X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/47d80ec0b18245caeb97018d4c1af18d0b5b972b..HEAD:/youtube_dl/extractor/drtuber.py diff --git a/youtube_dl/extractor/drtuber.py b/youtube_dl/extractor/drtuber.py index 22da8e4..2baea58 100644 --- a/youtube_dl/extractor/drtuber.py +++ b/youtube_dl/extractor/drtuber.py @@ -4,13 +4,15 @@ import re from .common import InfoExtractor from ..utils import ( + int_or_none, NO_DEFAULT, + parse_duration, str_to_int, ) class DrTuberIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?drtuber\.com/(?:video|embed)/(?P\d+)(?:/(?P[\w-]+))?' + _VALID_URL = r'https?://(?:(?:www|m)\.)?drtuber\.com/(?:video|embed)/(?P\d+)(?:/(?P[\w-]+))?' _TESTS = [{ 'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf', 'md5': '93e680cf2536ad0dfb7e74d94a89facd', @@ -22,12 +24,15 @@ class DrTuberIE(InfoExtractor): 'like_count': int, 'comment_count': int, 'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'], - 'thumbnail': 're:https?://.*\.jpg$', + 'thumbnail': r're:https?://.*\.jpg$', 'age_limit': 18, } }, { 'url': 'http://www.drtuber.com/embed/489939', 'only_matching': True, + }, { + 'url': 'http://m.drtuber.com/video/3893529/lingerie-blowjob-from-beautiful-teen', + 'only_matching': True, }] @staticmethod @@ -44,11 +49,31 @@ class DrTuberIE(InfoExtractor): webpage = self._download_webpage( 'http://www.drtuber.com/video/%s' % video_id, display_id) - video_url = self._html_search_regex( - r']*><(?:p|h\d+)[^>]*>([^<]+)<', + (r']+class=["\']title[^>]+>([^<]+)', + r'([^<]+)\s*@\s+DrTuber', + r'class="title_watch"[^>]*><(?:p|h\d+)[^>]*>([^<]+)<', r'<p[^>]+class="title_substrate">([^<]+)</p>', r'<title>([^<]+) - \d+'), webpage, 'title') @@ -75,7 +100,7 @@ class DrTuberIE(InfoExtractor): return { 'id': video_id, 'display_id': display_id, - 'url': video_url, + 'formats': formats, 'title': title, 'thumbnail': thumbnail, 'like_count': like_count, @@ -83,4 +108,5 @@ class DrTuberIE(InfoExtractor): 'comment_count': comment_count, 'categories': categories, 'age_limit': self._rta_search(webpage), + 'duration': duration, }