X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube-dl;h=7eaafdcd5f2c6ea8d55949850716c71f47c87a3c;hb=0c2dc87d9e299fb413d103f08df0d03fed55adb1;hp=2c1d1aa3b84b5e3cda680e22fe0a6a39dc91c777;hpb=90663284b2c742ae84d3dd00876af9b681ee78ee;p=youtube-dl diff --git a/youtube-dl b/youtube-dl index 2c1d1aa3b..7eaafdcd5 100755 --- a/youtube-dl +++ b/youtube-dl @@ -78,6 +78,7 @@ class FileDownloader(object): format: Video format code. outtmpl: Template for output names. ignoreerrors: Do not stop on download errors. + ratelimit: Download speed limit, in bytes/sec. """ _params = None @@ -93,6 +94,7 @@ class FileDownloader(object): """Create directory components in filename. Similar to Unix "mkdir -p".""" components = filename.split(os.sep) aggregate = [os.sep.join(components[0:x]) for x in xrange(1, len(components))] + aggregate = ['%s%s' % (x, os.sep) for x in aggregate] # Finish names with separator for dir in aggregate: if not os.path.exists(dir): os.mkdir(dir) @@ -149,6 +151,16 @@ class FileDownloader(object): return int(new_min) return int(rate) + @staticmethod + def parse_bytes(bytestr): + """Parse a string indicating a byte quantity into a long integer.""" + matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr) + if matchobj is None: + return None + number = float(matchobj.group(1)) + multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower()) + return long(round(number * multiplier)) + def set_params(self, params): """Sets parameters.""" if type(params) != dict: @@ -193,6 +205,32 @@ class FileDownloader(object): raise DownloadError(message) return 1 + def slow_down(self, start_time, byte_counter): + """Sleep if the download speed is over the rate limit.""" + rate_limit = self._params.get('ratelimit', None) + if rate_limit is None or byte_counter == 0: + return + now = time.time() + elapsed = now - start_time + if elapsed <= 0.0: + return + speed = float(byte_counter) / elapsed + if speed > rate_limit: + time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit) + + def report_destination(self, filename): + """Report destination filename.""" + self.to_stdout('[download] Destination: %s' % filename) + + def report_progress(self, percent_str, data_len_str, speed_str, eta_str): + """Report download progress.""" + self.to_stdout('\r[download] %s of %s at %s ETA %s' % + (percent_str, data_len_str, speed_str, eta_str), skip_eol=True) + + def report_finish(self): + """Report download finished.""" + self.to_stdout('') + def download(self, url_list): """Download a given list of URLs.""" retcode = 0 @@ -215,7 +253,6 @@ class FileDownloader(object): raise SameFileError(self._params['outtmpl']) for result in results: - # Forced printings if self._params.get('forcetitle', False): print result['title'] @@ -228,7 +265,7 @@ class FileDownloader(object): try: filename = self._params['outtmpl'] % result - self.to_stdout('[download] Destination: %s' % filename) + self.report_destination(filename) except (ValueError, KeyError), err: retcode = self.trouble('ERROR: invalid output template: %s' % str(err)) continue @@ -266,12 +303,13 @@ class FileDownloader(object): block_size = 1024 start = time.time() while True: + # Progress message percent_str = self.calc_percent(byte_counter, data_len) eta_str = self.calc_eta(start, time.time(), data_len, byte_counter) speed_str = self.calc_speed(start, time.time(), byte_counter) - self.to_stdout('\r[download] %s of %s at %s ETA %s' % - (percent_str, data_len_str, speed_str, eta_str), skip_eol=True) + self.report_progress(percent_str, data_len_str, speed_str, eta_str) + # Download and write before = time.time() data_block = data.read(block_size) after = time.time() @@ -282,7 +320,10 @@ class FileDownloader(object): stream.write(data_block) block_size = self.best_block_size(after - before, data_block_len) - self.to_stdout('') + # Apply rate limit + self.slow_down(start, byte_counter) + + self.report_finish() if data_len is not None and str(byte_counter) != data_len: raise ValueError('Content too short: %s/%s bytes' % (byte_counter, data_len)) @@ -321,7 +362,7 @@ class InfoExtractor(object): @staticmethod def suitable(url): """Receives a URL and returns True if suitable for this IE.""" - return True + return False def initialize(self): """Initializes an instance (authentication, etc).""" @@ -358,10 +399,35 @@ 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).+)?$' _LOGIN_URL = 'http://www.youtube.com/login?next=/' _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/' _NETRC_MACHINE = 'youtube' + @staticmethod + def suitable(url): + return (re.match(YoutubeIE._VALID_URL, url) is not None) + + def report_login(self): + """Report attempt to log in.""" + self.to_stdout('[youtube] Logging in') + + def report_age_confirmation(self): + """Report attempt to confirm age.""" + self.to_stdout('[youtube] Confirming age') + + def report_webpage_download(self, video_id): + """Report attempt to download webpage.""" + self.to_stdout('[youtube] %s: Downloading video webpage' % video_id) + + def report_information_extraction(self, video_id): + """Report attempt to extract video information.""" + self.to_stdout('[youtube] %s: Extracting video information' % video_id) + + def report_video_url(self, video_id, video_real_url): + """Report extracted video URL.""" + self.to_stdout('[youtube] %s: URL: %s' % (video_id, video_real_url)) + def _real_initialize(self): if self._downloader is None: return @@ -400,7 +466,7 @@ class YoutubeIE(InfoExtractor): } request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form), std_headers) try: - self.to_stdout('[youtube] Logging in') + self.report_login() login_results = urllib2.urlopen(request).read() if re.search(r'(?i)]* name="loginForm"', login_results) is not None: self.to_stderr('WARNING: unable to log in: bad username or password') @@ -416,7 +482,7 @@ class YoutubeIE(InfoExtractor): } request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form), std_headers) try: - self.to_stdout('[youtube] Confirming age') + self.report_age_confirmation() age_results = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: self.to_stderr('ERROR: unable to confirm age: %s' % str(err)) @@ -424,7 +490,7 @@ class YoutubeIE(InfoExtractor): def _real_extract(self, url): # Extract video id from URL - mobj = re.match(r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:\.php)?)?\?(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$', url) + mobj = re.match(self._VALID_URL, url) if mobj is None: self.to_stderr('ERROR: invalid URL: %s' % url) return [None] @@ -445,12 +511,12 @@ class YoutubeIE(InfoExtractor): normalized_url = '%s&fmt=%s' % (normalized_url, format_param) request = urllib2.Request(normalized_url, None, std_headers) try: - self.to_stdout('[youtube] %s: Downloading video webpage' % video_id) + self.report_webpage_download(video_id) video_webpage = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: self.to_stderr('ERROR: unable to download video webpage: %s' % str(err)) return [None] - self.to_stdout('[youtube] %s: Extracting video information' % video_id) + self.report_information_extraction(video_id) # "t" param mobj = re.search(r', "t": "([^"]+)"', video_webpage) @@ -460,7 +526,7 @@ class YoutubeIE(InfoExtractor): video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s' % (video_id, mobj.group(1)) if format_param is not None: video_real_url = '%s&fmt=%s' % (video_real_url, format_param) - self.to_stdout('[youtube] %s: URL: %s' % (video_id, video_real_url)) + self.report_video_url(video_id, video_real_url) # uploader mobj = re.search(r'More From: ([^<]*)<', video_webpage) @@ -492,6 +558,184 @@ class YoutubeIE(InfoExtractor): 'ext': video_extension, }] +class MetacafeIE(InfoExtractor): + """Information Extractor for metacafe.com.""" + + _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*' + _DISCLAIMER = 'http://www.metacafe.com/disclaimer' + _youtube_ie = None + + def __init__(self, youtube_ie, downloader=None): + InfoExtractor.