+ # No authentication to be performed
+ if username is None:
+ return
+
+ # Log in
+ login_form = {
+ 'current_form': 'loginForm',
+ 'next': '/',
+ 'action_login': 'Log In',
+ 'username': username,
+ 'password': password,
+ }
+ request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form), std_headers)
+ try:
+ self.report_login()
+ login_results = urllib2.urlopen(request).read()
+ if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None:
+ self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password')
+ return
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err))
+ return
+
+ # Confirm age
+ age_form = {
+ 'next_url': '/',
+ 'action_confirm': 'Confirm',
+ }
+ request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form), std_headers)
+ try:
+ self.report_age_confirmation()
+ age_results = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))
+ return
+
+ def _real_extract(self, url):
+ # Extract video id from URL
+ 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(2)
+
+ # Downloader parameters
+ best_quality = False
+ format_param = None
+ quality_index = 0
+ if self._downloader is not None:
+ params = self._downloader.params
+ format_param = params.get('format', None)
+ if format_param == '0':
+ format_param = self._available_formats[quality_index]
+ best_quality = True
+
+ while True:
+ # Extension
+ video_extension = self._video_extensions.get(format_param, 'flv')
+
+ # Get video info
+ video_info_url = 'http://www.youtube.com/get_video_info?&video_id=%s&el=detailpage&ps=default&eurl=&gl=US&hl=en' % video_id
+ request = urllib2.Request(video_info_url, None, std_headers)
+ try:
+ self.report_video_info_webpage_download(video_id)
+ video_info_webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
+ return
+ self.report_information_extraction(video_id)
+
+ # "t" param
+ mobj = re.search(r'(?m)&token=([^&]+)(?:&|$)', video_info_webpage)
+ if mobj is None:
+ # Attempt to see if YouTube has issued an error message
+ mobj = re.search(r'(?m)&reason=([^&]+)(?:&|$)', video_info_webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract "t" parameter for unknown reason')
+ stream = open('reportme-ydl-%s.dat' % time.time(), 'wb')
+ stream.write(video_info_webpage)
+ stream.close()
+ else:
+ reason = urllib.unquote_plus(mobj.group(1))
+ self._downloader.trouble(u'ERROR: YouTube said: %s' % reason.decode('utf-8'))
+ return
+ token = urllib.unquote(mobj.group(1))
+ video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&eurl=&el=detailpage&ps=default&gl=US&hl=en' % (video_id, token)
+ if format_param is not None:
+ video_real_url = '%s&fmt=%s' % (video_real_url, format_param)
+
+ # uploader
+ mobj = re.search(r'(?m)&author=([^&]+)(?:&|$)', video_info_webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
+ return
+ video_uploader = urllib.unquote(mobj.group(1))
+
+ # title
+ mobj = re.search(r'(?m)&title=([^&]+)(?:&|$)', video_info_webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video title')
+ return
+ video_title = urllib.unquote(mobj.group(1))
+ video_title = video_title.decode('utf-8')
+ video_title = re.sub(ur'(?u)&(.+?);', self.htmlentity_transform, video_title)
+ video_title = video_title.replace(os.sep, u'%')
+
+ # simplified title
+ simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+ simple_title = simple_title.strip(ur'_')
+
+ try:
+ # Process video information
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': video_real_url.decode('utf-8'),
+ 'uploader': video_uploader.decode('utf-8'),
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ })
+
+ return
+
+ except UnavailableFormatError, err:
+ if best_quality:
+ if quality_index == len(self._available_formats) - 1:
+ # I don't ever expect this to happen
+ self._downloader.trouble(u'ERROR: no known formats available for video')
+ return
+ else:
+ self.report_unavailable_format(video_id, format_param)
+ quality_index += 1
+ format_param = self._available_formats[quality_index]
+ continue
+ else:
+ self._downloader.trouble('ERROR: format not available for video')
+ return
+
+
+class MetacafeIE(InfoExtractor):
+ """Information Extractor for metacafe.com."""
+
+ _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
+ _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
+ _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
+ _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._downloader.to_stdout(u'[metacafe] Retrieving disclaimer')
+
+ def report_age_confirmation(self):
+ """Report attempt to confirm age."""
