X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;ds=sidebyside;f=youtube-dl;h=677f938dd4a62e19869d18fbfc27bc0e5329fce7;hb=209e9e27e777f4c320dada6857b8e984af816e7a;hp=d3f2771101aa0bb0b0811ce08d02ec89a9468035;hpb=14c300687e4a2724fb458676cd2b0214acb9647a;p=youtube-dl diff --git a/youtube-dl b/youtube-dl index d3f277110..677f938dd 100755 --- a/youtube-dl +++ b/youtube-dl @@ -17,7 +17,7 @@ import urllib import urllib2 std_headers = { - 'User-Agent': 'UserAgent: Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9) Gecko/2008052906 Firefox/3.0', + 'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.1) Gecko/2008070208 Firefox/3.0.1', 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7', 'Accept': 'text/xml,application/xml,application/xhtml+xml,text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5', 'Accept-Language': 'en-us,en;q=0.5', @@ -55,6 +55,8 @@ class FileDownloader(object): password: Password for authentication purposes. usenetrc: Use netrc for authentication instead. quiet: Do not print messages to stdout. + forceurl: Force printing final URL. + forcetitle: Force printing title. simulate: Do not download the video files. format: Video format code. outtmpl: Template for output names. @@ -152,9 +154,16 @@ class FileDownloader(object): def to_stderr(self, message): """Print message to stderr.""" sys.stderr.write('%s\n' % message) + + def fixed_template(self): + """Checks if the output template is fixed.""" + return (re.search(ur'(?u)%\(.+?\)s', self._params['outtmpl']) is None) def download(self, url_list): """Download a given list of URLs.""" + if len(url_list) > 1 and self.fixed_template(): + sys.exit('ERROR: fixed output name but more than one file to download') + for url in url_list: suitable_found = False for ie in self._ies: @@ -164,13 +173,21 @@ class FileDownloader(object): suitable_found = True results = [x for x in ie.extract(url) if x is not None] - if (len(url_list) > 1 or len(results) > 1) and re.search(r'%\(.+?\)s', self._params['outtmpl']) is None: + if len(results) > 1 and self.fixed_template(): sys.exit('ERROR: fixed output name but more than one file to download') - if self._params.get('simulate', False): - continue - for result in results: + + # Forced printings + if self._params.get('forcetitle', False): + print result['title'] + if self._params.get('forceurl', False): + print result['url'] + + # Do nothing else if in simulate mode + if self._params.get('simulate', False): + continue + try: filename = self._params['outtmpl'] % result except (ValueError, KeyError), err: @@ -375,7 +392,7 @@ class YoutubeIE(InfoExtractor): format_param = params.get('format', None) # Extension - video_extension = {18: 'mp4'}.get(format_param, 'flv') + video_extension = {'18': 'mp4'}.get(format_param, 'flv') # Normalize URL, including format normalized_url = 'http://www.youtube.com/watch?v=%s' % video_id @@ -412,11 +429,11 @@ class YoutubeIE(InfoExtractor): self.to_stderr('ERROR: Unable to extract video title') return [None] video_title = mobj.group(1).decode('utf-8') - video_title = re.sub(u'&(.+?);', lambda x: unichr(htmlentitydefs.name2codepoint[x.group(1)]), video_title) + video_title = re.sub(ur'(?u)&(.+?);', lambda x: unichr(htmlentitydefs.name2codepoint[x.group(1)]), video_title) # simplified title - simple_title = re.sub(u'([^%s]+)' % simple_title_chars, u'_', video_title) - simple_title = simple_title.strip(u'_') + simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) + simple_title = simple_title.strip(ur'_') # Return information return [{ @@ -430,29 +447,89 @@ class YoutubeIE(InfoExtractor): 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='INTERNAL', + 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('-u', '--username', + dest='username', metavar='UN', help='account username') + parser.add_option('-p', '--password', + dest='password', metavar='PW', help='account password') + parser.add_option('-o', '--output', + dest='outtmpl', metavar='TPL', help='output filename template') + parser.add_option('-q', '--quiet', + action='store_true', dest='quiet', help='activates quiet mode', default=False) + parser.add_option('-s', '--simulate', + action='store_true', dest='simulate', help='do not download video', default=False) + parser.add_option('-t', '--title', + action='store_true', dest='usetitle', help='use title in file name', default=False) + parser.add_option('-l', '--literal', + action='store_true', dest='useliteral', help='use literal title in file name', default=False) + parser.add_option('-n', '--netrc', + action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False) + parser.add_option('-g', '--get-url', + action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False) + parser.add_option('-e', '--get-title', + action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False) + parser.add_option('-f', '--format', + dest='format', metavar='FMT', help='video format code') + parser.add_option('-b', '--best-quality', + action='store_const', dest='video_format', help='alias for -f 18', const='18') + (opts, args) = parser.parse_args() + + # Conflicting, missing and erroneous options + if len(args) < 1: + sys.exit('ERROR: you must provide at least one URL') + if opts.usenetrc and (opts.username is not None or opts.password is not None): + sys.exit('ERROR: using .netrc conflicts with giving username/password') + if opts.password is not None and opts.username is None: + sys.exit('ERROR: account username missing') + if opts.outtmpl is not None and (opts.useliteral or opts.usetitle): + sys.exit('ERROR: using output template conflicts with using title or literal title') + if opts.usetitle and opts.useliteral: + sys.exit('ERROR: using title conflicts with using literal title') + if opts.username is not None and opts.password is None: + opts.password = getpass.getpass('Type account password and press return:') # Information extractors youtube_ie = YoutubeIE() # File downloader fd = FileDownloader({ - 'usenetrc': False, - 'username': None, - 'password': None, - 'quiet': False, - 'simulate': False, - 'format': None, - 'outtmpl': '%(ext)s/%(ext)s/%(id)s.%(ext)s' + '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.usetitle and '%(stitle)s-%(id)s.%(ext)s') + or (opts.useliteral and '%(title)s-%(id)s.%(ext)s') + or '%(id)s.%(ext)s'), }) fd.add_info_extractor(youtube_ie) - fd.download([ - 'http://www.youtube.com/watch?v=t7qdwI7TVe8', - 'http://www.youtube.com/watch?v=IJyn3pRcy_Q', - 'http://www.youtube.com/watch?v=DZRXe1wtC-M', - ]) + fd.download(args) + #fd.download([ + # 'http://www.youtube.com/watch?v=t7qdwI7TVe8', + # 'http://www.youtube.com/watch?v=IJyn3pRcy_Q', + # 'http://www.youtube.com/watch?v=DZRXe1wtC-M', + # ]) except KeyboardInterrupt: sys.exit('\nERROR: Interrupted by user')