[soundcloud/generic] Add support for playlists

This commit is contained in:
Philipp Hagemeister 2014-05-05 03:12:41 +02:00
parent b48f147d5a
commit 2099125333
5 changed files with 86 additions and 32 deletions

View File

@ -10,6 +10,7 @@ import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import ( from test.helper import (
assertRegexpMatches,
expect_info_dict, expect_info_dict,
FakeYDL, FakeYDL,
) )
@ -25,6 +26,7 @@ from youtube_dl.extractor import (
UstreamChannelIE, UstreamChannelIE,
SoundcloudSetIE, SoundcloudSetIE,
SoundcloudUserIE, SoundcloudUserIE,
SoundcloudPlaylistIE,
LivestreamIE, LivestreamIE,
NHLVideocenterIE, NHLVideocenterIE,
BambuserChannelIE, BambuserChannelIE,
@ -124,6 +126,17 @@ class TestPlaylists(unittest.TestCase):
self.assertEqual(result['id'], '9615865') self.assertEqual(result['id'], '9615865')
self.assertTrue(len(result['entries']) >= 12) self.assertTrue(len(result['entries']) >= 12)
def test_soundcloud_playlist(self):
dl = FakeYDL()
ie = SoundcloudPlaylistIE(dl)
result = ie.extract('http://api.soundcloud.com/playlists/4110309')
self.assertIsPlaylist(result)
self.assertEqual(result['id'], '4110309')
self.assertEqual(result['title'], 'TILT Brass - Bowery Poetry Club, August \'03 [Non-Site SCR 02]')
assertRegexpMatches(
self, result['description'], r'TILT Brass - Bowery Poetry Club')
self.assertEqual(len(result['entries']), 6)
def test_livestream_event(self): def test_livestream_event(self):
dl = FakeYDL() dl = FakeYDL()
ie = LivestreamIE(dl) ie = LivestreamIE(dl)

View File

@ -237,7 +237,12 @@ from .smotri import (
SmotriBroadcastIE, SmotriBroadcastIE,
) )
from .sohu import SohuIE from .sohu import SohuIE
from .soundcloud import SoundcloudIE, SoundcloudSetIE, SoundcloudUserIE from .soundcloud import (
SoundcloudIE,
SoundcloudSetIE,
SoundcloudUserIE,
SoundcloudPlaylistIE
)
from .southparkstudios import ( from .southparkstudios import (
SouthParkStudiosIE, SouthParkStudiosIE,
SouthparkDeIE, SouthparkDeIE,

View File

@ -548,6 +548,13 @@ class InfoExtractor(object):
) )
formats.sort(key=_formats_key) formats.sort(key=_formats_key)
def http_scheme(self):
""" Either "https:" or "https:", depending on the user's preferences """
return (
'http:'
if self._downloader.params.get('prefer_insecure', False)
else 'https:')
class SearchInfoExtractor(InfoExtractor): class SearchInfoExtractor(InfoExtractor):
""" """
@ -591,3 +598,4 @@ class SearchInfoExtractor(InfoExtractor):
@property @property
def SEARCH_KEY(self): def SEARCH_KEY(self):
return self._SEARCH_KEY return self._SEARCH_KEY

View File

@ -348,10 +348,7 @@ class GenericIE(InfoExtractor):
if url.startswith('//'): if url.startswith('//'):
return { return {
'_type': 'url', '_type': 'url',
'url': ( 'url': self.http_scheme() + url,
'http:'
if self._downloader.params.get('prefer_insecure', False)
else 'https:') + url,
} }
parsed_url = compat_urlparse.urlparse(url) parsed_url = compat_urlparse.urlparse(url)
@ -636,6 +633,14 @@ class GenericIE(InfoExtractor):
if smotri_url: if smotri_url:
return self.url_result(smotri_url, 'Smotri') return self.url_result(smotri_url, 'Smotri')
# Look for embeded soundcloud player
mobj = re.search(
r'<iframe src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
webpage)
if mobj is not None:
url = unescapeHTML(mobj.group('url'))
return self.url_result(url)
# Start with something easy: JW Player in SWFObject # Start with something easy: JW Player in SWFObject
found = re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage) found = re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
if not found: if not found:

