$item['content'] = $summary . $articleImage . $article;
array_push($this->items, $item);
}
}
private function parseAuthor($articlePage)
{
$authorDivs = $articlePage->find('div address');
if (!$authorDivs) {
return '';
}
$a = $authorDivs[0]->find('a')[0];
if ($a) {
return $a->innertext;
}
return $authorDivs[0]->innertext;
}
}

View File

@ -54,7 +54,7 @@ class CaschyBridge extends FeedExpander
{
// remove unwanted stuff
foreach (
$article->find('div.video-container, div.aawp, p.aawp-disclaimer, iframe.wp-embedded-content,
$article->find('div.aawp, p.aawp-disclaimer, iframe.wp-embedded-content,
div.wp-embed, p.wp-caption-text, script') as $element
) {
$element->remove();

View File

@ -0,0 +1,279 @@
<?php
class CentreFranceBridge extends BridgeAbstract
{
const NAME = 'Centre France Newspapers';
const URI = 'https://www.centrefrance.com/';
const DESCRIPTION = 'Common bridge for all Centre France group newspapers.';
const CACHE_TIMEOUT = 7200; // 2h
const MAINTAINER = 'quent1';
const PARAMETERS = [
'global' => [
'newspaper' => [
'name' => 'Newspaper',
'type' => 'list',
'values' => [
'La Montagne' => 'lamontagne.fr',
'Le Populaire du Centre' => 'lepopulaire.fr',
'La République du Centre' => 'larep.fr',
'Le Berry Républicain' => 'leberry.fr',
'L\'Yonne Républicaine' => 'lyonne.fr',
'L\'Écho Républicain' => 'lechorepublicain.fr',
'Le Journal du Centre' => 'lejdc.fr',
'L\'Éveil de la Haute-Loire' => 'leveil.fr',
'Le Pays' => 'le-pays.fr'
]
],
'remove-reserved-for-subscribers-articles' => [
'name' => 'Remove reserved for subscribers articles',
'type' => 'checkbox',
'title' => 'Filter out articles that are only available to subscribers'
],
'limit' => [
'name' => 'Limit',
'type' => 'number',
'title' => 'How many articles to fetch. 0 to disable.',
'required' => true,
'defaultValue' => 15
]
],
'Local news' => [
'locality-slug' => [
'name' => 'Locality slug',
'type' => 'text',
'required' => false,
'title' => 'Fetch articles for a specific locality. If not set, headlines from the front page will be used instead.',
'exampleValue' => 'moulins-03000'
],
]
];
public function collectData()
{
$value = $this->getInput('limit');
if (is_numeric($value) && (int)$value >= 0) {
$limit = $value;
} else {
$limit = static::PARAMETERS['global']['limit']['defaultValue'];
}
if (empty($this->getInput('newspaper'))) {
return;
}
$localitySlug = $this->getInput('locality-slug') ?? '';
$alreadyFoundArticlesURIs = [];
$newspaperUrl = 'https://www.' . $this->getInput('newspaper') . '/' . $localitySlug . '/';
$html = getSimpleHTMLDOM($newspaperUrl);
// Articles are detected through their titles
foreach ($html->find('.c-titre') as $articleTitleDOMElement) {
$articleLinkDOMElement = $articleTitleDOMElement->find('a', 0);
// Ignore articles in the « Les + partagés » block
if (strpos($articleLinkDOMElement->id, 'les_plus_partages') !== false) {
continue;
}
$articleURI = $articleLinkDOMElement->href;
// If the URI has already been processed, ignore it
if (in_array($articleURI, $alreadyFoundArticlesURIs, true)) {
continue;
}
// If news are filtered for a specific locality, filter out article for other localities
if ($localitySlug !== '' && !str_contains($articleURI, $localitySlug)) {
continue;
}
$articleTitle = '';
// If article is reserved for subscribers
if ($articleLinkDOMElement->find('span.premium-picto', 0)) {
if ($this->getInput('remove-reserved-for-subscribers-articles') === true) {
continue;
}
$articleTitle .= '🔒 ';
}
$articleTitleDOMElement = $articleLinkDOMElement->find('span[data-tb-title]', 0);
if ($articleTitleDOMElement === null) {
continue;
}
if ($limit > 0 && count($this->items) === $limit) {
break;
}
$articleTitle .= $articleLinkDOMElement->find('span[data-tb-title]', 0)->innertext;
$articleFullURI = urljoin('https://www.' . $this->getInput('newspaper') . '/', $articleURI);
$item = [
'title' => $articleTitle,
'uri' => $articleFullURI,
...$this->collectArticleData($articleFullURI)
];
$this->items[] = $item;
$alreadyFoundArticlesURIs[] = $articleURI;
}
}
private function collectArticleData($uri): array
{
$html = getSimpleHTMLDOMCached($uri, 86400 * 90); // 90d
$item = [
'enclosures' => [],
];
$articleInformations = $html->find('.c-article-informations p');
if (is_array($articleInformations) && $articleInformations !== []) {
$authorPosition = 1;
// Article publication date
if (preg_match('/(\d{2})\/(\d{2})\/(\d{4})( à (\d{2})h(\d{2}))?/', $articleInformations[0]->innertext, $articleDateParts) > 0) {
$articleDate = new \DateTime('midnight');
$articleDate->setDate($articleDateParts[3], $articleDateParts[2], $articleDateParts[1]);
if (count($articleDateParts) === 7) {
$articleDate->setTime($articleDateParts[5], $articleDateParts[6]);
}
$item['timestamp'] = $articleDate->getTimestamp();
}
// Article update date
if (count($articleInformations) >= 2 && preg_match('/(\d{2})\/(\d{2})\/(\d{4})( à (\d{2})h(\d{2}))?/', $articleInformations[1]->innertext, $articleDateParts) > 0) {
$authorPosition = 2;
$articleDate = new \DateTime('midnight');
$articleDate->setDate($articleDateParts[3], $articleDateParts[2], $articleDateParts[1]);
if (count($articleDateParts) === 7) {
$articleDate->setTime($articleDateParts[5], $articleDateParts[6]);
}
$item['timestamp'] = $articleDate->getTimestamp();
}
if (count($articleInformations) === ($authorPosition + 1)) {
$item['author'] = $articleInformations[$authorPosition]->innertext;
}
}
$articleContent = $html->find('.b-article .contenu > *');
if (is_array($articleContent)) {
$item['content'] = '';
foreach ($articleContent as $contentPart) {
if (in_array($contentPart->getAttribute('id'), ['cf-audio-player', 'poool-widget'], true)) {
continue;
}
$articleHiddenParts = $contentPart->find('.bloc, .p402_hide');
if (is_array($articleHiddenParts)) {
foreach ($articleHiddenParts as $articleHiddenPart) {
$contentPart->removeChild($articleHiddenPart);
}
}
$item['content'] .= $contentPart->innertext;
}
}
$articleIllustration = $html->find('.photo-wrapper .photo-box img');
if (is_array($articleIllustration) && count($articleIllustration) === 1) {
$item['enclosures'][] = $articleIllustration[0]->getAttribute('src');
}
$articleAudio = $html->find('#cf-audio-player-container audio');
if (is_array($articleAudio) && count($articleAudio) === 1) {
$item['enclosures'][] = $articleAudio[0]->getAttribute('src');
}
$articleTags = $html->find('.b-article > ul.c-tags > li > a.t-simple');
if (is_array($articleTags)) {
$item['categories'] = array_map(static fn ($articleTag) => $articleTag->innertext, $articleTags);
}
$explode = explode('_', $uri);
$array_reverse = array_reverse($explode);
$string = $array_reverse[0];
$uid = rtrim($string, '/');
if (is_numeric($uid)) {
$item['uid'] = $uid;
}
// If the article is a "grand format", we use another parsing strategy
if ($item['content'] === '' && $html->find('article') !== []) {
$articleContent = $html->find('article > section');
foreach ($articleContent as $contentPart) {
if ($contentPart->find('#journo') !== []) {
$item['author'] = $contentPart->find('#journo')->innertext;
continue;
}
$item['content'] .= $contentPart->innertext;
}
}
$item['content'] = str_replace('<span class="p-premium">premium</span>', '🔒', $item['content']);
$item['content'] = trim($item['content']);
return $item;
}
public function getName()
{
if (empty($this->getInput('newspaper'))) {
return static::NAME;
}
$newspaperNameByDomain = array_flip(self::PARAMETERS['global']['newspaper']['values']);
if (!isset($newspaperNameByDomain[$this->getInput('newspaper')])) {
return static::NAME;
}
$completeTitle = $newspaperNameByDomain[$this->getInput('newspaper')];
if (!empty($this->getInput('locality-slug'))) {
$localityName = explode('-', $this->getInput('locality-slug'));
array_pop($localityName);
$completeTitle .= ' ' . ucfirst(implode('-', $localityName));
}
return $completeTitle;
}
public function getIcon()
{
if (empty($this->getInput('newspaper'))) {
return static::URI . '/favicon.ico';
}
return 'https://www.' . $this->getInput('newspaper') . '/favicon.ico';
}
public function detectParameters($url)
{
$regex = '/^(https?:\/\/)?(www\.)?([a-z-]+\.fr)(\/)?([a-z-]+-[0-9]{5})?(\/)?$/';
$url = strtolower($url);
if (preg_match($regex, $url, $urlMatches) === 0) {
return null;
}
if (!in_array($urlMatches[3], self::PARAMETERS['global']['newspaper']['values'], true)) {
return null;
}
return [
'newspaper' => $urlMatches[3],
'locality-slug' => empty($urlMatches[5]) ? null : $urlMatches[5]
];
}
}

View File

@ -57,10 +57,10 @@ class CeskaTelevizeBridge extends BridgeAbstract
$this->feedName .= " ({$category})";
}
foreach ($html->find('#episodeListSection a[data-testid=next-link]') as $element) {
foreach ($html->find('#episodeListSection a[data-testid=card]') as $element) {
$itemTitle = $element->find('h3', 0);
$itemContent = $element->find('div[class^=content-]', 0);
$itemDate = $element->find('div[class^=playTime-] span', 0);
$itemContent = $element->find('p[class^=content-]', 0);
$itemDate = $element->find('div[class^=playTime-] span, [data-testid=episode-item-broadcast] span', 0);
$itemThumbnail = $element->find('img', 0);
$itemUri = self::URI . $element->getAttribute('href');

View File

@ -275,22 +275,26 @@ class CodebergBridge extends BridgeAbstract
*/
private function extractPulls($html)
{
$div = $html->find('div.issue.list', 0);
$div = $html->find('div#issue-list', 0);
foreach ($div->find('li.item') as $li) {
$var2 = $div->find('div.flex-item');
foreach ($var2 as $li) {
$item = [];
$number = trim($li->find('a.index,ml-0.mr-2', 0)->plaintext);
$item['title'] = $li->find('a.title', 0)->plaintext . ' (' . $number . ')';
$item['uri'] = $li->find('a.title', 0)->href;
$a = $li->find('a.issue-title', 0);
$item['title'] = $a->plaintext . ' (' . $number . ')';
$item['uri'] = $a->href;
$time = $li->find('relative-time.time-since', 0);
if ($time) {
$item['timestamp'] = $time->datetime;
}
$item['author'] = $li->find('div.desc', 0)->find('a', 1)->plaintext;
// Extracting the author is a bit awkward after they changed their html
//$desc = $li->find('div.desc', 0);
//$item['author'] = $desc->find('a', 1)->plaintext;
// Fetch pull request page
$pullRequestPage = getSimpleHTMLDOMCached($item['uri'], 3600);

View File

@ -2,59 +2,65 @@
class ComicsKingdomBridge extends BridgeAbstract
{
const MAINTAINER = 'stjohnjohnson';
const MAINTAINER = 'TReKiE';
// const MAINTAINER = 'stjohnjohnson';
const NAME = 'Comics Kingdom Unofficial RSS';
const URI = 'https://comicskingdom.com/';
const URI = 'https://wp.comicskingdom.com/wp-json/wp/v2/ck_comic';
const CACHE_TIMEOUT = 21600; // 6h
const DESCRIPTION = 'Comics Kingdom Unofficial RSS';
const PARAMETERS = [ [
'comicname' => [
'name' => 'comicname',
'name' => 'Name of comic',
'type' => 'text',
'exampleValue' => 'mutts',
'title' => 'The name of the comic in the URL after https://comicskingdom.com/',
'required' => true
],
'limit' => [
'name' => 'Limit',
'type' => 'number',
'title' => 'The number of recent comics to get',
'defaultValue' => 10
]
]];
protected $comicName;
public function collectData()
{
$html = getSimpleHTMLDOM($this->getURI(), [], [], true, false);
$json = getContents($this->getURI());
$data = json_decode($json, false);
// Get author from first page
$author = $html->find('div.author p', 0);
;
if (isset($data[0]->_embedded->{'wp:term'}[0][0])) {
$this->comicName = $data[0]->_embedded->{'wp:term'}[0][0]->name;
}
// Get current date/link
$link = $html->find('meta[property=og:url]', -1)->content;
for ($i = 0; $i < 3; $i++) {
foreach ($data as $comicitem) {
$item = [];
$page = getSimpleHTMLDOM($link);
$imagelink = $page->find('meta[property=og:image]', 0)->content;
$date = explode('/', $link);
$item['id'] = $imagelink;
$item['uri'] = $link;
$item['author'] = $author;
$item['title'] = 'Comics Kingdom ' . $this->getInput('comicname');
$item['timestamp'] = DateTime::createFromFormat('Y-m-d', $date[count($date) - 1])->getTimestamp();
$item['content'] = '<img src="' . $imagelink . '" />';
$item['id'] = $comicitem->id;
$item['uri'] = $comicitem->yoast_head_json->og_url;
$item['author'] = str_ireplace('By ', '', $comicitem->ck_comic_byline);
$item['title'] = $comicitem->yoast_head_json->title;
$item['timestamp'] = $comicitem->date;
$item['content'] = '<img src="' . $comicitem->yoast_head_json->og_image[0]->url . '" />';
$this->items[] = $item;
$link = $page->find('div.comic-viewer-inline a', 0)->href;
if (empty($link)) {
break; // allow bridge to continue if there's less than 3 comics
}
}
}
public function getURI()
{
if (!is_null($this->getInput('comicname'))) {
return self::URI . urlencode($this->getInput('comicname'));
$params = [
'ck_feature' => $this->getInput('comicname'),
'per_page' => $this->getInput('limit'),
'date_inclusive' => 'true',
'order' => 'desc',
'page' => '1',
'_embed' => 'true'
];
return self::URI . '?' . http_build_query($params);
}
return parent::getURI();
@ -62,8 +68,8 @@ class ComicsKingdomBridge extends BridgeAbstract
public function getName()
{
if (!is_null($this->getInput('comicname'))) {
return $this->getInput('comicname') . ' - Comics Kingdom';
if ($this->comicName) {
return $this->comicName . ' - Comics Kingdom';
}
return parent::getName();

