mirror of
https://github.com/searxng/searxng.git
synced 2024-05-23 05:48:05 +00:00
86b4d2f2d0
We have been using a static type checker (pyright) for a long time, but its check was not yet a prerequisite for passing the quality gate. It was checked in the CI, but the error messages were only logged. As is always the case in life, with checks that you have to do but which have no consequences; you neglect them :-) We didn't activate the checks back then because we (even today) have too much monkey patching in our code (not only in the engines, httpx and others objects are also affected). We want to replace monkey patching with clear interfaces for a long time, the basis for this is increased typing and we can only achieve this if we make type checking an integral part of the quality gate. This PR activates the type check; in order to pass the check, a few typings were corrected in the code, but most type inconsistencies were deactivated via inline comments. This was particularly necessary in places where the code uses properties that stick to the objects (monkey patching). The sticking of properties only happens in a few places, but the access to these properties extends over the entire code, which is why there are many `# type: ignore` markers in the code ... which we will hopefully be able to remove again successively in the future. Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
124 lines
3.2 KiB
Python
124 lines
3.2 KiB
Python
# SPDX-License-Identifier: AGPL-3.0-or-later
|
|
"""BT4G_ (bt4g.com) is not a tracker and doesn't store any content and only
|
|
collects torrent metadata (such as file names and file sizes) and a magnet link
|
|
(torrent identifier).
|
|
|
|
This engine does not parse the HTML page because there is an API in XML (RSS).
|
|
The RSS feed provides fewer data like amount of seeders/leechers and the files
|
|
in the torrent file. It's a tradeoff for a "stable" engine as the XML from RSS
|
|
content will change way less than the HTML page.
|
|
|
|
.. _BT4G: https://bt4g.com/
|
|
|
|
Configuration
|
|
=============
|
|
|
|
The engine has the following additional settings:
|
|
|
|
- :py:obj:`bt4g_order_by`
|
|
- :py:obj:`bt4g_category`
|
|
|
|
With this options a SearXNG maintainer is able to configure **additional**
|
|
engines for specific torrent searches. For example a engine to search only for
|
|
Movies and sort the result list by the count of seeders.
|
|
|
|
.. code:: yaml
|
|
|
|
- name: bt4g.movie
|
|
engine: bt4g
|
|
shortcut: bt4gv
|
|
categories: video
|
|
bt4g_order_by: seeders
|
|
bt4g_category: 'movie'
|
|
|
|
Implementations
|
|
===============
|
|
|
|
"""
|
|
|
|
import re
|
|
from datetime import datetime
|
|
from urllib.parse import quote
|
|
|
|
from lxml import etree # type: ignore
|
|
|
|
from searx.utils import get_torrent_size
|
|
|
|
# about
|
|
about = {
|
|
"website": 'https://bt4gprx.com',
|
|
"use_official_api": False,
|
|
"require_api_key": False,
|
|
"results": 'XML',
|
|
}
|
|
|
|
# engine dependent config
|
|
categories = ['files']
|
|
paging = True
|
|
time_range_support = True
|
|
|
|
# search-url
|
|
url = 'https://bt4gprx.com'
|
|
search_url = url + '/search?q={search_term}&orderby={order_by}&category={category}&p={pageno}&page=rss'
|
|
bt4g_order_by = 'relevance'
|
|
"""Result list can be ordered by ``relevance`` (default), ``size``, ``seeders``
|
|
or ``time``.
|
|
|
|
.. hint::
|
|
|
|
When *time_range* is activate, the results always ordered by ``time``.
|
|
"""
|
|
|
|
bt4g_category = 'all'
|
|
"""BT$G offers categories: ``all`` (default), ``audio``, ``movie``, ``doc``,
|
|
``app`` and `` other``.
|
|
"""
|
|
|
|
|
|
def request(query, params):
|
|
|
|
order_by = bt4g_order_by
|
|
if params['time_range']:
|
|
order_by = 'time'
|
|
|
|
params['url'] = search_url.format(
|
|
search_term=quote(query),
|
|
order_by=order_by,
|
|
category=bt4g_category,
|
|
pageno=params['pageno'],
|
|
)
|
|
return params
|
|
|
|
|
|
def response(resp):
|
|
results = []
|
|
|
|
search_results = etree.XML(resp.content)
|
|
|
|
# return empty array if nothing is found
|
|
if len(search_results) == 0:
|
|
return []
|
|
|
|
for entry in search_results.xpath('./channel/item'):
|
|
title = entry.find("title").text
|
|
link = entry.find("guid").text
|
|
fullDescription = entry.find("description").text.split('<br>')
|
|
filesize = fullDescription[1]
|
|
filesizeParsed = re.split(r"([A-Z]+)", filesize)
|
|
magnetlink = entry.find("link").text
|
|
pubDate = entry.find("pubDate").text
|
|
results.append(
|
|
{
|
|
'url': link,
|
|
'title': title,
|
|
'magnetlink': magnetlink,
|
|
'seed': 'N/A',
|
|
'leech': 'N/A',
|
|
'filesize': get_torrent_size(filesizeParsed[0], filesizeParsed[1]),
|
|
'publishedDate': datetime.strptime(pubDate, '%a,%d %b %Y %H:%M:%S %z'),
|
|
'template': 'torrent.html',
|
|
}
|
|
)
|
|
|
|
return results
|