X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/a5f3018bec4ce17c57059f2384d9110f850ba28d..46ef599ac108f9d54c9d505ef1ac1c62dde6bbbe:/youtube-dl?ds=sidebyside diff --git a/youtube-dl b/youtube-dl index 47c6465..48c13b7 100755 --- a/youtube-dl +++ b/youtube-dl @@ -27,9 +27,9 @@ except ImportError: from cgi import parse_qs std_headers = { - 'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.2) Gecko/20100115 Firefox/3.6', + 'User-Agent': 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.7) Gecko/20100720 Firefox/3.6.7', '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': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', 'Accept-Language': 'en-us,en;q=0.5', } @@ -93,11 +93,13 @@ def sanitize_open(filename, open_mode): It returns the tuple (stream, definitive_file_name). """ try: + if filename == u'-': + return (sys.stdout, filename) stream = open(filename, open_mode) return (stream, filename) except (IOError, OSError), err: # In case of error, try to remove win32 forbidden chars - filename = re.sub(ur'[<>:"\|\?\*]', u'#', filename) + filename = re.sub(ur'[/<>:"\|\?\*]', u'#', filename) # An exception here should be caught in the caller stream = open(filename, open_mode) @@ -129,7 +131,7 @@ class PostProcessingError(Exception): """ pass -class UnavailableFormatError(Exception): +class UnavailableVideoError(Exception): """Unavailable Format exception. This exception will be thrown when a video is requested @@ -187,23 +189,28 @@ class FileDownloader(object): forcetitle: Force printing title. simulate: Do not download the video files. format: Video format code. + format_limit: Highest quality format to try. outtmpl: Template for output names. ignoreerrors: Do not stop on download errors. ratelimit: Download speed limit, in bytes/sec. nooverwrites: Prevent overwriting files. + retries: Number of times to retry for HTTP error 503 continuedl: Try to continue downloads if possible. + noprogress: Do not print the progress bar. """ params = None _ies = [] _pps = [] _download_retcode = None + _num_downloads = None def __init__(self, params): """Create a FileDownloader object with the given options.""" self._ies = [] self._pps = [] self._download_retcode = 0 + self._num_downloads = 0 self.params = params @staticmethod @@ -300,11 +307,15 @@ class FileDownloader(object): self._pps.append(pp) pp.set_downloader(self) - def to_stdout(self, message, skip_eol=False): + def to_stdout(self, message, skip_eol=False, ignore_encoding_errors=False): """Print message to stdout if not in quiet mode.""" - if not self.params.get('quiet', False): - print (u'%s%s' % (message, [u'\n', u''][skip_eol])).encode(preferredencoding()), + try: + if not self.params.get('quiet', False): + print (u'%s%s' % (message, [u'\n', u''][skip_eol])).encode(preferredencoding()), sys.stdout.flush() + except (UnicodeEncodeError), err: + if not ignore_encoding_errors: + raise def to_stderr(self, message): """Print message to stderr.""" @@ -342,10 +353,12 @@ class FileDownloader(object): def report_destination(self, filename): """Report destination filename.""" - self.to_stdout(u'[download] Destination: %s' % filename) + self.to_stdout(u'[download] Destination: %s' % filename, ignore_encoding_errors=True) def report_progress(self, percent_str, data_len_str, speed_str, eta_str): """Report download progress.""" + if self.params.get('noprogress', False): + return self.to_stdout(u'\r[download] %s of %s at %s ETA %s' % (percent_str, data_len_str, speed_str, eta_str), skip_eol=True) @@ -353,9 +366,16 @@ class FileDownloader(object): """Report attemtp to resume at given byte.""" self.to_stdout(u'[download] Resuming download at byte %s' % resume_len) + def report_retry(self, count, retries): + """Report retry in case of HTTP error 503""" + self.to_stdout(u'[download] Got HTTP error 503. Retrying (attempt %d of %d)...' % (count, retries)) + def report_file_already_downloaded(self, file_name): """Report file has already been fully downloaded.""" - self.to_stdout(u'[download] %s has already been downloaded' % file_name) + try: + self.to_stdout(u'[download] %s has already been downloaded' % file_name) + except (UnicodeEncodeError), err: + self.to_stdout(u'[download] The file has already been downloaded') def report_unable_to_resume(self): """Report it was impossible to resume download.""" @@ -363,7 +383,14 @@ class FileDownloader(object): def report_finish(self): """Report download finished.""" - self.to_stdout(u'') + if self.params.get('noprogress', False): + self.to_stdout(u'[download] Download