X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/b4c12b5580c7412a055e109387d704425557755b..187e6306160793cab151b129f35dbcf432ec6ca8:/youtube-dl?ds=inline diff --git a/youtube-dl b/youtube-dl index 5fd331e..24722d2 100755 --- a/youtube-dl +++ b/youtube-dl @@ -4,6 +4,7 @@ # Author: Danny Colligan # Author: Benjamin Johnson # License: Public domain code +import cookielib import htmlentitydefs import httplib import locale @@ -27,7 +28,7 @@ except ImportError: from cgi import parse_qs std_headers = { - 'User-Agent': 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.7) Gecko/20100720 Firefox/3.6.7', + 'User-Agent': 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.12) Gecko/20101028 Firefox/3.6.12', 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7', 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', 'Accept-Language': 'en-us,en;q=0.5', @@ -35,6 +36,21 @@ std_headers = { simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii') +month_name_to_number = { + 'January': '01', + 'February': '02', + 'March': '03', + 'April': '04', + 'May': '05', + 'June': '06', + 'July': '07', + 'August': '08', + 'September': '09', + 'October': '10', + 'November': '11', + 'December': '12', +} + def preferredencoding(): """Get preferred encoding. @@ -94,6 +110,9 @@ def sanitize_open(filename, open_mode): """ try: if filename == u'-': + if sys.platform == 'win32': + import msvcrt + msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY) return (sys.stdout, filename) stream = open(filename, open_mode) return (stream, filename) @@ -181,22 +200,27 @@ class FileDownloader(object): Available options: - username: Username for authentication purposes. - password: Password for authentication purposes. - usenetrc: Use netrc for authentication instead. - quiet: Do not print messages to stdout. - forceurl: Force printing final URL. - forcetitle: Force printing title. - simulate: Do not download the video files. - format: Video format code. - 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. + username: Username for authentication purposes. + password: Password for authentication purposes. + usenetrc: Use netrc for authentication instead. + quiet: Do not print messages to stdout. + forceurl: Force printing final URL. + forcetitle: Force printing title. + forcethumbnail: Force printing thumbnail URL. + forcedescription: Force printing description. + 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 5xx + continuedl: Try to continue downloads if possible. + noprogress: Do not print the progress bar. + playliststart: Playlist item to start at. + playlistend: Playlist item to end at. + logtostderr: Log messages to stderr instead of stdout. """ params = None @@ -204,6 +228,7 @@ class FileDownloader(object): _pps = [] _download_retcode = None _num_downloads = None + _screen_file = None def __init__(self, params): """Create a FileDownloader object with the given options.""" @@ -211,6 +236,7 @@ class FileDownloader(object): self._pps = [] self._download_retcode = 0 self._num_downloads = 0 + self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)] self.params = params @staticmethod @@ -287,16 +313,6 @@ class FileDownloader(object): multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower()) return long(round(number * multiplier)) - @staticmethod - def verify_url(url): - """Verify a URL is valid and data could be downloaded. Return real data URL.""" - request = urllib2.Request(url, None, std_headers) - data = urllib2.urlopen(request) - data.read(1) - url = data.geturl() - data.close() - return url - def add_info_extractor(self, ie): """Add an InfoExtractor object to the end of the list.""" self._ies.append(ie) @@ -307,12 +323,13 @@ class FileDownloader(object): self._pps.append(pp) pp.set_downloader(self) - def to_stdout(self, message, skip_eol=False, ignore_encoding_errors=False): + def to_screen(self, message, skip_eol=False, ignore_encoding_errors=False): """Print message to stdout if not in quiet mode.""" try: if not self.params.get('quiet', False): - print (u'%s%s' % (message, [u'\n', u''][skip_eol])).encode(preferredencoding()), - sys.stdout.flush() + terminator = [u'\n', u''][skip_eol] + print >>self._screen_file, (u'%s%s' % (message, terminator)).encode(preferredencoding()), + self._screen_file.flush() except (UnicodeEncodeError), err: if not ignore_encoding_errors: raise @@ -353,40 +370,40 @@ class FileDownloader(object): def report_destination(self, filename): """Report destination filename.""" - self.to_stdout(u'[download] Destination: %s' % filename, ignore_encoding_errors=True) + self.to_screen(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' % + self.to_screen(u'\r[download] %s of %s at %s ETA %s' % (percent_str, data_len_str, speed_str, eta_str), skip_eol=True) def report_resuming_byte(self, resume_len): - """Report attemtp to resume at given byte.""" - self.to_stdout(u'[download] Resuming download at byte %s' % resume_len) + """Report attempt to resume at given byte.""" + self.to_screen(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)) + """Report retry in case of HTTP error 5xx""" + self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries)) def report_file_already_downloaded(self, file_name): """Report file has already been fully downloaded.""" try: - self.to_stdout(u'[download] %s has already been downloaded' % file_name) + self.to_screen(u'[download] %s has already been downloaded' % file_name) except (UnicodeEncodeError), err: - self.to_stdout(u'[download] The file has already been downloaded') + self.to_screen(u'[download] The file has already been downloaded') def report_unable_to_resume(self): """Report it was impossible to resume download.""" - self.to_stdout(u'[download] Unable to resume') + self.to_screen(u'[download] Unable to resume') def report_finish(self): """Report download finished.""" if self.params.get('noprogress', False): - self.to_stdout(u'[download] Download completed') + self.to_screen(u'[download] Download completed') else: - self.to_stdout(u'') + self.to_screen(u'') def increment_downloads(self): """Increment the ordinal that assigns a number to each file.""" @@ -396,13 +413,6 @@ class FileDownloader(object): """Process a single dictionary returned by an InfoExtractor.""" # Do nothing else if in simulate mode if self.params.get('simulate', False): - # Verify URL if it's an HTTP one - if info_dict['url'].startswith('http'): - try: - self.verify_url(info_dict['url'].encode('utf-8')).decode('utf-8') - except (OSError, IOError, urllib2.URLError, httplib.HTTPException, socket.error), err: - raise UnavailableVideoError - # Forced printings if self.params.get('forcetitle', False): print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace') @@ -418,18 +428,19 @@ class FileDownloader(object): try: template_dict = dict(info_dict) template_dict['epoch'] = unicode(long(time.time())) - template_dict['ord'] = unicode('%05d' % self._num_downloads) + template_dict['autonumber'] = 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)) + self.trouble(u'ERROR: invalid system charset or erroneous output template') + return if self.params.get('nooverwrites', False) and os.path.exists(filename): - self.to_stderr(u'WARNING: file exists: %s; skipping' % filename) + self.to_stderr(u'WARNING: file exists and will be skipped') return try: self.pmkdir(filename) except (OSError, IOError), err: - self.trouble('ERROR: unable to create directories: %s' % str(err)) + self.trouble(u'ERROR: unable to create directories: %s' % str(err)) return try: @@ -437,17 +448,17 @@ class FileDownloader(object): except (OSError, IOError), err: raise UnavailableVideoError except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self.trouble('ERROR: unable to download video data: %s' % str(err)) + self.trouble(u'ERROR: unable to download video data: %s' % str(err)) return except (ContentTooShortError, ), err: - self.trouble('ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded)) + self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded)) return if success: try: self.post_process(filename, info_dict) except (PostProcessingError), err: - self.trouble('ERROR: postprocessing: %s' % str(err)) + self.trouble(u'ERROR: postprocessing: %s' % str(err)) return def download(self, url_list): @@ -472,7 +483,7 @@ class FileDownloader(object): break if not suitable_found: - self.trouble('ERROR: no suitable InfoExtractor: %s' % url) + self.trouble(u'ERROR: no suitable InfoExtractor: %s' % url) return self._download_retcode @@ -502,17 +513,17 @@ class FileDownloader(object): retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)]) while retval == 2 or retval == 1: prevsize = os.path.getsize(filename) - self.to_stdout(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True) + self.to_screen(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)) + self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(filename)) return True else: - self.trouble('\nERROR: rtmpdump exited with code %d' % retval) + self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval) return False def _do_download(self, filename, url, player_url): @@ -539,32 +550,50 @@ class FileDownloader(object): count = 0 retries = self.params.get('retries', 0) - while True: + while count <= retries: # 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' + if (err.code < 500 or err.code >= 600) and err.code != 416: + # Unexpected HTTP error 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' + elif err.code == 416: + # Unable to resume (requested range not satisfiable) + try: + # Open the connection again without the range header + data = urllib2.urlopen(basic_request) + content_length = data.info()['Content-Length'] + except (urllib2.HTTPError, ), err: + if err.code < 500 or err.code >= 600: + raise + else: + # Examine the reported length + if (content_length is not None and + (resume_len - 100 < long(content_length) < resume_len + 100)): + # The file had already