X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/a516d4529b9137e9f0ecb83191bc3da8a35e6626..98fc143f81b2d152abc11b5eb782892031f37a8c:/youtube-dl diff --git a/youtube-dl b/youtube-dl index 48c13b7..a8e3bd3 100755 --- a/youtube-dl +++ b/youtube-dl @@ -3,7 +3,10 @@ # Author: Ricardo Garcia Gonzalez # Author: Danny Colligan # Author: Benjamin Johnson +# Author: Vasyl' Vavrychuk # License: Public domain code +import cookielib +import datetime import htmlentitydefs import httplib import locale @@ -27,7 +30,7 @@ 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', @@ -94,6 +97,9 @@ 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) @@ -105,7 +111,6 @@ def sanitize_open(filename, open_mode): stream = open(filename, open_mode) return (stream, filename) - class DownloadError(Exception): """Download Error exception. @@ -181,22 +186,27 @@ 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 +214,7 @@ 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 +222,7 @@ 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 @@ -223,6 +235,13 @@ class FileDownloader(object): if not os.path.exists(dir): os.mkdir(dir) + @staticmethod + def temp_name(filename): + """Returns a temporary filename for the given filename.""" + if filename == u'-' or (os.path.exists(filename) and not os.path.isfile(filename)): + return filename + return filename + u'.part' + @staticmethod def format_bytes(bytes): if bytes is None: @@ -287,16 +306,6 @@ 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 +316,13 @@ 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 @@ -350,43 +360,51 @@ class FileDownloader(object): speed = float(byte_counter) / elapsed if speed > rate_limit: time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit) + + def try_rename(self, old_filename, new_filename): + try: + if old_filename == new_filename: + return + os.rename(old_filename, new_filename) + except (IOError, OSError), err: + self.trouble(u'ERROR: unable to rename file') 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 +414,6 @@ 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 +429,19 @@ 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 +449,17 @@ 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 +484,7 @@ 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 @@ -487,6 +499,7 @@ class FileDownloader(object): def _download_with_rtmpdump(self, filename, url, player_url): self.report_destination(filename) + tmpfilename = self.temp_name(filename) # Check for rtmpdump first try: @@ -498,36 +511,43 @@ 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'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', filename] + basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', tmpfilename] 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) + prevsize = os.path.getsize(tmpfilename) + 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) + cursize = os.path.getsize(tmpfilename) 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(tmpfilename)) + self.try_rename(tmpfilename, 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): + # Check file already present + if self.params.get('continuedl', False) and os.path.isfile(filename): + self.report_file_already_downloaded(filename) + return True + # Attempt to download using rtmpdump if url.startswith('rtmp'): return self._download_with_rtmpdump(filename, url, player_url) + tmpfilename = self.temp_name(filename) stream = None open_mode = 'wb' basic_request = urllib2.Request(url, None, std_headers) request = urllib2.Request(url, None, std_headers) # Establish possible resume length - if os.path.isfile(filename): - resume_len = os.path.getsize(filename) + if os.path.isfile(tmpfilename): + resume_len = os.path.getsize(tmpfilename) else: resume_len = 0 @@ -539,32 +559,51 @@ 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) + self.try_rename(tmpfilename, 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) @@ -584,15 +623,16 @@ class FileDownloader(object): # Open file just in time if stream is None: try: - (stream, filename) = sanitize_open(filename, open_mode) + (stream, tmpfilename) = sanitize_open(tmpfilename, 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 @@ -604,9 +644,11 @@ class FileDownloader(object): # Apply rate limit self.slow_down(start, byte_counter) + stream.close() self.report_finish() if data_len is not None and str(byte_counter) != data_len: raise ContentTooShortError(byte_counter, long(data_len)) + self.try_rename(tmpfilename, filename) return True class InfoExtractor(object): @@ -683,9 +725,9 @@ 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 +749,35 @@ 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 +858,7 @@ 