completed') + else: + self.to_stdout(u'') + + def increment_downloads(self): + """Increment the ordinal that assigns a number to each file.""" + self._num_downloads += 1 def process_info(self, info_dict): """Process a single dictionary returned by an InfoExtractor.""" @@ -372,21 +399,26 @@ class FileDownloader(object): # Verify URL if it's an HTTP one if info_dict['url'].startswith('http'): try: - info_dict['url'] = self.verify_url(info_dict['url'].encode('utf-8')).decode('utf-8') + self.verify_url(info_dict['url'].encode('utf-8')).decode('utf-8') except (OSError, IOError, urllib2.URLError, httplib.HTTPException, socket.error), err: - raise UnavailableFormatError + raise UnavailableVideoError # Forced printings if self.params.get('forcetitle', False): print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace') if self.params.get('forceurl', False): print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace') + if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict: + print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace') + if self.params.get('forcedescription', False) and 'description' in info_dict: + print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace') return try: template_dict = dict(info_dict) template_dict['epoch'] = unicode(long(time.time())) + template_dict['ord'] = unicode('%05d' % self._num_downloads) filename = self.params['outtmpl'] % template_dict except (ValueError, KeyError), err: self.trouble('ERROR: invalid output template or system charset: %s' % str(err)) @@ -401,9 +433,9 @@ class FileDownloader(object): return try: - success = self._do_download(filename, info_dict['url'].encode('utf-8')) + success = self._do_download(filename, info_dict['url'].encode('utf-8'), info_dict.get('player_url', None)) except (OSError, IOError), err: - raise UnavailableFormatError + raise UnavailableVideoError except (urllib2.URLError, httplib.HTTPException, socket.error), err: self.trouble('ERROR: unable to download video data: %s' % str(err)) return @@ -453,7 +485,7 @@ class FileDownloader(object): if info is None: break - def _download_with_rtmpdump(self, filename, url): + def _download_with_rtmpdump(self, filename, url, player_url): self.report_destination(filename) # Check for rtmpdump first @@ -466,23 +498,27 @@ class FileDownloader(object): # Download using rtmpdump. rtmpdump returns exit code 2 when # the connection was interrumpted and resuming appears to be # possible. This is part of rtmpdump's normal usage, AFAIK. - basic_args = ['rtmpdump', '-q', '-r', url, '-o', filename] + basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', filename] retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)]) while retval == 2 or retval == 1: - self.to_stdout(u'\r[rtmpdump] %s bytes' % os.path.getsize(filename), skip_eol=True) - time.sleep(2.0) # This seems to be needed + prevsize = os.path.getsize(filename) + self.to_stdout(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True) + time.sleep(5.0) # This seems to be needed retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1]) + cursize = os.path.getsize(filename) + if prevsize == cursize and retval == 1: + break if retval == 0: self.to_stdout(u'\r[rtmpdump] %s bytes' % os.path.getsize(filename)) return True else: - self.trouble('ERROR: rtmpdump exited with code %d' % retval) + self.trouble('\nERROR: rtmpdump exited with code %d' % retval) return False - def _do_download(self, filename, url): + def _do_download(self, filename, url, player_url): # Attempt to download using rtmpdump if url.startswith('rtmp'): - return self._download_with_rtmpdump(filename, url) + return self._download_with_rtmpdump(filename, url, player_url) stream = None open_mode = 'wb' @@ -501,24 +537,34 @@ class FileDownloader(object): request.add_header('Range','bytes=%d-' % resume_len) open_mode = 'ab' - # Establish connection - try: - data = urllib2.urlopen(request) - except (urllib2.HTTPError, ), err: - if err.code != 416: # 416 is 'Requested range not satisfiable' - raise - # Unable to resume - data = urllib2.urlopen(basic_request) - content_length = data.info()['Content-Length'] - - if content_length is not None and long(content_length) == resume_len: - # Because the file had already been fully downloaded - self.report_file_already_downloaded(filename) - return True - else: - # Because the server didn't let us - self.report_unable_to_resume() - open_mode = 'wb' + count = 0 + retries = self.params.get('retries', 0) + while True: + # Establish connection + try: + data = urllib2.urlopen(request) + break + except (urllib2.HTTPError, ), err: + if err.code == 503: + # Retry in case of HTTP error 503 + count += 1 + if count <= retries: + self.report_retry(count, retries) + continue + if err.code != 416: # 416 is 'Requested range not satisfiable' + raise + # Unable to resume + data = urllib2.urlopen(basic_request) + content_length = data.info()['Content-Length'] + + if content_length is not None and long(content_length) == resume_len: + # Because the file had already been fully downloaded + self.report_file_already_downloaded(filename) + return True + else: + # Because the server didn't let us + self.report_unable_to_resume() + open_mode = 'wb' data_len = data.info().get('Content-length', None) data_len_str = self.format_bytes(data_len) @@ -543,7 +589,10 @@ class FileDownloader(object): except (OSError, IOError), err: self.trouble('ERROR: unable to open for writing: %s' % str(err)) return False - stream.write(data_block) + try: + stream.write(data_block) + except (IOError, OSError), err: + self.trouble('\nERROR: unable to write data: %s' % str(err)) block_size = self.best_block_size(after - before, data_block_len) # Progress message @@ -578,6 +627,16 @@ class InfoExtractor(object): title: Literal title. stitle: Simplified title. ext: Video filename extension. + format: Video format. + player_url: SWF Player URL (may be None). + + The following fields are optional. Their primary purpose is to allow + youtube-dl to serve as the backend for a video search function, such + as the one in youtube2mp3. They are only used when their respective + forced printing functions are called: + + thumbnail: Full URL to a video thumbnail image. + description: One-line video description. Subclasses of this one should re-define the _real_initialize() and _real_extract() methods, as well as the suitable() static method. @@ -624,18 +683,22 @@ class InfoExtractor(object): class YoutubeIE(InfoExtractor): """Information extractor for youtube.com.""" - _VALID_URL = r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:\.php)?)?[\?#](?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$' - _LANG_URL = r'http://uk.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' + _VALID_URL = r'^((?:http://)?(?:youtu\.be/|(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:_popup)?(?:\.php)?)?[\?#](?:.+&)?v=))))?([0-9A-Za-z_-]+)(?(1).+)?$' + _LANG_URL = r'http://www.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' - _available_formats = ['37', '22', '35', '18', '5', '17', '13', None] # listed in order of priority for -b flag + # Listed in order of quality + _available_formats = ['38', '37', '22', '45', '35', '34', '43', '18', '6', '5', '17', '13'] _video_extensions = { '13': '3gp', '17': 'mp4', '18': 'mp4', '22': 'mp4', '37': 'mp4', + '38': 'video', # You actually don't know if this will be MOV, AVI or whatever + '43': 'webm', + '45': 'webm', } @staticmethod @@ -654,6 +717,10 @@ class YoutubeIE(InfoExtractor): """Report attempt to confirm age.""" self._downloader.to_stdout(u'[youtube] Confirming age') + def report_video_webpage_download(self, video_id): + """Report attempt to download video webpage.""" + self._downloader.to_stdout(u'[youtube] %s: Downloading video webpage' % video_id) + def report_video_info_webpage_download(self, video_id): """Report attempt to download video info webpage.""" self._downloader.to_stdout(u'[youtube] %s: Downloading video info webpage' % video_id) @@ -747,73 +814,111 @@ class YoutubeIE(InfoExtractor): 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 + # Get video webpage + self.report_video_webpage_download(video_id) + request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id, None, std_headers) + try: + video_webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) + return - while True: - # Extension - video_extension = self._video_extensions.get(format_param, 'flv') + # Attempt to extract SWF player URL + mobj = re.search(r'swfConfig.*"(http://.*?watch.*?-.*?