now downloads soundcloud songs, need to polish title grabbing and file naming
[youtube-dl.git] / youtube-dl
index d3582c4..949d2e5 100755 (executable)
@@ -15,7 +15,7 @@ __author__  = (
        )
 
 __license__ = 'Public Domain'
-__version__ = '2011.09.30'
+__version__ = '2011.10.19'
 
 UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl'
 
@@ -1236,7 +1236,7 @@ class YoutubeIE(InfoExtractor):
 
                # Get video webpage
                self.report_video_webpage_download(video_id)
-               request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id)
+               request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id)
                try:
                        video_webpage = urllib2.urlopen(request).read()
                except (urllib2.URLError, httplib.HTTPException, socket.error), err:
@@ -2059,6 +2059,18 @@ class VimeoIE(InfoExtractor):
                        return
                sig = mobj.group(1).decode('utf-8')
 
+               # Vimeo specific: extract video quality information
+               mobj = re.search(r'<isHD>(\d+)</isHD>', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract video quality information')
+                       return
+               quality = mobj.group(1).decode('utf-8')
+
+               if int(quality) == 1:
+                       quality = 'hd'
+               else:
+                       quality = 'sd'
+
                # Vimeo specific: Extract request signature expiration
                mobj = re.search(r'<request_signature_expires>(.*?)</request_signature_expires>', webpage)
                if mobj is None:
@@ -2066,7 +2078,7 @@ class VimeoIE(InfoExtractor):
                        return
                sig_exp = mobj.group(1).decode('utf-8')
 
-               video_url = "http://vimeo.com/moogaloop/play/clip:%s/%s/%s" % (video_id, sig, sig_exp)
+               video_url = "http://vimeo.com/moogaloop/play/clip:%s/%s/%s/?q=%s" % (video_id, sig, sig_exp, quality)
 
                try:
                        # Process video information
@@ -2458,7 +2470,7 @@ class YahooSearchIE(InfoExtractor):
 class YoutubePlaylistIE(InfoExtractor):
        """Information Extractor for YouTube playlists."""
 
-       _VALID_URL = r'(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?: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>'
@@ -2697,11 +2709,12 @@ class DepositFilesIE(InfoExtractor):
 class FacebookIE(InfoExtractor):
        """Information Extractor for Facebook"""
 
-       _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/video/video\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
+       _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
        _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&'
        _NETRC_MACHINE = 'facebook'
-       _available_formats = ['highqual', 'lowqual']
+       _available_formats = ['video', 'highqual', 'lowqual']
        _video_extensions = {
+               'video': 'mp4',
                'highqual': 'mp4',
                'lowqual': 'mp4',
        }
@@ -2729,10 +2742,9 @@ class FacebookIE(InfoExtractor):
        def _parse_page(self, video_webpage):
                """Extract video information from page"""
                # General data
-               data = {'title': r'class="video_title datawrap">(.*?)</',
+               data = {'title': r'\("video_title", "(.*?)"\)',
                        'description': r'<div class="datawrap">(.*?)</div>',
                        'owner': r'\("video_owner_name", "(.*?)"\)',
-                       'upload_date': r'data-date="(.*?)"',
                        'thumbnail':  r'\("thumb_url", "(?P<THUMB>.*?)"\)',
                        }
                video_info = {}
@@ -3306,6 +3318,264 @@ class EscapistIE(InfoExtractor):
                        self._downloader.trouble(u'\nERROR: unable to download ' + videoId)
 
