X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube-dl;h=20e26f99c06d7b70fda144c6a95a9b5655caa3a9;hb=b0eddb2eb4b8cad325ba3224c8550a21f67e4315;hp=e3c324f1f20ce8efed6e9b9817ab6030898e15e9;hpb=240b737ebd2356f9d117ccd0c14349d4ec88e90e;p=youtube-dl.git diff --git a/youtube-dl b/youtube-dl index e3c324f1f..20e26f99c 100755 --- a/youtube-dl +++ b/youtube-dl @@ -1,6 +1,7 @@ #!/usr/bin/env python # -*- coding: utf-8 -*- # Author: Ricardo Garcia Gonzalez +# Author: Danny Colligan # License: Public domain code import htmlentitydefs import httplib @@ -17,8 +18,8 @@ import time import urllib import urllib2 -std_headers = { - 'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.1) Gecko/2008070208 Firefox/3.0.1', +std_headers = { + 'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.0.8) Gecko/2009032609 Firefox/3.0.8', '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', @@ -70,10 +71,10 @@ class FileDownloader(object): File downloaders accept a lot of parameters. In order not to saturate the object constructor with arguments, it receives a dictionary of - options instead. These options are available through the get_params() - method for the InfoExtractors to use. The FileDownloader also registers - itself as the downloader in charge for the InfoExtractors that are - added to it, so this is a "mutual registration". + options instead. These options are available through the params + attribute for the InfoExtractors to use. The FileDownloader also + registers itself as the downloader in charge for the InfoExtractors + that are added to it, so this is a "mutual registration". Available options: @@ -88,9 +89,10 @@ class FileDownloader(object): outtmpl: Template for output names. ignoreerrors: Do not stop on download errors. ratelimit: Download speed limit, in bytes/sec. + nooverwrites: Prevent overwriting files. """ - _params = None + params = None _ies = [] _pps = [] @@ -98,7 +100,7 @@ class FileDownloader(object): """Create a FileDownloader object with the given options.""" self._ies = [] self._pps = [] - self.set_params(params) + self.params = params @staticmethod def pmkdir(filename): @@ -142,7 +144,7 @@ class FileDownloader(object): return '--:--' return '%02d:%02d' % (eta_mins, eta_secs) - @staticmethod + @staticmethod def calc_speed(start, now, bytes): dif = now - start if bytes == 0 or dif < 0.001: # One millisecond @@ -172,16 +174,6 @@ class FileDownloader(object): multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower()) return long(round(number * multiplier)) - def set_params(self, params): - """Sets parameters.""" - if type(params) != dict: - raise ValueError('params: dictionary expected') - self._params = params - - def get_params(self): - """Get parameters.""" - return self._params - def add_info_extractor(self, ie): """Add an InfoExtractor object to the end of the list.""" self._ies.append(ie) @@ -194,7 +186,7 @@ class FileDownloader(object): def to_stdout(self, message, skip_eol=False): """Print message to stdout if not in quiet mode.""" - if not self._params.get('quiet', False): + if not self.params.get('quiet', False): print u'%s%s' % (message, [u'\n', u''][skip_eol]), sys.stdout.flush() @@ -204,7 +196,7 @@ class FileDownloader(object): def fixed_template(self): """Checks if the output template is fixed.""" - return (re.search(ur'(?u)%\(.+?\)s', self._params['outtmpl']) is None) + return (re.search(ur'(?u)%\(.+?\)s', self.params['outtmpl']) is None) def trouble(self, message=None): """Determine action to take when a download problem appears. @@ -217,13 +209,13 @@ class FileDownloader(object): """ if message is not None: self.to_stderr(message) - if not self._params.get('ignoreerrors', False): + if not self.params.get('ignoreerrors', False): raise DownloadError(message) return 1 def slow_down(self, start_time, byte_counter): """Sleep if the download speed is over the rate limit.""" - rate_limit = self._params.get('ratelimit', None) + rate_limit = self.params.get('ratelimit', None) if rate_limit is None or byte_counter == 0: return now = time.time() @@ -247,70 +239,87 @@ class FileDownloader(object): """Report download finished.""" self.to_stdout(u'') + def process_info(self, info_dict): + """Process a single dictionary returned by an InfoExtractor.""" + # Forced printings + if self.params.get('forcetitle', False): + print info_dict['title'] + if self.params.get('forceurl', False): + print info_dict['url'] + + # Do nothing else if in simulate mode + if self.params.get('simulate', False): + return 0 + + try: + filename = self.params['outtmpl'] % info_dict + self.report_destination(filename) + except (ValueError, KeyError), err: + return self.trouble('ERROR: invalid output template or system charset: %s' % str(err)) + if self.params['nooverwrites'] and os.path.exists(filename): + self.to_stderr('WARNING: file exists: %s; skipping' % filename) + return 0 + try: + self.pmkdir(filename) + except (OSError, IOError), err: + return self.trouble('ERROR: unable to create directories: %s' % str(err)) + try: + outstream = open(filename, 'wb') + except (OSError, IOError), err: + return self.trouble('ERROR: unable to open for writing: %s' % str(err)) + try: + self._do_download(outstream, info_dict['url']) + outstream.close() + except (OSError, IOError), err: + return self.trouble('ERROR: unable to write video data: %s' % str(err)) + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + return self.trouble('ERROR: unable to download video data: %s' % str(err)) + try: + self.post_process(filename, info_dict) + except (PostProcessingError), err: + return self.trouble('ERROR: postprocessing: %s' % str(err)) + + return 0 + def download(self, url_list): """Download a given list of URLs.""" retcode = 0 if len(url_list) > 1 and self.fixed_template(): - raise SameFileError(self._params['outtmpl']) + raise SameFileError(self.params['outtmpl']) for url in url_list: suitable_found = False for ie in self._ies: + # Go to next InfoExtractor if not suitable if not ie.suitable(url): continue + # Suitable InfoExtractor found suitable_found = True + + # Extract information from URL all_results = ie.extract(url) results = [x for x in all_results if x is not None] + + # See if there were problems extracting any information if len(results) != len(all_results): retcode = self.trouble() + # Two results could go to the same file if len(results) > 1 and self.fixed_template(): - raise SameFileError(self._params['outtmpl']) + raise SameFileError(self.params['outtmpl']) + # Process each result 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 - self.report_destination(filename) - except (ValueError, KeyError), err: - retcode = self.trouble('ERROR: invalid output template or system charset: %s' % str(err)) - continue - try: - self.pmkdir(filename) - except (OSError, IOError), err: - retcode = self.trouble('ERROR: unable to create directories: %s' % str(err)) - continue - try: - outstream = open(filename, 'wb') - except (OSError, IOError), err: - retcode = self.trouble('ERROR: unable to open for writing: %s' % str(err)) - continue - try: - self._do_download(outstream, result['url']) - outstream.close() - except (OSError, IOError), err: - retcode = self.trouble('ERROR: unable to write video data: %s' % str(err)) - continue - 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 + result = self.process_info(result) + + # Do not overwrite an error code with a success code + if result != 0: + retcode = result + # Suitable InfoExtractor had been found; go to next URL break + if not suitable_found: retcode = self.trouble('ERROR: no suitable InfoExtractor: %s' % url) @@ -412,7 +421,7 @@ class InfoExtractor(object): 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): + if self._downloader is None or not self._downloader.params.get('quiet', False): print message def to_stderr(self, message): @@ -431,14 +440,42 @@ class YoutubeIE(InfoExtractor): """Information extractor for youtube.com.""" _VALID_URL = r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:\.php)?)?\?(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$' - _LOGIN_URL = 'http://uk.youtube.com/login?next=/' - _AGE_URL = 'http://uk.youtube.com/verify_age?next_url=/' + _LANG_URL = r'http://uk.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' + _LOGIN_URL = 'http://www.youtube.com/signup?next=/&gl=US&hl=en' + _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' _NETRC_MACHINE = 'youtube' @staticmethod def suitable(url): return (re.match(YoutubeIE._VALID_URL, url) is not None) + @staticmethod + def htmlentity_transform(matchobj): + """Transforms an HTML entity to a Unicode character.""" + entity = matchobj.group(1) + + # Known non-numeric HTML entity + if entity in htmlentitydefs.name2codepoint: + return unichr(htmlentitydefs.name2codepoint[entity]) + + # Unicode character + mobj = re.match(ur'(?u)#(x?\d+)', entity) + if mobj is not None: + numstr = mobj.group(1) + if numstr.startswith(u'x'): + base = 16 + numstr = u'0%s' % numstr + else: + base = 10 + return unichr(long(numstr, base)) + + # Unknown entity in name, return its literal representation + return (u'&%s;' % entity) + + def report_lang(self): + """Report attempt to set language.""" + self.to_stdout(u'[youtube] Setting language') + def report_login(self): """Report attempt to log in.""" self.to_stdout(u'[youtube] Logging in') @@ -458,14 +495,14 @@ class YoutubeIE(InfoExtractor): def report_video_url(self, video_id, video_real_url): """Report extracted video URL.""" self.to_stdout(u'[youtube] %s: URL: %s' % (video_id, video_real_url)) - + def _real_initialize(self): if self._downloader is None: return username = None password = None - downloader_params = self._downloader.get_params() + downloader_params = self._downloader.params # Attempt to use provided username and password or .netrc data if downloader_params.get('username', None) is not None: @@ -483,6 +520,15 @@ class YoutubeIE(InfoExtractor): self.to_stderr(u'WARNING: parsing .netrc: %s' % str(err)) return + # Set language + request = urllib2.Request(self._LANG_URL, None, std_headers) + try: + self.report_lang() + urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self.to_stderr(u'WARNING: unable to set language: %s' % str(err)) + return + # No authentication to be performed if username is None: return @@ -530,14 +576,20 @@ class YoutubeIE(InfoExtractor): # Downloader parameters format_param = None if self._downloader is not None: - params = self._downloader.get_params() + params = self._downloader.params format_param = params.get('format', None) + if format_param is None: + format_param = '34' # Extension - video_extension = {'18': 'mp4', '17': '3gp'}.get(format_param, 'flv') + video_extension = { + '17': '3gp', + '18': 'mp4', + '22': 'mp4', + }.get(format_param, 'flv') # Normalize URL, including format - normalized_url = 'http://uk.youtube.com/watch?v=%s' % video_id + normalized_url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id if format_param is not None: normalized_url = '%s&fmt=%s' % (normalized_url, format_param) request = urllib2.Request(normalized_url, None, std_headers) @@ -554,7 +606,7 @@ class YoutubeIE(InfoExtractor): if mobj is None: self.to_stderr(u'ERROR: unable to extract "t" parameter') return [None] - video_real_url = 'http://uk.youtube.com/get_video?video_id=%s&t=%s' % (video_id, mobj.group(1)) + video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&el=detailpage&ps=' % (video_id, mobj.group(1)) if format_param is not None: video_real_url = '%s&fmt=%s' % (video_real_url, format_param) self.report_video_url(video_id, video_real_url) @@ -572,7 +624,7 @@ class YoutubeIE(InfoExtractor): self.to_stderr(u'ERROR: unable to extract video title') return [None] video_title = mobj.group(1).decode('utf-8') - video_title = re.sub(ur'(?u)&(.+?);', lambda x: unichr(htmlentitydefs.name2codepoint[x.group(1)]), video_title) + video_title = re.sub(ur'(?u)&(.+?);', self.htmlentity_transform, video_title) video_title = video_title.replace(os.sep, u'%') # simplified title @@ -655,7 +707,7 @@ class MetacafeIE(InfoExtractor): # Check if video comes from YouTube mobj2 = re.match(r'^yt-(.*)$', video_id) if mobj2 is not None: - return self._youtube_ie.extract('http://uk.youtube.com/watch?v=%s' % mobj2.group(1)) + 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' @@ -707,11 +759,99 @@ class MetacafeIE(InfoExtractor): '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' + _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.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, self._max_youtube_results) + else: + try: + n = int(prefix) + if n <= 0: + self.to_stderr(u'ERROR: invalid download number %s for query "%s"' % (n, query)) + return [None] + elif n > self._max_youtube_results: + self.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n)) + n = self._max_youtube_results + 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://uk.youtube.com/view_play_list?p=%s&page=%s' + _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 @@ -765,7 +905,7 @@ class YoutubePlaylistIE(InfoExtractor): information = [] for id in video_ids: - information.extend(self._youtube_ie.extract('http://uk.youtube.com/watch?v=%s' % id)) + information.extend(self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)) return information class PostProcessor(object): @@ -792,7 +932,7 @@ class PostProcessor(object): 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): + if self._downloader is None or not self._downloader.params.get('quiet', False): print message def to_stderr(self, message): @@ -838,7 +978,7 @@ if __name__ == '__main__': # Parse command line parser = optparse.OptionParser( usage='Usage: %prog [options] url...', - version='2008.11.01', + version='INTERNAL', conflict_handler='resolve', ) parser.add_option('-h', '--help', @@ -867,18 +1007,31 @@ if __name__ == '__main__': 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='format', help='alias for -f 18', const='18') parser.add_option('-m', '--mobile-version', action='store_const', dest='format', help='alias for -f 17', const='17') + parser.add_option('-d', '--high-def', + action='store_const', dest='format', help='alias for -f 22', const='22') 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)') + parser.add_option('-a', '--batch-file', + dest='batchfile', metavar='F', help='file containing URLs to download') + parser.add_option('-w', '--no-overwrites', + action='store_true', dest='nooverwrites', help='do not overwrite files', default=False) (opts, args) = parser.parse_args() + # Batch file verification + batchurls = [] + if opts.batchfile is not None: + try: + batchurls = [line.strip() for line in open(opts.batchfile, 'r')] + except IOError: + sys.exit(u'ERROR: batch file could not be read') + all_urls = batchurls + args + # Conflicting, missing and erroneous options - if len(args) < 1: + if len(all_urls) < 1: sys.exit(u'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(u'ERROR: using .netrc conflicts with giving username/password') @@ -900,6 +1053,7 @@ if __name__ == '__main__': youtube_ie = YoutubeIE() metacafe_ie = MetacafeIE(youtube_ie) youtube_pl_ie = YoutubePlaylistIE(youtube_ie) + youtube_search_ie = YoutubeSearchIE(youtube_ie) # File downloader charset = locale.getdefaultlocale()[1] @@ -920,11 +1074,13 @@ if __name__ == '__main__': or u'%(id)s.%(ext)s'), 'ignoreerrors': opts.ignoreerrors, 'ratelimit': opts.ratelimit, + 'nooverwrites': opts.nooverwrites, }) + 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(args) + retcode = fd.download(all_urls) sys.exit(retcode) except DownloadError: