Prepare to upload.

[youtubedl] / youtube_dl / extractor / myspace.py

diff --git a/youtube_dl/extractor/myspace.py b/youtube_dl/extractor/myspace.py
index ab32e632e34375561980f168834443754f606383..e164d5940044fc57bd9d760927b8f83c638fa198 100644 (file)
--- a/youtube_dl/extractor/myspace.py
+++ b/youtube_dl/extractor/myspace.py
@@ -12,88 +12,102 @@ from ..utils import (
 
 
 class MySpaceIE(InfoExtractor):
 
 
 class MySpaceIE(InfoExtractor):

-    _VALID_URL = r'https?://myspace\.com/([^/]+)/(?P<mediatype>video/[^/]+/|music/song/.*?)(?P<id>\d+)'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        myspace\.com/[^/]+/
+                        (?P<mediatype>
+                            video/[^/]+/(?P<video_id>\d+)|
+                            music/song/[^/?#&]+-(?P<song_id>\d+)-\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',
-                'timestamp': 1414108751,
-                'upload_date': '20141023',
-            },
-            'params': {
-                # rtmp download
-                'skip_download': True,
-            },
+    _TESTS = [{
+        'url': 'https://myspace.com/fiveminutestothestage/video/little-big-town/109594919',
+        'md5': '9c1483c106f4a695c47d2911feed50a7',
+        'info_dict': {
+            'id': '109594919',
+            'ext': 'mp4',
+            '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',
+            'timestamp': 1414108751,
+            'upload_date': '20141023',

         },
         },

+    }, {

         # songs
         # songs

-        {
-            'url': 'https://myspace.com/killsorrow/music/song/of-weakened-soul...-93388656-103880681',
-            'info_dict': {
-                'id': '93388656',
-                'ext': 'flv',
-                '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': 'Yumi K',
-                'uploader_id': 'SorenPromotions',
-                'upload_date': '20140725',
-            }
+        'url': 'https://myspace.com/killsorrow/music/song/of-weakened-soul...-93388656-103880681',
+        'md5': '1d7ee4604a3da226dd69a123f748b262',
+        'info_dict': {
+            'id': '93388656',
+            'ext': 'm4a',
+            'title': 'Of weakened soul...',
+            'uploader': 'Killsorrow',
+            'uploader_id': 'killsorrow',

         },
         },

-    ]
+    }, {
+        'add_ie': ['Youtube'],
+        'url': 'https://myspace.com/threedaysgrace/music/song/animal-i-have-become-28400208-28218041',
+        'info_dict': {
+            'id': 'xqds0B_meys',
+            'ext': 'webm',
+            'title': 'Three Days Grace - Animal I Have Become',
+            'description': 'md5:8bd86b3693e72a077cf863a8530c54bb',
+            'uploader': 'ThreeDaysGraceVEVO',
+            'uploader_id': 'ThreeDaysGraceVEVO',
+            'upload_date': '20091002',
+        },
+    }, {
+        'url': 'https://myspace.com/starset2/music/song/first-light-95799905-106964426',
+        'only_matching': True,
+    }, {
+        'url': 'https://myspace.com/thelargemouthbassband/music/song/02-pure-eyes.mp3-94422330-105113388',
+        'only_matching': True,
+    }]

 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

-        video_id = mobj.group('id')
+        video_id = mobj.group('video_id') or mobj.group('song_id')
+        is_song = mobj.group('mediatype').startswith('music/song')

         webpage = self._download_webpage(url, video_id)
         player_url = self._search_regex(
         webpage = self._download_webpage(url, video_id)
         player_url = self._search_regex(

-            r'playerSwf":"([^"?]*)', webpage, 'player URL')
+            r'videoSwf":"([^"?]*)', webpage, 'player URL', fatal=False)

 
 

-        def rtmp_format_from_stream_url(stream_url, width=None, height=None):
-            rtmp_url, play_path = stream_url.split(';', 1)
-            return {
-                'format_id': 'rtmp',
-                'url': rtmp_url,
-                'play_path': play_path,
-                'player_url': player_url,
-                'protocol': 'rtmp',
-                'ext': 'flv',
-                'width': width,
-                'height': height,
-            }
+        def formats_from_stream_urls(stream_url, hls_stream_url, http_stream_url, width=None, height=None):
+            formats = []
+            vcodec = 'none' if is_song else None
+            if hls_stream_url:
+                formats.append({
+                    'format_id': 'hls',
+                    'url': hls_stream_url,
+                    'protocol': 'm3u8_native',
+                    'ext': 'm4a' if is_song else 'mp4',
+                    'vcodec': vcodec,
+                })
+            if stream_url and player_url:
+                rtmp_url, play_path = stream_url.split(';', 1)
+                formats.append({
+                    'format_id': 'rtmp',
+                    'url': rtmp_url,
+                    'play_path': play_path,
+                    'player_url': player_url,
+                    'protocol': 'rtmp',
+                    'ext': 'flv',
+                    'width': width,
+                    'height': height,
+                    'vcodec': vcodec,
+                })
+            if http_stream_url:
+                formats.append({
+                    'format_id': 'http',
+                    'url': http_stream_url,
+                    'width': width,
+                    'height': height,
+                    'vcodec': vcodec,
+                })
+            return formats

 
 

-        if mobj.group('mediatype').startswith('music/song'):
+        if is_song:

             # songs don't store any useful info in the 'context' variable
             song_data = self._search_regex(
                 r'''<button.*data-song-id=(["\'])%s\1.*''' % video_id,
             # songs don't store any useful info in the 'context' variable
             song_data = self._search_regex(
                 r'''<button.*data-song-id=(["\'])%s\1.*''' % video_id,


@@ -108,8 +122,10 @@ class MySpaceIE(InfoExtractor):
                 return self._search_regex(
                     r'''data-%s=([\'"])(?P<data>.*?)\1''' % name,
                     song_data, name, default='', group='data')
                 return self._search_regex(
                     r'''data-%s=([\'"])(?P<data>.*?)\1''' % name,
                     song_data, name, default='', group='data')

-            stream_url = search_data('stream-url')
-            if not stream_url:
+            formats = formats_from_stream_urls(
+                search_data('stream-url'), search_data('hls-stream-url'),
+                search_data('http-stream-url'))
+            if not formats:

                 vevo_id = search_data('vevo-id')
                 youtube_id = search_data('youtube-id')
                 if vevo_id:
                 vevo_id = search_data('vevo-id')
                 youtube_id = search_data('youtube-id')
                 if vevo_id:


@@ -121,6 +137,7 @@ class MySpaceIE(InfoExtractor):
                 else:
                     raise ExtractorError(
                         'Found song but don\'t know how to download it')
                 else:
                     raise ExtractorError(
                         'Found song but don\'t know how to download it')

+            self._sort_formats(formats)

             return {
                 'id': video_id,
                 'title': self._og_search_title(webpage),
             return {
                 'id': video_id,
                 'title': self._og_search_title(webpage),


@@ -128,27 +145,16 @@ class MySpaceIE(InfoExtractor):
                 'uploader_id': search_data('artist-username'),
                 'thumbnail': self._og_search_thumbnail(webpage),
                 'duration': int_or_none(search_data('duration')),
                 'uploader_id': search_data('artist-username'),
                 'thumbnail': self._og_search_thumbnail(webpage),
                 'duration': int_or_none(search_data('duration')),

-                'formats': [rtmp_format_from_stream_url(stream_url)]
+                'formats': formats,

             }
         else:
             video = self._parse_json(self._search_regex(
                 r'context = ({.*?});', webpage, 'context'),
                 video_id)['video']
             }
         else:
             video = self._parse_json(self._search_regex(
                 r'context = ({.*?});', webpage, 'context'),
                 video_id)['video']

-            formats = []
-            hls_stream_url = video.get('hlsStreamUrl')
-            if hls_stream_url:
-                formats.append({
-                    'format_id': 'hls',
-                    'url': hls_stream_url,
-                    'protocol': 'm3u8_native',
-                    'ext': 'mp4',
-                })
-            stream_url = video.get('streamUrl')
-            if stream_url:
-                formats.append(rtmp_format_from_stream_url(
-                    stream_url,
-                    int_or_none(video.get('width')),
-                    int_or_none(video.get('height'))))
+            formats = formats_from_stream_urls(
+                video.get('streamUrl'), video.get('hlsStreamUrl'),
+                video.get('mp4StreamUrl'), int_or_none(video.get('width')),
+                int_or_none(video.get('height')))

             self._sort_formats(formats)
             return {
                 'id': video_id,
             self._sort_formats(formats)
             return {
                 'id': video_id,