+ self._downloader.to_stdout(u'[metacafe] Confirming age')
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_stdout(u'[metacafe] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.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._downloader.trouble(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(self._FILTER_POST, 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._downloader.trouble(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._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+
+ video_id = mobj.group(1)
+
+ # Check if video comes from YouTube
+ mobj2 = re.match(r'^yt-(.*)$', video_id)
+ if mobj2 is not None:
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1))
+ return
+
+ 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._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err))
+ return
+
+ # Extract URL, uploader and title from webpage
+ self.report_extraction(video_id)
+ mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract media URL')
+ return
+ mediaURL = urllib.unquote(mobj.group(1))
+
+ #mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
+ #if mobj is None:
+ # self._downloader.trouble(u'ERROR: unable to extract gdaKey')
+ # return
+ #gdaKey = mobj.group(1)
+ #
+ #video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
+
+ video_url = mediaURL
+
+ mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract title')
+ return
+ video_title = mobj.group(1).decode('utf-8')
+
+ mobj = re.search(r'(?ms)<li id="ChnlUsr">.*?Submitter:.*?<a .*?>(.*?)<', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
+ return
+ video_uploader = mobj.group(1)
+
+ try:
+ # Process video information
+ self._downloader.process_info({
+ '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'),
+ })
+ except UnavailableFormatError:
+ self._downloader.trouble(u'ERROR: format not available for video')
+
+
+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'(?m)>\s*Next\s*</a>'
+ _youtube_ie = None
+ _max_youtube_results = 1000
+
+ 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._downloader.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._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
+ return
+
+ prefix, query = query.split(':')
+ prefix = prefix[8:]
+ if prefix == '':
+ self._download_n_results(query, 1)
+ return
+ elif prefix == 'all':
+ self._download_n_results(query, self._max_youtube_results)
+ return
+ else:
+ try:
+ n = long(prefix)
+ if n <= 0:
+ self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
+ return
+ elif n > self._max_youtube_results:
+ self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
+ n = self._max_youtube_results
+ self._download_n_results(query, n)
+ return
+ except ValueError: # parsing prefix as integer fails
+ self._download_n_results(query, 1)
+ return
+
+ 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._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ return
+
+ # 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
+ for id in video_ids:
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
+ return
+
+ if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+ for id in video_ids:
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
+ return
+
+ pagenum = pagenum + 1
+
+class YoutubePlaylistIE(InfoExtractor):
+ """Information Extractor for YouTube playlists."""
+
+ _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:view_play_list|my_playlists)\?.*?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._downloader.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._downloader.trouble(u'ERROR: invalid url: %s' % url)
+ return
+
+ # 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._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+ return
+
+ # 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.upper(), pagenum + 1)) not in page:
+ break
+ pagenum = pagenum + 1
+
+ for id in video_ids:
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
+ return
+
+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 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
+ composed 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 ###
+if __name__ == '__main__':
+ try:
+ # Modules needed only when running the main program
+ import getpass
+ import optparse
+
+ # General configuration
+ urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler()))
+ urllib2.install_opener(urllib2.build_opener(urllib2.HTTPCookieProcessor()))
+ socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
+
+ # Parse command line
+ parser = optparse.OptionParser(
+ usage='Usage: %prog [options] url...',
+ version='2009.09.13',
+ conflict_handler='resolve',
+ )
+
+ parser.add_option('-h', '--help',
+ action='help', help='print this help text and exit')
+ parser.add_option('-v', '--version',
+ action='version', help='print program version and exit')
+ parser.add_option('-i', '--ignore-errors',
+ action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
+ parser.add_option('-r', '--rate-limit',
+ dest='ratelimit', metavar='L', help='download rate limit (e.g. 50k or 44.6m)')
+