\.swf)"', video_webpage) + if mobj is not None: + player_url = mobj.group(1) + else: + player_url = None - # 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 + # Get video info + self.report_video_info_webpage_download(video_id) + for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']: + video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' + % (video_id, el_type)) 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() video_info = parse_qs(video_info_webpage) + if 'token' in video_info: + break 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 - if 'token' not in video_info: - # Attempt to see if YouTube has issued an error message - if 'reason' not in video_info: - 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(video_info['reason'][0]) - self._downloader.trouble(u'ERROR: YouTube said: %s' % reason.decode('utf-8')) - return - token = urllib.unquote_plus(video_info['token'][0]) - 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) - - # Check possible RTMP download - if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): - self.report_rtmp_download() - video_real_url = video_info['conn'][0] - - # uploader - if 'author' not in video_info: - self._downloader.trouble(u'ERROR: unable to extract uploader nickname') - return - video_uploader = urllib.unquote_plus(video_info['author'][0]) + self.report_information_extraction(video_id) + + # uploader + if 'author' not in video_info: + self._downloader.trouble(u'ERROR: unable to extract uploader nickname') + return + video_uploader = urllib.unquote_plus(video_info['author'][0]) - # title - if 'title' not in video_info: - self._downloader.trouble(u'ERROR: unable to extract video title') + # title + if 'title' not in video_info: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = urllib.unquote_plus(video_info['title'][0]) + video_title = video_title.decode('utf-8') + video_title = sanitize_title(video_title) + + # simplified title + simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) + simple_title = simple_title.strip(ur'_') + + # thumbnail image + if 'thumbnail_url' not in video_info: + self._downloader.trouble(u'WARNING: unable to extract video thumbnail') + video_thumbnail = '' + else: # don't panic if we can't find it + video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0]) + + # description + video_description = 'No description available.' + if self._downloader.params.get('forcedescription', False): + mobj = re.search(r'', video_webpage) + if mobj is not None: + video_description = mobj.group(1) + + # token + video_token = urllib.unquote_plus(video_info['token'][0]) + + # Decide which formats to download + requested_format = self._downloader.params.get('format', None) + get_video_template = 'http://www.youtube.com/get_video?video_id=%s&t=%s&eurl=&el=&ps=&asv=&fmt=%%s' % (video_id, video_token) + + if 'fmt_url_map' in video_info: + url_map = dict(tuple(pair.split('|')) for pair in video_info['fmt_url_map'][0].split(',')) + format_limit = self._downloader.params.get('format_limit', None) + if format_limit is not None and format_limit in self._available_formats: + format_list = self._available_formats[self._available_formats.index(format_limit):] + else: + format_list = self._available_formats + existing_formats = [x for x in format_list if x in url_map] + if len(existing_formats) == 0: + self._downloader.trouble(u'ERROR: no known formats available for video') return - video_title = urllib.unquote_plus(video_info['title'][0]) - video_title = video_title.decode('utf-8') - video_title = sanitize_title(video_title) + if requested_format is None: + video_url_list = [(existing_formats[0], get_video_template % existing_formats[0])] # Best quality + elif requested_format == '-1': + video_url_list = [(f, get_video_template % f) for f in existing_formats] # All formats + else: + video_url_list = [(requested_format, get_video_template % requested_format)] # Specific format - # simplified title - simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) - simple_title = simple_title.strip(ur'_') + elif 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): + self.report_rtmp_download() + video_url_list = [(None, video_info['conn'][0])] + + else: + self._downloader.trouble(u'ERROR: no fmt_url_map or conn information found in video info') + return + for format_param, video_real_url in video_url_list: + # At this point we have a new video + self._downloader.increment_downloads() + + # Extension + video_extension = self._video_extensions.get(format_param, 'flv') + + # Find the video URL in fmt_url_map or conn paramters try: # Process video information self._downloader.process_info({ @@ -823,24 +928,13 @@ class YoutubeIE(InfoExtractor): 'title': video_title, 'stitle': simple_title, 'ext': video_extension.decode('utf-8'), + 'format': (format_param is None and u'NA' or format_param.decode('utf-8')), + 'thumbnail': video_thumbnail.decode('utf-8'), + 'description': video_description.decode('utf-8'), + 'player_url': player_url, }) - - 