X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/c512650955de0b16d37e7fa7fb29ea0985e415bb..2b4515201a54c38e34434ea2817d606be134a7c9:/youtube_dl/extractor/xvideos.py?ds=inline diff --git a/youtube_dl/extractor/xvideos.py b/youtube_dl/extractor/xvideos.py index 7e00448..30825da 100644 --- a/youtube_dl/extractor/xvideos.py +++ b/youtube_dl/extractor/xvideos.py @@ -3,58 +3,70 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_urllib_parse_unquote from ..utils import ( - compat_urllib_parse, - ExtractorError, clean_html, + ExtractorError, + determine_ext, ) class XVideosIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)' + _VALID_URL = r'https?://(?:www\.)?xvideos\.com/video(?P[0-9]+)(?:.*)' _TEST = { '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', 'age_limit': 18, } } 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(url, video_id) - self.report_extraction(video_id) - mobj = re.search(r'

(.+?)

', webpage) if mobj: raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(mobj.group(1))), expected=True) - # Extract video URL - video_url = compat_urllib_parse.unquote( - self._search_regex(r'flv_url=(.+?)&', webpage, 'video URL')) - - # Extract title video_title = self._html_search_regex( r'(.*?)\s+-\s+XVID', webpage, 'title') - - # Extract video thumbnail video_thumbnail = self._search_regex( r'url_bigthumb=(.+?)&', webpage, 'thumbnail', 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': + 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, + 'formats': formats, 'title': video_title, - 'ext': 'flv', 'thumbnail': video_thumbnail, - 'description': None, 'age_limit': 18, }