mirror of
https://codeberg.org/polarisfm/youtube-dl
synced 2024-10-31 22:44:32 +01:00
[soundgasm] Improve extraction (closes #14588)
This commit is contained in:
parent
dc24a7d4a2
commit
30e6161799
@ -8,36 +8,49 @@ from .common import InfoExtractor
|
|||||||
|
|
||||||
class SoundgasmIE(InfoExtractor):
|
class SoundgasmIE(InfoExtractor):
|
||||||
IE_NAME = 'soundgasm'
|
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 = {
|
_TEST = {
|
||||||
'url': 'http://soundgasm.net/u/ytdl/Piano-sample',
|
'url': 'http://soundgasm.net/u/ytdl/Piano-sample',
|
||||||
'md5': '010082a2c802c5275bb00030743e75ad',
|
'md5': '010082a2c802c5275bb00030743e75ad',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '88abd86ea000cafe98f96321b23cc1206cbcbcc9',
|
'id': '88abd86ea000cafe98f96321b23cc1206cbcbcc9',
|
||||||
'ext': 'm4a',
|
'ext': 'm4a',
|
||||||
'title': 'ytdl_Piano-sample',
|
'title': 'Piano sample',
|
||||||
'description': 'Royalty Free Sample Music'
|
'description': 'Royalty Free Sample Music',
|
||||||
|
'uploader': 'ytdl',
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
mobj = re.match(self._VALID_URL, url)
|
mobj = re.match(self._VALID_URL, url)
|
||||||
display_id = mobj.group('title')
|
display_id = mobj.group('display_id')
|
||||||
audio_title = mobj.group('user') + '_' + mobj.group('title')
|
|
||||||
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')
|
r'(?s)m4a\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
|
||||||
audio_id = re.split(r'\/|\.', audio_url)[-2]
|
'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',
|
(r'(?s)<div[^>]+\bclass=["\']jp-description[^>]+>(.+?)</div>',
|
||||||
fatal=False)
|
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 {
|
return {
|
||||||
'id': audio_id,
|
'id': audio_id,
|
||||||
'display_id': display_id,
|
'display_id': display_id,
|
||||||
'url': audio_url,
|
'url': audio_url,
|
||||||
'title': audio_title,
|
'vcodec': 'none',
|
||||||
'description': description
|
'title': title,
|
||||||
|
'description': description,
|
||||||
|
'uploader': mobj.group('user'),
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
|
Loading…
Reference in New Issue
Block a user