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 +866,9 @@ 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 +886,14 @@ 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 +921,18 @@ 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: + upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) + format_expressions = ['%d %B %Y', '%B %d %Y'] + for expression in format_expressions: + try: + upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d') + except: + pass + # description video_description = 'No description available.' if self._downloader.params.get('forcedescription', False): @@ -882,7 +944,7 @@ class YoutubeIE(InfoExtractor): video_token = urllib.unquote_plus(video_info['token'][0]) # Decide which formats to download - requested_format = self._downloader.params.get('format', None) + req_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: @@ -896,12 +958,15 @@ class YoutubeIE(InfoExtractor): if len(existing_formats) == 0: self._downloader.trouble(u'ERROR: no known formats available for video') return - 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 + if req_format is None: + video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality + elif req_format == '-1': + video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats else: - video_url_list = [(requested_format, get_video_template % requested_format)] # Specific format + if req_format in url_map: + video_url_list = [(req_format, url_map[req_format])] # Specific format + else: + video_url_list = [(req_format, get_video_template % req_format)] # Specific format elif 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): self.report_rtmp_download() @@ -925,6 +990,7 @@ 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'), @@ -955,19 +1021,19 @@ 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 @@ -1011,7 +1077,6 @@ 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) @@ -1025,20 +1090,33 @@ 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)(.*) - Video', webpage) if mobj is None: @@ -1059,6 +1137,7 @@ class MetacafeIE(InfoExtractor): 'id': video_id.decode('utf-8'), 'url': video_url.decode('utf-8'), 'uploader': video_uploader.decode('utf-8'), + 'upload_date': u'NA', 'title': video_title, 'stitle': simple_title, 'ext': video_extension.decode('utf-8'), @@ -1083,11 +1162,11 @@ class DailymotionIE(InfoExtractor): def report_download_webpage(self, video_id): """Report webpage download.""" - self._downloader.to_stdout(u'[dailymotion] %s: Downloading webpage' % video_id) + self._downloader.to_screen(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) + self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id) def _real_initialize(self): return @@ -1135,7 +1214,7 @@ class DailymotionIE(InfoExtractor): video_title = mobj.group(1).decode('utf-8') video_title = sanitize_title(video_title) - mobj = re.search(r'(?im)
.*?(.+?)
', webpage) + mobj = re.search(r'(?im)
.*?(.+?)', webpage) if mobj is None: self._downloader.trouble(u'ERROR: unable to extract uploader nickname') return @@ -1147,6 +1226,7 @@ class DailymotionIE(InfoExtractor): 'id': video_id.decode('utf-8'), 'url': video_url.decode('utf-8'), 'uploader': video_uploader.decode('utf-8'), + 'upload_date': u'NA', 'title': video_title, 'stitle': simple_title, 'ext': video_extension.decode('utf-8'), @@ -1170,11 +1250,11 @@ class GoogleIE(InfoExtractor): def report_download_webpage(self, video_id): """Report webpage download.""" - self._downloader.to_stdout(u'[video.google] %s: Downloading webpage' % video_id) + self._downloader.to_screen(u'[video.google] %s: Downloading webpage' % video_id) def report_extraction(self, video_id): """Report information extraction.""" - self._downloader.to_stdout(u'[video.google] %s: Extracting information' % video_id) + self._downloader.to_screen(u'[video.google] %s: Extracting information' % video_id) def _real_initialize(self): return @@ -1256,6 +1336,7 @@ class GoogleIE(InfoExtractor): 'id': video_id.decode('utf-8'), 'url': video_url.decode('utf-8'), 'uploader': u'NA', + 'upload_date': u'NA', 'title': video_title, 'stitle': simple_title, 'ext': video_extension.decode('utf-8'), @@ -1280,11 +1361,11 @@ class PhotobucketIE(InfoExtractor): def report_download_webpage(self, video_id): """Report webpage download.""" - self._downloader.to_stdout(u'[photobucket] %s: Downloading webpage' % video_id) + self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id) def report_extraction(self, video_id): """Report information extraction.""" - self._downloader.to_stdout(u'[photobucket] %s: Extracting information' % video_id) + self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id) def _real_initialize(self): return @@ -1337,6 +1418,7 @@ class PhotobucketIE(InfoExtractor): 'id': video_id.decode('utf-8'), 'url': video_url.decode('utf-8'), 'uploader': video_uploader, + 'upload_date': u'NA', 'title': video_title, 'stitle': simple_title, 'ext': video_extension.decode('utf-8'), @@ -1364,11 +1446,11 @@ class YahooIE(InfoExtractor): def report_download_webpage(self, video_id): """Report webpage download.""" - self._downloader.to_stdout(u'[video.yahoo] %s: Downloading webpage' % video_id) + self._downloader.to_screen(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) + self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id) def _real_initialize(self): return @@ -1491,6 +1573,7 @@ class YahooIE(InfoExtractor): 'id': video_id.decode('utf-8'), 'url': video_url, 'uploader': video_uploader, + 'upload_date': u'NA', 'title': video_title, 'stitle': simple_title, 'ext': video_extension.decode('utf-8'), @@ -1516,12 +1599,12 @@ class GenericIE(InfoExtractor): def report_download_webpage(self, video_id): """Report webpage download.""" - self._downloader.to_stdout(u'WARNING: Falling back on generic information extractor.') - self._downloader.to_stdout(u'[generic] %s: Downloading webpage' % video_id) + self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.') + self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id) def report_extraction(self, video_id): """Report information extraction.""" - self._downloader.to_stdout(u'[generic] %s: Extracting information' % video_id) + self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id) def _real_initialize(self): return @@ -1544,6 +1627,7 @@ class GenericIE(InfoExtractor): self._downloader.trouble(u'ERROR: Invalid URL: %s' % url) return + self.report_extraction(video_id) # Start with something easy: JW Player in SWFObject mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage) if mobj is None: @@ -1593,6 +1677,7 @@ class GenericIE(InfoExtractor): 'id': video_id.decode('utf-8'), 'url': video_url.decode('utf-8'), 'uploader': video_uploader, + 'upload_date': u'NA', 'title': video_title, 'stitle': simple_title, 'ext': video_extension.decode('utf-8'), @@ -1623,7 +1708,7 @@ 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)) + self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum)) def _real_initialize(self): self._youtube_ie.initialize() @@ -1714,7 +1799,7 @@ class GoogleSearchIE(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'[video.google] query "%s": Downloading page %s' % (query, pagenum)) + self._downloader.to_screen(u'[video.google] query "%s": Downloading page %s' % (query, pagenum)) def _real_initialize(self): self._google_ie.initialize() @@ -1805,7 +1890,7 @@ class YahooSearchIE(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'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum)) + self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum)) def _real_initialize(self): self._yahoo_ie.initialize() @@ -1895,7 +1980,7 @@ class YoutubePlaylistIE(InfoExtractor): def report_download_page(self, playlist_id, pagenum): """Report attempt to download playlist page with given number.""" - self._downloader.to_stdout(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum)) + self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum)) def _real_initialize(self): self._youtube_ie.initialize() @@ -1932,6 +2017,10 @@ class YoutubePlaylistIE(InfoExtractor): break pagenum = pagenum + 1 + playliststart = self._downloader.params.get('playliststart', 1) - 1 + playlistend = self._downloader.params.get('playlistend', -1) + video_ids = video_ids[playliststart:playlistend] + for id in video_ids: self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) return @@ -1954,7 +2043,7 @@ class YoutubeUserIE(InfoExtractor): def report_download_page(self, username): """Report attempt to download user page.""" - self._downloader.to_stdout(u'[youtube] user %s: Downloading page ' % (username)) + self._downloader.to_screen(u'[youtube] user %s: Downloading page ' % (username)) def _real_initialize(self): self._youtube_ie.initialize() @@ -1987,10 +2076,93 @@ class YoutubeUserIE(InfoExtractor): ids_in_page.append(mobj.group(1)) video_ids.extend(ids_in_page) + playliststart = self._downloader.params.get('playliststart', 1) - 1 + playlistend = self._downloader.params.get('playlistend', -1) + video_ids = video_ids[playliststart:playlistend] + for id in video_ids: self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id) return +class DepositFilesIE(InfoExtractor): + """Information extractor for depositfiles.com""" + + _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles.com/(?:../(?#locale))?files/(.