 
+class CollegeHumorIE(InfoExtractor):
+       """Information extractor for collegehumor.com"""
+
+       _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/video/(?P<videoid>[0-9]+)/(?P<shorttitle>.*)$'
+       IE_NAME = u'collegehumor'
+
+       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
+               video_id = mobj.group('videoid')
+
+               self.report_webpage(video_id)
+               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
+
+               m = re.search(r'id="video:(?P<internalvideoid>[0-9]+)"', webpage)
+               if m is None:
+                       self._downloader.trouble(u'ERROR: Cannot extract internal video ID')
+                       return
+               internal_video_id = m.group('internalvideoid')
+
+               info = {
+                       'id': video_id,
+                       'internal_id': internal_video_id,
+               }
+
+               self.report_extraction(video_id)
+               xmlUrl = 'http://www.collegehumor.com/moogaloop/video:' + internal_video_id
+               try:
+                       metaXml = urllib2.urlopen(xmlUrl).read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % str(err))
+                       return
+
+               mdoc = xml.etree.ElementTree.fromstring(metaXml)
+               try:
+                       videoNode = mdoc.findall('./video')[0]
+                       info['description'] = videoNode.findall('./description')[0].text
+                       info['title'] = videoNode.findall('./caption')[0].text
+                       info['stitle'] = self._simplify_title(info['title'])
+                       info['url'] = videoNode.findall('./file')[0].text
+                       info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
+                       info['ext'] = info['url'].rpartition('.')[2]
+                       info['format'] = info['ext']
+               except IndexError:
+                       self._downloader.trouble(u'\nERROR: Invalid metadata XML file')
+                       return
+
+               self._downloader.increment_downloads()
+
+               try:
+                       self._downloader.process_info(info)
+               except UnavailableVideoError, err:
+                       self._downloader.trouble(u'\nERROR: unable to download video')
+
+
+class XVideosIE(InfoExtractor):
+       """Information extractor for xvideos.com"""
+
+       _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
+       IE_NAME = u'xvideos'
+
+       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
+               video_id = mobj.group(1).decode('utf-8')
+
+               self.report_webpage(video_id)
+
+               request = urllib2.Request(r'http://www.xvideos.com/video' + video_id)
+               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(video_id)
+
+
+               # Extract video URL
+               mobj = re.search(r'flv_url=(.+?)&', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract video url')
+                       return
+               video_url = urllib2.unquote(mobj.group(1).decode('utf-8'))
+
+
+               # Extract title
+               mobj = re.search(r'<title>(.*?)\s+-\s+XVID', 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 video thumbnail
+               mobj = re.search(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]/[a-fA-F0-9]/[a-fA-F0-9]/([a-fA-F0-9.]+jpg)', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
+                       return
+               video_thumbnail = mobj.group(1).decode('utf-8')
+
+
+
+               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': 'flv',
+                       'format': 'flv',
+                       'thumbnail': video_thumbnail,
+                       'description': None,
+                       'player_url': None,
+               }
+
+               try:
+                       self._downloader.process_info(info)
+               except UnavailableVideoError, err:
+                       self._downloader.trouble(u'\nERROR: unable to download ' + video_id)
+
+
+class SoundcloudIE(InfoExtractor):
+       """Information extractor for soundcloud.com
+          To access the media, the uid of the song and a stream token
+          must be extracted from the page source and the script must make
+          a request to media.soundcloud.com/crossdomain.xml. Then
+          the media can be grabbed by requesting from an url composed
+          of the stream token and uid
+        """
+
+       _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)'
+       IE_NAME = u'soundcloud'
+
+       def __init__(self, downloader=None):
+               InfoExtractor.__init__(self, downloader)
+
+       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 _real_initialize(self):
+               return
+
+       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
+
+               # extract uploader (which is in the url)
+               uploader = mobj.group(1).decode('utf-8')
+               # extract simple title (uploader + slug of song title)
+               slug_title =  mobj.group(2).decode('utf-8')
+               simple_title = uploader + '-' + slug_title
+
+               self.report_webpage('%s/%s' % (uploader, slug_title))
+
+               request = urllib2.Request('http://soundcloud.com/%s/%s' % (uploader, slug_title))
+               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('%s/%s' % (uploader, slug_title))
+
+               # extract uid and access token
+               mobj = re.search('"uid":"([\w\d]+?)".*?stream_token=([\w\d]+)', webpage)   
+               if mobj:
+                       video_id = mobj.group(1)
+                       stream_token = mobj.group(2)
+
+               # construct media url (with uid/token) to request song
+               mediaURL = "http://media.soundcloud.com/stream/%s?stream_token=%s"
+               mediaURL = mediaURL % (video_id, stream_token)
+
+               # description
+               description = u'No description available'
+               mobj = re.search('track-description-value"><p>(.*?)</p>', webpage)
+               if mobj:
+                       description = mobj.group(1)
+               
+               # upload date
+               upload_date = None
+               mobj = re.search("pretty-date'>on ([\w]+ [\d]+, [\d]+ \d+:\d+)</abbr></h2>", webpage)
+               if mobj:
+                       try:
+                               upload_date = datetime.datetime.strptime(mobj.group(1), '%B %d, %Y %H:%M').strftime('%Y%m%d')
+                       except Exception as e:
+                               print str(e)
+
+               # for soundcloud, a request must be made to a cross domain to establish
+               # needed cookies
+               request = urllib2.Request('http://media.soundcloud.com/crossdomain.xml', std_headers)
+
+               try:
+                       self._downloader.process_info({
+                               'id':           video_id,
+                               'url':          mediaURL,
+                               'uploader':     uploader,
+                               'upload_date':  upload_date,
+                               'title':        simple_title,
+                               'stitle':       simple_title,
+                               'ext':          u'mp3',
+                               'format':       u'NA',
+                               'player_url':   None,
+                               'description': description
+                       })
+               except UnavailableVideoError:
+                       self._downloader.trouble(u'\nERROR: unable to download video')
 
 class PostProcessor(object):
        """Post Processor class.
@@ -3701,6 +3971,9 @@ def gen_extractors():
                MyVideoIE(),
                ComedyCentralIE(),
                EscapistIE(),
+               CollegeHumorIE(),
+               XVideosIE(),
+        SoundcloudIE(),
 
                GenericIE()
        ]