Unverified Commit b477fc13 authored by Sergey M․'s avatar Sergey M․
Browse files

[youtube] Fix thumbnails extraction and remove uploader id extraction warning (closes #25676)

parent d84b21b4
...@@ -2225,8 +2225,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): ...@@ -2225,8 +2225,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
if mobj is not None: if mobj is not None:
video_uploader_id = mobj.group('uploader_id') video_uploader_id = mobj.group('uploader_id')
video_uploader_url = mobj.group('uploader_url') video_uploader_url = mobj.group('uploader_url')
else:
self._downloader.report_warning('unable to extract uploader nickname')
channel_id = ( channel_id = (
str_or_none(video_details.get('channelId')) str_or_none(video_details.get('channelId'))
...@@ -2237,17 +2235,33 @@ class YoutubeIE(YoutubeBaseInfoExtractor): ...@@ -2237,17 +2235,33 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
video_webpage, 'channel id', default=None, group='id')) video_webpage, 'channel id', default=None, group='id'))
channel_url = 'http://www.youtube.com/channel/%s' % channel_id if channel_id else None channel_url = 'http://www.youtube.com/channel/%s' % channel_id if channel_id else None
# thumbnail image thumbnails = []
# We try first to get a high quality image: thumbnails_list = try_get(
m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">', video_details, lambda x: x['thumbnail']['thumbnails'], list) or []
video_webpage, re.DOTALL) for t in thumbnails_list:
if m_thumb is not None: if not isinstance(t, dict):
video_thumbnail = m_thumb.group(1) continue
elif 'thumbnail_url' not in video_info: thumbnail_url = url_or_none(t.get('url'))
self._downloader.report_warning('unable to extract video thumbnail') if not thumbnail_url:
continue
thumbnails.append({
'url': thumbnail_url,
'width': int_or_none(t.get('width')),
'height': int_or_none(t.get('height')),
})
if not thumbnails:
video_thumbnail = None video_thumbnail = None
else: # don't panic if we can't find it # We try first to get a high quality image:
video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0]) m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
video_webpage, re.DOTALL)
if m_thumb is not None:
video_thumbnail = m_thumb.group(1)
thumbnail_url = try_get(video_info, lambda x: x['thumbnail_url'][0], compat_str)
if thumbnail_url:
video_thumbnail = compat_urllib_parse_unquote_plus(thumbnail_url)
if video_thumbnail:
thumbnails.append({'url': video_thumbnail})
# upload date # upload date
upload_date = self._html_search_meta( upload_date = self._html_search_meta(
...@@ -2480,7 +2494,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): ...@@ -2480,7 +2494,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'creator': video_creator or artist, 'creator': video_creator or artist,
'title': video_title, 'title': video_title,
'alt_title': video_alt_title or track, 'alt_title': video_alt_title or track,
'thumbnail': video_thumbnail, 'thumbnails': thumbnails,
'description': video_description, 'description': video_description,
'categories': video_categories, 'categories': video_categories,
'tags': video_tags, 'tags': video_tags,
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment