w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[youtube] Extract like and dislike count (#1895)

Browse source
This commit is contained in:
Jaime Marquínez Ferrándiz 2013-12-06 13:22:04 +01:00
parent 4e76179476
commit 336c3a69bd
1 changed files with 11 additions and 12 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

23
youtube_dl/extractor/youtube.py
View file

@ -388,10 +388,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
super(YoutubeIE, self).__init__(*args, **kwargs) super(YoutubeIE, self).__init__(*args, **kwargs)
self._player_cache = {} self._player_cache = {}
def report_video_webpage_download(self, video_id):
"""Report attempt to download video webpage."""
self.to_screen(u'%s: Downloading video webpage' % video_id)
def report_video_info_webpage_download(self, video_id): def report_video_info_webpage_download(self, video_id):
"""Report attempt to download video info webpage.""" """Report attempt to download video info webpage."""
self.to_screen(u'%s: Downloading video info webpage' % video_id) self.to_screen(u'%s: Downloading video info webpage' % video_id)
@ -1258,15 +1254,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
video_id = self._extract_id(url) video_id = self._extract_id(url)
# Get video webpage # Get video webpage
self.report_video_webpage_download(video_id)
url = 'https://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id url = 'https://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id
request = compat_urllib_request.Request(url) video_webpage = self._download_webpage(url, video_id)
try:
video_webpage_bytes = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
raise ExtractorError(u'Unable to download video webpage: %s' % compat_str(err))
video_webpage = video_webpage_bytes.decode('utf-8', 'ignore')
# Attempt to extract SWF player URL # Attempt to extract SWF player URL
mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage) mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
@ -1383,6 +1372,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
else: else:
video_description = u'' video_description = u''
def _extract_count(klass):
count = self._search_regex(r'class="%s">([\d,]+)</span>' % re.escape(klass), video_webpage, klass, fatal=False)
if count is not None:
return int(count.replace(',', ''))
return None
like_count = _extract_count(u'likes-count')
dislike_count = _extract_count(u'dislikes-count')
# subtitles # subtitles
video_subtitles = self.extract_subtitles(video_id, video_webpage) video_subtitles = self.extract_subtitles(video_id, video_webpage)
@ -1515,6 +1512,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
'annotations': video_annotations, 'annotations': video_annotations,
'webpage_url': 'https://www.youtube.com/watch?v=%s' % video_id, 'webpage_url': 'https://www.youtube.com/watch?v=%s' % video_id,
'view_count': view_count, 'view_count': view_count,
'like_count': like_count,
'dislike_count': dislike_count,
}) })
return results return results