Merge remote-tracking branch 'anovicecodemonkey/generic-data-video-url'

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

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index f97b59845706b8e33d4438b5cab968a2251b1ad9..7246ea7fc288754a529b4536e9bc8c2c055ff940 100644 (file)
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -289,6 +289,20 @@ class GenericIE(InfoExtractor):
                 'description': 'Mario\'s life in the fast lane has never looked so good.',
             },
         },
+        # YouTube embed via <data-embed-url="">
+        {
+            'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
+            'md5': 'c267b1ab6d736057d64babaa37e07a66',
+            'info_dict': {
+                'id': 'Ybd-qmqYYpA',
+                'ext': 'mp4',
+                'title': 'Asphalt 8: Airborne -  Chinese Great Wall - Android Game Trailer',
+                'uploader': 'gameloftandroid',
+                'uploader_id': 'gameloftandroid',
+                'upload_date': '20140321',
+                'description': 'md5:9c6dca5dd75b7131ce482ccf080749d6'
+            }
+        }
     ]
 
     def report_download_webpage(self, video_id):
@@ -383,13 +397,13 @@ class GenericIE(InfoExtractor):
         if not parsed_url.scheme:
             default_search = self._downloader.params.get('default_search')
             if default_search is None:
-                default_search = 'error'
+                default_search = 'fixup_error'
 
-            if default_search in ('auto', 'auto_warning'):
+            if default_search in ('auto', 'auto_warning', 'fixup_error'):
                 if '/' in url:
                     self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
                     return self.url_result('http://' + url)
-                else:
+                elif default_search != 'fixup_error':
                     if default_search == 'auto_warning':
                         if re.match(r'^(?:url|URL)$', url):
                             raise ExtractorError(
@@ -399,10 +413,11 @@ class GenericIE(InfoExtractor):
                             self._downloader.report_warning(
                                 'Falling back to youtube search for  %s . Set --default-search "auto" to suppress this warning.' % url)
                     return self.url_result('ytsearch:' + url)
-            elif default_search == 'error':
+
+            if default_search in ('error', 'fixup_error'):
                 raise ExtractorError(
                     ('%r is not a valid URL. '
-                     'Set --default-search "ytseach" (or run  youtube-dl "ytsearch:%s" ) to search YouTube'
+                     'Set --default-search "ytsearch" (or run  youtube-dl "ytsearch:%s" ) to search YouTube'
                     ) % (url, url), expected=True)
             else:
                 assert ':' in default_search
@@ -513,6 +528,7 @@ class GenericIE(InfoExtractor):
         matches = re.findall(r'''(?x)
             (?:
                 <iframe[^>]+?src=|
+                data-video-url=|
                 <embed[^>]+?src=|
                 embedSWF\(?:\s*
             )
@@ -523,6 +539,14 @@ class GenericIE(InfoExtractor):
         if matches:
             urlrs = [self.url_result(unescapeHTML(tuppl[1]), 'Youtube')
                      for tuppl in matches]
+            # First, ensure we have a duplicate free list of entries
+            seen = set()
+            new_list = []
+            theurl = tuple(url.items())
+            if theurl not in seen:
+                seen.add(theurl)
+                new_list.append(url)
+                urlrs = new_list
             return self.playlist_result(
                 urlrs, playlist_id=video_id, playlist_title=video_title)
 
@@ -532,6 +556,14 @@ class GenericIE(InfoExtractor):
         if matches:
             urlrs = [self.url_result(unescapeHTML(tuppl[1]))
                      for tuppl in matches]
+            # First, ensure we have a duplicate free list of entries
+            seen = set()
+            new_list = []
+            theurl = tuple(url.items())
+            if theurl not in seen:
+                seen.add(theurl)
+                new_list.append(url)
+                urlrs = new_list
             return self.playlist_result(
                 urlrs, playlist_id=video_id, playlist_title=video_title)
 
@@ -649,6 +681,14 @@ class GenericIE(InfoExtractor):
         if matches:
             urlrs = [self.url_result(unescapeHTML(eurl), 'FunnyOrDie')
                      for eurl in matches]
+            # First, ensure we have a duplicate free list of entries
+            seen = set()
+            new_list = []
+            theurl = tuple(url.items())
+            if theurl not in seen:
+                seen.add(theurl)
+                new_list.append(url)
+                urlrs = new_list
             return self.playlist_result(
                 urlrs, playlist_id=video_id, playlist_title=video_title)
 
@@ -705,6 +745,13 @@ class GenericIE(InfoExtractor):
             url = unescapeHTML(mobj.group('url'))
             return self.url_result(url, ie='MTVServicesEmbedded')
 
+        # Look for embedded yahoo player
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
+            webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'Yahoo')
+
         # Start with something easy: JW Player in SWFObject
         found = re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
         if not found: