+class MetacafeIE(InfoExtractor):
+ """Information Extractor for metacafe.com."""
+
+ _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
+ _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
+ _youtube_ie = None
+
+ def __init__(self, youtube_ie, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+ self._youtube_ie = youtube_ie
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(MetacafeIE._VALID_URL, url) is not None)
+
+ def report_disclaimer(self):
+ """Report disclaimer retrieval."""
+ self.to_stdout(u'[metacafe] Retrieving disclaimer')
+
+ def report_age_confirmation(self):
+ """Report attempt to confirm age."""
+ self.to_stdout(u'[metacafe] Confirming age')
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self.to_stdout(u'[metacafe] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self.to_stdout(u'[metacafe] %s: Extracting information' % video_id)
+
+ def _real_initialize(self):
+ # Retrieve disclaimer
+ request = urllib2.Request(self._DISCLAIMER, None, std_headers)
+ try:
+ self.report_disclaimer()
+ disclaimer = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self.to_stderr(u'ERROR: unable to retrieve disclaimer: %s' % str(err))
+ return
+
+ # Confirm age
+ disclaimer_form = {
+ 'filters': '0',
+ 'submit': "Continue - I'm over 18",
+ }
+ request = urllib2.Request('http://www.metacafe.com/', urllib.urlencode(disclaimer_form), std_headers)
+ try:
+ self.report_age_confirmation()
+ disclaimer = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self.to_stderr(u'ERROR: unable to confirm age: %s' % str(err))
+ return
+
+ def _real_extract(self, url):
+ # Extract id and simplified title from URL
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self.to_stderr(u'ERROR: invalid URL: %s' % url)
+ return [None]
+
+ video_id = mobj.group(1)
+
+ # Check if video comes from YouTube
+ mobj2 = re.match(r'^yt-(.*)$', video_id)
+ if mobj2 is not None:
+ return self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1))
+
+ simple_title = mobj.group(2).decode('utf-8')
+ video_extension = 'flv'
+
+ # Retrieve video webpage to extract further information
+ request = urllib2.Request('http://www.metacafe.com/watch/%s/' % video_id)
+ try:
+ self.report_download_webpage(video_id)
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self.to_stderr(u'ERROR: unable retrieve video webpage: %s' % str(err))
+ return [None]
+
+ # Extract URL, uploader and title from webpage
+ self.report_extraction(video_id)
+ mobj = re.search(r'(?m)"mediaURL":"(http.*?\.flv)"', webpage)
+ if mobj is None:
+ self.to_stderr(u'ERROR: unable to extract media URL')
+ return [None]
+ mediaURL = mobj.group(1).replace('\\', '')
+
+ mobj = re.search(r'(?m)"gdaKey":"(.*?)"', webpage)
+ if mobj is None:
+ self.to_stderr(u'ERROR: unable to extract gdaKey')
+ return [None]
+ gdaKey = mobj.group(1)
+
+ video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
+
+ mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
+ if mobj is None:
+ self.to_stderr(u'ERROR: unable to extract title')
+ return [None]
+ video_title = mobj.group(1).decode('utf-8')
+
+ mobj = re.search(r'(?m)<li id="ChnlUsr">.*?Submitter:<br />(.*?)</li>', webpage)
+ if mobj is None:
+ self.to_stderr(u'ERROR: unable to extract uploader nickname')
+ return [None]
+ video_uploader = re.sub(r'<.*?>', '', mobj.group(1))
+
+ # Return information
+ return [{
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url.decode('utf-8'),
+ 'uploader': video_uploader.decode('utf-8'),
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ }]
+
+
+class YoutubeSearchIE(InfoExtractor):
+ """Information Extractor for YouTube search queries."""
+ _VALID_QUERY = r'ytsearch(\d+|all)?:[\s\S]+'
+ _TEMPLATE_URL = 'http://www.youtube.com/results?search_query=%s&page=%s&gl=US&hl=en'
+ _VIDEO_INDICATOR = r'href="/watch\?v=.+?"'
+ _MORE_PAGES_INDICATOR = r'>Next</a>'
+ _youtube_ie = None
+
+ def __init__(self, youtube_ie, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+ self._youtube_ie = youtube_ie
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(YoutubeSearchIE._VALID_QUERY, url) is not None)
+
+ def report_download_page(self, query, pagenum):
+ """Report attempt to download playlist page with given number."""
+ self.to_stdout(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
+
+ def _real_initialize(self):
+ self._youtube_ie.initialize()
+
+ def _real_extract(self, query):
+ mobj = re.match(self._VALID_QUERY, query)
+ if mobj is None:
+ self.to_stderr(u'ERROR: invalid search query "%s"' % query)
+ return [None]
+
+ prefix, query = query.split(':')
+ prefix = prefix[8:]
+ if prefix == '':
+ return self._download_n_results(query, 1)
+ elif prefix == 'all':
+ return self._download_n_results(query, -1)
+ else:
+ try:
+ n = int(prefix)
+ if n <= 0:
+ self.to_stderr(u'ERROR: invalid download number %s for query "%s"' % (n, query))
+ return [None]
+ return self._download_n_results(query, n)
+ except ValueError: # parsing prefix as int fails
+ return self._download_n_results(query, 1)
+
+ def _download_n_results(self, query, n):
+ """Downloads a specified number of results for a query"""
+
+ video_ids = []
+ already_seen = set()
+ pagenum = 1
+
+ while True:
+ self.report_download_page(query, pagenum)
+ result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
+ request = urllib2.Request(result_url, None, std_headers)
+ try:
+ page = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self.to_stderr(u'ERROR: unable to download webpage: %s' % str(err))
+ return [None]
+
+ # Extract video identifiers
+ for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+ video_id = page[mobj.span()[0]:mobj.span()[1]].split('=')[2][:-1]
+ if video_id not in already_seen:
+ video_ids.append(video_id)
+ already_seen.add(video_id)
+ if len(video_ids) == n:
+ # Specified n videos reached
+ information = []
+ for id in video_ids:
+ information.extend(self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id))
+ return information
+
+ if self._MORE_PAGES_INDICATOR not in page:
+ information = []
+ for id in video_ids:
+ information.extend(self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id))
+ return information
+
+ pagenum = pagenum + 1
+
+class YoutubePlaylistIE(InfoExtractor):
+ """Information Extractor for YouTube playlists."""
+
+ _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/view_play_list\?p=(.+)'
+ _TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en'
+ _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
+ _MORE_PAGES_INDICATOR = r'/view_play_list?p=%s&page=%s'
+ _youtube_ie = None
+
+ def __init__(self, youtube_ie, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+ self._youtube_ie = youtube_ie
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(YoutubePlaylistIE._VALID_URL, url) is not None)
+
+ def report_download_page(self, playlist_id, pagenum):
+ """Report attempt to download playlist page with given number."""
+ self.to_stdout(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
+
+ def _real_initialize(self):
+ self._youtube_ie.initialize()
+
+ def _real_extract(self, url):
+ # Extract playlist id
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self.to_stderr(u'ERROR: invalid url: %s' % url)
+ return [None]
+
+ # Download playlist pages
+ playlist_id = mobj.group(1)
+ video_ids = []
+ pagenum = 1
+
+ while True:
+ self.report_download_page(playlist_id, pagenum)
+ request = urllib2.Request(self._TEMPLATE_URL % (playlist_id, pagenum), None, std_headers)
+ try:
+ page = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self.to_stderr(u'ERROR: unable to download webpage: %s' % str(err))
+ return [None]
+
+ # Extract video identifiers
+ ids_in_page = []
+ for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+ if mobj.group(1) not in ids_in_page:
+ ids_in_page.append(mobj.group(1))
+ video_ids.extend(ids_in_page)
+
+ if (self._MORE_PAGES_INDICATOR % (playlist_id, pagenum + 1)) not in page:
+ break
+ pagenum = pagenum + 1
+
+ information = []
+ for id in video_ids:
+ information.extend(self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id))
+ return information
+
+class PostProcessor(object):
+ """Post Processor class.
+
+ PostProcessor objects can be added to downloaders with their
+ add_post_processor() method. When the downloader has finished a
+ successful download, it will take its internal chain of PostProcessors
+ and start calling the run() method on each one of them, first with
+ an initial argument and then with the returned value of the previous
+ PostProcessor.
+
+ The chain will be stopped if one of them ever returns None or the end
+ of the chain is reached.
+
+ PostProcessor objects follow a "mutual registration" process similar
+ to InfoExtractor objects.
+ """
+
+ _downloader = None
+
+ def __init__(self, downloader=None):
+ self._downloader = downloader
+
+ def to_stdout(self, message):
+ """Print message to stdout if downloader is not in quiet mode."""
+ if self._downloader is None or not self._downloader.params.get('quiet', False):
+ print message
+
+ def to_stderr(self, message):
+ """Print message to stderr."""
+ print >>sys.stderr, message
+
+ def set_downloader(self, downloader):
+ """Sets the downloader for this PP."""
+ self._downloader = downloader
+
+ def run(self, information):
+ """Run the PostProcessor.
+
+ The "information" argument is a dictionary like the ones
+ returned by InfoExtractors. The only difference is that this
+ one has an extra field called "filepath" that points to the
+ downloaded file.
+
+ When this method returns None, the postprocessing chain is
+ stopped. However, this method may return an information
+ dictionary that will be passed to the next postprocessing
+ object in the chain. It can be the one it received after
+ changing some fields.
+
+ In addition, this method may raise a PostProcessingError
+ exception that will be taken into account by the downloader
+ it was called from.
+ """
+ return information # by default, do nothing
+
+### MAIN PROGRAM ###
projects / youtube-dl / blobdiff