InfoQ IE

[youtube-dl.git] / youtube-dl

diff --git a/youtube-dl b/youtube-dl
index 30a02e5..884e6f9 100755 (executable)
--- a/youtube-dl
+++ b/youtube-dl
@@ -2470,7 +2470,7 @@ 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)?([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)?([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 = r'/watch\?v=(.+?)&'
        _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
@@ -2514,7 +2514,8 @@ class YoutubePlaylistIE(InfoExtractor):
 
                while True:
                        self.report_download_page(playlist_id, pagenum)
-                       request = urllib2.Request(self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum))
+                       url = self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum)
+                       request = urllib2.Request(url)
                        try:
                                page = urllib2.urlopen(request).read()
                        except (urllib2.URLError, httplib.HTTPException, socket.error), err:
@@ -2548,7 +2549,7 @@ class YoutubeUserIE(InfoExtractor):
        _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=(.+?)&'
+       _VIDEO_INDICATOR = r'/watch\?v=(.+?)[\<&]'
        _youtube_ie = None
        IE_NAME = u'youtube:user'
 
@@ -3481,6 +3482,91 @@ class XVideosIE(InfoExtractor):
                        self._downloader.trouble(u'\nERROR: unable to download ' + video_id)
 
 
+class InfoQIE(InfoExtractor):
+       """Information extractor for infoq.com"""
+
+       _VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$'
+       IE_NAME = u'infoq'
+
+       def report_webpage(self, video_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
+
+       def report_extraction(self, video_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+
+       def _simplify_title(self, title):
+               res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
+               res = res.strip(ur'_')
+               return res
+
+       def _real_extract(self, url):
+               htmlParser = HTMLParser.HTMLParser()
+
+               mobj = re.match(self._VALID_URL, url)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+                       return
+
+               self.report_webpage(url)
+
+               request = urllib2.Request(url)
+               try:
+                       webpage = urllib2.urlopen(request).read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+                       return
+
+               self.report_extraction(url)
+
+
+               # Extract video URL
+               mobj = re.search(r"jsclassref='([^']*)'", webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract video url')
+                       return
+               video_url = 'rtmpe://video.infoq.com/cfx/st/' + urllib2.unquote(mobj.group(1).decode('base64'))
+
+
+               # Extract title
+               mobj = re.search(r'contentTitle = "(.*?)";', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract video title')
+                       return
+               video_title = mobj.group(1).decode('utf-8')
+
+
+               # Extract description
+               video_description = u'No description available.'
+               mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', webpage)
+               if mobj is not None:
+                       video_description = mobj.group(1).decode('utf-8')
+
+               video_filename = video_url.split('/')[-1]
+               video_id, extension = video_filename.split('.')
+
+               self._downloader.increment_downloads()
+               info = {
+                       'id': video_id,
+                       'url': video_url,
+                       'uploader': None,
+                       'upload_date': None,
+                       'title': video_title,
+                       'stitle': self._simplify_title(video_title),
+                       'ext': extension,
+                       'format': extension, # Extension is always(?) mp4, but seems to be flv
+                       'thumbnail': None,
+                       'description': video_description,
+                       'player_url': None,
+               }
+
+               try:
+                       self._downloader.process_info(info)
+               except UnavailableVideoError, err:
+                       self._downloader.trouble(u'\nERROR: unable to download ' + video_url)
+
+
 class PostProcessor(object):
        """Post Processor class.
 
@@ -3877,6 +3963,7 @@ def gen_extractors():
                EscapistIE(),
                CollegeHumorIE(),
                XVideosIE(),
+               InfoQIE(),
 
                GenericIE()
        ]