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

[mixcloud] Fix extraction of some metadata

Browse source 
The second test had some wrong info.
I couldn't find the timestamp, so I have removed it.
This commit is contained in:
Jaime Marquínez Ferrándiz 2015-03-18 16:50:23 +01:00
parent fa8ce26904
commit 7a757b7194
1 changed files with 5 additions and 12 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

17
youtube_dl/extractor/mixcloud.py
View file

@ -10,7 +10,6 @@ from ..utils import (
ExtractorError, ExtractorError,
HEADRequest, HEADRequest,
str_to_int, str_to_int,
parse_iso8601,
) )
@ -27,8 +26,6 @@ class MixcloudIE(InfoExtractor):
'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.', 'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
'uploader': 'Daniel Holbach', 'uploader': 'Daniel Holbach',
'uploader_id': 'dholbach', 'uploader_id': 'dholbach',
'upload_date': '20111115',
'timestamp': 1321359578,
'thumbnail': 're:https?://.*\.jpg', 'thumbnail': 're:https?://.*\.jpg',
'view_count': int, 'view_count': int,
'like_count': int, 'like_count': int,
@ -37,12 +34,12 @@ class MixcloudIE(InfoExtractor):
'url': 'http://www.mixcloud.com/gillespeterson/caribou-7-inch-vinyl-mix-chat/', 'url': 'http://www.mixcloud.com/gillespeterson/caribou-7-inch-vinyl-mix-chat/',
'info_dict': { 'info_dict': {
'id': 'gillespeterson-caribou-7-inch-vinyl-mix-chat', 'id': 'gillespeterson-caribou-7-inch-vinyl-mix-chat',
'ext': 'm4a', 'ext': 'mp3',
'title': 'Electric Relaxation vol. 3', 'title': 'Caribou 7 inch Vinyl Mix & Chat',
'description': 'md5:2b8aec6adce69f9d41724647c65875e8', 'description': 'md5:2b8aec6adce69f9d41724647c65875e8',
'uploader': 'Daniel Drumz', 'uploader': 'Gilles Peterson Worldwide',
'uploader_id': 'gillespeterson', 'uploader_id': 'gillespeterson',
'thumbnail': 're:https?://.*\.jpg', 'thumbnail': 're:https?://.*/images/',
'view_count': int, 'view_count': int,
'like_count': int, 'like_count': int,
}, },
@ -85,7 +82,7 @@ class MixcloudIE(InfoExtractor):
raise ExtractorError('Unable to extract track url') raise ExtractorError('Unable to extract track url')
PREFIX = ( PREFIX = (
r'<span class="play-button[^"]*?"' r'm-play-on-spacebar[^>]+'
r'(?:\s+[a-zA-Z0-9-]+(?:="[^"]+")?)*?\s+') r'(?:\s+[a-zA-Z0-9-]+(?:="[^"]+")?)*?\s+')
title = self._html_search_regex( title = self._html_search_regex(
PREFIX + r'm-title="([^"]+)"', webpage, 'title') PREFIX + r'm-title="([^"]+)"', webpage, 'title')
@ -105,9 +102,6 @@ class MixcloudIE(InfoExtractor):
[r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"', [r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
r'/listeners/?">([0-9,.]+)</a>'], r'/listeners/?">([0-9,.]+)</a>'],
webpage, 'play count', fatal=False)) webpage, 'play count', fatal=False))
timestamp = parse_iso8601(self._search_regex(
r'<time itemprop="dateCreated" datetime="([^"]+)">',
webpage, 'upload date', default=None))
return { return {
'id': track_id, 'id': track_id,
@ -117,7 +111,6 @@ class MixcloudIE(InfoExtractor):
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'uploader': uploader, 'uploader': uploader,
'uploader_id': uploader_id, 'uploader_id': uploader_id,
'timestamp': timestamp,
'view_count': view_count, 'view_count': view_count,
'like_count': like_count, 'like_count': like_count,
} }