diff options
Diffstat (limited to 'youtube_dl/extractor/drtuber.py')
-rw-r--r-- | youtube_dl/extractor/drtuber.py | 24 |
1 files changed, 12 insertions, 12 deletions
diff --git a/youtube_dl/extractor/drtuber.py b/youtube_dl/extractor/drtuber.py index ca274dff6..639f9182c 100644 --- a/youtube_dl/extractor/drtuber.py +++ b/youtube_dl/extractor/drtuber.py @@ -15,7 +15,7 @@ class DrTuberIE(InfoExtractor): 'id': '1740434', 'display_id': 'hot-perky-blonde-naked-golf', 'ext': 'mp4', - 'title': 'Hot Perky Blonde Naked Golf', + 'title': 'hot perky blonde naked golf', 'like_count': int, 'dislike_count': int, 'comment_count': int, @@ -36,24 +36,24 @@ class DrTuberIE(InfoExtractor): r'<source src="([^"]+)"', webpage, 'video URL') title = self._html_search_regex( - r'<title>([^<]+)\s*-\s*Free', webpage, 'title') + [r'<p[^>]+class="title_substrate">([^<]+)</p>', r'<title>([^<]+) - \d+'], + webpage, 'title') thumbnail = self._html_search_regex( r'poster="([^"]+)"', webpage, 'thumbnail', fatal=False) - like_count = str_to_int(self._html_search_regex( - r'<span id="rate_likes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>', - webpage, 'like count', fatal=False)) - dislike_count = str_to_int(self._html_search_regex( - r'<span id="rate_dislikes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>', - webpage, 'like count', fatal=False)) - comment_count = str_to_int(self._html_search_regex( - r'<span class="comments_count">([\d,\.]+)</span>', - webpage, 'comment count', fatal=False)) + def extract_count(id_, name): + return str_to_int(self._html_search_regex( + r'<span[^>]+(?:class|id)="%s"[^>]*>([\d,\.]+)</span>' % id_, + webpage, '%s count' % name, fatal=False)) + + like_count = extract_count('rate_likes', 'like') + dislike_count = extract_count('rate_dislikes', 'dislike') + comment_count = extract_count('comments_count', 'comment') cats_str = self._search_regex( - r'<span>Categories:</span><div>(.+?)</div>', webpage, 'categories', fatal=False) + r'<div[^>]+class="categories_list">(.+?)</div>', webpage, 'categories', fatal=False) categories = [] if not cats_str else re.findall(r'<a title="([^"]+)"', cats_str) return { |