diff --git a/test/test_download.py b/test/test_download.py index d0be8d27ca..0d925ae69b 100644 --- a/test/test_download.py +++ b/test/test_download.py @@ -148,7 +148,7 @@ def generator(test_case): for key, value in info_dict.items() if value and key in ('title', 'description', 'uploader', 'upload_date', 'uploader_id', 'location')) if not all(key in tc.get('info_dict', {}).keys() for key in test_info_dict.keys()): - sys.stderr.write(u'\n"info_dict": ' + json.dumps(test_info_dict, ensure_ascii=False, indent=2) + u'\n') + sys.stderr.write(u'\n"info_dict": ' + json.dumps(test_info_dict, ensure_ascii=False, indent=4) + u'\n') # Check for the presence of mandatory fields for key in ('id', 'url', 'title', 'ext'): diff --git a/test/test_playlists.py b/test/test_playlists.py index b3bfbd9238..5eeba091ee 100644 --- a/test/test_playlists.py +++ b/test/test_playlists.py @@ -32,6 +32,7 @@ from youtube_dl.extractor import ( IviCompilationIE, ImdbListIE, KhanAcademyIE, + EveryonesMixtapeIE, ) @@ -210,6 +211,15 @@ class TestPlaylists(unittest.TestCase): self.assertEqual(result['description'], 'How have humans protected their secret messages through history? What has changed today?') self.assertTrue(len(result['entries']) >= 3) + def test_EveryonesMixtape(self): + dl = FakeYDL() + ie = EveryonesMixtapeIE(dl) + result = ie.extract('http://everyonesmixtape.com/#/mix/m7m0jJAbMQi') + self.assertIsPlaylist(result) + self.assertEqual(result['id'], 'm7m0jJAbMQi') + self.assertEqual(result['title'], 'Driving') + self.assertEqual(len(result['entries']), 24) + if __name__ == '__main__': unittest.main() diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index b887c7f101..01659e5753 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -52,6 +52,7 @@ from .ehow import EHowIE from .eighttracks import EightTracksIE from .eitb import EitbIE from .escapist import EscapistIE +from .everyonesmixtape import EveryonesMixtapeIE from .exfm import ExfmIE from .extremetube import ExtremeTubeIE from .facebook import FacebookIE diff --git a/youtube_dl/extractor/everyonesmixtape.py b/youtube_dl/extractor/everyonesmixtape.py new file mode 100644 index 0000000000..12829cbcc0 --- /dev/null +++ b/youtube_dl/extractor/everyonesmixtape.py @@ -0,0 +1,69 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_request, + ExtractorError, +) + + +class EveryonesMixtapeIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?everyonesmixtape\.com/#/mix/(?P[0-9a-zA-Z]+)(?:/(?P[0-9]))?$' + + _TEST = { + 'url': 'http://everyonesmixtape.com/#/mix/m7m0jJAbMQi/5', + 'file': '5bfseWNmlds.mp4', + "info_dict": { + "title": "Passion Pit - \"Sleepyhead\" (Official Music Video)", + "uploader": "FKR.TV", + "uploader_id": "frenchkissrecords", + "description": "Music video for \"Sleepyhead\" from Passion Pit's debut EP Chunk Of Change.\nBuy on iTunes: https://itunes.apple.com/us/album/chunk-of-change-ep/id300087641\n\nDirected by The Wilderness.\n\nhttp://www.passionpitmusic.com\nhttp://www.frenchkissrecords.com", + "upload_date": "20081015" + }, + 'params': { + 'skip_download': True, # This is simply YouTube + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + playlist_id = mobj.group('id') + + pllist_url = 'http://everyonesmixtape.com/mixtape.php?a=getMixes&u=-1&linked=%s&explore=' % playlist_id + pllist_req = compat_urllib_request.Request(pllist_url) + pllist_req.add_header('X-Requested-With', 'XMLHttpRequest') + + playlist_list = self._download_json( + pllist_req, playlist_id, note='Downloading playlist metadata') + try: + playlist_no = next(playlist['id'] + for playlist in playlist_list + if playlist['code'] == playlist_id) + except StopIteration: + raise ExtractorError('Playlist id not found') + + pl_url = 'http://everyonesmixtape.com/mixtape.php?a=getMix&id=%s&userId=null&code=' % playlist_no + pl_req = compat_urllib_request.Request(pl_url) + pl_req.add_header('X-Requested-With', 'XMLHttpRequest') + playlist = self._download_json( + pl_req, playlist_id, note='Downloading playlist info') + + entries = [{ + '_type': 'url', + 'url': t['url'], + 'title': t['title'], + } for t in playlist['tracks']] + + if mobj.group('songnr'): + songnr = int(mobj.group('songnr')) - 1 + return entries[songnr] + + playlist_title = playlist['mixData']['name'] + return { + '_type': 'playlist', + 'id': playlist_id, + 'title': playlist_title, + 'entries': entries, + } diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 28c88ffc7b..bf3fde6102 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -131,6 +131,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): ( (?:https?://|//)? # http(s):// or protocol-independent URL (optional) (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/| + (?:www\.)?deturl\.com/www\.youtube\.com/| + (?:www\.)?pwnyoutube\.com| tube\.majestyc\.net/| youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains (?:.*?\#/)? # handle anchor (#/) redirect urls