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 + except UnavailableVideoError, err: + self._downloader.trouble(u'ERROR: unable to download video (format may not be available)') class MetacafeIE(InfoExtractor): @@ -913,6 +1007,9 @@ class MetacafeIE(InfoExtractor): self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1)) return + # At this point we have a new video + self._downloader.increment_downloads() + simple_title = mobj.group(2).decode('utf-8') video_extension = 'flv' @@ -965,10 +1062,99 @@ class MetacafeIE(InfoExtractor): 'title': video_title, 'stitle': simple_title, 'ext': video_extension.decode('utf-8'), + 'format': u'NA', + 'player_url': None, }) - except UnavailableFormatError: - self._downloader.trouble(u'ERROR: format not available for video') + except UnavailableVideoError: + self._downloader.trouble(u'ERROR: unable to download video') + + +class DailymotionIE(InfoExtractor): + """Information Extractor for Dailymotion""" + + _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + @staticmethod + def suitable(url): + return (re.match(DailymotionIE._VALID_URL, url) is not None) + + def report_download_webpage(self, video_id): + """Report webpage download.""" + self._downloader.to_stdout(u'[dailymotion] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_stdout(u'[dailymotion] %s: Extracting information' % video_id) + + def _real_initialize(self): + 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 + + # At this point we have a new video + self._downloader.increment_downloads() + video_id = mobj.group(1) + + simple_title = mobj.group(2).decode('utf-8') + video_extension = 'flv' + + # Retrieve video webpage to extract further information + request = urllib2.Request(url) + 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'(?i)addVariable\(\"video\"\s*,\s*\"([^\"]*)\"\)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract media URL') + return + mediaURL = urllib.unquote(mobj.group(1)) + # if needed add http://www.dailymotion.com/ if relative URL + + video_url = mediaURL + + # '' + mobj = re.search(r'(?im)Dailymotion\s*[\-:]\s*(.+?)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract title') + return + video_title = mobj.group(1).decode('utf-8') + video_title = sanitize_title(video_title) + + mobj = re.search(r'(?im)
.*?(.+?)
', 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'), + 'format': u'NA', + 'player_url': None, + }) + except UnavailableVideoError: + self._downloader.trouble(u'ERROR: unable to download video') class GoogleIE(InfoExtractor): """Information extractor for video.google.com.""" @@ -1000,6 +1186,8 @@ class GoogleIE(InfoExtractor): self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) return + # At this point we have a new video + self._downloader.increment_downloads() video_id = mobj.group(1) video_extension = 'mp4' @@ -1034,22 +1222,48 @@ class GoogleIE(InfoExtractor): return video_title = mobj.group(1).decode('utf-8') video_title = sanitize_title(video_title) + simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) + + # Extract video description + mobj = re.search(r'([^<]*)', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video description') + return + video_description = mobj.group(1).decode('utf-8') + if not video_description: + video_description = 'No description available.' + + # Extract video thumbnail + if self._downloader.params.get('forcethumbnail', False): + request = urllib2.Request('http://video.google.com/videosearch?q=%s+site:video.google.com&hl=en' % abs(int(video_id))) + try: + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) + return + mobj = re.search(r'', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video thumbnail') + return + video_thumbnail = mobj.group(1) + else: # we need something to pass to process_info + video_thumbnail = '' - # Google Video doesn't show uploader nicknames? - video_uploader = 'NA' 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'), + 'uploader': u'NA', 'title': video_title, - 'stitle': video_title, + 'stitle': simple_title, 'ext': video_extension.decode('utf-8'), + 'format': u'NA', + 'player_url': None, }) - except UnavailableFormatError: - self._downloader.trouble(u'ERROR: format not available for video') + except UnavailableVideoError: + self._downloader.trouble(u'ERROR: unable to download video') class PhotobucketIE(InfoExtractor): @@ -1082,6 +1296,8 @@ class PhotobucketIE(InfoExtractor): self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) return + # At this point