Akkariin/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2024-11-20 22:33:01 +08:00
Code Issues Releases Wiki Activity

[soundcloud] Generalize playlist entries extraction (#10733)

Browse Source
This commit is contained in:
Sergey M․ 2016-09-24 19:18:01 +07:00
parent f0bc5a8609
commit 8e45e1cc4d
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 26 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
youtube_dl/extractor/soundcloud.py
View File

@ -260,7 +260,20 @@ class SoundcloudIE(InfoExtractor):
return self._extract_info_dict(info, full_title, secret_token=token) return self._extract_info_dict(info, full_title, secret_token=token)
class SoundcloudSetIE(SoundcloudIE): class SoundcloudBaseIE(SoundcloudIE):
@staticmethod
def _extract_id(e):
return compat_str(e['id']) if e.get('id') else None
def _extract_track_entries(self, tracks):
return [
self.url_result(
track['permalink_url'], SoundcloudIE.ie_key(),
video_id=self._extract_id(track))
for track in tracks if track.get('permalink_url')]
class SoundcloudSetIE(SoundcloudBaseIE):
_VALID_URL = r'https?://(?:(?:www|m)\.)?soundcloud\.com/(?P<uploader>[\w\d-]+)/sets/(?P<slug_title>[\w\d-]+)(?:/(?P<token>[^?/]+))?' _VALID_URL = r'https?://(?:(?:www|m)\.)?soundcloud\.com/(?P<uploader>[\w\d-]+)/sets/(?P<slug_title>[\w\d-]+)(?:/(?P<token>[^?/]+))?'
IE_NAME = 'soundcloud:set' IE_NAME = 'soundcloud:set'
_TESTS = [{ _TESTS = [{
@ -299,7 +312,7 @@ class SoundcloudSetIE(SoundcloudIE):
msgs = (compat_str(err['error_message']) for err in info['errors']) msgs = (compat_str(err['error_message']) for err in info['errors'])
raise ExtractorError('unable to download video webpage: %s' % ','.join(msgs)) raise ExtractorError('unable to download video webpage: %s' % ','.join(msgs))
entries = [self.url_result(track['permalink_url'], 'Soundcloud') for track in info['tracks']] entries = self._extract_track_entries(info['tracks'])
return { return {
'_type': 'playlist', '_type': 'playlist',
@ -309,7 +322,7 @@ class SoundcloudSetIE(SoundcloudIE):
} }
class SoundcloudUserIE(SoundcloudIE): class SoundcloudUserIE(SoundcloudBaseIE):
_VALID_URL = r'''(?x) _VALID_URL = r'''(?x)
https?:// https?://
(?:(?:www|m)\.)?soundcloud\.com/ (?:(?:www|m)\.)?soundcloud\.com/
@ -326,21 +339,21 @@ class SoundcloudUserIE(SoundcloudIE):
'id': '114582580', 'id': '114582580',
'title': 'The Akashic Chronicler (All)', 'title': 'The Akashic Chronicler (All)',
}, },
'playlist_mincount': 111, 'playlist_mincount': 74,
}, { }, {
'url': 'https://soundcloud.com/the-akashic-chronicler/tracks', 'url': 'https://soundcloud.com/the-akashic-chronicler/tracks',
'info_dict': { 'info_dict': {
'id': '114582580', 'id': '114582580',
'title': 'The Akashic Chronicler (Tracks)', 'title': 'The Akashic Chronicler (Tracks)',
}, },
'playlist_mincount': 50, 'playlist_mincount': 37,
}, { }, {
'url': 'https://soundcloud.com/the-akashic-chronicler/sets', 'url': 'https://soundcloud.com/the-akashic-chronicler/sets',
'info_dict': { 'info_dict': {
'id': '114582580', 'id': '114582580',
'title': 'The Akashic Chronicler (Playlists)', 'title': 'The Akashic Chronicler (Playlists)',
}, },
'playlist_mincount': 3, 'playlist_mincount': 2,
}, { }, {
'url': 'https://soundcloud.com/the-akashic-chronicler/reposts', 'url': 'https://soundcloud.com/the-akashic-chronicler/reposts',
'info_dict': { 'info_dict': {
@ -359,7 +372,7 @@ class SoundcloudUserIE(SoundcloudIE):
'url': 'https://soundcloud.com/grynpyret/spotlight', 'url': 'https://soundcloud.com/grynpyret/spotlight',
'info_dict': { 'info_dict': {
'id': '7098329', 'id': '7098329',
'title': 'Grynpyret (Spotlight)', 'title': 'GRYNPYRET (Spotlight)',
}, },
'playlist_mincount': 1, 'playlist_mincount': 1,
}] }]
@ -421,13 +434,14 @@ class SoundcloudUserIE(SoundcloudIE):
for cand in candidates: for cand in candidates:
if isinstance(cand, dict): if isinstance(cand, dict):
permalink_url = cand.get('permalink_url') permalink_url = cand.get('permalink_url')
entry_id = self._extract_id(cand)
if permalink_url and permalink_url.startswith('http'): if permalink_url and permalink_url.startswith('http'):
return permalink_url return permalink_url, entry_id
for e in collection: for e in collection:
permalink_url = resolve_permalink_url((e, e.get('track'), e.get('playlist'))) permalink_url, entry_id = resolve_permalink_url((e, e.get('track'), e.get('playlist')))
if permalink_url: if permalink_url:
entries.append(self.url_result(permalink_url)) entries.append(self.url_result(permalink_url, video_id=entry_id))
next_href = response.get('next_href') next_href = response.get('next_href')
if not next_href: if not next_href:
@ -447,7 +461,7 @@ class SoundcloudUserIE(SoundcloudIE):
} }
class SoundcloudPlaylistIE(SoundcloudIE): class SoundcloudPlaylistIE(SoundcloudBaseIE):
_VALID_URL = r'https?://api\.soundcloud\.com/playlists/(?P<id>[0-9]+)(?:/?\?secret_token=(?P<token>[^&]+?))?$' _VALID_URL = r'https?://api\.soundcloud\.com/playlists/(?P<id>[0-9]+)(?:/?\?secret_token=(?P<token>[^&]+?))?$'
IE_NAME = 'soundcloud:playlist' IE_NAME = 'soundcloud:playlist'
_TESTS = [{ _TESTS = [{
@ -477,11 +491,7 @@ class SoundcloudPlaylistIE(SoundcloudIE):
data = self._download_json( data = self._download_json(
base_url + data, playlist_id, 'Downloading playlist') base_url + data, playlist_id, 'Downloading playlist')
entries = [ entries = self._extract_track_entries(data['tracks'])
self.url_result(
track['permalink_url'], SoundcloudIE.ie_key(),
video_id=compat_str(track['id']) if track.get('id') else None)
for track in data['tracks'] if track.get('permalink_url')]
return { return {
'_type': 'playlist', '_type': 'playlist',