X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/00368b4c3a5d4e909e1b7ecfc4030bf28da020f3..201856721e6959e772b5e5ddee42d4d75d966703:/youtube_dl/extractor/youporn.py diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py index 547adef..d4eccb4 100644 --- a/youtube_dl/extractor/youporn.py +++ b/youtube_dl/extractor/youporn.py @@ -3,13 +3,13 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( int_or_none, sanitized_Request, str_to_int, unescapeHTML, unified_strdate, + url_or_none, ) from ..aes import aes_decrypt_text @@ -68,11 +68,9 @@ class YouPornIE(InfoExtractor): request.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(request, display_id) - title = self._search_regex( - [r'(?:video_titles|videoTitle)\s*[:=]\s*(["\'])(?P(?:(?!\1).)+)\1', - r'<h1[^>]+class=["\']heading\d?["\'][^>]*>(?P<title>[^<]+)<'], - webpage, 'title', group='title', - default=None) or self._og_search_title( + title = self._html_search_regex( + r'(?s)<div[^>]+class=["\']watchVideoTitle[^>]+>(.+?)</div>', + webpage, 'title', default=None) or self._og_search_title( webpage, default=None) or self._html_search_meta( 'title', webpage, fatal=True) @@ -88,8 +86,8 @@ class YouPornIE(InfoExtractor): for definition in definitions: if not isinstance(definition, dict): continue - video_url = definition.get('videoUrl') - if isinstance(video_url, compat_str) and video_url: + video_url = url_or_none(definition.get('videoUrl')) + if video_url: links.append(video_url) # Fallback #1, this also contains extra low quality 180p format @@ -134,7 +132,11 @@ class YouPornIE(InfoExtractor): formats.append(f) self._sort_formats(formats) - description = self._og_search_description(webpage, default=None) + description = self._html_search_regex( + r'(?s)<div[^>]+\bid=["\']description["\'][^>]*>(.+?)</div>', + webpage, 'description', + default=None) or self._og_search_description( + webpage, default=None) thumbnail = self._search_regex( r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1', webpage, 'thumbnail', fatal=False, group='thumbnail')