Merge pull request #538 from zejn/patch-1

[youtube-dl] / youtube_dl / InfoExtractors.py

diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index 88973cce8982b70a57039a26208a9c647474160f..d2d8d7b778107e0321bd7b684bc89ec19a88de0b 100644 (file)
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -102,6 +102,7 @@ class YoutubeIE(InfoExtractor):
                             (?:https?://)?                                       # http(s):// (optional)
                             (?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|
                                tube\.majestyc\.net/)                             # the various hostnames, with wildcard subdomains
+                            (?:.*?\#/)?                                          # handle anchor (#/) redirect urls
                             (?!view_play_list|my_playlists|artist|playlist)      # ignore playlist URLs
                             (?:                                                  # the various things that can precede the ID:
                                 (?:(?:v|embed|e)/)                               # v/ or embed/ or e/
@@ -413,6 +414,12 @@ class YoutubeIE(InfoExtractor):
                        except Trouble as trouble:
                                self._downloader.trouble(trouble[0])
 
+               if 'length_seconds' not in video_info:
+                       self._downloader.trouble(u'WARNING: unable to extract video duration')
+                       video_duration = ''
+               else:
+                       video_duration = urllib.unquote_plus(video_info['length_seconds'][0])
+
                # token
                video_token = urllib.unquote_plus(video_info['token'][0])
 
@@ -479,7 +486,8 @@ class YoutubeIE(InfoExtractor):
                                'thumbnail':    video_thumbnail.decode('utf-8'),
                                'description':  video_description,
                                'player_url':   player_url,
-                               'subtitles':    video_subtitles
+                               'subtitles':    video_subtitles,
+                               'duration':             video_duration
                        })
                return results
 
@@ -595,7 +603,7 @@ class MetacafeIE(InfoExtractor):
                        return
                video_title = mobj.group(1).decode('utf-8')
 
-               mobj = re.search(r'(?ms)By:\s*<a .*?>(.+?)<', webpage)
+               mobj = re.search(r'submitter=(.*?);', webpage)
                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
                        return
@@ -684,9 +692,14 @@ class DailymotionIE(InfoExtractor):
                video_title = unescapeHTML(mobj.group('title').decode('utf-8'))
 
                video_uploader = u'NA'
-               mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a></span>', webpage)
+               mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>', webpage)
                if mobj is None:
-                       self._downloader.trouble(u'WARNING: unable to extract uploader nickname')
+                       # lookin for official user
+                       mobj_official = re.search(r'<span rel="author"[^>]+?>([^<]+?)</span>', webpage)
+                       if mobj_official is None:
+                               self._downloader.trouble(u'WARNING: unable to extract uploader nickname')
+                       else:
+                               video_uploader = mobj_official.group(1)
                else:
                        video_uploader = mobj.group(1)
 
@@ -1017,7 +1030,7 @@ class VimeoIE(InfoExtractor):
        """Information extractor for vimeo.com."""
 
        # _VALID_URL matches Vimeo URLs
-       _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:groups/[^/]+/)?(?:videos?/)?([0-9]+)'
+       _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:(?:groups|album)/[^/]+/)?(?:videos?/)?([0-9]+)'
        IE_NAME = u'vimeo'
 
        def __init__(self, downloader=None):
@@ -1087,21 +1100,32 @@ class VimeoIE(InfoExtractor):
                timestamp = config['request']['timestamp']
 
                # Vimeo specific: extract video codec and quality information
+               # First consider quality, then codecs, then take everything
                # TODO bind to format param
                codecs = [('h264', 'mp4'), ('vp8', 'flv'), ('vp6', 'flv')]
-               for codec in codecs:
-                       if codec[0] in config["video"]["files"]:
-                               video_codec = codec[0]
-                               video_extension = codec[1]
-                               if 'hd' in config["video"]["files"][codec[0]]: quality = 'hd'
-                               else: quality = 'sd'
+               files = { 'hd': [], 'sd': [], 'other': []}
+               for codec_name, codec_extension in codecs:
+                       if codec_name in config["video"]["files"]:
+                               if 'hd' in config["video"]["files"][codec_name]:
+                                       files['hd'].append((codec_name, codec_extension, 'hd'))
+                               elif 'sd' in config["video"]["files"][codec_name]:
+                                       files['sd'].append((codec_name, codec_extension, 'sd'))
+                               else:
+                                       files['other'].append((codec_name, codec_extension, config["video"]["files"][codec_name][0]))
+
+               for quality in ('hd', 'sd', 'other'):
+                       if len(files[quality]) > 0:
+                               video_quality = files[quality][0][2]
+                               video_codec = files[quality][0][0]
+                               video_extension = files[quality][0][1]
+                               self._downloader.to_screen(u'[vimeo] %s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality))
                                break
                else:
                        self._downloader.trouble(u'ERROR: no known codec found')
                        return
 
                video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \
-                                       %(video_id, sig, timestamp, quality, video_codec.upper())
+                                       %(video_id, sig, timestamp, video_quality, video_codec.upper())
 
                return [{
                        'id':           video_id,
@@ -1508,7 +1532,7 @@ class YahooSearchIE(InfoExtractor):
 class YoutubePlaylistIE(InfoExtractor):
        """Information Extractor for YouTube playlists."""
 
-       _VALID_URL = r'(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL|EC)?([0-9A-Za-z-_]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
+       _VALID_URL = r'(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL|EC)?|PL|EC)([0-9A-Za-z-_]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
        _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
        _VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&amp;([^&"]+&amp;)*list=.*?%s'
        _MORE_PAGES_INDICATOR = r'yt-uix-pager-next'