View File

@ -56,6 +56,11 @@ class CssSelectorBridge extends BridgeAbstract
'title' => 'Some sites set their logo as thumbnail for every article. Use this option to discard it.',
'type' => 'checkbox',
],
'thumbnail_as_header' => [
'name' => '[Optional] Insert thumbnail as article header',
'title' => 'Insert article main image on top of article contents.',
'type' => 'checkbox',
],
'limit' => self::LIMIT
]
];
@ -89,6 +94,7 @@ class CssSelectorBridge extends BridgeAbstract
$content_cleanup = $this->getInput('content_cleanup');
$title_cleanup = $this->getInput('title_cleanup');
$discard_thumbnail = $this->getInput('discard_thumbnail');
$thumbnail_as_header = $this->getInput('thumbnail_as_header');
$limit = $this->getInput('limit') ?? 10;
$html = defaultLinkTo(getSimpleHTMLDOM($this->homepageUrl), $this->homepageUrl);
@ -109,6 +115,9 @@ class CssSelectorBridge extends BridgeAbstract
if ($discard_thumbnail && isset($item['enclosures'])) {
unset($item['enclosures']);
}
if ($thumbnail_as_header && isset($item['enclosures'][0])) {
$item['content'] = '<p><img src="' . $item['enclosures'][0] . '" /></p>' . $item['content'];
}
$this->items[] = $item;
}
}
@ -267,7 +276,7 @@ class CssSelectorBridge extends BridgeAbstract
}
$entry_html = getSimpleHTMLDOMCached($entry_url);
$item = $this->entryHtmlRetrieveMetadata($entry_html);
$item = html_find_seo_metadata($entry_html);
if (empty($item['uri'])) {
$item['uri'] = $entry_url;
@ -297,247 +306,4 @@ class CssSelectorBridge extends BridgeAbstract
return $item;
}
/**
* Retrieve metadata from entry HTML: title, author, date published, etc. from metadata intended for social media embeds and SEO
* @param obj $entry_html DOM object representing the webpage HTML
* @return array Entry data collected from Metadata
*/
protected function entryHtmlRetrieveMetadata($entry_html)
{
$item = [];
// == First source of metadata: Meta tags ==
// Facebook Open Graph (og:KEY) - https://developers.facebook.com/docs/sharing/webmasters
// Twitter (twitter:KEY) - https://developer.twitter.com/en/docs/twitter-for-websites/cards/guides/getting-started
// Standard meta tags - https://www.w3schools.com/tags/tag_meta.asp
// Each Entry field mapping defines a list of possible <meta> tags names that contains the expected value
static $meta_mappings = [
// <meta property="article:KEY" content="VALUE" />
// <meta property="og:KEY" content="VALUE" />
// <meta property="KEY" content="VALUE" />
// <meta name="twitter:KEY" content="VALUE" />
// <meta name="KEY" content="VALUE">
// <link rel="canonical" href="URL" />
'uri' => [
'og:url',
'twitter:url',
'canonical'
],
'title' => [
'og:title',
'twitter:title'
],
'content' => [
'og:description',
'twitter:description',
'description'
],
'timestamp' => [
'article:published_time',
'og:article:published_time',
'releaseDate',
'releasedate',
'article:modified_time',
'og:article:modified_time',
'lastModified',
'lastmodified'
],
'enclosures' => [
'og:image:secure_url',
'og:image:url',
'og:image',
'twitter:image',
'thumbnailImg',
'thumbnailimg'
],
'author' => [
'article:author',
'og:article:author',
'author',
'article:author:username',
'profile:first_name',
'profile:last_name',
'article:author:first_name',
'article:author:last_name',
'twitter:creator',
],
];
$author_first_name = null;
$author_last_name = null;
// For each Entry property, look for corresponding HTML tags using a list of candidates
foreach ($meta_mappings as $property => $field_list) {
foreach ($field_list as $field) {
// Look for HTML meta tag
$element = null;
if ($field === 'canonical') {
$element = $entry_html->find('link[rel=canonical]');
} else {
$element = $entry_html->find("meta[property=$field], meta[name=$field]");
}
// Found something? Extract the value and populate Entry field
if (!empty($element)) {
$element = $element[0];
$field_value = '';
if ($field === 'canonical') {
$field_value = $element->href;
} else {
$field_value = $element->content;
}
if (!empty($field_value)) {
if ($field === 'article:author:first_name' || $field === 'profile:first_name') {
$author_first_name = $field_value;
} else if ($field === 'article:author:last_name' || $field === 'profile:last_name') {
$author_last_name = $field_value;
} else {
$item[$property] = $field_value;
break; // Stop on first match, e.g. og:url has priority over canonical url.
}
}
}
}
}
// Populate author from first name and last name if all we have is nothing or Twitter @username
if ((!isset($item['author']) || $item['author'][0] === '@') && (is_string($author_first_name) || is_string($author_last_name))) {
$author = '';
if (is_string($author_first_name)) {
$author = $author_first_name;
}
if (is_string($author_last_name)) {
$author = $author . ' ' . $author_last_name;
}
$item['author'] = trim($author);
}
// == Second source of metadata: Embedded JSON ==
// JSON linked data - https://www.w3.org/TR/2014/REC-json-ld-20140116/
// JSON linked data is COMPLEX and MAY BE LESS RELIABLE than <meta> tags. Used for fields not found as <meta> tags.
// The implementation below will load all ld+json we can understand and attempt to extract relevant information.
// ld+json object types that hold article metadata
// Each mapping define item fields and a list of possible JSON field for this field
// Each candiate JSON field is either a string (field name) or a list (path to nested field)
static $ldjson_article_types = ['webpage', 'article', 'newsarticle', 'blogposting'];
static $ldjson_article_mappings = [
'uri' => ['url', 'mainEntityOfPage'],
'title' => ['headline'],
'content' => ['description'],
'timestamp' => ['dateModified', 'datePublished'],
'enclosures' => ['image'],
'author' => [['author', 'name'], ['author', '@id'], 'author'],
];
// ld+json object types that hold author metadata
$ldjson_author_types = ['person', 'organization'];
$ldjson_author_mappings = []; // ID => Name
$ldjson_author_id = null;
// Utility function for checking if JSON array matches one of the desired ld+json object types
// A JSON object may have a single ld+json @type as a string OR several types at once as a list
$ldjson_is_of_type = function ($json, $allowed_types) {
if (isset($json['@type'])) {
$json_types = $json['@type'];
if (!is_array($json_types)) {
$json_types = [ $json_types ];
}
foreach ($json_types as $item_type) {
if (in_array(strtolower($item_type), $allowed_types)) {
return true;
}
}
}
return false;
};
// Process ld+json objects embedded in the HTML DOM
foreach ($entry_html->find('script[type=application/ld+json]') as $html_ldjson_node) {
$json_raw = json_decode($html_ldjson_node->innertext, true);
if (is_array($json_raw)) {
// The JSON we just loaded may contain directly a single ld+json object AND/OR several ones under the '@graph' key
$json_items = [ $json_raw ];
if (isset($json_raw['@graph'])) {
foreach ($json_raw['@graph'] as $json_raw_sub_item) {
$json_items[] = $json_raw_sub_item;
}
}
// Now that we have a list of distinct JSON items, we can process them individually
foreach ($json_items as $json) {
// JSON item that holds an ld+json Article object (or a variant)
if ($ldjson_is_of_type($json, $ldjson_article_types)) {
// For each item property, look for corresponding JSON fields and populate the item
foreach ($ldjson_article_mappings as $property => $field_list) {
// Skip fields already found as <meta> tags, except Twitter @username (because we might find a better name)
if (!isset($item[$property]) || ($property === 'author' && $item['author'][0] === '@')) {
foreach ($field_list as $field) {
$json_root = $json;
// If necessary, navigate inside the JSON object to access a nested field
if (is_array($field)) {
// At this point, $field = ['author', 'name'] and $json_root = {"author": {"name": "John Doe"}}
$json_navigate_ok = true;
while (count($field) > 1) {
$sub_field = array_shift($field);
if (array_key_exists($sub_field, $json_root)) {
$json_root = $json_root[$sub_field];
if (array_is_list($json_root) && count($json_root) === 1) {
$json_root = $json_root[0]; // Unwrap list of single item e.g. {"author":[{"name":"John Doe"}]}
}
} else {
// Desired path not found in JSON, stop navigating
$json_navigate_ok = false;
break;
}
}
if (!$json_navigate_ok) {
continue; //Desired path not found in JSON, skip this field
}
$field = $field[0];
// At this point, $field = "name" and $json_root = {"name": "John Doe"}
}
// Now we can check for desired field in JSON and populate $item accordingly
if (isset($json_root[$field])) {
$field_value = $json_root[$field];
if (is_array($field_value) && isset($field_value[0])) {
$field_value = $field_value[0]; // Different versions of the same enclosure? Take the first one
}
if (is_string($field_value) && !empty($field_value)) {
if ($property === 'author' && $field === '@id') {
$ldjson_author_id = $field_value; // Author is referred to by its ID: We'll see later if we can resolve it
} else {
$item[$property] = $field_value;
break; // Stop on first match, e.g. {"author":{"name":"John Doe"}} has priority over {"author":"John Doe"}
}
}
}
}
}
}
// JSON item that holds an ld+json Author object (or a variant)
} else if ($ldjson_is_of_type($json, $ldjson_author_types)) {
if (isset($json['@id']) && isset($json['name'])) {
$ldjson_author_mappings[$json['@id']] = $json['name'];
}
}
}
}
}
// Attempt to resolve ld+json author if all we have is nothing or Twitter @username
if ((!isset($item['author']) || $item['author'][0] === '@') && !is_null($ldjson_author_id) && isset($ldjson_author_mappings[$ldjson_author_id])) {
$item['author'] = $ldjson_author_mappings[$ldjson_author_id];
}
// Adjust item field types
if (isset($item['enclosures'])) {
$item['enclosures'] = [ $item['enclosures'] ];
}
if (isset($item['timestamp'])) {
$item['timestamp'] = strtotime($item['timestamp']);
}
return $item;
}
}

View File

@ -245,7 +245,7 @@ class CssSelectorComplexBridge extends BridgeAbstract
protected function getTitle($page, $title_cleanup)
{
if (is_string($page)) {
$page = getSimpleHTMLDOMCached($page);
$page = getSimpleHTMLDOMCached($page, 86400, $this->getHeaders());
}
$title = html_entity_decode($page->find('title', 0)->plaintext);
if (!empty($title)) {
@ -302,7 +302,7 @@ class CssSelectorComplexBridge extends BridgeAbstract
protected function htmlFindEntryElements($page, $entry_selector, $url_selector, $url_pattern = '', $limit = 0)
{
if (is_string($page)) {
$page = getSimpleHTMLDOM($page);
$page = getSimpleHTMLDOM($page, $this->getHeaders());
}
$entryElements = $page->find($entry_selector);
@ -355,7 +355,7 @@ class CssSelectorComplexBridge extends BridgeAbstract
*/
protected function fetchArticleElementFromPage($entry_url, $content_selector)
{
$entry_html = getSimpleHTMLDOMCached($entry_url);
$entry_html = getSimpleHTMLDOMCached($entry_url, 86400, $this->getHeaders());
$article_content = $entry_html->find($content_selector, 0);
if (is_null($article_content)) {
@ -442,7 +442,7 @@ class CssSelectorComplexBridge extends BridgeAbstract
if (!is_null($time_selector) && $time_selector != '') {
$time_element = $entry_html->find($time_selector, 0);
$time = $time_element->getAttribute('datetime');
if (is_null($time)) {
if (empty($time)) {
$time = $time_element->innertext;
}

View File

@ -37,6 +37,11 @@ class CssSelectorFeedExpanderBridge extends CssSelectorBridge
'title' => 'Some sites set their logo as thumbnail for every article. Use this option to discard it.',
'type' => 'checkbox',
],
'thumbnail_as_header' => [
'name' => '[Optional] Insert thumbnail as article header',
'title' => 'Insert article main image on top of article contents.',
'type' => 'checkbox',
],
'limit' => self::LIMIT
]
];
@ -48,6 +53,7 @@ class CssSelectorFeedExpanderBridge extends CssSelectorBridge
$content_cleanup = $this->getInput('content_cleanup');
$dont_expand_metadata = $this->getInput('dont_expand_metadata');
$discard_thumbnail = $this->getInput('discard_thumbnail');
$thumbnail_as_header = $this->getInput('thumbnail_as_header');
$limit = $this->getInput('limit');
$feedParser = new FeedParser();
@ -100,6 +106,13 @@ class CssSelectorFeedExpanderBridge extends CssSelectorBridge
unset($item_expanded['enclosures']);
}
if ($thumbnail_as_header && isset($item_expanded['enclosures'][0])) {
$item_expanded['content'] = '<p><img src="'
. $item_expanded['enclosures'][0]
. '" /></p>'
. $item_expanded['content'];
}
$this->items[] = $item_expanded;
}
}

View File

@ -47,8 +47,10 @@ class CubariBridge extends BridgeAbstract
*/
public function collectData()
{
// TODO: fix trivial SSRF
$json = getContents($this->getInput('gist'));
$jsonFile = json_decode($json, true);
$jsonFile = Json::decode($json);
$this->mangaTitle = $jsonFile['title'];

View File

@ -0,0 +1,129 @@
<?php
class CubariProxyBridge extends BridgeAbstract
{
const NAME = 'Cubari Proxy';
const MAINTAINER = 'phantop';
const URI = 'https://cubari.moe';
const DESCRIPTION = 'Returns chapters from Cubari.';
const PARAMETERS = [[
'service' => [
'name' => 'Content service',
'type' => 'list',
'defaultValue' => 'mangadex',
'values' => [
'MangAventure' => 'mangadventure',
'MangaDex' => 'mangadex',
'MangaKatana' => 'mangakatana',
'MangaSee' => 'mangasee',
]
],
'series' => [
'name' => 'Series ID/Name',
'exampleValue' => '8c1d7d0c-e0b7-4170-941d-29f652c3c19d', # KnH
'required' => true,
],
'fetch' => [
'name' => 'Fetch chapter page images',
'type' => 'list',
'title' => 'Places chapter images in feed contents. Entries will consume more bandwidth.',
'defaultValue' => 'c',
'values' => [
'None' => 'n',
'Content' => 'c',
'Enclosure' => 'e'
]
],
'limit' => self::LIMIT
]];
private $title;
public function collectData()
{
$limit = $this->getInput('limit') ?? 10;
$url = parent::getURI() . '/read/api/' . $this->getInput('service') . '/series/' . $this->getInput('series');
$json = Json::decode(getContents($url));
$this->title = $json['title'];
$chapters = $json['chapters'];
krsort($chapters);
$count = 0;
foreach ($chapters as $number => $element) {
$item = [];
$item['uri'] = $this->getURI() . '/' . $number;
if ($element['title']) {
$item['title'] = $number . ' - ' . $element['title'];
} else {
$item['title'] = 'Volume ' . $element['volume'] . ' Chapter ' . $number;
}
$group = '1';
if (isset($element['release_date'])) {
$dates = $element['release_date'];
$date = max($dates);
$item['timestamp'] = $date;
$group = array_keys($dates, $date)[0];
}
$page = $element['groups'][$group];
$item['author'] = $json['groups'][$group];
$api = parent::getURI() . $page;
$item['uid'] = $page;
$item['comments'] = $api;
if ($this->getInput('fetch') != 'n') {
$pages = [];
try {
$jsonp = getContents($api);
$pages = Json::decode($jsonp);
} catch (HttpException $e) {
// allow error 500, as it's effectively a 429
if ($e->getCode() != 500) {
throw $e;
}
}
if ($this->getInput('fetch') == 'e') {
$item['enclosures'] = $pages;
}
if ($this->getInput('fetch') == 'c') {
$item['content'] = '';
foreach ($pages as $img) {
$item['content'] .= '<img src="' . $img . '"/>';
}
}
}
if ($count++ == $limit) {
break;
}
$this->items[] = $item;
}
}
public function getName()
{
$name = parent::getName();
if (isset($this->title)) {
$name .= ' - ' . $this->title;
}
return $name;
}
public function getURI()
{
$uri = parent::getURI();
if ($this->getInput('service')) {
$uri .= '/read/' . $this->getInput('service') . '/' . $this->getInput('series');
}
return $uri;
}
public function getFavicon()
{
return parent::getURI() . '/static/favicon.ico';
}
}

View File

@ -0,0 +1,107 @@
<?php
class DRKBlutspendeBridge extends FeedExpander
{
const MAINTAINER = 'User123698745';
const NAME = 'DRK-Blutspende';
const BASE_URI = 'https://www.drk-blutspende.de';
const URI = self::BASE_URI;
const CACHE_TIMEOUT = 60 * 60 * 1; // 1 hour
const DESCRIPTION = 'German Red Cross (Deutsches Rotes Kreuz) blood donation service feed with more details';
const CONTEXT_APPOINTMENTS = 'Termine';
const PARAMETERS = [
self::CONTEXT_APPOINTMENTS => [
'term' => [
'name' => 'PLZ / Ort',
'required' => true,
'exampleValue' => '12555',
],
'radius' => [
'name' => 'Umkreis in km',
'type' => 'number',
'exampleValue' => 10,
],
'limit_days' => [
'name' => 'Limit von Tagen',
'title' => 'Nur Termine innerhalb der nächsten x Tagen',
'type' => 'number',
'exampleValue' => 28,
],
'limit_items' => [
'name' => 'Limit von Terminen',
'title' => 'Nicht mehr als x Termine',
'type' => 'number',
'required' => true,
'defaultValue' => 20,
]
]
];
public function collectData()
{
$limitItems = intval($this->getInput('limit_items'));
$this->collectExpandableDatas(self::buildAppointmentsURI(), $limitItems);
}
protected function parseItem(array $item)
{
$html = getSimpleHTMLDOM($item['uri']);
$detailsElement = $html->find('.details', 0);
$dateElement = $detailsElement->find('.datum', 0);
$dateLines = self::explodeLines($dateElement->plaintext);
$addressElement = $detailsElement->find('.adresse', 0);
$addressLines = self::explodeLines($addressElement->plaintext);
$infoElement = $detailsElement->find('.angebote > h4 + p', 0);
$info = $infoElement ? $infoElement->innertext : '';
$imageElements = $detailsElement->find('.fotos img');
$item['title'] = $dateLines[0] . ' ' . $dateLines[1] . ' ' . $addressLines[0] . ' - ' . $addressLines[1];
$item['content'] = <<<HTML
<p><b>{$dateLines[0]} {$dateLines[1]}</b></p>
<p>{$addressElement->innertext}</p>
<p>{$info}</p>
HTML;
foreach ($imageElements as $imageElement) {
$src = $imageElement->getAttribute('src');
$item['content'] .= <<<HTML
<p><img src="{$src}"></p>
HTML;
}
$item['description'] = null;
return $item;
}
public function getURI()
{
if ($this->queriedContext === self::CONTEXT_APPOINTMENTS) {
return str_replace('.rss?', '?', self::buildAppointmentsURI());
}
return parent::getURI();
}
private function buildAppointmentsURI()
{
$term = $this->getInput('term') ?? '';
$radius = $this->getInput('radius') ?? '';
$limitDays = intval($this->getInput('limit_days'));
$dateTo = $limitDays > 0 ? date('Y-m-d', time() + (60 * 60 * 24 * $limitDays)) : '';
return self::BASE_URI . '/blutspendetermine/termine.rss?date_to=' . $dateTo . '&radius=' . $radius . '&term=' . $term;
}
/**
* Returns an array of strings, each of which is a substring of string formed by splitting it on boundaries formed by line breaks.
*/
private function explodeLines(string $text): array
{
return array_map('trim', preg_split('/(\s*(\r\n|\n|\r)\s*)+/', $text));
}
}

104
bridges/DacksnackBridge.php Normal file
View File

@ -0,0 +1,104 @@
<?PHP
class DacksnackBridge extends BridgeAbstract
{
const NAME = 'Däcksnack';
const URI = 'https://www.tidningendacksnack.se';
const DESCRIPTION = 'Latest news by the magazine Däcksnack';
const MAINTAINER = 'ajain-93';
public function getIcon()
{
return self::URI . '/upload/favicon/2591047722.png';
}
private function parseSwedishDates($dateString)
{
// Mapping of Swedish month names to English month names
$monthNames = [
'januari' => '01',
'februari' => '02',
'mars' => '03',
'april' => '04',
'maj' => '05',
'juni' => '06',
'juli' => '07',
'augusti' => '08',
'september' => '09',
'oktober' => '10',
'november' => '11',
'december' => '12'
];
// Split the date string into parts
list($day, $monthName, $year) = explode(' ', $dateString);
// Convert month name to month number
$month = $monthNames[$monthName];
// Format to a string recognizable by DateTime
$formattedDate = sprintf('%04d-%02d-%02d', $year, $month, $day);
// Create a DateTime object
$dateValue = new DateTime($formattedDate);
if ($dateValue) {
$dateValue->setTime(0, 0); // Set time to 00:00
return $dateValue->getTimestamp();
}
return $dateValue ? $dateValue->getTimestamp() : false;
}
public function collectData()
{
$NEWSURL = self::URI;
$html = getSimpleHTMLDOMCached($NEWSURL, 18000) or
returnServerError('Could not request: ' . $NEWSURL);
foreach ($html->find('a.main-news-item') as $element) {
// Debug::log($element);
$title = trim($element->find('h2', 0)->plaintext);
$category = trim($element->find('.category-tag', 0)->plaintext);
$url = self::URI . $element->getAttribute('href');
$published = $this->parseSwedishDates(trim($element->find('.published', 0)->plaintext));
$article_html = getSimpleHTMLDOMCached($url, 18000) or
returnServerError('Could not request: ' . $url);
$article_content = $article_html->find('#ctl00_ContentPlaceHolder1_NewsArticleVeiw_pnlArticle', 0);
$figure = self::URI . $article_content->find('img.news-image', 0)->getAttribute('src');
$figure_caption = $article_content->find('.image-description', 0)->plaintext;
$author = $article_content->find('span.main-article-author', 0)->plaintext;
$preamble = $article_content->find('h4.main-article-ingress', 0)->plaintext;
$article_text = '';
foreach ($article_content->find('div') as $div) {
if (!$div->hasAttribute('class')) {
$article_text = $div;
}
}
// Use a regular expression to extract the name
if (preg_match('/Text:\s*(.*?)\s*Foto:/', $author, $matches)) {
$author = $matches[1]; // This will contain 'Jonna Jansson'
}
$content = '<b> [' . $category . '] <i>' . $preamble . '</i></b><br/><br/>';
$content .= '<figure>';
$content .= '<img src=' . $figure . '>';
$content .= '<figcaption>' . $figure_caption . '</figcaption>';
$content .= '</figure>';
$content .= $article_text;
$this->items[] = [
'uri' => $url,
'title' => $title,
'author' => $author,
'timestamp' => $published,
'content' => trim($content),
];
}
}
}

View File

@ -27,11 +27,6 @@ class DagensNyheterDirektBridge extends BridgeAbstract
$url = self::BASEURL . $link;
$title = $element->find('h2', 0)->plaintext;
$author = $element->find('div.ds-byline__titles', 0)->plaintext;
// Debug::log($link);
// Debug::log($datetime);
// Debug::log($title);
// Debug::log($url);
// Debug::log($author);
$article_content = $element->find('div.direkt-post__content', 0);
$article_html = '';

View File

@ -0,0 +1,96 @@
<?php
class DailythanthiBridge extends BridgeAbstract
{
const NAME = 'Dailythanthi';
const URI = 'https://www.dailythanthi.com';
const DESCRIPTION = 'Retrieve news from dailythanthi.com';
const MAINTAINER = 'tillcash';
const PARAMETERS = [
[
'topic' => [
'name' => 'topic',
'type' => 'list',
'values' => [
'news' => [
'tamilnadu' => 'news/state',
'india' => 'news/india',
'world' => 'news/world',
'sirappu-katturaigal' => 'news/sirappukatturaigal',
],
'cinema' => [
'news' => 'cinema/cinemanews',
],
'sports' => [
'sports' => 'sports',
'cricket' => 'sports/cricket',
'football' => 'sports/football',
'tennis' => 'sports/tennis',
'hockey' => 'sports/hockey',
'other-sports' => 'sports/othersports',
],
'devotional' => [
'devotional' => 'others/devotional',
'aalaya-varalaru' => 'aalaya-varalaru',
],
],
],
],
];
public function getName()
{
$topic = $this->getKey('topic');
return self::NAME . ($topic ? ' - ' . ucfirst($topic) : '');
}
public function collectData()
{
$dom = getSimpleHTMLDOM(self::URI . '/' . $this->getInput('topic'));
foreach ($dom->find('div.ListingNewsWithMEDImage') as $element) {
$slug = $element->find('a', 1);
$title = $element->find('h3', 0);
if (!$slug || !$title) {
continue;
}
$url = self::URI . $slug->href;
$date = $element->find('span', 1);
$date = $date ? $date->{'data-datestring'} : '';
$this->items[] = [
'content' => $this->constructContent($url),
'timestamp' => $date ? $date . 'UTC' : '',
'title' => $title->plaintext,
'uid' => $slug->href,
'uri' => $url,
];
}
}
private function constructContent($url)
{
$dom = getSimpleHTMLDOMCached($url);
$article = $dom->find('div.details-content-story', 0);
if (!$article) {
return 'Content Not Found';
}
// Remove ads
foreach ($article->find('div[id*="_ad"]') as $remove) {
$remove->outertext = '';
}
// Correct image tag in $article
foreach ($article->find('h-img') as $img) {
$img->parent->outertext = sprintf('<p><img src="%s"></p>', $img->src);
}
$image = $dom->find('div.main-image-caption-container img', 0);
$image = $image ? '<p>' . $image->outertext . '</p>' : '';
return $image . $article;
}
}

View File

@ -9,7 +9,7 @@ class DarkReadingBridge extends FeedExpander
const PARAMETERS = [ [
'feed' => [
'name' => 'Feed',
'name' => 'Feed (NOT IN USE)',
'type' => 'list',
'values' => [
'All Dark Reading Stories' => '000_AllArticles',
@ -41,17 +41,7 @@ class DarkReadingBridge extends FeedExpander
public function collectData()
{
$feed = $this->getInput('feed');
$feed_splitted = explode('_', $feed);
$feed_id = $feed_splitted[0];
$feed_name = $feed_splitted[1];
if (empty($feed) || !ctype_digit($feed_id) || !preg_match('/[A-Za-z%20\/]/', $feed_name)) {
returnClientError('Invalid feed, please check the "feed" parameter.');
}
$feed_url = $this->getURI() . 'rss_simple.asp';
if ($feed_id != '000') {
$feed_url .= '?f_n=' . $feed_id . '&f_ln=' . $feed_name;
}
$feed_url = 'https://www.darkreading.com/rss.xml';
$limit = $this->getInput('limit') ?? 10;
$this->collectExpandableDatas($feed_url, $limit);
}
@ -71,7 +61,7 @@ class DarkReadingBridge extends FeedExpander
private function extractArticleContent($article)
{
$content = $article->find('div.article-content', 0)->innertext;
$content = $article->find('div.ContentModule-Wrapper', 0)->innertext;
foreach (
[

View File

@ -1,40 +0,0 @@
<?php
class DavesTrailerPageBridge extends BridgeAbstract
{
const MAINTAINER = 'johnnygroovy';
const NAME = 'Daves Trailer Page Bridge';
const URI = 'https://www.davestrailerpage.co.uk/';
const DESCRIPTION = 'Last trailers in HD thanks to Dave.';
public function collectData()
{
$html = getSimpleHTMLDOM(static::URI)
or returnClientError('No results for this query.');
$curr_date = null;
foreach ($html->find('tr') as $tr) {
// If it's a date row, update the current date
if ($tr->align == 'center') {
$curr_date = $tr->plaintext;
continue;
}
$item = [];
// title
$item['title'] = $tr->find('td', 0)->find('b', 0)->plaintext;
// content
$item['content'] = $tr->find('ul', 1);
// uri
$item['uri'] = $tr->find('a', 3)->getAttribute('href');
// date: parsed by FeedItem using strtotime
$item['timestamp'] = $curr_date;
$this->items[] = $item;
}
}
}

File diff suppressed because it is too large Load Diff

View File

@ -24,7 +24,8 @@ class DemosBerlinBridge extends BridgeAbstract
public function collectData()
{
$json = getContents('https://www.berlin.de/polizei/service/versammlungsbehoerde/versammlungen-aufzuege/index.php/index/all.json');
$url = 'https://www.berlin.de/polizei/service/versammlungsbehoerde/versammlungen-aufzuege/index.php/index/all.json';
$json = getContents($url);
$jsonFile = json_decode($json, true);
$daysInterval = DateInterval::createFromDateString($this->getInput('days') . ' day');

View File

@ -78,13 +78,9 @@ class DerpibooruBridge extends BridgeAbstract
public function collectData()
{
$queryJson = json_decode(getContents(
self::URI
. 'api/v1/json/search/images?filter_id='
. urlencode($this->getInput('f'))
. '&q='
. urlencode($this->getInput('q'))
));
$url = self::URI . 'api/v1/json/search/images?filter_id=' . urlencode($this->getInput('f')) . '&q=' . urlencode($this->getInput('q'));
$queryJson = json_decode(getContents($url));
foreach ($queryJson->images as $post) {
$item = [];

View File

@ -73,12 +73,12 @@ class DeutscheWelleBridge extends FeedExpander
protected function parseItem(array $item)
{
$parsedUrl = parse_url($item['uri']);
unset($parsedUrl['query']);
$url = $this->unparseUrl($parsedUrl);
$parsedUri = parse_url($item['uri']);
unset($parsedUri['query']);
$item['uri'] = $this->unparseUrl($parsedUri);
$page = getSimpleHTMLDOM($url);
$page = defaultLinkTo($page, $url);
$page = getSimpleHTMLDOM($item['uri']);
$page = defaultLinkTo($page, $item['uri']);
$article = $page->find('article', 0);
@ -112,6 +112,13 @@ class DeutscheWelleBridge extends FeedExpander
$img->height = null;
}
// remove bad img src's added by defaultLinkTo() above
// these images should have src="" and will then use
// the srcset attribute to load the best image for the displayed size
foreach ($article->find('figure > picture > img') as $img) {
$img->src = '';
}
// replace lazy-loaded images
foreach ($article->find('figure.placeholder-image') as $figure) {
$img = $figure->find('img', 0);

View File

@ -0,0 +1,28 @@
<?php
class DeutscherAeroClubBridge extends XPathAbstract
{
const NAME = 'Deutscher Aero Club';
const URI = 'https://www.daec.de/news/';
const DESCRIPTION = 'News aus Luftsport und Dachverband';
const MAINTAINER = 'hleskien';
const FEED_SOURCE_URL = 'https://www.daec.de/news/';
const XPATH_EXPRESSION_FEED_ICON = './/link[@rel="icon"][1]/@href';
const XPATH_EXPRESSION_ITEM = '//div[contains(@class, "news-list-view")]/div[contains(@class, "article")]';
const XPATH_EXPRESSION_ITEM_TITLE = './/span[@itemprop="headline"]';
const XPATH_EXPRESSION_ITEM_CONTENT = './/div[@itemprop="description"]/p';
const XPATH_EXPRESSION_ITEM_URI = './/div[@class="news-header"]//a/@href';
//const XPATH_EXPRESSION_ITEM_AUTHOR = './/';
const XPATH_EXPRESSION_ITEM_TIMESTAMP = './/time/@datetime';
const XPATH_EXPRESSION_ITEM_ENCLOSURES = './/img/@src';
//const XPATH_EXPRESSION_ITEM_CATEGORIES = './/';
protected function formatItemTimestamp($value)
{
$dti = DateTimeImmutable::createFromFormat('Y-m-d', $value);
$dti = $dti->setTime(0, 0, 0);
return $dti->getTimestamp();
}
}

View File

@ -47,7 +47,7 @@ class DiarioDoAlentejoBridge extends BridgeAbstract
}, self::PT_MONTH_NAMES),
array_map(function ($num) {
return sprintf('-%02d-', $num);
}, range(1, sizeof(self::PT_MONTH_NAMES))),
}, range(1, count(self::PT_MONTH_NAMES))),
$element->find('span.date', 0)->innertext
);

View File

@ -18,12 +18,12 @@ favicon-63b2904a073c89b52b19aa08cebc16a154bcf83fee8ecc6439968b1e6db569c7.ico';
{
$html = getSimpleHTMLDOM(self::URI);
$json = $this->loadEmbeddedJsonData($html);
$data = $this->fetchData($html);
foreach ($html->find('li[id^="screenshot-"]') as $shot) {
$item = [];
$additional_data = $this->findJsonForShot($shot, $json);
$additional_data = $this->findJsonForShot($shot, $data);
if ($additional_data === null) {
$item['uri'] = self::URI . $shot->find('a', 0)->href;
$item['title'] = $shot->find('.shot-title', 0)->plaintext;
@ -46,9 +46,8 @@ favicon-63b2904a073c89b52b19aa08cebc16a154bcf83fee8ecc6439968b1e6db569c7.ico';
}
}
private function loadEmbeddedJsonData($html)
private function fetchData($html)
{
$json = [];
$scripts = $html->find('script');
foreach ($scripts as $script) {
@ -69,12 +68,17 @@ favicon-63b2904a073c89b52b19aa08cebc16a154bcf83fee8ecc6439968b1e6db569c7.ico';
$end = strpos($script->innertext, '];') + 1;
// convert JSON to PHP array
$json = json_decode(substr($script->innertext, $start, $end - $start), true);
break;
$json = substr($script->innertext, $start, $end - $start);
try {
// TODO: fix broken json
return Json::decode($json);
} catch (\JsonException $e) {
return [];
}
}
}
return $json;
return [];
}
private function findJsonForShot($shot, $json)

View File

@ -0,0 +1,86 @@
<?php
class DuvarOrgBridge extends BridgeAbstract
{
const NAME = 'Duvar.org - Haberler';
const MAINTAINER = 'yourname';
const URI = 'https://duvar.org';
const DESCRIPTION = 'Returns the latest articles from Duvar.org - News from Turkey and the world';
const CACHE_TIMEOUT = 3600; // 60min
const PARAMETERS = [[
'postcount' => [
'name' => 'Limit',
'type' => 'number',
'required' => true,
'title' => 'Maximum number of items to return',
'defaultValue' => 20,
],
'urlsuffix' => [
'name' => 'URL Suffix',
'type' => 'list',
'title' => 'Suffix for the URL to scrape a specific section',
'defaultValue' => 'Main',
'values' => [
'Main' => '',
'Balanced' => '/uyumlu',
'Protest' => '/muhalif',
'Center' => '/merkez',
'Alternative' => '/alternatif',
'Global' => '/global',
],
],
]];
public function collectData()
{
$postCount = $this->getInput('postcount');
$urlSuffix = $this->getInput('urlsuffix');
$url = self::URI . $urlSuffix;
$html = getSimpleHTMLDOM($url);
foreach ($html->find('article.news-item') as $data) {
if ($data === null) {
continue;
}
try {
$item = [];
$linkElement = $data->find('h2.news-title a', 0);
$titleElement = $data->find('h2.news-title a', 0);
$timestampElement = $data->find('time.meta-tag.date-tag', 0);
$contentElement = $data->find('div.news-description', 0);
if ($linkElement) {
$item['uri'] = $linkElement->getAttribute('href');
} else {
continue;
}
if ($titleElement) {
$item['title'] = trim($titleElement->plaintext);
} else {
continue;
}
if ($timestampElement) {
$item['timestamp'] = strtotime($timestampElement->plaintext);
} else {
$item['timestamp'] = time();
}
if ($contentElement) {
$item['content'] = trim($contentElement->plaintext);
} else {
$item['content'] = '';
}
$item['uid'] = hash('sha256', $item['title']);
$this->items[] = $item;
if (count($this->items) >= $postCount) {
break;
}
} catch (Exception $e) {
continue;
}
}
}
}

42
bridges/EASeedBridge.php Normal file
View File

@ -0,0 +1,42 @@
<?php
class EASeedBridge extends BridgeAbstract
{
const NAME = 'EA Seed Blog';
const URI = 'https://www.ea.com/seed';
const DESCRIPTION = 'Posts from the EA Seed blog';
const MAINTAINER = 'thefranke';
const CACHE_TIMEOUT = 86400; // 24h
public function collectData()
{
$dom = getSimpleHTMLDOM(static::URI);
$dom = $dom->find('ea-grid', 0);
if (!$dom) {
throw new \Exception(sprintf('Unable to find css selector on `%s`', $url));
}
$dom = defaultLinkTo($dom, $this->getURI());
foreach ($dom->find('ea-tile') as $article) {
$a = $article->find('a', 0);
$date = $article->find('div', 1)->plaintext;
$title = $article->find('h3', 0)->plaintext;
$author = $article->find('div', 0)->plaintext;
$entry = getSimpleHTMLDOMCached($a->href, static::CACHE_TIMEOUT * 7 * 4);
$content = $entry->find('main', 0);
// remove header and links to other posts
$content->find('ea-header', 0)->outertext = '';
$content->find('ea-section', -1)->outertext = '';
$this->items[] = [
'title' => $title,
'author' => $author,
'uri' => $a->href,
'content' => $content,
'timestamp' => strtotime($date),
];
}
}
}

