Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-23 08:54:33 +01:00
Code Issues Releases Wiki Activity

[soundgasm] add internet archive support

Browse Source
This commit is contained in:
ZerataX 2018-12-19 00:04:03 +01:00
parent 65e29cdac3
commit 7642b142b4
No known key found for this signature in database
GPG Key ID: 8333735E784DF9D4
1 changed files with 43 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

57
youtube_dl/extractor/soundgasm.py
View File

@ -8,18 +8,33 @@ 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<display_id>[0-9a-zA-Z_-]+)' _VALID_URL = r'(?P<archive>https?://web\.archive\.org/web/\d+/)?' + \
_TEST = { r'https?://(?:www\.)?soundgasm\.net(?::80)?/u/' + \
'url': 'http://soundgasm.net/u/ytdl/Piano-sample', r'(?P<user>[0-9a-zA-Z_-]+)/(?P<display_id>[0-9a-zA-Z_-]+)'
'md5': '010082a2c802c5275bb00030743e75ad', _TESTS = [{
'info_dict': { 'url': 'http://soundgasm.net/u/ytdl/Piano-sample',
'id': '88abd86ea000cafe98f96321b23cc1206cbcbcc9', 'md5': '010082a2c802c5275bb00030743e75ad',
'ext': 'm4a', 'info_dict': {
'title': 'Piano sample', 'id': '88abd86ea000cafe98f96321b23cc1206cbcbcc9',
'description': 'Royalty Free Sample Music', 'ext': 'm4a',
'uploader': 'ytdl', 'title': 'Piano sample',
'description': 'Royalty Free Sample Music',
'uploader': 'ytdl',
}
},
{
'url': 'http://web.archive.org/web/20181218221507/' +
'https://soundgasm.net/u/ytdl/Piano-sample',
'md5': '010082a2c802c5275bb00030743e75ad',
'info_dict': {
'id': '88abd86ea000cafe98f96321b23cc1206cbcbcc9',
'ext': 'm4a',
'title': 'Piano sample',
'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)
@ -31,6 +46,9 @@ class SoundgasmIE(InfoExtractor):
r'(?s)m4a\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, r'(?s)m4a\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
'audio URL', group='url') 'audio URL', group='url')
if mobj.group('archive'):
audio_url = audio_url[:41] + "if_" + audio_url[41:]
title = self._search_regex( title = self._search_regex(
r'<div[^>]+\bclass=["\']jp-title[^>]+>([^<]+)', r'<div[^>]+\bclass=["\']jp-title[^>]+>([^<]+)',
webpage, 'title', default=display_id) webpage, 'title', default=display_id)
@ -56,14 +74,25 @@ class SoundgasmIE(InfoExtractor):
class SoundgasmProfileIE(InfoExtractor): class SoundgasmProfileIE(InfoExtractor):
IE_NAME = 'soundgasm:profile' IE_NAME = 'soundgasm:profile'
_VALID_URL = r'https?://(?:www\.)?soundgasm\.net/u/(?P<id>[^/]+)/?(?:\#.*)?$' _VALID_URL = r'(?P<archive>https?://web\.archive\.org/web/\d+/)?' + \
_TEST = { r'https?://(?:www\.)?soundgasm\.net/u/' + \
r'(?P<id>[^/]+)/?(?:\#.*)?$'
_TESTS = [{
'url': 'http://soundgasm.net/u/ytdl', 'url': 'http://soundgasm.net/u/ytdl',
'info_dict': { 'info_dict': {
'id': 'ytdl', 'id': 'ytdl',
}, },
'playlist_count': 1, 'playlist_count': 1,
} },
{
'url': 'http://web.archive.org/web/20181218222843/' +
'https://soundgasm.net/u/ytdl',
'info_dict': {
'id': 'ytdl',
},
'playlist_count': 1,
}
]
def _real_extract(self, url): def _real_extract(self, url):
profile_id = self._match_id(url) profile_id = self._match_id(url)