been fully downloaded. + # Explanation to the above condition: in issue #175 it was revealed that + # YouTube sometimes adds or removes a few bytes from the end of the file, + # changing the file size slightly and causing problems for some users. So + # I decided to implement a suggested change and consider the file + # completely downloaded if the file size differs less than 100 bytes from + # the one in the hard drive. + self.report_file_already_downloaded(filename) + return True + else: + # The length does not match, we start the download over + self.report_unable_to_resume() + open_mode = 'wb' + break + # Retry + count += 1 + if count <= retries: + self.report_retry(count, retries) + + if count > retries: + self.trouble(u'ERROR: giving up after %s retries' % retries) + return False data_len = data.info().get('Content-length', None) data_len_str = self.format_bytes(data_len) @@ -587,12 +616,13 @@ class FileDownloader(object): (stream, filename) = sanitize_open(filename, open_mode) self.report_destination(filename) except (OSError, IOError), err: - self.trouble('ERROR: unable to open for writing: %s' % str(err)) + self.trouble(u'ERROR: unable to open for writing: %s' % str(err)) return False try: stream.write(data_block) except (IOError, OSError), err: - self.trouble('\nERROR: unable to write data: %s' % str(err)) + self.trouble(u'\nERROR: unable to write data: %s' % str(err)) + return False block_size = self.best_block_size(after - before, data_block_len) # Progress message @@ -683,9 +713,9 @@ class InfoExtractor(object): class YoutubeIE(InfoExtractor): """Information extractor for youtube.com.""" - _VALID_URL = r'^((?:http://)?(?:youtu\.be/|(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:_popup)?(?:\.php)?)?[\?#](?:.+&)?v=))))?([0-9A-Za-z_-]+)(?(1).+)?$' + _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/(?:(?:v/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))))?([0-9A-Za-z_-]+)(?(1).+)?$' _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' + _LOGIN_URL = 'https://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' # Listed in order of quality @@ -707,35 +737,35 @@ class YoutubeIE(InfoExtractor): def report_lang(self): """Report attempt to set language.""" - self._downloader.to_stdout(u'[youtube] Setting language') + self._downloader.to_screen(u'[youtube] Setting language') def report_login(self): """Report attempt to log in.""" - self._downloader.to_stdout(u'[youtube] Logging in') + self._downloader.to_screen(u'[youtube] Logging in') def report_age_confirmation(self): """Report attempt to confirm age.""" - self._downloader.to_stdout(u'[youtube] Confirming age') + self._downloader.to_screen(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) + self._downloader.to_screen(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) + self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id) def report_information_extraction(self, video_id): """Report attempt to extract video information.""" - self._downloader.to_stdout(u'[youtube] %s: Extracting video information' % video_id) + self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id) def report_unavailable_format(self, video_id, format): """Report extracted video URL.""" - self._downloader.to_stdout(u'[youtube] %s: Format %s not available' % (video_id, format)) + self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format)) def report_rtmp_download(self): """Indicate the download will use the RTMP protocol.""" - self._downloader.to_stdout(u'[youtube] RTMP download detected') + self._downloader.to_screen(u'[youtube] RTMP download detected') def _real_initialize(self): if self._downloader is None: @@ -816,7 +846,7 @@ class YoutubeIE(InfoExtractor): # 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) + request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id, None, std_headers) try: video_webpage = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: @@ -824,9 +854,9 @@ class YoutubeIE(InfoExtractor): return # Attempt to extract SWF player URL - mobj = re.search(r'swfConfig.*"(http://.*?watch.*?-.*?\.swf)"', video_webpage) + mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage) if mobj is not None: - player_url = mobj.group(1) + player_url = re.sub(r'\\(.)', r'\1', mobj.group(1)) else: player_url = None @@ -844,6 +874,14 @@ class YoutubeIE(InfoExtractor): except (urllib2.URLError, httplib.HTTPException, socket.error), err: self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err)) return + if 'token' not in video_info: + if 'reason' in video_info: + self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0].decode('utf-8')) + else: + self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason') + return + + # Start extracting information self.report_information_extraction(video_id) # uploader @@ -871,6 +909,23 @@ class YoutubeIE(InfoExtractor): else: # don't panic if we can't find it video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0]) + # upload date + upload_date = u'NA' + mobj = re.search(r'id="eow-date".