View File

@ -5,15 +5,21 @@ class EBayBridge extends BridgeAbstract
const NAME = 'eBay';
const DESCRIPTION = 'Returns the search results from the eBay auctioning platforms';
const URI = 'https://www.eBay.com';
const MAINTAINER = 'wrobelda';
const MAINTAINER = 'NotsoanoNimus, wrobelda';
const PARAMETERS = [[
'url' => [
'name' => 'Search URL',
'title' => 'Copy the URL from your browser\'s address bar after searching for your items and paste it here',
'pattern' => '^(https:\/\/)?(www.)?ebay\.(com|com\.au|at|be|ca|ch|cn|es|fr|de|com\.hk|ie|it|com\.my|nl|ph|pl|com\.sg|co\.uk).*$',
'pattern' => '^(https:\/\/)?(www\.)?(befr\.|benl\.)?ebay\.(com|com\.au|at|be|ca|ch|cn|es|fr|de|com\.hk|ie|it|com\.my|nl|ph|pl|com\.sg|co\.uk)\/.*$',
'exampleValue' => 'https://www.ebay.com/sch/i.html?_nkw=atom+rss',
'required' => true,
]
],
'includesSearchLink' => [
'name' => 'Include Original Search Link',
'title' => 'Whether or not each feed item should include the original search query link to eBay which was used to find the given listing.',
'type' => 'checkbox',
'defaultValue' => false,
],
]];
public function getURI()
@ -23,6 +29,10 @@ class EBayBridge extends BridgeAbstract
$uri = trim(preg_replace('/([?&])_sop=[^&]+(&|$)/', '$1', $this->getInput('url')), '?&/');
$uri .= (parse_url($uri, PHP_URL_QUERY) ? '&' : '?') . '_sop=10';
// Ensure the List View is used instead of the Gallery View.
$uri = trim(preg_replace('/[?&]_dmd=[^&]+(&|$)/i', '$1', $uri), '?&/');
$uri .= '&_dmd=1';
return $uri;
} else {
return parent::getURI();
@ -31,7 +41,11 @@ class EBayBridge extends BridgeAbstract
public function getName()
{
$urlQueries = explode('&', parse_url($this->getInput('url'), PHP_URL_QUERY));
$url = $this->getInput('url');
if (!$url) {
return parent::getName();
}
$urlQueries = explode('&', parse_url($url, PHP_URL_QUERY));
$searchQuery = array_reduce($urlQueries, function ($q, $p) {
if (preg_match('/^_nkw=(.+)$/i', $p, $matches)) {
@ -42,7 +56,7 @@ class EBayBridge extends BridgeAbstract
});
if ($searchQuery) {
return $searchQuery[0];
return 'eBay - ' . $searchQuery[0];
}
return parent::getName();
@ -57,44 +71,90 @@ class EBayBridge extends BridgeAbstract
$inexactMatches->remove();
}
// Remove "NEW LISTING" labels: we sort by the newest, so this is redundant.
foreach ($html->find('.LIGHT_HIGHLIGHT') as $new_listing_label) {
$new_listing_label->remove();
}
$results = $html->find('ul.srp-results > li.s-item');
foreach ($results as $listing) {
$item = [];
// Remove "NEW LISTING" label, we sort by the newest, so this is redundant
foreach ($listing->find('.LIGHT_HIGHLIGHT') as $new_listing_label) {
$new_listing_label->remove();
// Define a closure to shorten the ugliness of querying the current listing.
$find = function ($query, $altText = '') use ($listing) {
return $listing->find($query, 0)->plaintext ?? $altText;
};
$item['title'] = $find('.s-item__title');
if (!$item['title']) {
// Skip entries where the title cannot be found (for w/e reason).
continue;
}
$listingTitle = $listing->find('.s-item__title', 0);
if ($listingTitle) {
$item['title'] = $listingTitle->plaintext;
}
$subtitle = implode('', $listing->find('.s-item__subtitle'));
$listingUrl = $listing->find('.s-item__link', 0);
if ($listingUrl) {
$item['uri'] = $listingUrl->href;
// It appears there may be more than a single 'subtitle' subclass in the listing. Collate them.
$subtitles = $listing->find('.s-item__subtitle');
if (is_array($subtitles)) {
$subtitle = trim(implode(' ', array_column($subtitles, 'plaintext')));
} else {
$item['uri'] = null;
$subtitle = trim($subtitles->plaintext ?? '');
}
// Get the listing's link and uid.
$itemUri = $listing->find('.s-item__link', 0);
if ($itemUri) {
$item['uri'] = $itemUri->href;
}
if (preg_match('/.*\/itm\/(\d+).*/i', $item['uri'], $matches)) {
$item['uid'] = $matches[1];
}
$priceDom = $listing->find('.s-item__details > .s-item__detail > .s-item__price', 0);
$price = $priceDom->plaintext ?? 'N/A';
// Price should be fetched on its own so we can provide the alt text without complication.
$price = $find('.s-item__price', '[NO PRICE]');
$shippingFree = $listing->find('.s-item__details > .s-item__detail > .s-item__freeXDays', 0)->plaintext ?? '';
$localDelivery = $listing->find('.s-item__details > .s-item__detail > .s-item__localDelivery', 0)->plaintext ?? '';
$logisticsCost = $listing->find('.s-item__details > .s-item__detail > .s-item__logisticsCost', 0)->plaintext ?? '';
// Map a list of dynamic variable names to their subclasses within the listing.
// This is just a bit of sugar to make this cleaner and more maintainable.
$propertyMappings = [
'additionalPrice' => '.s-item__additional-price',
'discount' => '.s-item__discount',
'shippingFree' => '.s-item__freeXDays',
'localDelivery' => '.s-item__localDelivery',
'logisticsCost' => '.s-item__logisticsCost',
'location' => '.s-item__location',
'obo' => '.s-item__formatBestOfferEnabled',
'sellerInfo' => '.s-item__seller-info-text',
'bids' => '.s-item__bidCount',
'timeLeft' => '.s-item__time-left',
'timeEnd' => '.s-item__time-end',
];
$location = $listing->find('.s-item__details > .s-item__detail > .s-item__location', 0)->plaintext ?? '';
foreach ($propertyMappings as $k => $v) {
$$k = $find($v);
}
$sellerInfo = $listing->find('.s-item__seller-info-text', 0)->plaintext ?? '';
// When an additional price detail or discount is defined, create the 'discountLine'.
if ($additionalPrice || $discount) {
$discountLine = '<br /><em>('
. trim($additionalPrice ?? '')
. '; ' . trim($discount ?? '')
. ')</em>';
} else {
$discountLine = '';
}
// Prepend the time-left info with a comma if the right details were found.
$timeInfo = trim($timeLeft . ' ' . $timeEnd);
if ($timeInfo) {
$timeInfo = ', ' . $timeInfo;
}
// Set the listing type.
if ($bids) {
$listingTypeDetails = "Auction: {$bids}{$timeInfo}";
} else {
$listingTypeDetails = 'Buy It Now';
}
// Acquire the listing's primary image and atach it.
$image = $listing->find('.s-item__image-wrapper > img', 0);
if ($image) {
// Not quite sure why append fragment here
@ -102,11 +162,23 @@ class EBayBridge extends BridgeAbstract
$item['enclosures'] = [$imageUrl];
}
// Include the original search link, if specified.
if ($this->getInput('includesSearchLink')) {
$searchLink = '<p><small><a target="_blank" href="' . e($this->getURI()) . '">View Search</a></small></p>';
} else {
$searchLink = '';
}
// Build the final item's content to display and add the item onto the list.
$item['content'] = <<<CONTENT
<p>$sellerInfo $location</p>
<p><span style="font-weight:bold">$price</span> $shippingFree $localDelivery $logisticsCost<span></span></p>
<p>$subtitle</p>
<p><strong>$price</strong> $obo ($listingTypeDetails)
$discountLine
<br /><small>$shippingFree $localDelivery $logisticsCost</small></p>
<p>{$subtitle}</p>
$searchLink
CONTENT;
$this->items[] = $item;
}
}

View File

@ -0,0 +1,85 @@
<?php
class EDDHPiRepsBridge extends BridgeAbstract
{
const NAME = 'EDDH.de PIREPs';
const URI = 'https://eddh.de/info/pireps_08days.php';
const DESCRIPTION = 'Erfahrungen und Tipps von Piloten für Piloten: Die Einträge der letzten 8 Tage';
const MAINTAINER = 'hleskien';
//const PARAMETERS = [];
//const CACHE_TIMEOUT = 3600;
public function collectData()
{
$dom = getSimpleHTMLDOM(self::URI);
foreach ($dom->find('table table table td') as $itemnode) {
$texts = $this->extractTexts($itemnode->find('text, br'));
$timestamp = $itemnode->find('.su_dat', 0)->innertext();
$uri = $itemnode->find('.pir_hd a', 0)->href;
$this->items[] = [
'timestamp' => $this->formatItemTimestamp($timestamp),
'title' => $this->formatItemTitle($texts),
'uri' => $this->formatItemUri($uri),
'author' => $this->formatItemAuthor($texts),
'content' => $this->formatItemContent($texts)
];
}
}
public function getIcon()
{
return 'https://eddh.de/favicon.ico';
}
private function extractTexts($nodes)
{
$texts = [];
$i = 0;
foreach ($nodes as $node) {
$text = trim($node->outertext());
if ($node->tag == 'br') {
$texts[$i++] = "\n";
} elseif (($node->tag == 'text') && ($text != '')) {
$text = iconv('Windows-1252', 'UTF-8', $text);
$text = str_replace('&nbsp;', '', $text);
$texts[$i++] = $text;
}
}
return $texts;
}
protected function formatItemAuthor($texts)
{
$pos = array_search('Name:', $texts);
return $texts[$pos + 1];
}
protected function formatItemContent($texts)
{
$pos1 = array_search('Bemerkungen:', $texts);
$pos2 = array_search('Bewertung:', $texts);
$content = '';
for ($i = $pos1 + 1; $i < $pos2; $i++) {
$content .= $texts[$i];
}
return trim($content);
}
protected function formatItemTitle($texts)
{
$texts[5] = ltrim($texts[5], '(');
return implode(' ', [$texts[1], $texts[2], $texts[3], $texts[5]]);
}
protected function formatItemTimestamp($value)
{
$value = str_replace('Eintrag vom', '', $value);
$value = trim($value);
return strtotime($value);
}
protected function formatItemUri($value)
{
return 'https://eddh.de/info/' . $value;
}
}

View File

@ -0,0 +1,42 @@
<?php
class EDDHPresseschauBridge extends XPathAbstract
{
const NAME = 'EDDH.de Presseschau';
const URI = 'https://eddh.de/presse/presseschau.php';
const DESCRIPTION = 'Luftfahrt-Presseschau: Presse-Artikel aus der Luftfahrt';
const MAINTAINER = 'hleskien';
const FEED_SOURCE_URL = 'https://eddh.de/presse/presseschau.php';
//const XPATH_EXPRESSION_FEED_ICON = './/link[@rel="icon"]/@href';
const XPATH_EXPRESSION_ITEM = '//table//table[.//p[@class="pressnews"]]//td';
const XPATH_EXPRESSION_ITEM_TITLE = './h4';
const XPATH_EXPRESSION_ITEM_CONTENT = './p[@class="pressnews"]';
const XPATH_EXPRESSION_ITEM_URI = './p[@class="pressnews"]/a/@href';
const XPATH_EXPRESSION_ITEM_AUTHOR = './p[@class="quelle"]';
const XPATH_EXPRESSION_ITEM_TIMESTAMP = './p[@class="quelle"]';
//const XPATH_EXPRESSION_ITEM_ENCLOSURES = './';
//const XPATH_EXPRESSION_ITEM_CATEGORIES = './/';
public function getIcon()
{
return 'https://eddh.de/favicon.ico';
}
protected function formatItemAuthor($value)
{
$parts = explode('(', $value);
$author = trim($parts[0]);
return $author;
}
protected function formatItemTimestamp($value)
{
$parts = explode('(', $value);
$ws = ["\n", "\t", ' ', ')'];
$value = str_replace($ws, '', $parts[1]);
$dti = DateTimeImmutable::createFromFormat('d.m.Y', $value);
$dti = $dti->setTime(0, 0, 0);
return $dti->getTimestamp();
}
}

View File

@ -50,7 +50,9 @@ class EZTVBridge extends BridgeAbstract
$eztv_uri = $this->getEztvUri();
$ids = explode(',', trim($this->getInput('ids')));
foreach ($ids as $id) {
$data = json_decode(getContents(sprintf('%s/api/get-torrents?imdb_id=%s', $eztv_uri, $id)));
$url = sprintf('%s/api/get-torrents?imdb_id=%s', $eztv_uri, $id);
$json = getContents($url);
$data = json_decode($json);
if (!isset($data->torrents)) {
// No results
continue;
@ -96,7 +98,7 @@ class EZTVBridge extends BridgeAbstract
protected function getItemFromTorrent($torrent)
{
$item = [];
$item['uri'] = $torrent->episode_url;
$item['uri'] = $torrent->episode_url ?? $torrent->torrent_url;
$item['author'] = $torrent->imdb_id;
$item['timestamp'] = $torrent->date_released_unix;
$item['title'] = $torrent->title;

View File

@ -8,6 +8,12 @@ class EconomistBridge extends FeedExpander
const CACHE_TIMEOUT = 3600; //1hour
const DESCRIPTION = 'Returns the latest articles for the selected category';
const CONFIGURATION = [
'cookie' => [
'required' => false,
]
];
const PARAMETERS = [
'global' => [
'limit' => [
@ -99,7 +105,24 @@ class EconomistBridge extends FeedExpander
protected function parseItem(array $item)
{
$dom = getSimpleHTMLDOM($item['uri']);
$headers = [];
if ($this->getOption('cookie')) {
$headers = [
'Authority: www.economist.com',
'Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
'Accept-language: en-US,en;q=0.9',
'Cache-control: max-age=0',
'Cookie: ' . $this->getOption('cookie'),
'Upgrade-insecure-requests: 1',
'User-agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.0.0 Safari/537.36'
];
}
try {
$dom = getSimpleHTMLDOM($item['uri'], $headers);
} catch (Exception $e) {
$item['content'] = $e->getMessage();
return $item;
}
$article = $dom->find('#new-article-template', 0);
if ($article == null) {
@ -204,6 +227,15 @@ class EconomistBridge extends FeedExpander
foreach ($elem->find('a.ds-link-with-arrow-icon') as $a) {
$a->parent->removeChild($a);
}
// Sections like "Leaders on day X"
foreach ($elem->find('div[data-tracking-id=content-well-chapter-list]') as $div) {
$div->parent->removeChild($div);
}
// "Explore more" section
foreach ($elem->find('h3[id=article-tags]') as $h3) {
$div = $h3->parent;
$div->parent->removeChild($div);
}
// The Economist puts infographics into iframes, which doesn't
// work in any of my readers. So this replaces iframes with

View File

@ -9,6 +9,12 @@ class EconomistWorldInBriefBridge extends BridgeAbstract
const CACHE_TIMEOUT = 3600; // 1 hour
const DESCRIPTION = 'Returns stories from the World in Brief section';
const CONFIGURATION = [
'cookie' => [
'required' => false,
]
];
const PARAMETERS = [
'' => [
'splitGobbets' => [
@ -41,19 +47,34 @@ class EconomistWorldInBriefBridge extends BridgeAbstract
public function collectData()
{
$html = getSimpleHTMLDOM(self::URI);
$gobbets = $html->find('._gobbets', 0);
$headers = [];
if ($this->getOption('cookie')) {
$headers = [
'Authority: www.economist.com',
'Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
'Accept-language: en-US,en;q=0.9',
'Cache-control: max-age=0',
'Cookie: ' . $this->getOption('cookie'),
'Upgrade-insecure-requests: 1',
'User-agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.0.0 Safari/537.36'
];
}
$html = getSimpleHTMLDOM(self::URI, $headers);
$gobbets = $html->find('p[data-component="the-world-in-brief-paragraph"]');
if ($this->getInput('splitGobbets') == 1) {
$this->splitGobbets($gobbets);
} else {
$this->mergeGobbets($gobbets);
};
if ($this->getInput('agenda') == 1) {
$articles = $html->find('._articles', 0);
$this->collectArticles($articles);
$articles = $html->find('div[data-test-id="chunks"] > div > div', 0);
if ($articles != null) {
$this->collectArticles($articles);
}
}
if ($this->getInput('quote') == 1) {
$quote = $html->find('._quote-container', 0);
$quote = $html->find('blockquote[data-test-id="inspirational-quote"]', 0);
$this->addQuote($quote);
}
}
@ -63,7 +84,7 @@ class EconomistWorldInBriefBridge extends BridgeAbstract
$today = new Datetime();
$today->setTime(0, 0, 0, 0);
$limit = $this->getInput('limit');
foreach ($gobbets->find('._gobbet') as $gobbet) {
foreach ($gobbets as $gobbet) {
$title = $gobbet->plaintext;
$match = preg_match('/[\.,]/', $title, $matches, PREG_OFFSET_CAPTURE);
if ($match > 0) {
@ -89,7 +110,7 @@ class EconomistWorldInBriefBridge extends BridgeAbstract
$today = new Datetime();
$today->setTime(0, 0, 0, 0);
$contents = '';
foreach ($gobbets->find('._gobbet') as $gobbet) {
foreach ($gobbets as $gobbet) {
$contents .= "<p>{$gobbet->innertext}";
}
$this->items[] = [
@ -106,10 +127,14 @@ class EconomistWorldInBriefBridge extends BridgeAbstract
$i = 0;
$today = new Datetime();
$today->setTime(0, 0, 0, 0);
foreach ($articles->find('._article') as $article) {
$title = $article->find('._headline', 0)->plaintext;
$image = $article->find('._main-image', 0);
$content = $article->find('._content', 0);
foreach ($articles->children() as $element) {
if ($element->tag != 'div') {
continue;
}
$image = $element->find('figure', 0);
$title = $element->find('h3', 0)->plaintext;
$content = $element->find('h3', 0)->parent();
$content->find('h3', 0)->outertext = '';
$res_content = '';
if ($image != null && $this->getInput('agendaPictures') == 1) {

