R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[mixcloud] Fix extraction of URL and like-count

Browse Source
This commit is contained in:
Roman Le Négrate 2015-03-15 22:32:06 +01:00
parent 082b1155a3
commit 93dbe3f12f
1 changed files with 4 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
youtube_dl/extractor/mixcloud.py
View File

@ -73,14 +73,10 @@ class MixcloudIE(InfoExtractor):
webpage = self._download_webpage(url, track_id) webpage = self._download_webpage(url, track_id)
preview_url = self._search_regex( preview_url = self._search_regex(
r'\s(?:data-preview-url|m-preview)="([^"]+)"', webpage, 'preview url') r'\bm-play-on-spacebar\b.*\n?.*\bm-preview="([^"]+)"', webpage, 'preview url')
song_url = preview_url.replace('/previews/', '/c/originals/') song_url = re.sub(r'\.mp3$', '.m4a', preview_url.replace('/previews/', '/c/m4a/64/'))
template_url = re.sub(r'(stream\d*)', 'stream%d', song_url) template_url = re.sub(r'(stream\d+)', 'stream%d', song_url)
final_song_url = self._get_url(track_id, template_url) final_song_url = self._get_url(track_id, template_url)
if final_song_url is None:
self.to_screen('Trying with m4a extension')
template_url = template_url.replace('.mp3', '.m4a').replace('originals/', 'm4a/64/')
final_song_url = self._get_url(track_id, template_url)
if final_song_url is None: if final_song_url is None:
raise ExtractorError('Unable to extract track url') raise ExtractorError('Unable to extract track url')
@ -99,8 +95,7 @@ class MixcloudIE(InfoExtractor):
r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False) r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False)
description = self._og_search_description(webpage) description = self._og_search_description(webpage)
like_count = str_to_int(self._search_regex( like_count = str_to_int(self._search_regex(
[r'<meta itemprop="interactionCount" content="UserLikes:([0-9]+)"', r'\bbutton-favorite\b.+m-ajax-toggle-count="([^"]+)"',
r'/favorites/?">([0-9]+)<'],
webpage, 'like count', fatal=False)) webpage, 'like count', fatal=False))
view_count = str_to_int(self._search_regex( view_count = str_to_int(self._search_regex(
[r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"', [r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',