You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
yt-dlp/yt_dlp/extractor/xvideos.py

181 lines
6.6 KiB
Python

import re
from .common import InfoExtractor
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
9 years ago
from ..compat import compat_urllib_parse_unquote
from ..utils import (
clean_html,
determine_ext,
ExtractorError,
int_or_none,
parse_duration,
)
class XVideosIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
(?:
(?:[^/]+\.)?xvideos2?\.com/video|
(?:www\.)?xvideos\.es/video|
(?:www|flashservice)\.xvideos\.com/embedframe/|
static-hw\.xvideos\.com/swf/xv-player\.swf\?.*?\bid_video=
)
(?P<id>[0-9]+)
'''
_TESTS = [{
'url': 'https://www.xvideos.com/video4588838/motorcycle_guy_cucks_influencer_steals_his_gf',
'md5': '14cea69fcb84db54293b1e971466c2e1',
'info_dict': {
'id': '4588838',
'ext': 'mp4',
'title': 'Motorcycle Guy Cucks Influencer, Steals his GF',
'duration': 108,
'age_limit': 18,
'thumbnail': r're:^https://img-hw.xvideos-cdn.com/.+\.jpg',
}
}, {
# Broken HLS formats
'url': 'https://www.xvideos.com/video65982001/what_s_her_name',
'md5': 'b82d7d7ef7d65a84b1fa6965f81f95a5',
'info_dict': {
'id': '65982001',
'ext': 'mp4',
'title': 'what\'s her name?',
'duration': 120,
'age_limit': 18,
'thumbnail': r're:^https://img-hw.xvideos-cdn.com/.+\.jpg',
}
}, {
'url': 'https://flashservice.xvideos.com/embedframe/4588838',
'only_matching': True,
}, {
'url': 'https://www.xvideos.com/embedframe/4588838',
'only_matching': True,
}, {
'url': 'http://static-hw.xvideos.com/swf/xv-player.swf?id_video=4588838',
'only_matching': True,
}, {
'url': 'http://xvideos.com/video4588838/biker_takes_his_girl',
'only_matching': True
}, {
'url': 'https://xvideos.com/video4588838/biker_takes_his_girl',
'only_matching': True
}, {
'url': 'https://xvideos.es/video4588838/biker_takes_his_girl',
'only_matching': True
}, {
'url': 'https://www.xvideos.es/video4588838/biker_takes_his_girl',
'only_matching': True
}, {
'url': 'http://xvideos.es/video4588838/biker_takes_his_girl',
'only_matching': True
}, {
'url': 'http://www.xvideos.es/video4588838/biker_takes_his_girl',
'only_matching': True
}, {
'url': 'http://fr.xvideos.com/video4588838/biker_takes_his_girl',
'only_matching': True
}, {
'url': 'https://fr.xvideos.com/video4588838/biker_takes_his_girl',
'only_matching': True
}, {
'url': 'http://it.xvideos.com/video4588838/biker_takes_his_girl',
'only_matching': True
}, {
'url': 'https://it.xvideos.com/video4588838/biker_takes_his_girl',
'only_matching': True
}, {
'url': 'http://de.xvideos.com/video4588838/biker_takes_his_girl',
'only_matching': True
}, {
'url': 'https://de.xvideos.com/video4588838/biker_takes_his_girl',
'only_matching': True
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
mobj = re.search(r'<h1 class="inlineError">(.+?)</h1>', webpage)
if mobj:
raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(mobj.group(1))), expected=True)
title = self._html_search_regex(
(r'<title>(?P<title>.+?)\s+-\s+XVID',
r'setVideoTitle\s*\(\s*(["\'])(?P<title>(?:(?!\1).)+)\1'),
webpage, 'title', default=None,
group='title') or self._og_search_title(webpage)
thumbnails = []
for preference, thumbnail in enumerate(('', '169')):
thumbnail_url = self._search_regex(
r'setThumbUrl%s\(\s*(["\'])(?P<thumbnail>(?:(?!\1).)+)\1' % thumbnail,
webpage, 'thumbnail', default=None, group='thumbnail')
if thumbnail_url:
thumbnails.append({
'url': thumbnail_url,
'preference': preference,
})
duration = int_or_none(self._og_search_property(
'duration', webpage, default=None)) or parse_duration(
self._search_regex(
r'<span[^>]+class=["\']duration["\'][^>]*>.*?(\d[^<]+)',
webpage, 'duration', fatal=False))
formats = []
video_url = compat_urllib_parse_unquote(self._search_regex(
r'flv_url=(.+?)&', webpage, 'video URL', default=''))
if video_url:
formats.append({
'url': video_url,
'format_id': 'flv',
})
for kind, _, format_url in re.findall(
r'setVideo([^(]+)\((["\'])(http.+?)\2\)', webpage):
format_id = kind.lower()
if format_id == 'hls':
hls_formats = self._extract_m3u8_formats(
format_url, video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
self._check_formats(hls_formats, video_id)
formats.extend(hls_formats)
elif format_id in ('urllow', 'urlhigh'):
formats.append({
'url': format_url,
'format_id': '%s-%s' % (determine_ext(format_url, 'mp4'), format_id[3:]),
'quality': -2 if format_id.endswith('low') else None,
})
return {
'id': video_id,
'formats': formats,
'title': title,
'duration': duration,
'thumbnails': thumbnails,
'age_limit': 18,
}
class XVideosQuickiesIE(InfoExtractor):
IE_NAME = 'xvideos:quickies'
_VALID_URL = r'https?://(?P<domain>(?:[^/]+\.)?xvideos2?\.com)/amateur-channels/[^#]+#quickies/a/(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.xvideos.com/amateur-channels/wifeluna#quickies/a/47258683',
'md5': '16e322a93282667f1963915568f782c1',
'info_dict': {
'id': '47258683',
'ext': 'mp4',
'title': 'Verification video',
'age_limit': 18,
'duration': 16,
'thumbnail': r're:^https://cdn.*-pic.xvideos-cdn.com/.+\.jpg',
}
}]
def _real_extract(self, url):
domain, id_ = self._match_valid_url(url).group('domain', 'id')
return self.url_result(f'https://{domain}/video{id_}/_', XVideosIE, id_)