[extractor/generic] Simplify upload_date extraction

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

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index ca745ae41ecf46dd4b0a6b5dbd80a3e836c5f794..a2e7ba5ad8418bd3f6827cac53966a85f837c16d 100644 (file)
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -239,6 +239,20 @@ 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,
+            }
+        },
         # 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',
@@ -1242,28 +1256,32 @@ class GenericIE(InfoExtractor):
             full_response = self._request_webpage(request, video_id)
             head_response = full_response
 
+        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', '')
-        m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>.+)$', content_type)
+        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'))
-            formats = []
-            if m.group('format_id').endswith('mpegurl'):
+            format_id = m.group('format_id')
+            if format_id.endswith('mpegurl'):
                 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
+            elif format_id == 'f4m':
+                formats = self._extract_f4m_formats(url, video_id)
             else:
                 formats = [{
                     'format_id': m.group('format_id'),
                     'url': url,
                     'vcodec': 'none' if m.group('type') == 'audio' else None
                 }]
-            return {
-                'id': video_id,
-                'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
+            info_dict.update({
                 'direct': True,
                 'formats': formats,
-                'upload_date': upload_date,
-            }
+            })
+            return info_dict
 
         if not self._downloader.params.get('test', False) and not is_intentional:
             force = self._downloader.params.get('force_generic_extractor', False)
@@ -1289,15 +1307,11 @@ class GenericIE(InfoExtractor):
         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'))
-            return {
-                'id': video_id,
-                'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
+            info_dict.update({
                 'direct': True,
                 'url': url,
-                'upload_date': upload_date,
-            }
+            })
+            return info_dict
 
         webpage = self._webpage_read_content(
             full_response, url, video_id, prefix=first_bytes)
@@ -1314,12 +1328,12 @@ class GenericIE(InfoExtractor):
             elif doc.tag == '{http://xspf.org/ns/0/}playlist':
                 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
             elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
-                return {
-                    'id': video_id,
-                    'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
-                    'formats': self._parse_mpd_formats(
-                        doc, video_id, mpd_base_url=url.rpartition('/')[0]),
-                }
+                info_dict['formats'] = self._parse_mpd_formats(
+                    doc, video_id, mpd_base_url=url.rpartition('/')[0])
+                return info_dict
+            elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
+                info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
+                return info_dict
         except compat_xml_parse_error:
             pass
 
@@ -1985,6 +1999,8 @@ class GenericIE(InfoExtractor):
                 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
             elif ext == 'mpd':
                 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
+            elif ext == 'f4m':
+                entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
             else:
                 entry_info_dict['url'] = video_url