Merge remote-tracking branch 'Dineshs91/f4m-2.0'

[youtube-dl] / youtube_dl / extractor / myspace.py

diff --git a/youtube_dl/extractor/myspace.py b/youtube_dl/extractor/myspace.py
index b4b1fb51db4d2803bf3182aa519a683143162433..83414a2325586d7319c06247fa037c42bb2b199a 100644 (file)
--- a/youtube_dl/extractor/myspace.py
+++ b/youtube_dl/extractor/myspace.py
@@ -1,3 +1,4 @@
+# encoding: utf-8
 from __future__ import unicode_literals
 
 import re
@@ -15,14 +16,14 @@ class MySpaceIE(InfoExtractor):
 
     _TESTS = [
         {
-            'url': 'https://myspace.com/coldplay/video/viva-la-vida/100008689',
+            'url': 'https://myspace.com/fiveminutestothestage/video/little-big-town/109594919',
             'info_dict': {
-                'id': '100008689',
+                'id': '109594919',
                 'ext': 'flv',
-                'title': 'Viva La Vida',
-                'description': 'The official Viva La Vida video, directed by Hype Williams',
-                'uploader': 'Coldplay',
-                'uploader_id': 'coldplay',
+                '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
@@ -32,11 +33,9 @@ class MySpaceIE(InfoExtractor):
         # songs
         {
             'url': 'https://myspace.com/killsorrow/music/song/of-weakened-soul...-93388656-103880681',
-            'md5': 'f1d7323321f6b7775bf1e3754c1707dc',
             'info_dict': {
                 'id': '93388656',
                 'ext': 'flv',
-                'playlist': 'The Demo',
                 'title': 'Of weakened soul...',
                 'uploader': 'Killsorrow',
                 'uploader_id': 'killsorrow',
@@ -49,10 +48,12 @@ class MySpaceIE(InfoExtractor):
             'add_ie': ['Vevo'],
             'url': 'https://myspace.com/threedaysgrace/music/song/animal-i-have-become-28400208-28218041',
             'info_dict': {
-                'id': u'USZM20600099',
-                'title': u'Animal I Have Become',
-                'uploader': u'Three Days Grace',
+                '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',
         }, {
@@ -60,7 +61,9 @@ class MySpaceIE(InfoExtractor):
             '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',
@@ -81,13 +84,15 @@ class MySpaceIE(InfoExtractor):
                 r'''<button.*data-song-id=(["\'])%s\1.*''' % video_id,
                 webpage, 'song_data', default=None, group=0)
             if song_data is None:
-                self.to_screen(
+                # some songs in an album are not playable
+                self.report_warning(
                     '%s: No downloadable song on this page' % video_id)
                 return
+
             def search_data(name):
                 return self._search_regex(
-                    r'''data-%s=([\'"])(.*?)\1''' % name,
-                    song_data, name, default='', group=2)
+                    r'''data-%s=([\'"])(?P<data>.*?)\1''' % name,
+                    song_data, name, default='', group='data')
             streamUrl = search_data('stream-url')
             if not streamUrl:
                 vevo_id = search_data('vevo-id')
@@ -106,7 +111,6 @@ class MySpaceIE(InfoExtractor):
                 'title': self._og_search_title(webpage),
                 'uploader': search_data('artist-name'),
                 'uploader_id': search_data('artist-username'),
-                'playlist': search_data('album-title'),
                 'thumbnail': self._og_search_thumbnail(webpage),
             }
         else:
@@ -131,3 +135,46 @@ class MySpaceIE(InfoExtractor):
             'ext': 'flv',
         })
         return info
+
+
+class MySpaceAlbumIE(InfoExtractor):
+    IE_NAME = 'MySpace:album'
+    _VALID_URL = r'https?://myspace\.com/([^/]+)/music/album/(?P<title>.*-)(?P<id>\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:
+            raise ExtractorError(
+                '%s: No songs found, try using proxy' % display_id,
+                expected=True)
+        entries = [
+            self.url_result(t_path, ie=MySpaceIE.ie_key())
+            for t_path in tracks_paths]
+        return {
+            '_type': 'playlist',
+            'id': playlist_id,
+            'display_id': display_id,
+            'title': self._og_search_title(webpage),
+            'entries': entries,
+        }