X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube-dl;h=ecc99b7c1bdf0f72c1992c3ea492bae95f82d506;hb=2546e7679f26147fce3ddb3fc49e869a03ec0a2e;hp=48f5d2bf1aefd959e772e8e141fbaf9cdbbf7f01;hpb=b1a1f8ea8f40ed26b7071eda139e31493f6f7972;p=youtube-dl.git diff --git a/youtube-dl b/youtube-dl index 48f5d2bf1..ecc99b7c1 100755 --- a/youtube-dl +++ b/youtube-dl @@ -4,6 +4,7 @@ # License: Public domain code import htmlentitydefs import httplib +import locale import math import netrc import os @@ -42,6 +43,14 @@ class SameFileError(Exception): """ pass +class PostProcessingError(Exception): + """Post Processing exception. + + This exception may be raised by PostProcessor's .run() method to + indicate an error in the postprocessing task. + """ + pass + class FileDownloader(object): """File Downloader class. @@ -83,10 +92,12 @@ class FileDownloader(object): _params = None _ies = [] + _pps = [] def __init__(self, params): """Create a FileDownloader object with the given options.""" self._ies = [] + self._pps = [] self.set_params(params) @staticmethod @@ -176,6 +187,11 @@ class FileDownloader(object): self._ies.append(ie) ie.set_downloader(self) + def add_post_processor(self, pp): + """Add a PostProcessor object to the end of the chain.""" + self._pps.append(pp) + pp.set_downloader(self) + def to_stdout(self, message, skip_eol=False): """Print message to stdout if not in quiet mode.""" if not self._params.get('quiet', False): @@ -288,11 +304,26 @@ class FileDownloader(object): except (urllib2.URLError, httplib.HTTPException, socket.error), err: retcode = self.trouble('ERROR: unable to download video data: %s' % str(err)) continue + try: + self.post_process(filename, result) + except (PostProcessingError), err: + retcode = self.trouble('ERROR: postprocessing: %s' % str(err)) + continue + break if not suitable_found: retcode = self.trouble('ERROR: no suitable InfoExtractor: %s' % url) return retcode + + def post_process(self, filename, ie_info): + """Run the postprocessing chain on the given file.""" + info = dict(ie_info) + info['filepath'] = filename + for pp in self._pps: + info = pp.run(info) + if info is None: + break def _do_download(self, stream, url): request = urllib2.Request(url, None, std_headers) @@ -529,7 +560,7 @@ class YoutubeIE(InfoExtractor): self.report_video_url(video_id, video_real_url) # uploader - mobj = re.search(r'More From: ([^<]*)<', video_webpage) + mobj = re.search(r"var watchUsername = '([^']+)';", video_webpage) if mobj is None: self.to_stderr(u'ERROR: unable to extract uploader nickname') return [None] @@ -562,7 +593,7 @@ class MetacafeIE(InfoExtractor): """Information Extractor for metacafe.com.""" _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*' - _DISCLAIMER = 'http://www.metacafe.com/disclaimer' + _DISCLAIMER = 'http://www.metacafe.com/family_filter/' _youtube_ie = None def __init__(self, youtube_ie, downloader=None): @@ -601,10 +632,10 @@ class MetacafeIE(InfoExtractor): # Confirm age disclaimer_form = { - 'allowAdultContent': '1', + 'filters': '0', 'submit': "Continue - I'm over 18", } - request = urllib2.Request('http://www.metacafe.com/watch/', urllib.urlencode(disclaimer_form), std_headers) + request = urllib2.Request('http://www.metacafe.com/', urllib.urlencode(disclaimer_form), std_headers) try: self.report_age_confirmation() disclaimer = urllib2.urlopen(request).read() @@ -654,7 +685,7 @@ class MetacafeIE(InfoExtractor): video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) - mobj = re.search(r'(?im)(.*) - Video', webpage) if mobj is None: self.to_stderr(u'ERROR: unable to extract title') return [None] @@ -682,7 +713,7 @@ class YoutubePlaylistIE(InfoExtractor): _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/view_play_list\?p=(.+)' _TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s' _VIDEO_INDICATOR = r'/watch\?v=(.+?)&' - _MORE_PAGES_INDICATOR = r'class="pagerNotCurrent">Next' + _MORE_PAGES_INDICATOR = r'/view_play_list?p=%s&page=%s' _youtube_ie = None def __init__(self, youtube_ie, downloader=None): @@ -727,7 +758,7 @@ class YoutubePlaylistIE(InfoExtractor): ids_in_page.add(mobj.group(1)) video_ids.extend(list(ids_in_page)) - if self._MORE_PAGES_INDICATOR not in page: + if (self._MORE_PAGES_INDICATOR % (playlist_id, pagenum + 1)) not in page: break pagenum = pagenum + 1 @@ -736,6 +767,62 @@ class YoutubePlaylistIE(InfoExtractor): 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.get_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 ### if __name__ == '__main__': try: # Modules needed only when running the main program @@ -750,7 +837,7 @@ if __name__ == '__main__': # Parse command line parser = optparse.OptionParser( usage='Usage: %prog [options] url...', - version='2008.07.22', + version='2008.08.09', conflict_handler='resolve', ) parser.add_option('-h', '--help', @@ -823,7 +910,7 @@ if __name__ == '__main__': '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()) + 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(locale.getdefaultlocale()[1])) 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'),