[youtube] Urls like youtube.com/NASA are now interpreted as users (fixes #1069)

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

diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index d331aa01b09e9a08cb01126b0fceda59d35a02a3..1facf1cc516ac0ea32f82fae3ffa8506f8764d8e 100644 (file)
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -135,7 +135,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
     _VALID_URL = r"""^
                      (
                          (?:https?://)?                                       # http(s):// (optional)
-                         (?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|
+                         (?:(?:(?:(?:\w+\.)?youtube(?:-nocookie)?\.com/|
                             tube\.majestyc\.net/)                             # the various hostnames, with wildcard subdomains
                          (?:.*?\#/)?                                          # handle anchor (#/) redirect urls
                          (?:                                                  # the various things that can precede the ID:
@@ -146,7 +146,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                                  (?:.*?&)?                                    # any other preceding param (like /?s=tuff&v=xxxx)
                                  v=
                              )
-                         )?                                                   # optional -> youtube.com/xxxx is OK
+                         ))
+                         |youtu\.be/                                          # just youtu.be/xxxx
+                         )
                      )?                                                       # all until now is optional -> you can pass the naked ID
                      ([0-9A-Za-z_-]+)                                         # here is it! the YouTube video ID
                      (?(1).+)?                                                # if we found the ID, everything can follow
@@ -154,7 +156,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
     _NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
     # Listed in order of quality
     _available_formats = ['38', '37', '46', '22', '45', '35', '44', '34', '18', '43', '6', '5', '36', '17', '13',
-                          # AHLS
+                          # Apple HTTP Live Streaming
                           '96', '95', '94', '93', '92', '132', '151',
                           # 3D
                           '85', '84', '102', '83', '101', '82', '100',
@@ -165,7 +167,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                           '141', '172', '140', '171', '139',
                           ]
     _available_formats_prefer_free = ['38', '46', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '36', '17', '13',
-                                      # AHLS
+                                      # Apple HTTP Live Streaming
                                       '96', '95', '94', '93', '92', '132', '151',
                                       # 3D
                                       '85', '102', '84', '101', '83', '100', '82',
@@ -203,7 +205,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         '101': 'webm',
         '102': 'webm',
 
-        # AHLS
+        # Apple HTTP Live Streaming
         '92': 'mp4',
         '93': 'mp4',
         '94': 'mp4',
@@ -943,8 +945,11 @@ class YoutubePlaylistIE(InfoExtractor):
 
             for entry in response['feed']['entry']:
                 index = entry['yt$position']['$t']
-                if 'media$group' in entry and 'media$player' in entry['media$group']:
-                    videos.append((index, entry['media$group']['media$player']['url']))
+                if 'media$group' in entry and 'yt$videoid' in entry['media$group']:
+                    videos.append((
+                        index,
+                        'https://www.youtube.com/watch?v=' + entry['media$group']['yt$videoid']['$t']
+                    ))
 
         videos = [v[1] for v in sorted(videos)]
 
@@ -1010,13 +1015,17 @@ class YoutubeChannelIE(InfoExtractor):
 
 class YoutubeUserIE(InfoExtractor):
     IE_DESC = u'YouTube.com user videos (URL or "ytuser" keyword)'
-    _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
+    _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:user/)?)|ytuser:)([A-Za-z0-9_-]+)'
     _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
     _GDATA_PAGE_SIZE = 50
     _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d'
     _VIDEO_INDICATOR = r'/watch\?v=(.+?)[\<&]'
     IE_NAME = u'youtube:user'
 
+    def suitable(cls, url):
+        if YoutubeIE.suitable(url): return False
+        else: return super(YoutubeUserIE, cls).suitable(url)
+
     def _real_extract(self, url):
         # Extract username
         mobj = re.match(self._VALID_URL, url)