From ccf65f9deee0edb007222aa957f4da6516478ae3 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Sun, 27 Jan 2013 03:01:23 +0100 Subject: [PATCH] 8tracks IE (Closes #652) --- test/tests.json | 62 ++++++++++++++++++++++++++++++++++++ youtube_dl/InfoExtractors.py | 45 ++++++++++++++++++++++++-- 2 files changed, 105 insertions(+), 2 deletions(-) diff --git a/test/tests.json b/test/tests.json index ef12d3019..a46ff491b 100644 --- a/test/tests.json +++ b/test/tests.json @@ -235,5 +235,67 @@ "title": "PEOPLE ARE AWESOME 2013", "duration": 279 } + }, + { + "name": "EightTracks", + "url": "http://8tracks.com/ytdl/youtube-dl-test-tracks-a", + "playlist": [ + { + "file": "11885610.m4a", + "md5": "96ce57f24389fc8734ce47f4c1abcc55", + "info_dict": { + "title": "youtube-dl test track 1 \"'/\\\u00e4\u21ad" + } + }, + { + "file": "11885608.m4a", + "md5": "4ab26f05c1f7291ea460a3920be8021f", + "info_dict": { + "title": "youtube-dl test track 2 \"'/\\\u00e4\u21ad" + } + }, + { + "file": "11885679.m4a", + "md5": "d30b5b5f74217410f4689605c35d1fd7", + "info_dict": { + "title": "youtube-dl test track 3 \"'/\\\u00e4\u21ad" + } + }, + { + "file": "11885680.m4a", + "md5": "4eb0a669317cd725f6bbd336a29f923a", + "info_dict": { + "title": "youtube-dl test track 4 \"'/\\\u00e4\u21ad" + } + }, + { + "file": "11885682.m4a", + "md5": "1893e872e263a2705558d1d319ad19e8", + "info_dict": { + "title": "youtube-dl test track 5 \"'/\\\u00e4\u21ad" + } + }, + { + "file": "11885683.m4a", + "md5": "b673c46f47a216ab1741ae8836af5899", + "info_dict": { + "title": "youtube-dl test track 6 \"'/\\\u00e4\u21ad" + } + }, + { + "file": "11885684.m4a", + "md5": "1d74534e95df54986da7f5abf7d842b7", + "info_dict": { + "title": "youtube-dl test track 7 \"'/\\\u00e4\u21ad" + } + }, + { + "file": "11885685.m4a", + "md5": "f081f47af8f6ae782ed131d38b9cd1c0", + "info_dict": { + "title": "youtube-dl test track 8 \"'/\\\u00e4\u21ad" + } + } + ] } ] diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index a708cc750..50a5a5cfb 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -5,6 +5,7 @@ import base64 import datetime +import itertools import netrc import os import re @@ -3812,8 +3813,6 @@ def _real_extract(self, url): return [info] - - class YouJizzIE(InfoExtractor): """Information extractor for youjizz.com.""" _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P[^.]+).html$' @@ -3860,6 +3859,47 @@ def _real_extract(self, url): return [info] +class EightTracksIE(InfoExtractor): + IE_NAME = '8tracks' + _VALID_URL = r'https?://8tracks.com/(?P[^/]+)/(?P[^/]+)' + + 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) + + m = re.search(r"new TRAX.Mix\((.*?)\);\n*\s*TRAX.initSearchAutocomplete\('#search'\);", webpage, flags=re.DOTALL) + if not m: + raise ExtractorError(u'Cannot find trax information') + json_like = m.group(1) + 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['name'], + '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 def gen_extractors(): """ Return a list of an instance of every supported extractor. @@ -3906,6 +3946,7 @@ def gen_extractors(): SteamIE(), UstreamIE(), RBMARadioIE(), + EightTracksIE(), GenericIE() ]