paradizelost/youtube-dl
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[jamendo] fix track extraction(closes #28686)

Browse Source
This commit is contained in:
Remita Amine 2021-04-07 10:41:06 +01:00
parent c0c5134c57
commit 281b8e3443
1 changed files with 41 additions and 33 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

74
youtube_dl/extractor/jamendo.py
View File

@ -29,34 +29,51 @@ class JamendoIE(InfoExtractor):
'id': '196219', 'id': '196219',
'display_id': 'stories-from-emona-i', 'display_id': 'stories-from-emona-i',
'ext': 'flac', 'ext': 'flac',
'title': 'Maya Filipič - Stories from Emona I', # 'title': 'Maya Filipič - Stories from Emona I',
'artist': 'Maya Filipič', 'title': 'Stories from Emona I',
# 'artist': 'Maya Filipič',
'track': 'Stories from Emona I', 'track': 'Stories from Emona I',
'duration': 210, 'duration': 210,
'thumbnail': r're:^https?://.*\.jpg', 'thumbnail': r're:^https?://.*\.jpg',
'timestamp': 1217438117, 'timestamp': 1217438117,
'upload_date': '20080730', 'upload_date': '20080730',
'license': 'by-nc-nd',
'view_count': int,
'like_count': int,
'average_rating': int,
'tags': ['piano', 'peaceful', 'newage', 'strings', 'upbeat'],
} }
}, { }, {
'url': 'https://licensing.jamendo.com/en/track/1496667/energetic-rock', 'url': 'https://licensing.jamendo.com/en/track/1496667/energetic-rock',
'only_matching': True, 'only_matching': True,
}] }]
def _call_api(self, resource, resource_id):
path = '/api/%ss' % resource
rand = compat_str(random.random())
return self._download_json(
'https://www.jamendo.com' + path, resource_id, query={
'id[]': resource_id,
}, headers={
'X-Jam-Call': '$%s*%s~' % (hashlib.sha1((path + rand).encode()).hexdigest(), rand)
})[0]
def _real_extract(self, url): def _real_extract(self, url):
track_id, display_id = self._VALID_URL_RE.match(url).groups() track_id, display_id = self._VALID_URL_RE.match(url).groups()
webpage = self._download_webpage( # webpage = self._download_webpage(
'https://www.jamendo.com/track/' + track_id, track_id) # 'https://www.jamendo.com/track/' + track_id, track_id)
models = self._parse_json(self._html_search_regex( # models = self._parse_json(self._html_search_regex(
r"data-bundled-models='([^']+)", # r"data-bundled-models='([^']+)",
webpage, 'bundled models'), track_id) # webpage, 'bundled models'), track_id)
track = models['track']['models'][0] # track = models['track']['models'][0]
track = self._call_api('track', track_id)
title = track_name = track['name'] title = track_name = track['name']
get_model = lambda x: try_get(models, lambda y: y[x]['models'][0], dict) or {} # get_model = lambda x: try_get(models, lambda y: y[x]['models'][0], dict) or {}
artist = get_model('artist') # artist = get_model('artist')
artist_name = artist.get('name') # artist_name = artist.get('name')
if artist_name: # if artist_name:
title = '%s - %s' % (artist_name, title) # title = '%s - %s' % (artist_name, title)
album = get_model('album') # album = get_model('album')
formats = [{ formats = [{
'url': 'https://%s.jamendo.com/?trackid=%s&format=%s&from=app-97dab294' 'url': 'https://%s.jamendo.com/?trackid=%s&format=%s&from=app-97dab294'
@ -74,7 +91,7 @@ class JamendoIE(InfoExtractor):
urls = [] urls = []
thumbnails = [] thumbnails = []
for _, covers in track.get('cover', {}).items(): for covers in (track.get('cover') or {}).values():
for cover_id, cover_url in covers.items(): for cover_id, cover_url in covers.items():
if not cover_url or cover_url in urls: if not cover_url or cover_url in urls:
continue continue
@ -88,13 +105,14 @@ class JamendoIE(InfoExtractor):
}) })
tags = [] tags = []
for tag in track.get('tags', []): for tag in (track.get('tags') or []):
tag_name = tag.get('name') tag_name = tag.get('name')
if not tag_name: if not tag_name:
continue continue
tags.append(tag_name) tags.append(tag_name)
stats = track.get('stats') or {} stats = track.get('stats') or {}
license = track.get('licenseCC') or []
return { return {
'id': track_id, 'id': track_id,
@ -103,11 +121,11 @@ class JamendoIE(InfoExtractor):
'title': title, 'title': title,
'description': track.get('description'), 'description': track.get('description'),
'duration': int_or_none(track.get('duration')), 'duration': int_or_none(track.get('duration')),
'artist': artist_name, # 'artist': artist_name,
'track': track_name, 'track': track_name,
'album': album.get('name'), # 'album': album.get('name'),
'formats': formats, 'formats': formats,
'license': '-'.join(track.get('licenseCC', [])) or None, 'license': '-'.join(license) if license else None,
'timestamp': int_or_none(track.get('dateCreated')), 'timestamp': int_or_none(track.get('dateCreated')),
'view_count': int_or_none(stats.get('listenedAll')), 'view_count': int_or_none(stats.get('listenedAll')),
'like_count': int_or_none(stats.get('favorited')), 'like_count': int_or_none(stats.get('favorited')),
@ -116,9 +134,9 @@ class JamendoIE(InfoExtractor):
} }
class JamendoAlbumIE(InfoExtractor): class JamendoAlbumIE(JamendoIE):
_VALID_URL = r'https?://(?:www\.)?jamendo\.com/album/(?P<id>[0-9]+)' _VALID_URL = r'https?://(?:www\.)?jamendo\.com/album/(?P<id>[0-9]+)'
_TEST = { _TESTS = [{
'url': 'https://www.jamendo.com/album/121486/duck-on-cover', 'url': 'https://www.jamendo.com/album/121486/duck-on-cover',
'info_dict': { 'info_dict': {
'id': '121486', 'id': '121486',
@ -151,17 +169,7 @@ class JamendoAlbumIE(InfoExtractor):
'params': { 'params': {
'playlistend': 2 'playlistend': 2
} }
} }]
def _call_api(self, resource, resource_id):
path = '/api/%ss' % resource
rand = compat_str(random.random())
return self._download_json(
'https://www.jamendo.com' + path, resource_id, query={
'id[]': resource_id,
}, headers={
'X-Jam-Call': '$%s*%s~' % (hashlib.sha1((path + rand).encode()).hexdigest(), rand)
})[0]
def _real_extract(self, url): def _real_extract(self, url):
album_id = self._match_id(url) album_id = self._match_id(url)
@ -169,7 +177,7 @@ class JamendoAlbumIE(InfoExtractor):
album_name = album.get('name') album_name = album.get('name')
entries = [] entries = []
for track in album.get('tracks', []): for track in (album.get('tracks') or []):
track_id = track.get('id') track_id = track.get('id')
if not track_id: if not track_id:
continue continue