mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-09-01 20:16:38 +02:00
Using https://github.com/asottile/pyupgrade 1. `__future__` imports and `coding: utf-8` were removed 2. Files were rewritten with `pyupgrade --py36-plus --keep-percent-format` 3. f-strings were cherry-picked from `pyupgrade --py36-plus` Extractors are left untouched (except removing header) to avoid unnecessary merge conflicts
156 lines
5.8 KiB
Python
156 lines
5.8 KiB
Python
import itertools
|
|
import re
|
|
|
|
from .common import InfoExtractor
|
|
from ..utils import (
|
|
ExtractorError,
|
|
GeoRestrictedError,
|
|
orderedSet,
|
|
unified_strdate,
|
|
urlencode_postdata,
|
|
)
|
|
|
|
|
|
class BitChuteIE(InfoExtractor):
|
|
_VALID_URL = r'https?://(?:www\.)?bitchute\.com/(?:video|embed|torrent/[^/]+)/(?P<id>[^/?#&]+)'
|
|
_TESTS = [{
|
|
'url': 'https://www.bitchute.com/video/UGlrF9o9b-Q/',
|
|
'md5': '7e427d7ed7af5a75b5855705ec750e2b',
|
|
'info_dict': {
|
|
'id': 'szoMrox2JEI',
|
|
'ext': 'mp4',
|
|
'title': 'This is the first video on #BitChute !',
|
|
'description': 'md5:a0337e7b1fe39e32336974af8173a034',
|
|
'thumbnail': r're:^https?://.*\.jpg$',
|
|
'uploader': 'BitChute',
|
|
'upload_date': '20170103',
|
|
},
|
|
}, {
|
|
'url': 'https://www.bitchute.com/embed/lbb5G1hjPhw/',
|
|
'only_matching': True,
|
|
}, {
|
|
'url': 'https://www.bitchute.com/torrent/Zee5BE49045h/szoMrox2JEI.webtorrent',
|
|
'only_matching': True,
|
|
}]
|
|
|
|
@staticmethod
|
|
def _extract_urls(webpage):
|
|
return [
|
|
mobj.group('url')
|
|
for mobj in re.finditer(
|
|
r'<(?:script|iframe)[^>]+\bsrc=(["\'])(?P<url>%s)' % BitChuteIE._VALID_URL,
|
|
webpage)]
|
|
|
|
def _real_extract(self, url):
|
|
video_id = self._match_id(url)
|
|
|
|
webpage = self._download_webpage(
|
|
'https://www.bitchute.com/video/%s' % video_id, video_id, headers={
|
|
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.57 Safari/537.36',
|
|
})
|
|
|
|
title = self._html_search_regex(
|
|
(r'<[^>]+\bid=["\']video-title[^>]+>([^<]+)', r'<title>([^<]+)'),
|
|
webpage, 'title', default=None) or self._html_search_meta(
|
|
'description', webpage, 'title',
|
|
default=None) or self._og_search_description(webpage)
|
|
|
|
format_urls = []
|
|
for mobj in re.finditer(
|
|
r'addWebSeed\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage):
|
|
format_urls.append(mobj.group('url'))
|
|
format_urls.extend(re.findall(r'as=(https?://[^&"\']+)', webpage))
|
|
|
|
formats = [
|
|
{'url': format_url}
|
|
for format_url in orderedSet(format_urls)]
|
|
|
|
if not formats:
|
|
entries = self._parse_html5_media_entries(
|
|
url, webpage, video_id)
|
|
if not entries:
|
|
error = self._html_search_regex(r'<h1 class="page-title">([^<]+)</h1>', webpage, 'error', default='Cannot find video')
|
|
if error == 'Video Unavailable':
|
|
raise GeoRestrictedError(error)
|
|
raise ExtractorError(error)
|
|
formats = entries[0]['formats']
|
|
|
|
self._check_formats(formats, video_id)
|
|
self._sort_formats(formats)
|
|
|
|
description = self._html_search_regex(
|
|
r'(?s)<div\b[^>]+\bclass=["\']full hidden[^>]+>(.+?)</div>',
|
|
webpage, 'description', fatal=False)
|
|
thumbnail = self._og_search_thumbnail(
|
|
webpage, default=None) or self._html_search_meta(
|
|
'twitter:image:src', webpage, 'thumbnail')
|
|
uploader = self._html_search_regex(
|
|
(r'(?s)<div class=["\']channel-banner.*?<p\b[^>]+\bclass=["\']name[^>]+>(.+?)</p>',
|
|
r'(?s)<p\b[^>]+\bclass=["\']video-author[^>]+>(.+?)</p>'),
|
|
webpage, 'uploader', fatal=False)
|
|
|
|
upload_date = unified_strdate(self._search_regex(
|
|
r'class=["\']video-publish-date[^>]+>[^<]+ at \d+:\d+ UTC on (.+?)\.',
|
|
webpage, 'upload date', fatal=False))
|
|
|
|
return {
|
|
'id': video_id,
|
|
'title': title,
|
|
'description': description,
|
|
'thumbnail': thumbnail,
|
|
'uploader': uploader,
|
|
'upload_date': upload_date,
|
|
'formats': formats,
|
|
}
|
|
|
|
|
|
class BitChuteChannelIE(InfoExtractor):
|
|
_VALID_URL = r'https?://(?:www\.)?bitchute\.com/channel/(?P<id>[^/?#&]+)'
|
|
_TEST = {
|
|
'url': 'https://www.bitchute.com/channel/victoriaxrave/',
|
|
'playlist_mincount': 185,
|
|
'info_dict': {
|
|
'id': 'victoriaxrave',
|
|
},
|
|
}
|
|
|
|
_TOKEN = 'zyG6tQcGPE5swyAEFLqKUwMuMMuF6IO2DZ6ZDQjGfsL0e4dcTLwqkTTul05Jdve7'
|
|
|
|
def _entries(self, channel_id):
|
|
channel_url = 'https://www.bitchute.com/channel/%s/' % channel_id
|
|
offset = 0
|
|
for page_num in itertools.count(1):
|
|
data = self._download_json(
|
|
'%sextend/' % channel_url, channel_id,
|
|
'Downloading channel page %d' % page_num,
|
|
data=urlencode_postdata({
|
|
'csrfmiddlewaretoken': self._TOKEN,
|
|
'name': '',
|
|
'offset': offset,
|
|
}), headers={
|
|
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
|
|
'Referer': channel_url,
|
|
'X-Requested-With': 'XMLHttpRequest',
|
|
'Cookie': 'csrftoken=%s' % self._TOKEN,
|
|
})
|
|
if data.get('success') is False:
|
|
break
|
|
html = data.get('html')
|
|
if not html:
|
|
break
|
|
video_ids = re.findall(
|
|
r'class=["\']channel-videos-image-container[^>]+>\s*<a\b[^>]+\bhref=["\']/video/([^"\'/]+)',
|
|
html)
|
|
if not video_ids:
|
|
break
|
|
offset += len(video_ids)
|
|
for video_id in video_ids:
|
|
yield self.url_result(
|
|
'https://www.bitchute.com/video/%s' % video_id,
|
|
ie=BitChuteIE.ie_key(), video_id=video_id)
|
|
|
|
def _real_extract(self, url):
|
|
channel_id = self._match_id(url)
|
|
return self.playlist_result(
|
|
self._entries(channel_id), playlist_id=channel_id)
|