X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/87a0165ca7e39af4dacb7ec637063b2cd35ae40b..0fc91537a0580721211b68e8cc4367a33cd6d4f2:/youtube_dl/extractor/youporn.py?ds=sidebyside diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py index 0265a64..547adef 100644 --- a/youtube_dl/extractor/youporn.py +++ b/youtube_dl/extractor/youporn.py @@ -3,6 +3,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( int_or_none, sanitized_Request, @@ -24,9 +25,9 @@ class YouPornIE(InfoExtractor): 'ext': 'mp4', 'title': 'Sex Ed: Is It Safe To Masturbate Daily?', 'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?', - 'thumbnail': 're:^https?://.*\.jpg$', + 'thumbnail': r're:^https?://.*\.jpg$', 'uploader': 'Ask Dan And Jennifer', - 'upload_date': '20101221', + 'upload_date': '20101217', 'average_rating': int, 'view_count': int, 'comment_count': int, @@ -43,9 +44,9 @@ class YouPornIE(InfoExtractor): 'ext': 'mp4', 'title': 'Big Tits Awesome Brunette On amazing webcam show', 'description': 'http://sweetlivegirls.com Big Tits Awesome Brunette On amazing webcam show.mp4', - 'thumbnail': 're:^https?://.*\.jpg$', + 'thumbnail': r're:^https?://.*\.jpg$', 'uploader': 'Unknown', - 'upload_date': '20111125', + 'upload_date': '20110418', 'average_rating': int, 'view_count': int, 'comment_count': int, @@ -68,28 +69,46 @@ class YouPornIE(InfoExtractor): webpage = self._download_webpage(request, display_id) title = self._search_regex( - [r'(?:video_titles|videoTitle)\s*[:=]\s*(["\'])(?P.+?)\1', - r'<h1[^>]+class=["\']heading\d?["\'][^>]*>([^<])<'], - webpage, 'title', group='title') + [r'(?:video_titles|videoTitle)\s*[:=]\s*(["\'])(?P<title>(?:(?!\1).)+)\1', + r'<h1[^>]+class=["\']heading\d?["\'][^>]*>(?P<title>[^<]+)<'], + webpage, 'title', group='title', + default=None) or self._og_search_title( + webpage, default=None) or self._html_search_meta( + 'title', webpage, fatal=True) links = [] + # Main source + definitions = self._parse_json( + self._search_regex( + r'mediaDefinition\s*=\s*(\[.+?\]);', webpage, + 'media definitions', default='[]'), + video_id, fatal=False) + if definitions: + for definition in definitions: + if not isinstance(definition, dict): + continue + video_url = definition.get('videoUrl') + if isinstance(video_url, compat_str) and video_url: + links.append(video_url) + + # Fallback #1, this also contains extra low quality 180p format + for _, link in re.findall(r'<a[^>]+href=(["\'])(http.+?)\1[^>]+title=["\']Download [Vv]ideo', webpage): + links.append(link) + + # Fallback #2 (unavailable as at 22.06.2017) sources = self._search_regex( r'(?s)sources\s*:\s*({.+?})', webpage, 'sources', default=None) if sources: for _, link in re.findall(r'[^:]+\s*:\s*(["\'])(http.+?)\1', sources): links.append(link) - # Fallback #1 + # Fallback #3 (unavailable as at 22.06.2017) for _, link in re.findall( - r'(?:videoUrl|videoSrc|videoIpadUrl|html5PlayerSrc)\s*[:=]\s*(["\'])(http.+?)\1', webpage): - links.append(link) - - # Fallback #2, this also contains extra low quality 180p format - for _, link in re.findall(r'<a[^>]+href=(["\'])(http.+?)\1[^>]+title=["\']Download [Vv]ideo', webpage): + r'(?:videoSrc|videoIpadUrl|html5PlayerSrc)\s*[:=]\s*(["\'])(http.+?)\1', webpage): links.append(link) - # Fallback #3, encrypted links + # Fallback #4, encrypted links (unavailable as at 22.06.2017) for _, encrypted_link in re.findall( r'encryptedQuality\d{3,4}URL\s*=\s*(["\'])([\da-zA-Z+/=]+)\1', webpage): links.append(aes_decrypt_text(encrypted_link, title, 32).decode('utf-8')) @@ -124,7 +143,8 @@ class YouPornIE(InfoExtractor): r'(?s)<div[^>]+class=["\']submitByLink["\'][^>]*>(.+?)</div>', webpage, 'uploader', fatal=False) upload_date = unified_strdate(self._html_search_regex( - r'(?s)<div[^>]+class=["\']videoInfo(?:Date|Time)["\'][^>]*>(.+?)</div>', + [r'Date\s+[Aa]dded:\s*<span>([^<]+)', + r'(?s)<div[^>]+class=["\']videoInfo(?:Date|Time)["\'][^>]*>(.+?)</div>'], webpage, 'upload date', fatal=False)) age_limit = self._rta_search(webpage)