we have a new video + self._downloader.increment_downloads() video_id = mobj.group(1) video_extension = 'flv' @@ -1111,6 +1327,7 @@ class PhotobucketIE(InfoExtractor): return video_title = mobj.group(1).decode('utf-8') video_title = sanitize_title(video_title) + simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) video_uploader = mobj.group(2).decode('utf-8') @@ -1121,11 +1338,170 @@ class PhotobucketIE(InfoExtractor): 'url': video_url.decode('utf-8'), 'uploader': video_uploader, 'title': video_title, - 'stitle': video_title, + 'stitle': simple_title, 'ext': video_extension.decode('utf-8'), + 'format': u'NA', + 'player_url': None, }) - except UnavailableFormatError: - self._downloader.trouble(u'ERROR: format not available for video') + except UnavailableVideoError: + self._downloader.trouble(u'ERROR: unable to download video') + + +class YahooIE(InfoExtractor): + """Information extractor for video.yahoo.com.""" + + # _VALID_URL matches all Yahoo! Video URLs + # _VPAGE_URL matches only the extractable '/watch/' URLs + _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?' + _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + @staticmethod + def suitable(url): + return (re.match(YahooIE._VALID_URL, url) is not None) + + def report_download_webpage(self, video_id): + """Report webpage download.""" + self._downloader.to_stdout(u'[video.yahoo] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self._downloader.to_stdout(u'[video.yahoo] %s: Extracting information' % video_id) + + def _real_initialize(self): + return + + def _real_extract(self, url, new_video=True): + # Extract ID from URL + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) + return + + # At this point we have a new video + self._downloader.increment_downloads() + video_id = mobj.group(2) + video_extension = 'flv' + + # Rewrite valid but non-extractable URLs as + # extractable English language /watch/ URLs + if re.match(self._VPAGE_URL, url) is None: + request = urllib2.Request(url) + try: + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) + return + + mobj = re.search(r'\("id", "([0-9]+)"\);', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: Unable to extract id field') + return + yahoo_id = mobj.group(1) + + mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: Unable to extract vid field') + return + yahoo_vid = mobj.group(1) + + url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id) + return self._real_extract(url, new_video=False) + + # Retrieve video webpage to extract further information + request = urllib2.Request(url) + 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 to retrieve video webpage: %s' % str(err)) + return + + # Extract uploader and title from webpage + self.report_extraction(video_id) + mobj = re.search(r'', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = mobj.group(1).decode('utf-8') + simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) + + mobj = re.search(r'

(.*)

', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video uploader') + return + video_uploader = mobj.group(1).decode('utf-8') + + # Extract video thumbnail + mobj = re.search(r'', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video thumbnail') + return + video_thumbnail = mobj.group(1).decode('utf-8') + + # Extract video description + mobj = re.search(r'', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video description') + return + video_description = mobj.group(1).decode('utf-8') + if not video_description: video_description = 'No description available.' + + # Extract video height and width + mobj = re.search(r'', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video height') + return + yv_video_height = mobj.group(1) + + mobj = re.search(r'', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract video width') + return + yv_video_width = mobj.group(1) + + # Retrieve video playlist to extract media URL + # I'm not completely sure what all these options are, but we + # seem to need most of them, otherwise the server sends a 401. + yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents + yv_bitrate = '700' # according to Wikipedia this is hard-coded + request = urllib2.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id + + '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height + + '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797') + 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 to retrieve video webpage: %s' % str(err)) + return + + # Extract media URL from playlist XML + mobj = re.search(r']+)\&' + _MORE_PAGES_INDICATOR = r'Next' + _google_ie = None + _max_google_results = 1000 + + def __init__(self, google_ie, downloader=None): + InfoExtractor.__init__(self, downloader) + self._google_ie = google_ie + + @staticmethod + def suitable(url): + return (re.match(GoogleSearchIE._VALID_QUERY, url) is not None) + + def report_download_page(self, query, pagenum): + """Report attempt to download playlist page with given number.""" + query = query.decode(preferredencoding()) + self._downloader.to_stdout(u'[video.google] query "%s": Downloading page %s' % (query, pagenum)) + + def _real_initialize(self): + self._google_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:] + query = query.encode('utf-8') + if prefix == '': + self._download_n_results(query, 1) + return + elif prefix == 'all': + self._download_n_results(query, self._max_google_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_google_results: + self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n)) + n = self._max_google_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 = mobj.group(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._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id) + return + + if re.search(self._MORE_PAGES_INDICATOR, page) is None: + for id in video_ids: + self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id) + return + + pagenum = pagenum + 1 + +class YahooSearchIE(InfoExtractor): + """Information Extractor for Yahoo! Video search queries.""" + _VALID_QUERY = r'yvsearch(\d+|all)?:[\s\S]+' + _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s' + _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"' + _MORE_PAGES_INDICATOR = r'\s*Next' + _yahoo_ie = None + _max_yahoo_results = 1000 + + def __init__(self, yahoo_ie, downloader=None): + InfoExtractor.__init__(self, downloader) + self._yahoo_ie = yahoo_ie + + @staticmethod + def suitable(url): + return (re.match(YahooSearchIE._VALID_QUERY, url) is not None) + + def report_download_page(self, query, pagenum): + """Report attempt to download playlist page with given number.""" + query = query.decode(preferredencoding()) + self._downloader.to_stdout(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum)) + + def _real_initialize(self): + self._yahoo_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:] + query = query.encode('utf-8') + if prefix == '': + self._download_n_results(query, 1) + return + elif prefix == 'all': + self._download_n_results(query, self._max_yahoo_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_yahoo_results: + self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n)) + n = self._max_yahoo_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 = mobj.group(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._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id) + return + + if re.search(self._MORE_PAGES_INDICATOR, page) is None: + for id in video_ids: + self._yahoo_ie.extract('http://video.yahoo.com/watch/%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=([^&]+).*' + _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists)\?.*?p=|user/.*?/user/)([^&]+).*' _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' + _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*' _youtube_ie = None def __init__(self, youtube_ie, downloader=None): @@ -1364,7 +1928,7 @@ class YoutubePlaylistIE(InfoExtractor): 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: + if re.search(self._MORE_PAGES_INDICATOR, page) is None: break pagenum = pagenum + 1 @@ -1504,7 +2068,7 @@ if __name__ == '__main__': # Parse command line parser = optparse.OptionParser( usage='Usage: %prog [options] url...', - version='2010.02.13', + version='2010.07.24', conflict_handler='resolve', ) @@ -1517,26 +2081,28 @@ if __name__ == '__main__': 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)') + dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)') + parser.add_option('-R', '--retries', + dest='retries', metavar='RETRIES', help='number of retries (default is 10)', default=10) authentication = optparse.OptionGroup(parser, 'Authentication Options') authentication.add_option('-u', '--username', - dest='username', metavar='UN', help='account username') + dest='username', metavar='USERNAME', help='account username') authentication.add_option('-p', '--password', - dest='password', metavar='PW', help='account password') + dest='password', metavar='PASSWORD', 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') + action='store', dest='format', metavar='FORMAT', help='video format code') 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') + video_format.add_option('--all-formats', + action='store_const', dest='format', help='download all available video formats', const='-1') + video_format.add_option('--max-quality', + action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download') parser.add_option_group(video_format) verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options') @@ -1548,6 +2114,12 @@ if __name__ == '__main__': 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) + verbosity.add_option('--get-thumbnail', + action='store_true', dest='getthumbnail', help='simulate, quiet but print thumbnail URL', default=False) + verbosity.add_option('--get-description', + action='store_true', dest='getdescription', help='simulate, quiet but print video description', default=False) + verbosity.add_option('--no-progress', + action='store_true', dest='noprogress', help='do not print progress bar', default=False) parser.add_option_group(verbosity) filesystem = optparse.OptionGroup(parser, 'Filesystem Options') @@ -1556,9 +2128,9 @@ if __name__ == '__main__': 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') + dest='outtmpl', metavar='TEMPLATE', help='output filename template') filesystem.add_option('-a', '--batch-file', - dest='batchfile', metavar='F', help='file containing URLs to download') + dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)') filesystem.add_option('-w', '--no-overwrites', action='store_true', dest='nooverwrites', help='do not overwrite files', default=False) filesystem.add_option('-c', '--continue', @@ -1566,22 +2138,22 @@ if __name__ == '__main__': 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() + if opts.batchfile == '-': + batchfd = sys.stdin + else: + batchfd = open(opts.batchfile, 'r') + batchurls = batchfd.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 - # Make sure all URLs are in our preferred encoding - for i in range(0, len(all_urls)): - all_urls[i] = unicode(all_urls[i], preferredencoding()) - # Conflicting, missing and erroneous options 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') @@ -1598,15 +2170,24 @@ if __name__ == '__main__': if numeric_limit is None: parser.error(u'invalid rate limit specified') opts.ratelimit = numeric_limit + if opts.retries is not None: + try: + opts.retries = long(opts.retries) + except (TypeError, ValueError), err: + parser.error(u'invalid retry count specified') # Information extractors youtube_ie = YoutubeIE() metacafe_ie = MetacafeIE(youtube_ie) + dailymotion_ie = DailymotionIE() youtube_pl_ie = YoutubePlaylistIE(youtube_ie) youtube_user_ie = YoutubeUserIE(youtube_ie) youtube_search_ie = YoutubeSearchIE(youtube_ie) google_ie = GoogleIE() + google_search_ie = GoogleSearchIE(google_ie) photobucket_ie = PhotobucketIE() + yahoo_ie = YahooIE() + yahoo_search_ie = YahooSearchIE(yahoo_ie) generic_ie = GenericIE() # File downloader @@ -1614,27 +2195,39 @@ if __name__ == '__main__': 'usenetrc': opts.usenetrc, 'username': opts.username, 'password': opts.password, - 'quiet': (opts.quiet or opts.geturl or opts.gettitle), + 'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription), 'forceurl': opts.geturl, 'forcetitle': opts.gettitle, - 'simulate': (opts.simulate or opts.geturl or opts.gettitle), + 'forcethumbnail': opts.getthumbnail, + 'forcedescription': opts.getdescription, + 'simulate': (opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription), 'format': opts.format, + 'format_limit': opts.format_limit, 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding())) + or (opts.format == '-1' and opts.usetitle and u'%(stitle)s-%(id)s-%(format)s.%(ext)s') + or (opts.format == '-1' and opts.useliteral and u'%(title)s-%(id)s-%(format)s.%(ext)s') + or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s') 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, + 'retries': opts.retries, 'continuedl': opts.continue_dl, + 'noprogress': opts.noprogress, }) fd.add_info_extractor(youtube_search_ie) fd.add_info_extractor(youtube_pl_ie) fd.add_info_extractor(youtube_user_ie) fd.add_info_extractor(metacafe_ie) + fd.add_info_extractor(dailymotion_ie) fd.add_info_extractor(youtube_ie) fd.add_info_extractor(google_ie) + fd.add_info_extractor(google_search_ie) fd.add_info_extractor(photobucket_ie) + fd.add_info_extractor(yahoo_ie) + fd.add_info_extractor(yahoo_search_ie) # This must come last since it's the # fallback if none of the others work