*?>(.*?)', video_webpage, re.DOTALL) + if mobj is not None: + try: + if ',' in mobj.group(1): + # Month Day, Year + m, d, y = mobj.group(1).replace(',', '').split() + else: + # Day Month Year, we'll suppose + d, m, y = mobj.group(1).split() + m = month_name_to_number[m] + d = '%02d' % (long(d)) + upload_date = '%s%s%s' % (y, m, d) + except: + upload_date = u'NA' + # description video_description = 'No description available.' if self._downloader.params.get('forcedescription', False): @@ -878,7 +933,13 @@ class YoutubeIE(InfoExtractor): 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) @@ -890,19 +951,17 @@ class YoutubeIE(InfoExtractor): if len(existing_formats) == 0: self._downloader.trouble(u'ERROR: no known formats available for video') return - requested_format = self._downloader.params.get('format', None) if requested_format is None: - video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality + video_url_list = [(existing_formats[0], get_video_template % existing_formats[0])] # Best quality elif requested_format == '-1': - video_url_list = url_map.items() # All formats + video_url_list = [(f, get_video_template % f) for f in existing_formats] # All formats else: - if requested_format not in existing_formats: - self._downloader.trouble(u'ERROR: format not available for video') - return - video_url_list = [(requested_format, url_map[requested_format])] # Specific format + video_url_list = [(requested_format, get_video_template % requested_format)] # Specific format + 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 @@ -921,6 +980,7 @@ class YoutubeIE(InfoExtractor): 'id': video_id.decode('utf-8'), 'url': video_real_url.decode('utf-8'), 'uploader': video_uploader.decode('utf-8'), + 'upload_date': upload_date, 'title': video_title, 'stitle': simple_title, 'ext': video_extension.decode('utf-8'), @@ -930,7 +990,7 @@ class YoutubeIE(InfoExtractor): 'player_url': player_url, }) except UnavailableVideoError, err: - self._downloader.trouble(u'ERROR: unable to download video') + self._downloader.trouble(u'ERROR: unable to download video (format may not be available)') class MetacafeIE(InfoExtractor): @@ -951,19 +1011,19 @@ class MetacafeIE(InfoExtractor): def report_disclaimer(self): """Report disclaimer retrieval.""" - self._downloader.to_stdout(u'[metacafe] Retrieving disclaimer') + self._downloader.to_screen(u'[metacafe] Retrieving disclaimer') def report_age_confirmation(self): """Report attempt to confirm age.""" - self._downloader.to_stdout(u'[metacafe] Confirming age') + self._downloader.to_screen(u'[metacafe] Confirming age') def report_download_webpage(self, video_id): """Report webpage download.""" - self._downloader.to_stdout(u'[metacafe] %s: Downloading webpage' % video_id) + self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id) def report_extraction(self, video_id): """Report information extraction.""" - self._downloader.to_stdout(u'[metacafe] %s: Extracting information' % video_id) + self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id) def _real_initialize(self): # Retrieve disclaimer @@ -1007,7 +1067,6 @@ class MetacafeIE(InfoExtractor): self._downloader.increment_downloads() simple_title = mobj.group(2).decode('utf-8') - video_extension = 'flv' # Retrieve video webpage to extract further information request = urllib2.Request('http://www.metacafe.com/watch/%s/' % video_id) @@ -1021,20 +1080,33 @@ class MetacafeIE(InfoExtractor): # Extract URL, uploader and title from webpage self.report_extraction(video_id) mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage) - if mobj is None: - self._downloader.trouble(u'ERROR: unable to extract media URL') - return - mediaURL = urllib.unquote(mobj.group(1)) - - #mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage) - #if mobj is None: - # self._downloader.trouble(u'ERROR: unable to extract gdaKey') - # return - #gdaKey = mobj.group(1) - # - #video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) - - video_url = mediaURL + if mobj is not None: + mediaURL = urllib.unquote(mobj.group(1)) + video_extension = mediaURL[-3:] + + # Extract gdaKey if available + mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage) + if mobj is None: + video_url = mediaURL + else: + gdaKey = mobj.group(1) + video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) + else: + mobj = re.search(r' name="flashvars" value="(.*?)"', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract media URL') + return + vardict = parse_qs(mobj.group(1)) + if 'mediaData' not in vardict: + self._downloader.trouble(u'ERROR: unable to extract media URL') + return + mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0]) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract media URL') + return + mediaURL = mobj.group(1).replace('\\/', '/') + video_extension = mediaURL[-3:] + video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2)) mobj = re.search(r'(?im)