X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/9dc487f48b50767cf540fa36c3de2c386fd74c04..291f6705b350d9f813b12efb37b7963555758994:/youtube_dl/extractor/xvideos.py?ds=inline diff --git a/youtube_dl/extractor/xvideos.py b/youtube_dl/extractor/xvideos.py index 1dfe031..efee956 100644 --- a/youtube_dl/extractor/xvideos.py +++ b/youtube_dl/extractor/xvideos.py @@ -6,67 +6,98 @@ from .common import InfoExtractor 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?:// + (?: + (?:www\.)?xvideos\.com/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, } - } + }, { + '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, + }] def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + + webpage = self._download_webpage( + 'http://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_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) + + thumbnail = self._search_regex( + (r'setThumbUrl\(\s*(["\'])(?P<thumbnail>(?:(?!\1).)+)\1', + r'url_bigthumb=(?P<thumbnail>.+?)&'), + webpage, 'thumbnail', fatal=False, group='thumbnail') + 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}) + formats.append({ + 'url': video_url, + 'format_id': 'flv', + }) - player_args = self._search_regex( - r'(?s)new\s+HTML5Player\((.+?)\)', webpage, ' html5 player', default=None) - if player_args: - for arg in player_args.split(','): - format_url = self._search_regex( - r'(["\'])(?P<url>https?://.+?)\1', arg, 'url', - default=None, group='url') - if not format_url: - continue - ext = determine_ext(format_url) - if ext == 'mp4': - formats.append({'url': format_url}) - elif ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - format_url, video_id, 'mp4', - entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)) + 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, - 'thumbnail': video_thumbnail, + 'title': title, + 'duration': duration, + 'thumbnail': thumbnail, 'age_limit': 18, }