106
bridges/EdfPricesBridge.php Normal file
View File

@ -0,0 +1,106 @@
<?php
class EdfPricesBridge extends BridgeAbstract
{
const NAME = 'EDF tarifs';
// pull info from this site for now because EDF do not provide correct opendata
const URI = 'https://www.jechange.fr';
const DESCRIPTION = 'Fetches the latest infos of EDF prices';
const MAINTAINER = 'floviolleau';
const PARAMETERS = [
[
'contract' => [
'name' => 'Choisir un contrat',
'type' => 'list',
// we can add later HCHP, EJP, base
'values' => ['Tempo' => '/energie/edf/tarifs/tempo'],
]
]
];
const CACHE_TIMEOUT = 7200; // 2h
/**
* @param simple_html_dom $html
* @param string $contractUri
* @return void
*/
private function tempo(simple_html_dom $html, string $contractUri): void
{
// current color and next
$daysDom = $html->find('#calendrier', 0)->nextSibling()->find('.card--ejp');
if ($daysDom && count($daysDom) === 2) {
foreach ($daysDom as $dayDom) {
$day = trim($dayDom->find('.card__title', 0)->innertext) . '/' . (new \DateTime('now'))->format(('Y'));
$dayColor = $dayDom->find('.card-ejp__icon span', 0)->innertext;
$text = $day . ' - ' . $dayColor;
$item['uri'] = self::URI . $contractUri;
$item['title'] = $text;
$item['author'] = self::MAINTAINER;
$item['content'] = $text;
$item['uid'] = hash('sha256', $item['title']);
$this->items[] = $item;
}
}
// colors
$ulDom = $html->find('#tarif-de-l-offre-edf-tempo-current-date-html-year', 0)->nextSibling()->nextSibling()->nextSibling();
$elementsDom = $ulDom->find('li');
if ($elementsDom && count($elementsDom) === 3) {
foreach ($elementsDom as $elementDom) {
$item = [];
$matches = [];
preg_match_all('/Jour (.*) : Heures (.*) : (.*) € \/ Heures (.*) : (.*) €/um', $elementDom->innertext, $matches, PREG_SET_ORDER, 0);
if ($matches && count($matches[0]) === 6) {
for ($i = 0; $i < 2; $i++) {
$text = 'Jour ' . $matches[0][1] . ' - Heures ' . $matches[0][2 + 2 * $i] . ' : ' . $matches[0][3 + 2 * $i] . '€';
$item['uri'] = self::URI . $contractUri;
$item['title'] = $text;
$item['author'] = self::MAINTAINER;
$item['content'] = $text;
$item['uid'] = hash('sha256', $item['title']);
$this->items[] = $item;
}
}
}
}
// powers
$ulPowerContract = $ulDom->nextSibling()->nextSibling();
$elementsPowerContractDom = $ulPowerContract->find('li');
if ($elementsPowerContractDom && count($elementsPowerContractDom) === 4) {
foreach ($elementsPowerContractDom as $elementPowerContractDom) {
$item = [];
$matches = [];
preg_match_all('/(.*) kVA : (.*) €/um', $elementPowerContractDom->innertext, $matches, PREG_SET_ORDER, 0);
if ($matches && count($matches[0]) === 3) {
$text = $matches[0][1] . ' kVA : ' . $matches[0][2] . '€';
$item['uri'] = self::URI . $contractUri;
$item['title'] = $text;
$item['author'] = self::MAINTAINER;
$item['content'] = $text;
$item['uid'] = hash('sha256', $item['title']);
$this->items[] = $item;
}
}
}
}
public function collectData()
{
$contract = $this->getKey('contract');
$contractUri = $this->getInput('contract');
$html = getSimpleHTMLDOM(self::URI . $contractUri);
if ($contract === 'Tempo') {
$this->tempo($html, $contractUri);
}
}
}

View File

@ -34,11 +34,9 @@ class ElloBridge extends BridgeAbstract
];
if (!empty($this->getInput('u'))) {
$postData = getContents(self::URI . 'api/v2/users/~' . urlencode($this->getInput('u')) . '/posts', $header) or
returnServerError('Unable to query Ello API.');
$postData = getContents(self::URI . 'api/v2/users/~' . urlencode($this->getInput('u')) . '/posts', $header);
} else {
$postData = getContents(self::URI . 'api/v2/posts?terms=' . urlencode($this->getInput('s')), $header) or
returnServerError('Unable to query Ello API.');
$postData = getContents(self::URI . 'api/v2/posts?terms=' . urlencode($this->getInput('s')), $header);
}
$postData = json_decode($postData);
@ -117,7 +115,7 @@ class ElloBridge extends BridgeAbstract
$apiKey = $this->cache->get($cacheKey);
if (!$apiKey) {
$keyInfo = getContents(self::URI . 'api/webapp-token') or returnServerError('Unable to get token.');
$keyInfo = getContents(self::URI . 'api/webapp-token');
$apiKey = json_decode($keyInfo)->token->access_token;
$ttl = 60 * 60 * 20;
$this->cache->set($cacheKey, $apiKey, $ttl);

View File

@ -98,7 +98,7 @@ class ErowallBridge extends BridgeAbstract
$ret .= 'dat/';
break;
default:
$tag = $this->getInput('tag');
$tag = $this->getInput('tag') ?? '';
$ret .= 'teg/' . str_replace(' ', '+', $tag);
}

View File

@ -31,7 +31,7 @@ class FDroidBridge extends BridgeAbstract
CURLOPT_NOBODY => true,
];
$reponse = getContents($url, [], $curlOptions, true);
$lastModified = $reponse['headers']['last-modified'][0] ?? null;
$lastModified = $reponse->getHeader('last-modified');
$timestamp = strtotime($lastModified ?? 'today');
return $timestamp;
}

View File

@ -14,7 +14,7 @@ class FDroidRepoBridge extends BridgeAbstract
'name' => 'Repository URL',
'title' => 'Usually ends with /repo/',
'required' => true,
'exampleValue' => 'https://srv.tt-rss.org/fdroid/repo'
'exampleValue' => 'https://molly.im/fdroid/foss/fdroid/repo'
]
],
'Latest Updates' => [
@ -35,7 +35,7 @@ class FDroidRepoBridge extends BridgeAbstract
'package' => [
'name' => 'Package Identifier',
'required' => true,
'exampleValue' => 'org.fox.ttrss'
'exampleValue' => 'im.molly.app'
]
]
];
@ -45,11 +45,7 @@ class FDroidRepoBridge extends BridgeAbstract
public function collectData()
{
if (!extension_loaded('zip')) {
throw new \Exception('FDroidRepoBridge requires the php-zip extension');
}
$this->repo = $this->getRepo();
$this->repo = $this->fetchData();
switch ($this->queriedContext) {
case 'Latest Updates':
$this->getAllUpdates();
@ -58,63 +54,15 @@ class FDroidRepoBridge extends BridgeAbstract
$this->getPackage($this->getInput('package'));
break;
default:
returnServerError('Unimplemented Context (collectData)');
throw new \Exception('Unimplemented Context (collectData)');
}
}
public function getURI()
{
if (empty($this->queriedContext)) {
return parent::getURI();
}
$url = rtrim($this->GetInput('url'), '/');
return strstr($url, '?', true) ?: $url;
}
public function getName()
{
if (empty($this->queriedContext)) {
return parent::getName();
}
$name = $this->repo['repo']['name'];
switch ($this->queriedContext) {
case 'Latest Updates':
return $name;
case 'Follow Package':
return $this->getInput('package') . ' - ' . $name;
default:
returnServerError('Unimplemented Context (getName)');
}
}
private function getRepo()
private function fetchData()
{
$url = $this->getURI();
// Get repo information (only available as JAR)
$jar = getContents($url . '/index-v1.jar');
$jar_loc = tempnam(sys_get_temp_dir(), '');
file_put_contents($jar_loc, $jar);
// JAR files are specially formatted ZIP files
$jar = new \ZipArchive();
if ($jar->open($jar_loc) !== true) {
unlink($jar_loc);
throw new \Exception('Failed to extract archive');
}
// Get file pointer to the relevant JSON inside
$fp = $jar->getStream('index-v1.json');
if (!$fp) {
returnServerError('Failed to get file pointer');
}
$data = json_decode(stream_get_contents($fp), true);
fclose($fp);
$jar->close();
unlink($jar_loc);
$json = getContents($url . '/index-v1.json');
$data = Json::decode($json);
return $data;
}
@ -158,9 +106,9 @@ class FDroidRepoBridge extends BridgeAbstract
$summary = $lang['summary'] ?? $app['summary'] ?? '';
$description = markdownToHtml(trim($lang['description'] ?? $app['description'] ?? 'None'));
$whatsNew = markdownToHtml(trim($lang['whatsNew'] ?? 'None'));
$website = $this->link($lang['webSite'] ?? $app['webSite'] ?? $app['authorWebSite'] ?? null);
$source = $this->link($app['sourceCode'] ?? null);
$issueTracker = $this->link($app['issueTracker'] ?? null);
$website = $this->createAnchor($lang['webSite'] ?? $app['webSite'] ?? $app['authorWebSite'] ?? null);
$source = $this->createAnchor($app['sourceCode'] ?? null);
$issueTracker = $this->createAnchor($app['issueTracker'] ?? null);
$license = $app['license'] ?? 'None';
$item['content'] = <<<EOD
{$icon}
@ -182,7 +130,7 @@ EOD;
private function getPackage($package)
{
if (!isset($this->repo['packages'][$package])) {
returnClientError('Invalid Package Name');
throw new \Exception('Invalid Package Name');
}
$package = $this->repo['packages'][$package];
@ -192,7 +140,7 @@ EOD;
$item['uri'] = $this->getURI() . '/' . $version['apkName'];
$item['title'] = $version['versionName'];
$item['timestamp'] = date(DateTime::ISO8601, (int) ($version['added'] / 1000));
$item['uid'] = $version['versionCode'];
$item['uid'] = (string) $version['versionCode'];
$size = round($version['size'] / 1048576, 1); // Bytes -> MB
$sdk_link = 'https://developer.android.com/studio/releases/platforms';
$item['content'] = <<<EOD
@ -208,11 +156,42 @@ EOD;
}
}
private function link($url)
public function getURI()
{
if (empty($this->queriedContext)) {
return parent::getURI();
}
$url = rtrim($this->getInput('url'), '/');
if (strstr($url, '?', true)) {
return strstr($url, '?', true);
} else {
return $url;
}
}
public function getName()
{
if (empty($this->queriedContext)) {
return parent::getName();
}
$name = $this->repo['repo']['name'];
switch ($this->queriedContext) {
case 'Latest Updates':
return $name;
case 'Follow Package':
return $this->getInput('package') . ' - ' . $name;
default:
throw new \Exception('Unimplemented Context (getName)');
}
}
private function createAnchor($url)
{
if (empty($url)) {
return null;
}
return '<a href="' . $url . '">' . $url . '</a>';
return sprintf('<a href="%s">%s</a>', $url, $url);
}
}

View File

@ -64,6 +64,7 @@ TEXT;
$this->collectExpandableDatas($feed);
} catch (HttpException $e) {
$this->logger->warning(sprintf('Exception in FeedMergeBridge: %s', create_sane_exception_message($e)));
// This feed item might be spammy. Considering dropping it.
$this->items[] = [
'title' => 'RSS-Bridge: ' . $e->getMessage(),
// Give current time so it sorts to the top
@ -71,7 +72,7 @@ TEXT;
];
continue;
} catch (\Exception $e) {
if (str_starts_with($e->getMessage(), 'Unable to parse xml')) {
if (str_starts_with($e->getMessage(), 'Failed to parse xml')) {
// Allow this particular exception from FeedExpander
$this->logger->warning(sprintf('Exception in FeedMergeBridge: %s', create_sane_exception_message($e)));
continue;
@ -83,6 +84,8 @@ TEXT;
}
}
// If $this->items is empty we should consider throw exception here
// Sort by timestamp descending
usort($this->items, function ($a, $b) {
$t1 = $a['timestamp'] ?? $a['uri'] ?? $a['title'];

View File

@ -187,7 +187,6 @@ class FicbookBridge extends BridgeAbstract
$fixed_date = str_replace(' г.', '', $fixed_date);
if ($fixed_date === $date) {
Debug::log('Unable to fix date: ' . $date);
return null;
}

View File

@ -15,6 +15,12 @@ class FilterBridge extends FeedExpander
'exampleValue' => 'https://lorem-rss.herokuapp.com/feed?unit=day',
'required' => true,
],
'name' => [
'name' => 'Feed name (optional)',
'type' => 'text',
'exampleValue' => 'My feed',
'required' => false,
],
'filter' => [
'name' => 'Filter (regular expression!!!)',
'required' => false,
@ -77,7 +83,7 @@ class FilterBridge extends FeedExpander
{
$url = $this->getInput('url');
if (!Url::validate($url)) {
returnClientError('The url parameter must either refer to http or https protocol.');
throw new \Exception('The url parameter must either refer to http or https protocol.');
}
$this->collectExpandableDatas($this->getURI());
}
@ -158,11 +164,18 @@ class FilterBridge extends FeedExpander
public function getURI()
{
$url = $this->getInput('url');
if (empty($url)) {
$url = parent::getURI();
if ($url) {
return $url;
}
return parent::getURI();
}
return $url;
public function getName()
{
$name = $this->getInput('name');
if ($name) {
return $name;
}
return parent::getName();
}
}

View File

@ -19,23 +19,6 @@ class FirefoxAddonsBridge extends BridgeAbstract
const CACHE_TIMEOUT = 3600;
private $feedName = '';
private $releaseDateRegex = '/Released ([\w, ]+) - ([\w. ]+)/';
private $xpiFileRegex = '/([A-Za-z0-9_.-]+)\.xpi$/';
private $outgoingRegex = '/https:\/\/prod.outgoing\.prod\.webservices\.mozgcp\.net\/v1\/(?:[A-z0-9]+)\//';
private $urlRegex = '/addons\.mozilla\.org\/(?:[\w-]+\/)?firefox\/addon\/([\w-]+)/';
public function detectParameters($url)
{
$params = [];
if (preg_match($this->urlRegex, $url, $matches)) {
$params['id'] = $matches[1];
return $params;
}
return null;
}
public function collectData()
{
@ -52,7 +35,8 @@ class FirefoxAddonsBridge extends BridgeAbstract
$item['uri'] = $this->getURI();
$item['author'] = $author;
if (preg_match($this->releaseDateRegex, $li->find('div.AddonVersionCard-fileInfo', 0)->plaintext, $match)) {
$releaseDateRegex = '/Released ([\w, ]+) - ([\w. ]+)/';
if (preg_match($releaseDateRegex, $li->find('div.AddonVersionCard-fileInfo', 0)->plaintext, $match)) {
$item['timestamp'] = $match[1];
$size = $match[2];
}
@ -68,7 +52,8 @@ class FirefoxAddonsBridge extends BridgeAbstract
$releaseNotes = $this->removeLinkRedirects($li->find('div.AddonVersionCard-releaseNotes', 0));
if (preg_match($this->xpiFileRegex, $downloadlink, $match)) {
$xpiFileRegex = '/([A-Za-z0-9_.-]+)\.xpi$/';
if (preg_match($xpiFileRegex, $downloadlink, $match)) {
$xpiFilename = $match[0];
}
@ -110,10 +95,25 @@ EOD;
*/
private function removeLinkRedirects($html)
{
$outgoingRegex = '/https:\/\/prod.outgoing\.prod\.webservices\.mozgcp\.net\/v1\/(?:[A-z0-9]+)\//';
foreach ($html->find('a') as $a) {
$a->href = urldecode(preg_replace($this->outgoingRegex, '', $a->href));
$a->href = urldecode(preg_replace($outgoingRegex, '', $a->href));
}
return $html->innertext;
}
public function detectParameters($url)
{
$params = [];
// Example: https://addons.mozilla.org/en-US/firefox/addon/ublock-origin
$pattern = '/addons\.mozilla\.org\/(?:[\w-]+\/)?firefox\/addon\/([\w-]+)/';
if (preg_match($pattern, $url, $matches)) {
$params['id'] = $matches[1];
return $params;
}
return null;
}
}

View File

@ -0,0 +1,47 @@
<?php
class FirefoxReleaseNotesBridge extends BridgeAbstract
{
const NAME = 'Firefox Release Notes';
const URI = 'https://www.mozilla.org/en-US/firefox/';
const DESCRIPTION = 'Retrieve the latest Firefox release notes.';
const MAINTAINER = 'tillcash';
const PARAMETERS = [
[
'platform' => [
'name' => 'Platform',
'type' => 'list',
'values' => [
'Desktop' => '',
'Beta' => 'beta',
'Nightly' => 'nightly',
'Android' => 'android',
'iOS' => 'ios',
]
]
]
];
public function getName()
{
$platform = $this->getKey('platform');
return sprintf('Firefox %s Release Notes', $platform ?? '');
}
public function collectData()
{
$platform = $this->getKey('platform');
$url = self::URI . $this->getInput('platform') . '/notes/';
$dom = getSimpleHTMLDOM($url);
$version = $dom->find('.c-release-version', 0)->innertext;
$this->items[] = [
'content' => $dom->find('.c-release-notes', 0)->innertext,
'timestamp' => $dom->find('.c-release-date', 0)->innertext,
'title' => sprintf('Firefox %s %s Release Note', $platform, $version),
'uri' => $url,
'uid' => $platform . $version,
];
}
}

View File

@ -0,0 +1,22 @@
<?php
class FliegermagazinBridge extends XPathAbstract
{
const NAME = 'fliegermagazin';
const URI = 'https://www.fliegermagazin.de/news-fuer-piloten/';
const DESCRIPTION = 'News für Piloten';
const MAINTAINER = 'hleskien';
const FEED_SOURCE_URL = 'https://www.fliegermagazin.de/news-fuer-piloten/';
const XPATH_EXPRESSION_FEED_ICON = './/link[@rel="shortcut icon"]/@href';
const XPATH_EXPRESSION_ITEM = '//article[@data-type="post"]';
const XPATH_EXPRESSION_ITEM_TITLE = './/h3/a/text()';
const XPATH_EXPRESSION_ITEM_CONTENT = './/h3/a/text()';
const XPATH_EXPRESSION_ITEM_URI = './/h3/a/@href';
const XPATH_EXPRESSION_ITEM_AUTHOR = './/p[@class="author-field"]';
// Timestamp kann nur durch Laden des Artikels herausgefunden werden
//const XPATH_EXPRESSION_ITEM_TIMESTAMP = './/span/i';
const XPATH_EXPRESSION_ITEM_ENCLOSURES = './/img/@src';
//const XPATH_EXPRESSION_ITEM_CATEGORIES = './/';
}

View File

@ -44,8 +44,6 @@ class FolhaDeSaoPauloBridge extends FeedExpander
$item['content'] = $text;
$item['uri'] = explode('*', $item['uri'])[1];
}
} else {
Debug::log('???: ' . $item['uri']);
}
} else {
$item['uri'] = explode('*', $item['uri'])[1];
@ -58,13 +56,11 @@ class FolhaDeSaoPauloBridge extends FeedExpander
{
$feed_input = $this->getInput('feed');
if (substr($feed_input, 0, strlen(self::URI)) === self::URI) {
Debug::log('Input:: ' . $feed_input);
$feed_url = $feed_input;
} else {
/* TODO: prepend `/` if missing */
$feed_url = self::URI . '/' . $this->getInput('feed');
}
Debug::log('URL: ' . $feed_url);
$limit = $this->getInput('amount');
$this->collectExpandableDatas($feed_url, $limit);
}

View File

@ -0,0 +1,25 @@
<?php
class ForensicArchitectureBridge extends BridgeAbstract
{
const NAME = 'Forensic Architecture';
const URI = 'https://forensic-architecture.org/';
const DESCRIPTION = 'Generates content feeds from forensic-architecture.org';
const MAINTAINER = 'tillcash';
public function collectData()
{
$url = 'https://forensic-architecture.org/api/fa/v1/investigations';
$jsonData = json_decode(getContents($url));
foreach ($jsonData->investigations as $investigation) {
$this->items[] = [
'content' => $investigation->abstract,
'timestamp' => $investigation->publication_date,
'title' => $investigation->title,
'uid' => $investigation->id,
'uri' => self::URI . 'investigation/' . $investigation->slug,
];
}
}
}

View File

@ -0,0 +1,78 @@
<?php
class FragDenStaatBridge extends BridgeAbstract
{
const MAINTAINER = 'swofl';
const NAME = 'FragDenStaat';
const URI = 'https://fragdenstaat.de';
const CACHE_TIMEOUT = 2 * 60 * 60; // 2h
const DESCRIPTION = 'Get latest blog posts from FragDenStaat Exklusiv';
const PARAMETERS = [ [
'qLimit' => [
'name' => 'Query Limit',
'title' => 'Amount of articles to query',
'type' => 'number',
'defaultValue' => 5,
],
] ];
protected function parseTeaser($teaser)
{
$result = [];
$header = $teaser->find('h3 > a', 0);
$result['title'] = $header->plaintext;
$result['uri'] = static::URI . $header->href;
$result['enclosures'] = [];
$result['enclosures'][] = $teaser->find('img', 0)->src;
$result['uid'] = hash('sha256', $result['title']);
$result['timestamp'] = strtotime($teaser->find('time', 0)->getAttribute('datetime'));
return $result;
}
public function collectData()
{
$html = getSimpleHTMLDOM(self::URI . '/artikel/exklusiv/');
$queryLimit = (int) $this->getInput('qLimit');
if ($queryLimit > 12) {
$queryLimit = 12;
}
$teasers = [];
$teaserElements = $html->find('article');
for ($i = 0; $i < $queryLimit; $i++) {
array_push($teasers, $this->parseTeaser($teaserElements[$i]));
}
foreach ($teasers as $article) {
$articleHtml = getSimpleHTMLDOMCached($article['uri'], static::CACHE_TIMEOUT * 6);
$articleCore = $articleHtml->find('article.blog-article', 0);
$content = '';
$lead = $articleCore->find('div.lead > p', 0)->innertext;
$content .= '<h2>' . $lead . '</h2>';
foreach ($articleCore->find('div.blog-content > p, div.blog-content > h3') as $paragraph) {
$content .= $paragraph->outertext;
}
$article['content'] = '<img src="' . $article['enclosures'][0] . '"/>' . $content;
$article['author'] = '';
foreach ($articleCore->find('a[rel="author"]') as $author) {
$article['author'] .= $author->innertext . ', ';
}
$article['author'] = rtrim($article['author'], ', ');
$this->items[] = $article;
}
}
}

View File

@ -3,7 +3,7 @@
class FreeTelechargerBridge extends BridgeAbstract
{
const NAME = 'Free-Telecharger';
const URI = 'https://www.free-telecharger.live/';
const URI = 'https://www.free-telecharger.art/';
const DESCRIPTION = 'Suivi de série sur Free-Telecharger';
const MAINTAINER = 'sysadminstory';
const PARAMETERS = [
@ -12,43 +12,46 @@ class FreeTelechargerBridge extends BridgeAbstract
'name' => 'URL de la série',
'type' => 'text',
'required' => true,
'title' => 'URL d\'une série sans le https://www.free-telecharger.live/',
'title' => 'URL d\'une série sans le https://www.free-telecharger.art/',
'pattern' => 'series.*\.html',
'exampleValue' => 'series-vf-hd/145458-the-last-of-us-saison-1-web-dl-720p.html'
'exampleValue' => 'series-vf-hd/151432-wolf-saison-1-complete-web-dl-720p.html'
],
]
];
const CACHE_TIMEOUT = 3600;
private string $showTitle;
private string $showTechDetails;
public function collectData()
{
$html = getSimpleHTMLDOM(self::URI . $this->getInput('url'));
$html = getSimpleHTMLDOM(self::URI . $this->getInput('url'));
// Find all block content of the page
$blocks = $html->find('div[class=block1]');
// Find all block content of the page
$blocks = $html->find('div[class=block1]');
// Global Infos block
$infosBlock = $blocks[0];
// Links block
$linksBlock = $blocks[2];
// Global Infos block
$infosBlock = $blocks[0];
// Links block
$linksBlock = $blocks[2];
// Extract Global Show infos
$this->showTitle = trim($infosBlock->find('div[class=titre1]', 0)->find('font', 0)->plaintext);
$this->showTechDetails = trim($infosBlock->find('div[align=center]', 0)->find('b', 0)->plaintext);
// Extract Global Show infos
$this->showTitle = trim($infosBlock->find('div[class=titre1]', 0)->find('font', 0)->plaintext);
$this->showTechDetails = trim($infosBlock->find('div[align=center]', 0)->find('b', 0)->plaintext);
// Get Episodes names and links
$episodes = $linksBlock->find('div[id=link]', 0)->find('font[color=#ff6600]');
$links = $linksBlock->find('div[id=link]', 0)->find('a');
// Get Episodes names and links
$episodes = $linksBlock->find('div[id=link]', 0)->find('font[color=#e93100]');
$links = $linksBlock->find('div[id=link]', 0)->find('a');
foreach ($episodes as $index => $episode) {
$item = []; // Create an empty item
$item['title'] = $this->showTitle . ' ' . $this->showTechDetails . ' - ' . ltrim(trim($episode->plaintext), '-');
$item['uri'] = $links[$index]->href;
$item['content'] = '<a href="' . $item['uri'] . '">' . $item['title'] . '</a>';
$item['uid'] = hash('md5', $item['uri']);
$item = []; // Create an empty item
$item['title'] = $this->showTitle . ' ' . $this->showTechDetails . ' - ' . ltrim(trim($episode->plaintext), '-');
$item['uri'] = $links[$index]->href;
$item['content'] = '<a href="' . $item['uri'] . '">' . $item['title'] . '</a>';
$item['uid'] = hash('md5', $item['uri']);
$this->items[] = $item; // Add this item to the list
$this->items[] = $item; // Add this item to the list
}
}
@ -57,7 +60,7 @@ class FreeTelechargerBridge extends BridgeAbstract
switch ($this->queriedContext) {
case 'Suivi de publication de série':
return $this->showTitle . ' ' . $this->showTechDetails . ' - ' . self::NAME;
break;
break;
default:
return self::NAME;
}
@ -68,7 +71,7 @@ class FreeTelechargerBridge extends BridgeAbstract
switch ($this->queriedContext) {
case 'Suivi de publication de série':
return self::URI . $this->getInput('url');
break;
break;
default:
return self::URI;
}
@ -76,14 +79,14 @@ class FreeTelechargerBridge extends BridgeAbstract
public function detectParameters($url)
{
// Example: https://www.free-telecharger.live/series-vf-hd/145458-the-last-of-us-saison-1-web-dl-720p.html
// Example: https://www.free-telecharger.art/series-vf-hd/151432-wolf-saison-1-complete-web-dl-720p.html
$params = [];
$regex = '/^https:\/\/www.*\.free-telecharger\.live\/(series.*\.html)/';
$regex = '/^https:\/\/www.*\.free-telecharger\.art\/(series.*\.html)/';
if (preg_match($regex, $url, $matches) > 0) {
$params['context'] = 'Suivi de publication de série';
$params['url'] = urldecode($matches[1]);
return $params;
$params['context'] = 'Suivi de publication de série';
$params['url'] = urldecode($matches[1]);
return $params;
}
return null;