+)' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + @staticmethod + def suitable(url): + return (re.match(DepositFilesIE._VALID_URL, url) is not None) + + def report_download_webpage(self, file_id): + """Report webpage download.""" + self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id) + + def report_extraction(self, file_id): + """Report information extraction.""" + self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id) + + def _real_initialize(self): + return + + def _real_extract(self, url): + # At this point we have a new file + self._downloader.increment_downloads() + + file_id = url.split('/')[-1] + # Rebuild url in english locale + url = 'http://depositfiles.com/en/files/' + file_id + + # Retrieve file webpage with 'Free download' button pressed + free_download_indication = { 'gateway_result' : '1' } + request = urllib2.Request(url, urllib.urlencode(free_download_indication), std_headers) + try: + self.report_download_webpage(file_id) + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % str(err)) + return + + # Search for the real file URL + mobj = re.search(r'
(Attention.*?)', webpage, re.DOTALL) + if (mobj is not None) and (mobj.group(1) is not None): + restriction_message = re.sub('\s+', ' ', mobj.group(1)).strip() + self._downloader.trouble(u'ERROR: %s' % restriction_message) + else: + self._downloader.trouble(u'ERROR: unable to extract download URL from: %s' % url) + return + + file_url = mobj.group(1) + file_extension = os.path.splitext(file_url)[1][1:] + + # Search for file title + mobj = re.search(r'', webpage) + if mobj is None: + self._downloader.trouble(u'ERROR: unable to extract title') + return + file_title = mobj.group(1).decode('utf-8') + + try: + # Process file information + self._downloader.process_info({ + 'id': file_id.decode('utf-8'), + 'url': file_url.decode('utf-8'), + 'uploader': u'NA', + 'upload_date': u'NA', + 'title': file_title, + 'stitle': file_title, + 'ext': file_extension.decode('utf-8'), + 'format': u'NA', + 'player_url': None, + }) + except UnavailableVideoError, err: + self._downloader.trouble(u'ERROR: unable to download file') + class PostProcessor(object): """Post Processor class. @@ -2050,25 +2222,20 @@ if __name__ == '__main__': if not os.access (filename, os.W_OK): sys.exit('ERROR: no write permissions on %s' % filename) - downloader.to_stdout('Updating to latest stable version...') - latest_url = 'http://bitbucket.org/rg3/youtube-dl/raw/tip/LATEST_VERSION' + downloader.to_screen('Updating to latest stable version...') + latest_url = 'http://github.com/rg3/youtube-dl/raw/master/LATEST_VERSION' latest_version = urllib.urlopen(latest_url).read().strip() - prog_url = 'http://bitbucket.org/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version + prog_url = 'http://github.com/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version newcontent = urllib.urlopen(prog_url).read() stream = open(filename, 'w') stream.write(newcontent) stream.close() - downloader.to_stdout('Updated to version %s' % latest_version) - - # General configuration - urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler())) - urllib2.install_opener(urllib2.build_opener(urllib2.HTTPCookieProcessor())) - socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words) + downloader.to_screen('Updated to version %s' % latest_version) # Parse command line parser = optparse.OptionParser( usage='Usage: %prog [options] url...', - version='2010.07.24', + version='2010.12.09', conflict_handler='resolve', ) @@ -2084,6 +2251,10 @@ if __name__ == '__main__': 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) + parser.add_option('--playlist-start', + dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1) + parser.add_option('--playlist-end', + dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1) authentication = optparse.OptionGroup(parser, 'Authentication Options') authentication.add_option('-u', '--username', @@ -2103,6 +2274,8 @@ if __name__ == '__main__': 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') + video_format.add_option('-b', '--best-quality', + action='store_true', dest='bestquality', help='download the best video quality (DEPRECATED)') parser.add_option_group(video_format) verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options') @@ -2127,6 +2300,8 @@ if __name__ == '__main__': action='store_true', dest='usetitle', help='use title in file name', default=False) filesystem.add_option('-l', '--literal', action='store_true', dest='useliteral', help='use literal title in file name', default=False) + filesystem.add_option('-A', '--auto-number', + action='store_true', dest='autonumber', help='number downloaded files starting from 