[generic] Add a test case for brightcove embed

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

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index cce7799e2078e0c8ddb80cbd282a39f7a1bf45e8..ea4009b415301502dd50393901075f0a7cc2b5c1 100644 (file)
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -59,6 +59,7 @@ from .videomore import VideomoreIE
 from .googledrive import GoogleDriveIE
 from .jwplatform import JWPlatformIE
 from .digiteka import DigitekaIE
+from .instagram import InstagramIE
 
 
 class GenericIE(InfoExtractor):
@@ -239,6 +240,35 @@ class GenericIE(InfoExtractor):
                 'format': 'bestvideo',
             },
         },
+        # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
+        {
+            'url': 'http://once.unicornmedia.com/now/master/playlist/bb0b18ba-64f5-4b1b-a29f-0ac252f06b68/77a785f3-5188-4806-b788-0893a61634ed/93677179-2d99-4ef4-9e17-fe70d49abfbf/content.m3u8',
+            'info_dict': {
+                'id': 'content',
+                'ext': 'mp4',
+                'title': 'content',
+                'formats': 'mincount:8',
+            },
+            'params': {
+                # m3u8 downloads
+                'skip_download': True,
+            }
+        },
+        # m3u8 served with Content-Type: text/plain
+        {
+            'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
+            'info_dict': {
+                'id': 'index',
+                'ext': 'mp4',
+                'title': 'index',
+                'upload_date': '20140720',
+                'formats': 'mincount:11',
+            },
+            'params': {
+                # m3u8 downloads
+                'skip_download': True,
+            }
+        },
         # google redirect
         {
             'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
@@ -1094,7 +1124,23 @@ class GenericIE(InfoExtractor):
                 # m3u8 downloads
                 'skip_download': True,
             }
-        }
+        },
+        # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
+        # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
+        {
+            'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
+            'info_dict': {
+                'id': '4785848093001',
+                'ext': 'mp4',
+                'title': 'The Cardinal Pell Interview',
+                'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
+                'uploader': 'GlobeCast Australia - GlobeStream',
+            },
+            'params': {
+                # m3u8 downloads
+                'skip_download': True,
+            },
+        },
     ]
 
     def report_following_redirect(self, new_url):
@@ -1245,14 +1291,13 @@ class GenericIE(InfoExtractor):
         info_dict = {
             'id': video_id,
             'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
+            'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
         }
 
         # Check for direct link to a video
         content_type = head_response.headers.get('Content-Type', '').lower()
         m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
         if m:
-            upload_date = unified_strdate(
-                head_response.headers.get('Last-Modified'))
             format_id = m.group('format_id')
             if format_id.endswith('mpegurl'):
                 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
@@ -1264,11 +1309,8 @@ class GenericIE(InfoExtractor):
                     'url': url,
                     'vcodec': 'none' if m.group('type') == 'audio' else None
                 }]
-            info_dict.update({
-                'direct': True,
-                'formats': formats,
-                'upload_date': upload_date,
-            })
+                info_dict['direct'] = True
+            info_dict['formats'] = formats
             return info_dict
 
         if not self._downloader.params.get('test', False) and not is_intentional:
@@ -1289,18 +1331,21 @@ class GenericIE(InfoExtractor):
             request.add_header('Accept-Encoding', '*')
             full_response = self._request_webpage(request, video_id)
 
+        first_bytes = full_response.read(512)
+
+        # Is it an M3U playlist?
+        if first_bytes.startswith(b'#EXTM3U'):
+            info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
+            return info_dict
+
         # Maybe it's a direct link to a video?
         # Be careful not to download the whole thing!
-        first_bytes = full_response.read(512)
         if not is_html(first_bytes):
             self._downloader.report_warning(
                 'URL could be a direct video link, returning it as such.')
-            upload_date = unified_strdate(
-                head_response.headers.get('Last-Modified'))
             info_dict.update({
                 'direct': True,
                 'url': url,
-                'upload_date': upload_date,
             })
             return info_dict
 
@@ -1881,6 +1926,19 @@ class GenericIE(InfoExtractor):
                 self._proto_relative_url(unescapeHTML(mobj.group(1))),
                 'AdobeTVVideo')
 
+        # Look for Vine embeds
+        mobj = re.search(
+            r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
+            webpage)
+        if mobj is not None:
+            return self.url_result(
+                self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
+
+        # Look for Instagram embeds
+        instagram_embed_url = InstagramIE._extract_embed_url(webpage)
+        if instagram_embed_url is not None:
+            return self.url_result(instagram_embed_url, InstagramIE.ie_key())
+
         def check_video(vurl):
             if YoutubeIE.suitable(vurl):
                 return True