Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[AnnasArchiveBridge] Add new bridge #3888

Merged
merged 4 commits into from
Jan 10, 2024
Merged

[AnnasArchiveBridge] Add new bridge #3888

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
5232257
[AnnasArchiveBridge] Add new bridge
Phantop Jan 10, 2024
5c88cbd
Merge branch 'master' of https://github.com/rss-bridge/rss-bridge
Phantop Jan 10, 2024
8f64ef1
[AnnasArchiveBridge] Add missing exampleValue
Phantop Jan 10, 2024
d8f20d0
[AnnasArchiveBridge] Remove vestigial debug print
Phantop Jan 10, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
175 changes: 175 additions & 0 deletions bridges/AnnasArchiveBridge.php
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,175 @@
<?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 [zh‑Hant]' => 'zh‑Hant',
'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 (non‑fiction)' => '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',
'Sci‑Hub' => 'scihub',
'Z‑Library' => '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;
}

foreach ($list->find('.w-full > .mb-4 > div > a') as $element) {
$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'];

if ($item_html = getSimpleHTMLDOMCached($item['uri'])) {
Copy link
Contributor

@dvikan dvikan Jan 10, 2024 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

please no assignment inside if statement

$item_html = defaultLinkTo($item_html, self::URI);
$item['content'] .= $item_html->find('main img', 0);
$item['content'] .= $item_html->find('main .mt-4', 0); // Summary
if ($links = $item_html->find('main ul.mb-4', -1)) {
foreach ($links->find('li > a.js-download-link') as $file) {
$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;
}
}