View File

@ -25,7 +25,7 @@ class SoundcloudIE(InfoExtractor):
of the stream token and uid of the stream token and uid
""" """
_VALID_URL = r'''^(?:https?://)? _VALID_URL = r'''(?x)^(?:https?://)?
(?:(?:(?:www\.|m\.)?soundcloud\.com/ (?:(?:(?:www\.|m\.)?soundcloud\.com/
(?P<uploader>[\w\d-]+)/ (?P<uploader>[\w\d-]+)/
(?!sets/)(?P<title>[\w\d-]+)/? (?!sets/)(?P<title>[\w\d-]+)/?
@ -94,10 +94,6 @@ class SoundcloudIE(InfoExtractor):
_CLIENT_ID = 'b45b1aa10f1ac2941910a7f0d10f8e28' _CLIENT_ID = 'b45b1aa10f1ac2941910a7f0d10f8e28'
_IPHONE_CLIENT_ID = '376f225bf427445fc4bfb6b99b72e0bf' _IPHONE_CLIENT_ID = '376f225bf427445fc4bfb6b99b72e0bf'
@classmethod
def suitable(cls, url):
return re.match(cls._VALID_URL, url, flags=re.VERBOSE) is not None
def report_resolve(self, video_id): def report_resolve(self, video_id):
"""Report information extraction.""" """Report information extraction."""
self.to_screen('%s: Resolving id' % video_id) self.to_screen('%s: Resolving id' % video_id)
@ -141,11 +137,10 @@ class SoundcloudIE(InfoExtractor):
# We have to retrieve the url # We have to retrieve the url
streams_url = ('http://api.soundcloud.com/i1/tracks/{0}/streams?' streams_url = ('http://api.soundcloud.com/i1/tracks/{0}/streams?'
'client_id={1}&secret_token={2}'.format(track_id, self._IPHONE_CLIENT_ID, secret_token)) 'client_id={1}&secret_token={2}'.format(track_id, self._IPHONE_CLIENT_ID, secret_token))
stream_json = self._download_webpage( format_dict = self._download_json(
streams_url, streams_url,
track_id, 'Downloading track url') track_id, 'Downloading track url')
format_dict = json.loads(stream_json)
for key, stream_url in format_dict.items(): for key, stream_url in format_dict.items():
if key.startswith('http'): if key.startswith('http'):
formats.append({ formats.append({
@ -198,7 +193,7 @@ class SoundcloudIE(InfoExtractor):
full_title = track_id full_title = track_id
elif mobj.group('player'): elif mobj.group('player'):
query = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) query = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
return self.url_result(query['url'][0], ie='Soundcloud') return self.url_result(query['url'][0])
else: else:
# extract uploader (which is in the url) # extract uploader (which is in the url)
uploader = mobj.group('uploader') uploader = mobj.group('uploader')
@ -213,11 +208,11 @@ class SoundcloudIE(InfoExtractor):
url = 'http://soundcloud.com/%s' % resolve_title url = 'http://soundcloud.com/%s' % resolve_title
info_json_url = self._resolv_url(url) info_json_url = self._resolv_url(url)
info_json = self._download_webpage(info_json_url, full_title, 'Downloading info JSON') info = self._download_json(info_json_url, full_title, 'Downloading info JSON')
info = json.loads(info_json)
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 SoundcloudSetIE(SoundcloudIE):
_VALID_URL = r'https?://(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)' _VALID_URL = r'https?://(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)'
IE_NAME = 'soundcloud:set' IE_NAME = 'soundcloud:set'
@ -232,16 +227,15 @@ class SoundcloudSetIE(SoundcloudIE):
# extract uploader (which is in the url) # extract uploader (which is in the url)
uploader = mobj.group(1) uploader = mobj.group(1)
# extract simple title (uploader + slug of song title) # extract simple title (uploader + slug of song title)
slug_title = mobj.group(2) slug_title = mobj.group(2)
full_title = '%s/sets/%s' % (uploader, slug_title) full_title = '%s/sets/%s' % (uploader, slug_title)
self.report_resolve(full_title) self.report_resolve(full_title)
url = 'http://soundcloud.com/%s/sets/%s' % (uploader, slug_title) url = 'http://soundcloud.com/%s/sets/%s' % (uploader, slug_title)
resolv_url = self._resolv_url(url) resolv_url = self._resolv_url(url)
info_json = self._download_webpage(resolv_url, full_title) info = self._download_json(resolv_url, full_title)
info = json.loads(info_json)
if 'errors' in info: if 'errors' in info:
for err in info['errors']: for err in info['errors']:
self._downloader.report_error('unable to download video webpage: %s' % compat_str(err['error_message'])) self._downloader.report_error('unable to download video webpage: %s' % compat_str(err['error_message']))
@ -268,26 +262,55 @@ class SoundcloudUserIE(SoundcloudIE):
url = 'http://soundcloud.com/%s/' % uploader url = 'http://soundcloud.com/%s/' % uploader
resolv_url = self._resolv_url(url) resolv_url = self._resolv_url(url)
user_json = self._download_webpage(resolv_url, uploader, user = self._download_json(
'Downloading user info') resolv_url, uploader, 'Downloading user info')
user = json.loads(user_json) base_url = 'http://api.soundcloud.com/users/%s/tracks.json?' % uploader
tracks = [] entries = []
for i in itertools.count(): for i in itertools.count():
data = compat_urllib_parse.urlencode({'offset': i*50, data = compat_urllib_parse.urlencode({
'client_id': self._CLIENT_ID, 'offset': i * 50,
}) 'client_id': self._CLIENT_ID,
tracks_url = 'http://api.soundcloud.com/users/%s/tracks.json?' % user['id'] + data })
response = self._download_webpage(tracks_url, uploader, new_entries = self._download_json(
'Downloading tracks page %s' % (i+1)) base_url + data, uploader, 'Downloading track page %s' % (i + 1))
new_tracks = json.loads(response) entries.extend(self._extract_info_dict(e, quiet=True) for e in new_entries)
tracks.extend(self._extract_info_dict(track, quiet=True) for track in new_tracks) if len(new_entries) < 50:
if len(new_tracks) < 50:
break break
return { return {
'_type': 'playlist', '_type': 'playlist',
'id': compat_str(user['id']), 'id': compat_str(user['id']),
'title': user['username'], 'title': user['username'],
'entries': tracks, 'entries': entries,
}
class SoundcloudPlaylistIE(SoundcloudIE):
_VALID_URL = r'https?://api\.soundcloud\.com/playlists/(?P<id>[0-9]+)'
IE_NAME = 'soundcloud:playlist'
# it's in tests/test_playlists.py
_TESTS = []
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
playlist_id = mobj.group('id')
base_url = '%s//api.soundcloud.com/playlists/%s.json?' % (self.http_scheme(), playlist_id)
data = compat_urllib_parse.urlencode({
'client_id': self._CLIENT_ID,
})
data = self._download_json(
base_url + data, playlist_id, 'Downloading playlist')
entries = [
self._extract_info_dict(t, quiet=True) for t in data['tracks']]
return {
'_type': 'playlist',
'id': playlist_id,
'title': data.get('title'),
'description': data.get('description'),
'entries': entries,
} }