projects
/
youtube-dl
/ commitdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
| commitdiff |
tree
raw
|
patch
|
inline
| side by side (parent:
dc24a7d
)
[soundgasm] Improve extraction (closes #14588)
author
Sergey M․
<dstftw@gmail.com>
Thu, 26 Oct 2017 16:16:16 +0000
(23:16 +0700)
committer
Sergey M․
<dstftw@gmail.com>
Thu, 26 Oct 2017 16:16:16 +0000
(23:16 +0700)
youtube_dl/extractor/soundgasm.py
patch
|
blob
|
history
diff --git
a/youtube_dl/extractor/soundgasm.py
b/youtube_dl/extractor/soundgasm.py
index e004e2c5ab12705c8d9ff5e12b25f53579539c72..3d78a9d76cce8aa28902111fe3f9018dafbb856a 100644
(file)
--- a/
youtube_dl/extractor/soundgasm.py
+++ b/
youtube_dl/extractor/soundgasm.py
@@
-8,36
+8,49
@@
from .common import InfoExtractor
class SoundgasmIE(InfoExtractor):
IE_NAME = 'soundgasm'
class SoundgasmIE(InfoExtractor):
IE_NAME = 'soundgasm'
- _VALID_URL = r'https?://(?:www\.)?soundgasm\.net/u/(?P<user>[0-9a-zA-Z_
\-]+)/(?P<title>[0-9a-zA-Z_\
-]+)'
+ _VALID_URL = r'https?://(?:www\.)?soundgasm\.net/u/(?P<user>[0-9a-zA-Z_
-]+)/(?P<display_id>[0-9a-zA-Z_
-]+)'
_TEST = {
'url': 'http://soundgasm.net/u/ytdl/Piano-sample',
'md5': '010082a2c802c5275bb00030743e75ad',
'info_dict': {
'id': '88abd86ea000cafe98f96321b23cc1206cbcbcc9',
'ext': 'm4a',
_TEST = {
'url': 'http://soundgasm.net/u/ytdl/Piano-sample',
'md5': '010082a2c802c5275bb00030743e75ad',
'info_dict': {
'id': '88abd86ea000cafe98f96321b23cc1206cbcbcc9',
'ext': 'm4a',
- 'title': 'ytdl_Piano-sample',
- 'description': 'Royalty Free Sample Music'
+ 'title': 'Piano sample',
+ 'description': 'Royalty Free Sample Music',
+ 'uploader': 'ytdl',
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
- display_id = mobj.group('
title
')
- audio_title = mobj.group('user') + '_' + mobj.group('title')
+ display_id = mobj.group('
display_id
')
+
webpage = self._download_webpage(url, display_id)
webpage = self._download_webpage(url, display_id)
+
audio_url = self._html_search_regex(
audio_url = self._html_search_regex(
- r'(?s)m4a\:\s"([^"]+)"', webpage, 'audio URL')
- audio_id = re.split(r'\/|\.', audio_url)[-2]
+ r'(?s)m4a\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
+ 'audio URL', group='url')
+
+ title = self._search_regex(
+ r'<div[^>]+\bclass=["\']jp-title[^>]+>([^<]+)',
+ webpage, 'title', default=display_id)
+
description = self._html_search_regex(
description = self._html_search_regex(
- r'(?s)<li>Description:\s(.*?)<\/li>', webpage, 'description',
- fatal=False)
+ (r'(?s)<div[^>]+\bclass=["\']jp-description[^>]+>(.+?)</div>',
+ r'(?s)<li>Description:\s(.*?)<\/li>'),
+ webpage, 'description', fatal=False)
+
+ audio_id = self._search_regex(
+ r'/([^/]+)\.m4a', audio_url, 'audio id', default=display_id)
return {
'id': audio_id,
'display_id': display_id,
'url': audio_url,
return {
'id': audio_id,
'display_id': display_id,
'url': audio_url,
- 'title': audio_title,
- 'description': description
+ 'vcodec': 'none',
+ 'title': title,
+ 'description': description,
+ 'uploader': mobj.group('user'),
}
}