View File

@ -32,7 +32,7 @@ class FunkBridge extends BridgeAbstract
$url .= '?size=' . $this->getInput('max');
}
$jsonString = getContents($url) or returnServerError('No contents received!');
$jsonString = getContents($url);
$json = json_decode($jsonString, true);
foreach ($json['list'] as $element) {

View File

@ -676,7 +676,7 @@ class FurAffinityBridge extends BridgeAbstract
$name = parent::getName();
if ($this->getOption('aCookie') !== null) {
$username = $this->loadCacheValue('username');
if ($username !== null) {
if ($username) {
$name = $username . '\'s ' . parent::getName();
}
}

View File

@ -31,7 +31,7 @@ class GBAtempBridge extends BridgeAbstract
$img = $this->findItemImage($newsItem, 'a.news_image');
$time = $this->findItemDate($newsItem);
$author = $newsItem->find('a.username', 0)->plaintext;
$title = $this->decodeHtmlEntities($newsItem->find('h3.news_title', 0)->plaintext);
$title = $this->decodeHtmlEntities($newsItem->find('h2.news_title', 0)->plaintext);
$content = $this->fetchPostContent($url, self::URI);
$this->items[] = $this->buildItem($url, $title, $author, $time, $img, $content);
unset($newsItem); // Some items are heavy, freeing the item proactively helps saving memory
@ -41,7 +41,7 @@ class GBAtempBridge extends BridgeAbstract
foreach ($html->find('li.portal_review') as $reviewItem) {
$url = urljoin(self::URI, $reviewItem->find('a.review_boxart', 0)->href);
$img = $this->findItemImage($reviewItem, 'a.review_boxart');
$title = $this->decodeHtmlEntities($reviewItem->find('h2.review_title', 0)->plaintext);
$title = $this->decodeHtmlEntities($reviewItem->find('div.review_title', 0)->find('h2', 0)->plaintext);
$content = getSimpleHTMLDOMCached($url);
$author = $content->find('span.author--name', 0)->plaintext;
$time = $this->findItemDate($content);

View File

@ -0,0 +1,164 @@
<?php
use Facebook\WebDriver\Exception\NoSuchElementException;
use Facebook\WebDriver\Remote\RemoteWebElement;
use Facebook\WebDriver\WebDriverBy;
use Facebook\WebDriver\WebDriverExpectedCondition;
class GULPProjekteBridge extends WebDriverAbstract
{
const NAME = 'GULP Projekte';
const URI = 'https://www.gulp.de/gulp2/g/projekte';
const DESCRIPTION = 'Projektsuche';
const MAINTAINER = 'hleskien';
const MAXITEMS = 60;
/**
* Adds accept language german to the Chrome Options.
*
* @return Facebook\WebDriver\Chrome\ChromeOptions
*/
protected function getBrowserOptions()
{
$chromeOptions = parent::getBrowserOptions();
$chromeOptions->addArguments(['--accept-lang=de']);
return $chromeOptions;
}
/**
* @throws Facebook\WebDriver\Exception\NoSuchElementException
* @throws Facebook\WebDriver\Exception\TimeoutException
*/
protected function clickAwayCookieBanner()
{
$this->getDriver()->wait()->until(WebDriverExpectedCondition::visibilityOfElementLocated(WebDriverBy::id('onetrust-reject-all-handler')));
$buttonRejectCookies = $this->getDriver()->findElement(WebDriverBy::id('onetrust-reject-all-handler'));
$buttonRejectCookies->click();
$this->getDriver()->wait()->until(WebDriverExpectedCondition::invisibilityOfElementLocated(WebDriverBy::id('onetrust-reject-all-handler')));
}
/**
* @throws Facebook\WebDriver\Exception\NoSuchElementException
* @throws Facebook\WebDriver\Exception\TimeoutException
*/
protected function clickNextPage()
{
$nextPage = $this->getDriver()->findElement(WebDriverBy::xpath('//app-linkable-paginator//li[@id="next-page"]/a'));
$href = $nextPage->getAttribute('href');
$nextPage->click();
$this->getDriver()->wait()->until(WebDriverExpectedCondition::not(
WebDriverExpectedCondition::presenceOfElementLocated(
WebDriverBy::xpath('//app-linkable-paginator//li[@id="next-page"]/a[@href="' . $href . '"]')
)
));
}
/**
* Returns the uri of the 'Projektanbieter' logo or false if there is
* no logo present in the item.
*
* @return string | false
*/
protected function getLogo(RemoteWebElement $item)
{
try {
$logo = $item->findElement(WebDriverBy::tagName('img'))->getAttribute('src');
if (str_starts_with($logo, 'http')) {
// different domain
return $logo;
} else {
// relative path
$remove = substr(self::URI, strrpos(self::URI, '/') + 1);
return substr(self::URI, 0, -strlen($remove)) . $logo;
}
} catch (NoSuchElementException $e) {
return false;
}
}
/**
* Converts a string like "vor einigen Minuten" into a reasonable timestamp.
* Long and complicated, but we don't want to be more specific than
* the information we have available.
*
* @throws Exception If the DateInterval can't be parsed.
*/
protected function getTimestamp(string $timeAgo): int
{
$dateTime = new DateTime();
$dateArray = explode(' ', $dateTime->format('Y m d H i s'));
$quantityStr = explode(' ', $timeAgo)[1];
// convert possible word into a number
if (in_array($quantityStr, ['einem', 'einer', 'einigen'])) {
$quantity = 1;
} else {
$quantity = intval($quantityStr);
}
// subtract time ago + inferior units for lower precision
if (str_contains($timeAgo, 'Sekunde')) {
$interval = new DateInterval('PT' . $quantity . 'S');
} elseif (str_contains($timeAgo, 'Minute')) {
$interval = new DateInterval('PT' . $quantity . 'M' . $dateArray[5] . 'S');
} elseif (str_contains($timeAgo, 'Stunde')) {
$interval = new DateInterval('PT' . $quantity . 'H' . $dateArray[4] . 'M' . $dateArray[5] . 'S');
} elseif (str_contains($timeAgo, 'Tag')) {
$interval = new DateInterval('P' . $quantity . 'DT' . $dateArray[3] . 'H' . $dateArray[4] . 'M' . $dateArray[5] . 'S');
} else {
throw new UnexpectedValueException($timeAgo);
}
$dateTime = $dateTime->sub($interval);
return $dateTime->getTimestamp();
}
/**
* The main loop which clicks through search result pages and puts
* the content into the $items array.
*
* @throws Facebook\WebDriver\Exception\NoSuchElementException
* @throws Facebook\WebDriver\Exception\TimeoutException
*/
public function collectData()
{
parent::collectData();
try {
$this->clickAwayCookieBanner();
$this->setIcon($this->getDriver()->findElement(WebDriverBy::xpath('//link[@rel="shortcut icon"]'))->getAttribute('href'));
while (true) {
$items = $this->getDriver()->findElements(WebDriverBy::tagName('app-project-view'));
foreach ($items as $item) {
$feedItem = [];
$heading = $item->findElement(WebDriverBy::xpath('.//app-heading-tag/h1/a'));
$feedItem['title'] = $heading->getText();
$feedItem['uri'] = 'https://www.gulp.de' . $heading->getAttribute('href');
$info = $item->findElement(WebDriverBy::tagName('app-icon-info-list'));
if ($logo = $this->getLogo($item)) {
$feedItem['enclosures'] = [$logo];
}
if (str_contains($info->getText(), 'Projektanbieter:')) {
$feedItem['author'] = $info->findElement(WebDriverBy::xpath('.//li/span[2]/span'))->getText();
} else {
// mostly "Direkt vom Auftraggeber" or "GULP Agentur"
$feedItem['author'] = $item->findElement(WebDriverBy::tagName('b'))->getText();
}
$feedItem['content'] = $item->findElement(WebDriverBy::xpath('.//p[@class="description"]'))->getText();
$timeAgo = $item->findElement(WebDriverBy::xpath('.//small[contains(@class, "time-ago")]'))->getText();
$feedItem['timestamp'] = $this->getTimestamp($timeAgo);
$this->items[] = $feedItem;
}
if (count($this->items) < self::MAXITEMS) {
$this->clickNextPage();
} else {
break;
}
}
} finally {
$this->cleanUp();
}
}
}

View File

@ -28,6 +28,8 @@ class GameBananaBridge extends BridgeAbstract
return 'https://images.gamebanana.com/static/img/favicon/favicon.ico';
}
private $title;
public function collectData()
{
$url = 'https://api.gamebanana.com/Core/List/New?itemtype=Mod&page=1&gameid=' . $this->getInput('gid');
@ -38,7 +40,7 @@ class GameBananaBridge extends BridgeAbstract
$json_list = json_decode($api_response, true); // Get first page mod list
$url = 'https://api.gamebanana.com/Core/Item/Data?itemtype[]=Game&fields[]=name&itemid[]=' . $this->getInput('gid');
$fields = 'name,Owner().name,text,screenshots,Files().aFiles(),date,Url().sProfileUrl(),udate';
$fields = 'name,Owner().name,text,screenshots,Files().aFiles(),date,Url().sProfileUrl(),udate,Updates().aLatestUpdates(),Category().name,RootCategory().name';
foreach ($json_list as $element) { // Build api request to minimize API calls
$mid = $element[1];
$url .= '&itemtype[]=Mod&fields[]=' . $fields . '&itemid[]=' . $mid;
@ -50,11 +52,18 @@ class GameBananaBridge extends BridgeAbstract
array_shift($json_list); // Take title from API request and remove from json
foreach ($json_list as $element) {
// Trashed mod IDs are still picked up and return null; skip
if ($element[0] == null) {
continue;
}
$item = [];
$item['uri'] = $element[6];
$item['comments'] = $item['uri'] . '#PostsListModule';
$item['title'] = $element[0];
$item['author'] = $element[1];
$item['categories'][] = $element[9];
$item['categories'][] = $element[10];
$item['timestamp'] = $element[5];
if ($this->getInput('updates')) {
@ -72,6 +81,22 @@ class GameBananaBridge extends BridgeAbstract
foreach ($img_list as $img_element) {
$item['content'] .= '<img src="https://images.gamebanana.com/img/ss/mods/' . $img_element['_sFile'] . '"/>';
}
// Get updates from element[8], if applicable
if ($this->getInput('updates') && count($element[8]) > 0) {
$update = $element[8][0];
$item['content'] .= '<br><strong>Update:</strong> ' . $update['_sTitle'];
if ($update['_sText'] != '') {
$item['content'] .= '<br>' . $update['_sText'];
}
foreach ($update['_aChangeLog'] as $change) {
if ($change['cat'] == '') {
$change['cat'] = 'Change';
}
$item['content'] .= '<br><em>' . $change['cat'] . '</em>: ' . $change['text'];
}
$item['content'] .= '<br><hr>';
}
$item['content'] .= '<br>' . $element[2];
$item['uid'] = $item['uri'] . $item['title'] . $item['timestamp'];

View File

@ -20,15 +20,18 @@ class GatesNotesBridge extends BridgeAbstract
$apiUrl = self::URI . $api_endpoint . http_build_query($params);
$rawContent = getContents($apiUrl);
$cleanedContent = trim($rawContent, '"');
$cleanedContent = str_replace([
'<string xmlns="http://schemas.microsoft.com/2003/10/Serialization/">',
'</string>',
'\r\n',
], '', $rawContent);
$cleanedContent = str_replace('\"', '"', $cleanedContent);
$cleanedContent = trim($cleanedContent, '"');
'</string>'
], '', $cleanedContent);
$cleanedContent = str_replace('\r\n', "\n", $cleanedContent);
$cleanedContent = stripslashes($cleanedContent);
$json = Json::decode($cleanedContent, false);
if (is_string($json)) {
throw new \Exception('wtf? ' . $json);
}
foreach ($json as $article) {
$item = [];

View File

@ -33,7 +33,7 @@ class GelbooruBridge extends BridgeAbstract
return $this->getURI()
. 'index.php?&page=dapi&s=post&q=index&json=1&pid=' . $this->getInput('p')
. '&limit=' . $this->getInput('l')
. '&tags=' . urlencode($this->getInput('t'));
. '&tags=' . urlencode($this->getInput('t') ?? '');
}
/*
@ -76,18 +76,16 @@ class GelbooruBridge extends BridgeAbstract
public function collectData()
{
$content = getContents($this->getFullURI());
// $content is empty string
$url = $this->getFullURI();
$content = getContents($url);
// Most other Gelbooru-based boorus put their content in the root of
// the JSON. This check is here for Bridges that inherit from this one
$posts = json_decode($content);
if (isset($posts->post)) {
$posts = $posts->post;
if ($content === '') {
return;
}
if (is_null($posts)) {
returnServerError('No posts found.');
$posts = Json::decode($content, false);
if (isset($posts->post)) {
$posts = $posts->post;
}
foreach ($posts as $post) {

Some files were not shown because too many files have changed in this diff Show More