X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/9c8b63077a48f758bf0c9a7351669557071bbd74..a4e5dfe95bc8baaa961161b75ac623ce5831abf9:/youtube_dl/extractor/xvideos.py diff --git a/youtube_dl/extractor/xvideos.py b/youtube_dl/extractor/xvideos.py index 90138d7..166bcf4 100644 --- a/youtube_dl/extractor/xvideos.py +++ b/youtube_dl/extractor/xvideos.py @@ -1,53 +1,110 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor +from ..compat import compat_urllib_parse_unquote from ..utils import ( - compat_urllib_parse, + clean_html, + determine_ext, + ExtractorError, + int_or_none, + parse_duration, ) class XVideosIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)' - _TEST = { - u'url': u'http://www.xvideos.com/video939581/funny_porns_by_s_-1', - u'file': u'939581.flv', - u'md5': u'1d0c835822f0a71a7bf011855db929d0', - u'info_dict': { - u"title": u"Funny Porns By >>>>S<<<<<< -1", - u"age_limit": 18, + _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': '14cea69fcb84db54293b1e971466c2e1', + 'info_dict': { + 'id': '4588838', + '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): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group(1) + video_id = self._match_id(url) + + 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) - webpage = self._download_webpage(url, video_id) + title = self._html_search_regex( + (r'(?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) - self.report_extraction(video_id) + 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, + }) - # Extract video URL - video_url = compat_urllib_parse.unquote(self._search_regex(r'flv_url=(.+?)&', - webpage, u'video URL')) + 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)) - # Extract title - video_title = self._html_search_regex(r'<title>(.*?)\s+-\s+XVID', - webpage, u'title') + formats = [] - # Extract video thumbnail - video_thumbnail = self._search_regex(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/([a-fA-F0-9.]+jpg)', - webpage, u'thumbnail', 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', + }) - info = { + 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, - 'url': video_url, - 'uploader': None, - 'upload_date': None, - 'title': video_title, - 'ext': 'flv', - 'thumbnail': video_thumbnail, - 'description': None, + 'formats': formats, + 'title': title, + 'duration': duration, + 'thumbnails': thumbnails, 'age_limit': 18, } - - return [info]