# encoding: utf-8 from __future__ import unicode_literals import re import json from .common import InfoExtractor from ..compat import ( compat_str, ) from ..utils import ExtractorError class MySpaceIE(InfoExtractor): _VALID_URL = r'https?://myspace\.com/([^/]+)/(?Pvideo/[^/]+/|music/song/.*?)(?P\d+)' _TESTS = [ { 'url': 'https://myspace.com/fiveminutestothestage/video/little-big-town/109594919', 'info_dict': { 'id': '109594919', 'ext': 'flv', 'title': 'Little Big Town', 'description': 'This country quartet was all smiles while playing a sold out show at the Pacific Amphitheatre in Orange County, California.', 'uploader': 'Five Minutes to the Stage', 'uploader_id': 'fiveminutestothestage', }, 'params': { # rtmp download 'skip_download': True, }, }, # songs { 'url': 'https://myspace.com/killsorrow/music/song/of-weakened-soul...-93388656-103880681', 'info_dict': { 'id': '93388656', 'ext': 'flv', 'playlist': 'The Demo', 'title': 'Of weakened soul...', 'uploader': 'Killsorrow', 'uploader_id': 'killsorrow', }, 'params': { # rtmp download 'skip_download': True, }, }, { 'add_ie': ['Vevo'], 'url': 'https://myspace.com/threedaysgrace/music/song/animal-i-have-become-28400208-28218041', 'info_dict': { 'id': 'USZM20600099', 'ext': 'mp4', 'title': 'Animal I Have Become', 'uploader': 'Three Days Grace', 'timestamp': int, 'upload_date': '20060502', }, 'skip': 'VEVO is only available in some countries', }, { 'add_ie': ['Youtube'], 'url': 'https://myspace.com/starset2/music/song/first-light-95799905-106964426', 'info_dict': { 'id': 'ypWvQgnJrSU', 'ext': 'mp4', 'title': 'Starset - First Light', 'description': 'md5:2d5db6c9d11d527683bcda818d332414', 'uploader': 'Jacob Soren', 'uploader_id': 'SorenPromotions', 'upload_date': '20140725', } }, ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) player_url = self._search_regex( r'playerSwf":"([^"?]*)', webpage, 'player URL') if mobj.group('mediatype').startswith('music/song'): # songs don't store any useful info in the 'context' variable song_data = self._search_regex( r'''.*-)(?P\d+)' _TESTS = [{ 'url': 'https://myspace.com/starset2/music/album/transmissions-19455773', 'info_dict': { 'title': 'Transmissions', 'id': '19455773', }, 'playlist_count': 14, 'skip': 'this album is only available in some countries', }, { 'url': 'https://myspace.com/killsorrow/music/album/the-demo-18596029', 'info_dict': { 'title': 'The Demo', 'id': '18596029', }, 'playlist_count': 5, }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) playlist_id = mobj.group('id') display_id = mobj.group('title') + playlist_id webpage = self._download_webpage(url, display_id) tracks_paths = re.findall(r'"music:song" content="(.*?)"', webpage) if not tracks_paths: self.to_screen('%s: No songs found, try using proxy' % display_id) return entries = [ self.url_result(t_path, ie=MySpaceIE.ie_key()) for t_path in tracks_paths] title = self._og_search_title(webpage) return { '_type': 'playlist', 'id': playlist_id, 'display_id': display_id, 'title': title, 'entries': entries, }