00000', default=False) filesystem.add_option('-o', '--output', dest='outtmpl', metavar='TEMPLATE', help='output filename template') filesystem.add_option('-a', '--batch-file', @@ -2135,10 +2310,29 @@ if __name__ == '__main__': action='store_true', dest='nooverwrites', help='do not overwrite files', default=False) filesystem.add_option('-c', '--continue', action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False) + filesystem.add_option('--cookies', + dest='cookiefile', metavar='FILE', help='file to dump cookie jar to') parser.add_option_group(filesystem) (opts, args) = parser.parse_args() + # Open appropriate CookieJar + if opts.cookiefile is None: + jar = cookielib.CookieJar() + else: + try: + jar = cookielib.MozillaCookieJar(opts.cookiefile) + if os.path.isfile(opts.cookiefile) and os.access(opts.cookiefile, os.R_OK): + jar.load() + except (IOError, OSError), err: + sys.exit(u'ERROR: unable to open cookie file') + + # General configuration + cookie_processor = urllib2.HTTPCookieProcessor(jar) + urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler())) + urllib2.install_opener(urllib2.build_opener(cookie_processor)) + socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words) + # Batch file verification batchurls = [] if opts.batchfile is not None: @@ -2149,18 +2343,20 @@ if __name__ == '__main__': 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] + batchurls = [x for x in batchurls if len(x) > 0 and not re.search(r'^[#/;]', x)] except IOError: sys.exit(u'ERROR: batch file could not be read') all_urls = batchurls + args # Conflicting, missing and erroneous options + if opts.bestquality: + print >>sys.stderr, u'\nWARNING: -b/--best-quality IS DEPRECATED AS IT IS THE DEFAULT BEHAVIOR NOW\n' 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') if opts.password is not None and opts.username is None: parser.error(u'account username missing') - if opts.outtmpl is not None and (opts.useliteral or opts.usetitle): - parser.error(u'using output template conflicts with using title or literal title') + if opts.outtmpl is not None and (opts.useliteral or opts.usetitle or opts.autonumber): + parser.error(u'using output template conflicts with using title, literal title or auto number') if opts.usetitle and opts.useliteral: parser.error(u'using title conflicts with using literal title') if opts.username is not None and opts.password is None: @@ -2175,6 +2371,18 @@ if __name__ == '__main__': opts.retries = long(opts.retries) except (TypeError, ValueError), err: parser.error(u'invalid retry count specified') + try: + opts.playliststart = long(opts.playliststart) + if opts.playliststart <= 0: + raise ValueError + except (TypeError, ValueError), err: + parser.error(u'invalid playlist start number specified') + try: + opts.playlistend = long(opts.playlistend) + if opts.playlistend != -1 and (opts.playlistend <= 0 or opts.playlistend < opts.playliststart): + raise ValueError + except (TypeError, ValueError), err: + parser.error(u'invalid playlist end number specified') # Information extractors youtube_ie = YoutubeIE() @@ -2188,6 +2396,7 @@ if __name__ == '__main__': photobucket_ie = PhotobucketIE() yahoo_ie = YahooIE() yahoo_search_ie = YahooSearchIE(yahoo_ie) + deposit_files_ie = DepositFilesIE() generic_ie = GenericIE() # File downloader @@ -2207,8 +2416,11 @@ if __name__ == '__main__': 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 opts.autonumber and u'%(autonumber)s-%(stitle)s-%(id)s.%(ext)s') + or (opts.useliteral and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)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 (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s') or u'%(id)s.%(ext)s'), 'ignoreerrors': opts.ignoreerrors, 'ratelimit': opts.ratelimit, @@ -2216,6 +2428,9 @@ if __name__ == '__main__': 'retries': opts.retries, 'continuedl': opts.continue_dl, 'noprogress': opts.noprogress, + 'playliststart': opts.playliststart, + 'playlistend': opts.playlistend, + 'logtostderr': opts.outtmpl == '-', }) fd.add_info_extractor(youtube_search_ie) fd.add_info_extractor(youtube_pl_ie) @@ -2228,6 +2443,7 @@ if __name__ == '__main__': fd.add_info_extractor(photobucket_ie) fd.add_info_extractor(yahoo_ie) fd.add_info_extractor(yahoo_search_ie) + fd.add_info_extractor(deposit_files_ie) # This must come last since it's the # fallback if none of the others work @@ -2244,6 +2460,14 @@ if __name__ == '__main__': else: sys.exit() retcode = fd.download(all_urls) + + # Dump cookie jar if requested + if opts.cookiefile is not None: + try: + jar.save() + except (IOError, OSError), err: + sys.exit(u'ERROR: unable to save cookie jar') + sys.exit(retcode) except DownloadError: