X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fdrtuber.py;h=e8870c4607d4e4f0293f134610ed8f1f8d48e956;hb=b6c4e36728e8f60ae7f4910a9b7027a2b702e8dc;hp=639f9182c5484a22f0056e25fc6aa7e56f193df5;hpb=804ad79985bf2cc7d04547d4c8fcfa4d7234222f;p=youtube-dl diff --git a/youtube_dl/extractor/drtuber.py b/youtube_dl/extractor/drtuber.py index 639f9182c..e8870c460 100644 --- a/youtube_dl/extractor/drtuber.py +++ b/youtube_dl/extractor/drtuber.py @@ -3,7 +3,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import str_to_int +from ..utils import ( + NO_DEFAULT, + str_to_int, +) class DrTuberIE(InfoExtractor): @@ -17,7 +20,6 @@ class DrTuberIE(InfoExtractor): 'ext': 'mp4', 'title': 'hot perky blonde naked golf', 'like_count': int, - 'dislike_count': int, 'comment_count': int, 'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'], 'thumbnail': 're:https?://.*\.jpg$', @@ -36,25 +38,29 @@ class DrTuberIE(InfoExtractor): r']+class="title_substrate">([^<]+)

', r'([^<]+) - \d+'], + (r'class="title_watch"[^>]*><p>([^<]+)<', + r'<p[^>]+class="title_substrate">([^<]+)</p>', + r'<title>([^<]+) - \d+'), webpage, 'title') thumbnail = self._html_search_regex( r'poster="([^"]+)"', webpage, 'thumbnail', fatal=False) - def extract_count(id_, name): + def extract_count(id_, name, default=NO_DEFAULT): return str_to_int(self._html_search_regex( r'<span[^>]+(?:class|id)="%s"[^>]*>([\d,\.]+)</span>' % id_, - webpage, '%s count' % name, fatal=False)) + webpage, '%s count' % name, default=default, fatal=False)) like_count = extract_count('rate_likes', 'like') - dislike_count = extract_count('rate_dislikes', 'dislike') + dislike_count = extract_count('rate_dislikes', 'dislike', default=None) comment_count = extract_count('comments_count', 'comment') cats_str = self._search_regex( - r'<div[^>]+class="categories_list">(.+?)</div>', webpage, 'categories', fatal=False) - categories = [] if not cats_str else re.findall(r'<a title="([^"]+)"', cats_str) + r'<div[^>]+class="categories_list">(.+?)</div>', + webpage, 'categories', fatal=False) + categories = [] if not cats_str else re.findall( + r'<a title="([^"]+)"', cats_str) return { 'id': video_id,