diff options
| -rwxr-xr-x | youtube_dl/InfoExtractors.py | 41 | ||||
| -rw-r--r-- | youtube_dl/extractor/eighttracks.py | 51 |
2 files changed, 52 insertions, 40 deletions
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 080563def..4002c9485 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -25,6 +25,7 @@ from .extractor.comedycentral import ComedyCentralIE from .extractor.collegehumor import CollegeHumorIE from .extractor.dailymotion import DailymotionIE from .extractor.depositfiles import DepositFilesIE +from .extractor.eighttracks import EightTracksIE from .extractor.escapist import EscapistIE from .extractor.facebook import FacebookIE from .extractor.funnyordie import FunnyOrDieIE @@ -83,46 +84,6 @@ from .extractor.zdf import ZDFIE -class EightTracksIE(InfoExtractor): - IE_NAME = '8tracks' - _VALID_URL = r'https?://8tracks.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$' - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) - playlist_id = mobj.group('id') - - webpage = self._download_webpage(url, playlist_id) - - json_like = self._search_regex(r"PAGE.mix = (.*?);\n", webpage, u'trax information', flags=re.DOTALL) - data = json.loads(json_like) - - session = str(random.randint(0, 1000000000)) - mix_id = data['id'] - track_count = data['tracks_count'] - first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id) - next_url = first_url - res = [] - for i in itertools.count(): - api_json = self._download_webpage(next_url, playlist_id, - note=u'Downloading song information %s/%s' % (str(i+1), track_count), - errnote=u'Failed to download song information') - api_data = json.loads(api_json) - track_data = api_data[u'set']['track'] - info = { - 'id': track_data['id'], - 'url': track_data['track_file_stream_url'], - 'title': track_data['performer'] + u' - ' + track_data['name'], - 'raw_title': track_data['name'], - 'uploader_id': data['user']['login'], - 'ext': 'm4a', - } - res.append(info) - if api_data['set']['at_last_track']: - break - next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % (session, mix_id, track_data['id']) - return res class KeekIE(InfoExtractor): _VALID_URL = r'http://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<videoID>\w+)' diff --git a/youtube_dl/extractor/eighttracks.py b/youtube_dl/extractor/eighttracks.py new file mode 100644 index 000000000..c3d4343f4 --- /dev/null +++ b/youtube_dl/extractor/eighttracks.py @@ -0,0 +1,51 @@ +import itertools +import json +import random +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, +) + + +class EightTracksIE(InfoExtractor): + IE_NAME = '8tracks' + _VALID_URL = r'https?://8tracks.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + raise ExtractorError(u'Invalid URL: %s' % url) + playlist_id = mobj.group('id') + + webpage = self._download_webpage(url, playlist_id) + + json_like = self._search_regex(r"PAGE.mix = (.*?);\n", webpage, u'trax information', flags=re.DOTALL) + data = json.loads(json_like) + + session = str(random.randint(0, 1000000000)) + mix_id = data['id'] + track_count = data['tracks_count'] + first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id) + next_url = first_url + res = [] + for i in itertools.count(): + api_json = self._download_webpage(next_url, playlist_id, + note=u'Downloading song information %s/%s' % (str(i+1), track_count), + errnote=u'Failed to download song information') + api_data = json.loads(api_json) + track_data = api_data[u'set']['track'] + info = { + 'id': track_data['id'], + 'url': track_data['track_file_stream_url'], + 'title': track_data['performer'] + u' - ' + track_data['name'], + 'raw_title': track_data['name'], + 'uploader_id': data['user']['login'], + 'ext': 'm4a', + } + res.append(info) + if api_data['set']['at_last_track']: + break + next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % (session, mix_id, track_data['id']) + return res |