X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/417b7ac0240ea38c1914a7c00575e8f225069a73..ef953f620ad04840bf1ce703610fe5871467a22f:/youtube-dl diff --git a/youtube-dl b/youtube-dl index 9e28621..01a61ba 100755 --- a/youtube-dl +++ b/youtube-dl @@ -27,7 +27,7 @@ except ImportError: from cgi import parse_qs std_headers = { - 'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.1.2) Gecko/20090729 Firefox/3.5.2', + 'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.2) Gecko/20100115 Firefox/3.6', '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', @@ -51,6 +51,61 @@ def preferredencoding(): yield pref return yield_preferredencoding().next() +def htmlentity_transform(matchobj): + """Transforms an HTML entity to a Unicode character. + + This function receives a match object and is intended to be used with + the re.sub() function. + """ + 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 sanitize_title(utitle): + """Sanitizes a video title so it could be used as part of a filename.""" + utitle = re.sub(ur'(?u)&(.+?);', htmlentity_transform, utitle) + return utitle.replace(unicode(os.sep), u'%') + +def sanitize_open(filename, open_mode): + """Try to open the given filename, and slightly tweak it if this fails. + + Attempts to open the given filename. If this fails, it tries to change + the filename slightly, step by step, until it's either able to open it + or it fails and raises a final exception, like the standard open() + function. + + 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) + + # An exception here should be caught in the caller + stream = open(filename, open_mode) + return (stream, filename) + + class DownloadError(Exception): """Download Error exception. @@ -138,19 +193,23 @@ class FileDownloader(object): 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 @@ -247,11 +306,15 @@ 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.""" @@ -289,10 +352,12 @@ 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) @@ -300,9 +365,16 @@ 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.""" @@ -310,7 +382,10 @@ 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 process_info(self, info_dict): """Process a single dictionary returned by an InfoExtractor.""" @@ -319,21 +394,26 @@ 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 # Forced printings if self.params.get('forcetitle', False): - print info_dict['title'].encode(preferredencoding()) + print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace') if self.params.get('forceurl', False): - print info_dict['url'].encode(preferredencoding()) + 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)) @@ -348,7 +428,7 @@ 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 except (urllib2.URLError, httplib.HTTPException, socket.error), err: @@ -400,7 +480,7 @@ 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 @@ -413,23 +493,27 @@ 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' @@ -448,24 +532,35 @@ 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) + self._num_downloads += 1 + 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) @@ -485,12 +580,16 @@ class FileDownloader(object): # Open file just in time if stream is None: try: - stream = open(filename, open_mode) + (stream, filename) = sanitize_open(filename, open_mode) self.report_destination(filename) + self._num_downloads += 1 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 @@ -525,6 +624,16 @@ 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. @@ -571,47 +680,26 @@ 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).+)?$' + _VALID_URL = r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:\.php)?)?[\?#](?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$' _LANG_URL = r'http://uk.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' _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 + _available_formats = ['37', '22', '35', '18', '34', '5', '17', '13', None] # listed in order of priority for -b flag _video_extensions = { '13': '3gp', '17': 'mp4', '18': 'mp4', '22': 'mp4', '37': 'mp4', + '43': 'webm', + '45': 'webm', } @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._downloader.to_stdout(u'[youtube] Setting language') @@ -624,6 +712,10 @@ 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) @@ -719,6 +811,7 @@ class YoutubeIE(InfoExtractor): # Downloader parameters best_quality = False + all_formats = False format_param = None quality_index = 0 if self._downloader is not None: @@ -727,21 +820,44 @@ class YoutubeIE(InfoExtractor): if format_param == '0': format_param = self._available_formats[quality_index] best_quality = True + elif format_param == '-1': + format_param = self._available_formats[quality_index] + all_formats = 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) + # 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: - self.report_video_info_webpage_download(video_id) - video_info_webpage = urllib2.urlopen(request).read() - video_info = parse_qs(video_info_webpage) + video_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)) + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) return + + # 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 + 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: + 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 @@ -778,13 +894,26 @@ class YoutubeIE(InfoExtractor): return video_title = urllib.unquote_plus(video_info['title'][0]) 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'%') + 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) + try: # Process video information self._downloader.process_info({ @@ -794,19 +923,32 @@ 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, }) + if all_formats: + quality_index += 1 + if quality_index == len(self._available_formats): + # None left to get + return + else: + format_param = self._available_formats[quality_index] + continue return except UnavailableFormatError, err: - if best_quality: - if quality_index == len(self._available_formats) - 1: + if best_quality or all_formats: + quality_index += 1 + if quality_index == len(self._available_formats): # I don't ever expect this to happen - self._downloader.trouble(u'ERROR: no known formats available for video') + if not all_formats: + 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: @@ -919,6 +1061,7 @@ class MetacafeIE(InfoExtractor): 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'(?ms)By:\s*(.+?)<', webpage) if mobj is None: @@ -935,6 +1078,8 @@ 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') @@ -943,7 +1088,7 @@ class MetacafeIE(InfoExtractor): class GoogleIE(InfoExtractor): """Information extractor for video.google.com.""" - _VALID_URL = r'(?:http://)?video\.google\.com/videoplay\?docid=([^\&]+).*' + _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*' def __init__(self, downloader=None): InfoExtractor.__init__(self, downloader) @@ -975,7 +1120,7 @@ class GoogleIE(InfoExtractor): video_extension = 'mp4' # Retrieve video webpage to extract further information - request = urllib2.Request('http://video.google.com/videoplay?docid=%s' % video_id) + request = urllib2.Request('http://video.google.com/videoplay?docid=%s&hl=en&oe=utf-8' % video_id) try: self.report_download_webpage(video_id) webpage = urllib2.urlopen(request).read() @@ -985,7 +1130,10 @@ class GoogleIE(InfoExtractor): # Extract URL, uploader, and title from webpage self.report_extraction(video_id) - mobj = re.search(r"download_url:'(.*)'", webpage) + mobj = re.search(r"download_url:'([^']+)'", webpage) + if mobj is None: + video_extension = 'flv' + mobj = re.search(r"(?i)videoUrl\\x3d(.+?)\\x26", webpage) if mobj is None: self._downloader.trouble(u'ERROR: unable to extract media URL') return @@ -1000,19 +1148,46 @@ class GoogleIE(InfoExtractor): self._downloader.trouble(u'ERROR: unable to extract title') 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 = 'uploader' 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.decode('utf-8'), - 'stitle': video_title.decode('utf-8'), + 'uploader': u'NA', + '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') @@ -1076,6 +1251,8 @@ class PhotobucketIE(InfoExtractor): self._downloader.trouble(u'ERROR: unable to extract title') 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') @@ -1084,10 +1261,263 @@ class PhotobucketIE(InfoExtractor): 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.decode('utf-8'), - 'stitle': video_title.decode('utf-8'), + 'uploader': video_uploader, + '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') + + +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): + # 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 + + 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) + + # 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'(.*)', 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) + simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) + + # video uploader is domain name + mobj = re.match(r'(?:https?://)?([^/]*)/.*', url) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract title') + return + video_uploader = mobj.group(1).decode('utf-8') + + try: + # Process video information + self._downloader.process_info({ + 'id': video_id.decode('utf-8'), + 'url': video_url.decode('utf-8'), + 'uploader': video_uploader, + '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') @@ -1112,6 +1542,7 @@ class YoutubeSearchIE(InfoExtractor): 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'[youtube] query "%s": Downloading page %s' % (query, pagenum)) def _real_initialize(self): @@ -1125,6 +1556,7 @@ class YoutubeSearchIE(InfoExtractor): prefix, query = query.split(':') prefix = prefix[8:] + query = query.encode('utf-8') if prefix == '': self._download_n_results(query, 1) return @@ -1182,13 +1614,195 @@ class YoutubeSearchIE(InfoExtractor): pagenum = pagenum + 1 +class GoogleSearchIE(InfoExtractor): + """Information Extractor for Google Video search queries.""" + _VALID_QUERY = r'gvsearch(\d+|all)?:[\s\S]+' + _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en' + _VIDEO_INDICATOR = r'videoplay\?docid=([^\&>]+)\&' + _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): @@ -1234,7 +1848,7 @@ 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 @@ -1374,7 +1988,7 @@ if __name__ == '__main__': # Parse command line parser = optparse.OptionParser( usage='Usage: %prog [options] url...', - version='2010.01.19', + version='2010.06.06', conflict_handler='resolve', ) @@ -1388,6 +2002,8 @@ if __name__ == '__main__': 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('-R', '--retries', + dest='retries', metavar='T', help='number of retries (default is 10)', default=10) authentication = optparse.OptionGroup(parser, 'Authentication Options') authentication.add_option('-u', '--username', @@ -1407,6 +2023,8 @@ if __name__ == '__main__': 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') parser.add_option_group(video_format) verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options') @@ -1418,6 +2036,12 @@ 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') @@ -1428,7 +2052,7 @@ if __name__ == '__main__': 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') + dest='batchfile', metavar='F', 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', @@ -1436,12 +2060,16 @@ 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: @@ -1464,6 +2092,11 @@ 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() @@ -1472,26 +2105,37 @@ if __name__ == '__main__': 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 fd = FileDownloader({ '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, '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) @@ -1499,7 +2143,14 @@ if __name__ == '__main__': fd.add_info_extractor(metacafe_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 + fd.add_info_extractor(generic_ie) # Update version if opts.update_self: