X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fxvideos.py;h=8fc64914caf7166bcc49525ae133325067b134d3;hb=HEAD;hp=5dcf2fdd12f9140f0bd373fd5db41c93f4b18b38;hpb=55801fc76e2813de9a84eaa830d70ed73cb44463;p=youtube-dl diff --git a/youtube_dl/extractor/xvideos.py b/youtube_dl/extractor/xvideos.py index 5dcf2fdd1..8fc64914c 100644 --- a/youtube_dl/extractor/xvideos.py +++ b/youtube_dl/extractor/xvideos.py @@ -3,73 +3,145 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse_unquote, - compat_urllib_request, -) +from ..compat import compat_urllib_parse_unquote from ..utils import ( clean_html, - ExtractorError, determine_ext, + ExtractorError, + int_or_none, + parse_duration, ) class XVideosIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?xvideos\.com/video(?P[0-9]+)(?:.*)' - _TEST = { + _VALID_URL = r'''(?x) + https?:// + (?: + (?:[^/]+\.)?xvideos2?\.com/video| + (?:www\.)?xvideos\.es/video| + flashservice\.xvideos\.com/embedframe/| + static-hw\.xvideos\.com/swf/xv-player\.swf\?.*?\bid_video= + ) + (?P[0-9]+) + ''' + _TESTS = [{ 'url': 'http://www.xvideos.com/video4588838/biker_takes_his_girl', - 'md5': '4b46ae6ea5e6e9086e714d883313c0c9', + 'md5': '14cea69fcb84db54293b1e971466c2e1', 'info_dict': { 'id': '4588838', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Biker Takes his Girl', + 'duration': 108, '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' + }, { + 'url': 'https://flashservice.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) + + webpage = self._download_webpage( + 'https://www.xvideos.com/video%s/' % video_id, video_id) mobj = re.search(r'

(.+?)

', 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'(.*?)\s+-\s+XVID', webpage, 'title') - video_thumbnail = self._search_regex( - r'url_bigthumb=(.+?)&', webpage, 'thumbnail', fatal=False) + 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 = [{ - 'url': video_url, - }] + formats = [] - android_req = compat_urllib_request.Request(url) - android_req.add_header('User-Agent', self._ANDROID_USER_AGENT) - android_webpage = self._download_webpage(android_req, video_id, fatal=False) + 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', + }) - 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']) + for kind, _, format_url in re.findall( + r'setVideo([^(]+)\((["\'])(http.+?)\2\)', webpage): + format_id = kind.lower() + if format_id == 'hls': + formats.extend(self._extract_m3u8_formats( + format_url, video_id, 'mp4', + entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)) + 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, + }) self._sort_formats(formats) return { 'id': video_id, 'formats': formats, - 'title': video_title, - 'ext': 'flv', - 'thumbnail': video_thumbnail, + 'title': title, + 'duration': duration, + 'thumbnails': thumbnails, 'age_limit': 18, }