X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fsexu.py;h=3df51520b06e8bc2da1b3afa3fee75db4e21be46;hb=HEAD;hp=45b33b3eafb01b32d6b2b6f70edce552e633f233;hpb=437f68d868176e7e3d56a8e2c258384b984baeec;p=youtube-dl diff --git a/youtube_dl/extractor/sexu.py b/youtube_dl/extractor/sexu.py index 45b33b3ea..3df51520b 100644 --- a/youtube_dl/extractor/sexu.py +++ b/youtube_dl/extractor/sexu.py @@ -1,7 +1,5 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor @@ -14,38 +12,42 @@ class SexuIE(InfoExtractor): 'id': '961791', 'ext': 'mp4', 'title': 'md5:4d05a19a5fc049a63dbbaf05fb71d91b', - 'description': 'md5:c5ed8625eb386855d5a7967bd7b77a54', + 'description': 'md5:2b75327061310a3afb3fbd7d09e2e403', 'categories': list, # NSFW - 'thumbnail': 're:https?://.*\.jpg$', + 'thumbnail': r're:https?://.*\.jpg$', 'age_limit': 18, } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - quality_arr = self._search_regex(r'sources:\s*\[([^\]]+)\]', webpage, 'quality formats') + jwvideo = self._parse_json( + self._search_regex(r'\.setup\(\s*({.+?})\s*\);', webpage, 'jwvideo'), + video_id) + + sources = jwvideo['sources'] formats = [{ - 'url': fmt[0].replace('\\', ''), - 'format_id': fmt[1], - 'height': int(fmt[1][:3]), - } for fmt in re.findall(r'"file":"([^"]+)","label":"([^"]+)"', quality_arr)] + 'url': source['file'].replace('\\', ''), + 'format_id': source.get('label'), + 'height': int(self._search_regex( + r'^(\d+)[pP]', source.get('label', ''), 'height', + default=None)), + } for source in sources if source.get('file')] self._sort_formats(formats) title = self._html_search_regex( - r'([^<]+)\s*-\s*Sexu.Com', webpage, 'title') + r'([^<]+)\s*-\s*Sexu\.Com', webpage, 'title') - description = self._html_search_meta('description', webpage, 'description') + description = self._html_search_meta( + 'description', webpage, 'description') - thumbnail = self._html_search_regex( - r'image:\s*"([^"]+)"', - webpage, 'thumbnail', fatal=False) + thumbnail = jwvideo.get('image') - categories_str = self._html_search_meta('keywords', webpage, 'categories', fatal=False) + categories_str = self._html_search_meta( + 'keywords', webpage, 'categories') categories = ( None if categories_str is None else categories_str.split(','))