5c2266df4b
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
73 lines
2.5 KiB
Python
73 lines
2.5 KiB
Python
from __future__ import unicode_literals
|
|
|
|
import re
|
|
|
|
from .common import InfoExtractor
|
|
from ..compat import compat_urllib_parse_unquote
|
|
from ..utils import (
|
|
clean_html,
|
|
ExtractorError,
|
|
determine_ext,
|
|
sanitized_Request,
|
|
)
|
|
|
|
|
|
class XVideosIE(InfoExtractor):
|
|
_VALID_URL = r'https?://(?:www\.)?xvideos\.com/video(?P<id>[0-9]+)(?:.*)'
|
|
_TEST = {
|
|
'url': 'http://www.xvideos.com/video4588838/biker_takes_his_girl',
|
|
'md5': '4b46ae6ea5e6e9086e714d883313c0c9',
|
|
'info_dict': {
|
|
'id': '4588838',
|
|
'ext': 'flv',
|
|
'title': 'Biker Takes his Girl',
|
|
'age_limit': 18,
|
|
}
|
|
}
|
|
|
|
_ANDROID_USER_AGENT = 'Mozilla/5.0 (Linux; Android 4.0.4; Galaxy Nexus Build/IMM76B) AppleWebKit/535.19 (KHTML, like Gecko) Chrome/18.0.1025.133 Mobile Safari/535.19'
|
|
|
|
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)
|
|
|
|
video_url = compat_urllib_parse_unquote(
|
|
self._search_regex(r'flv_url=(.+?)&', webpage, 'video URL'))
|
|
video_title = self._html_search_regex(
|
|
r'<title>(.*?)\s+-\s+XVID', webpage, 'title')
|
|
video_thumbnail = self._search_regex(
|
|
r'url_bigthumb=(.+?)&', webpage, 'thumbnail', fatal=False)
|
|
|
|
formats = [{
|
|
'url': video_url,
|
|
}]
|
|
|
|
android_req = sanitized_Request(url)
|
|
android_req.add_header('User-Agent', self._ANDROID_USER_AGENT)
|
|
android_webpage = self._download_webpage(android_req, video_id, fatal=False)
|
|
|
|
if android_webpage is not None:
|
|
player_params_str = self._search_regex(
|
|
'mobileReplacePlayerDivTwoQual\(([^)]+)\)',
|
|
android_webpage, 'player parameters', default='')
|
|
player_params = list(map(lambda s: s.strip(' \''), player_params_str.split(',')))
|
|
if player_params:
|
|
formats.extend([{
|
|
'url': param,
|
|
'preference': -10,
|
|
} for param in player_params if determine_ext(param) == 'mp4'])
|
|
|
|
self._sort_formats(formats)
|
|
|
|
return {
|
|
'id': video_id,
|
|
'formats': formats,
|
|
'title': video_title,
|
|
'ext': 'flv',
|
|
'thumbnail': video_thumbnail,
|
|
'age_limit': 18,
|
|
}
|