+ authentication = optparse.OptionGroup(parser, 'Authentication Options')
+ authentication.add_option('-u', '--username',
+ dest='username', metavar='UN', help='account username')
+ authentication.add_option('-p', '--password',
+ dest='password', metavar='PW', help='account password')
+ authentication.add_option('-n', '--netrc',
+ action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
+ parser.add_option_group(authentication)
+
+ video_format = optparse.OptionGroup(parser, 'Video Format Options')
+ video_format.add_option('-f', '--format',
+ action='store', dest='format', metavar='FMT', help='video format code')
+ video_format.add_option('-b', '--best-quality',
+ action='store_const', dest='format', help='download the best quality video possible', const='0')
+ video_format.add_option('-m', '--mobile-version',
+ action='store_const', dest='format', help='alias for -f 17', const='17')
+ video_format.add_option('-d', '--high-def',
+ action='store_const', dest='format', help='alias for -f 22', const='22')
+ parser.add_option_group(video_format)
+
+ verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
+ verbosity.add_option('-q', '--quiet',
+ action='store_true', dest='quiet', help='activates quiet mode', default=False)
+ verbosity.add_option('-s', '--simulate',
+ action='store_true', dest='simulate', help='do not download video', default=False)
+ verbosity.add_option('-g', '--get-url',
+ action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
+ verbosity.add_option('-e', '--get-title',
+ action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
+ parser.add_option_group(verbosity)
+
+ filesystem = optparse.OptionGroup(parser, 'Filesystem Options')
+ filesystem.add_option('-t', '--title',
+ action='store_true', dest='usetitle', help='use title in file name', default=False)
+ filesystem.add_option('-l', '--literal',
+ action='store_true', dest='useliteral', help='use literal title in file name', default=False)
+ filesystem.add_option('-o', '--output',
+ dest='outtmpl', metavar='TPL', help='output filename template')
+ filesystem.add_option('-a', '--batch-file',
+ dest='batchfile', metavar='F', help='file containing URLs to download')
+ filesystem.add_option('-w', '--no-overwrites',
+ action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
+ filesystem.add_option('-c', '--continue',
+ action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False)
+ parser.add_option_group(filesystem)
+
+ (opts, args) = parser.parse_args()
+
+ # Batch file verification
+ batchurls = []
+ if opts.batchfile is not None:
+ try:
+ batchurls = open(opts.batchfile, 'r').readlines()
+ batchurls = [x.strip() for x in batchurls]
+ batchurls = [x for x in batchurls if len(x) > 0]
+ except IOError:
+ sys.exit(u'ERROR: batch file could not be read')
+ all_urls = batchurls + args
+
+ # Conflicting, missing and erroneous options
+ if len(all_urls) < 1:
+ parser.error(u'you must provide at least one URL')
+ if opts.usenetrc and (opts.username is not None or opts.password is not None):
+ parser.error(u'using .netrc conflicts with giving username/password')
+ if opts.password is not None and opts.username is None:
+ parser.error(u'account username missing')
+ if opts.outtmpl is not None and (opts.useliteral or opts.usetitle):
+ parser.error(u'using output template conflicts with using title or literal title')
+ if opts.usetitle and opts.useliteral:
+ parser.error(u'using title conflicts with using literal title')
+ if opts.username is not None and opts.password is None:
+ opts.password = getpass.getpass(u'Type account password and press return:')
+ if opts.ratelimit is not None:
+ numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
+ if numeric_limit is None:
+ parser.error(u'invalid rate limit specified')
+ opts.ratelimit = numeric_limit
+
+ # Information extractors
+ youtube_ie = YoutubeIE()
+ metacafe_ie = MetacafeIE(youtube_ie)
+ youtube_pl_ie = YoutubePlaylistIE(youtube_ie)
+ youtube_search_ie = YoutubeSearchIE(youtube_ie)
+
+ # File downloader
+ fd = FileDownloader({
+ 'usenetrc': opts.usenetrc,
+ 'username': opts.username,
+ 'password': opts.password,
+ 'quiet': (opts.quiet or opts.geturl or opts.gettitle),
+ 'forceurl': opts.geturl,
+ 'forcetitle': opts.gettitle,
+ 'simulate': (opts.simulate or opts.geturl or opts.gettitle),
+ 'format': opts.format,
+ 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding()))
+ or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s')
+ or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s')
+ or u'%(id)s.%(ext)s'),
+ 'ignoreerrors': opts.ignoreerrors,
+ 'ratelimit': opts.ratelimit,
+ 'nooverwrites': opts.nooverwrites,
+ 'continuedl': opts.continue_dl,
+ })
+ fd.add_info_extractor(youtube_search_ie)
+ fd.add_info_extractor(youtube_pl_ie)
+ fd.add_info_extractor(metacafe_ie)
+ fd.add_info_extractor(youtube_ie)
+ retcode = fd.download(all_urls)
+ sys.exit(retcode)
+
+ except DownloadError:
+ sys.exit(1)
+ except SameFileError:
+ sys.exit(u'ERROR: fixed output name but more than one file to download')
+ except KeyboardInterrupt:
+ sys.exit(u'\nERROR: Interrupted by user')
Rapsys Git / youtubedl / blobdiff