__init__(self, downloader) + self._youtube_ie = youtube_ie + + @staticmethod + def suitable(url): + return (re.match(MetacafeIE._VALID_URL, url) is not None) + + def report_disclaimer(self): + """Report disclaimer retrieval.""" + self.to_stdout('[metacafe] Retrieving disclaimer') + + def report_age_confirmation(self): + """Report attempt to confirm age.""" + self.to_stdout('[metacafe] Confirming age') + + def report_download_webpage(self, video_id): + """Report webpage download.""" + self.to_stdout('[metacafe] %s: Downloading webpage' % video_id) + + def report_extraction(self, video_id): + """Report information extraction.""" + self.to_stdout('[metacafe] %s: Extracting information' % video_id) + + def _real_initialize(self): + # Retrieve disclaimer + request = urllib2.Request(self._DISCLAIMER, None, std_headers) + try: + self.report_disclaimer() + disclaimer = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self.to_stderr('ERROR: unable to retrieve disclaimer: %s' % str(err)) + return + + # Confirm age + disclaimer_form = { + 'allowAdultContent': '1', + 'submit': "Continue - I'm over 18", + } + request = urllib2.Request('http://www.metacafe.com/watch/', urllib.urlencode(disclaimer_form), std_headers) + try: + self.report_age_confirmation() + disclaimer = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self.to_stderr('ERROR: unable to confirm age: %s' % str(err)) + return + + def _real_extract(self, url): + # Extract id and simplified title from URL + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self.to_stderr('ERROR: invalid URL: %s' % url) + return [None] + + video_id = mobj.group(1) + + # Check if video comes from YouTube + mobj2 = re.match(r'^yt-(.*)$', video_id) + if mobj2 is not None: + return self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1)) + + simple_title = mobj.group(2).decode('utf-8') + video_extension = 'flv' + + # Retrieve video webpage to extract further information + request = urllib2.Request('http://www.metacafe.com/watch/%s/' % video_id) + try: + self.report_download_webpage(video_id) + webpage = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self.to_stderr('ERROR: unable retrieve video webpage: %s' % str(err)) + return [None] + + # Extract URL, uploader and title from webpage + self.report_extraction(video_id) + mobj = re.search(r'(?m)"mediaURL":"(http.*?\.flv)"', webpage) + if mobj is None: + self.to_stderr('ERROR: unable to extract media URL') + return [None] + mediaURL = mobj.group(1).replace('\\', '') + + mobj = re.search(r'(?m)"gdaKey":"(.*?)"', webpage) + if mobj is None: + self.to_stderr('ERROR: unable to extract gdaKey') + return [None] + gdaKey = mobj.group(1) + + video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) + + mobj = re.search(r'(?im).*?Submitter:
(.*?)', webpage) + if mobj is None: + self.to_stderr('ERROR: unable to extract uploader nickname') + return [None] + video_uploader = re.sub(r'<.*?>', '', mobj.group(1)) + + # Return information + return [{ + 'id': video_id, + 'url': video_url, + 'uploader': video_uploader, + 'title': video_title, + 'stitle': simple_title, + 'ext': video_extension, + }] + +class YoutubePlaylistIE(InfoExtractor): + """Information Extractor for YouTube playlists.""" + + _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/view_play_list\?p=(.+)' + _TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s' + _VIDEO_INDICATOR = r'/watch\?v=(.+?)&' + _MORE_PAGES_INDICATOR = r'class="pagerNotCurrent">Next' + _youtube_ie = None + + def __init__(self, youtube_ie, downloader=None): + InfoExtractor.__init__(self, downloader) + self._youtube_ie = youtube_ie + + @staticmethod + def suitable(url): + return (re.match(YoutubePlaylistIE._VALID_URL, url) is not None) + + def report_download_page(self, playlist_id, pagenum): + """Report attempt to download playlist page with given number.""" + self.to_stdout('[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum)) + + def _real_initialize(self): + self._youtube_ie.initialize() + + def _real_extract(self, url): + # Extract playlist id + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self.to_stderr('ERROR: invalid url: %s' % url) + return [None] + + # Download playlist pages + playlist_id = mobj.group(1) + video_ids = [] + pagenum = 1 + + while True: + self.report_download_page(playlist_id, pagenum) + request = urllib2.Request(self._TEMPLATE_URL % (playlist_id, pagenum), None, std_headers) + try: + page = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self.to_stderr('ERROR: unable to download webpage: %s' % str(err)) + return [None] + + # Extract video identifiers + ids_in_page = set() + for mobj in re.finditer(self._VIDEO_INDICATOR, page): + ids_in_page.add(mobj.group(1)) + video_ids.extend(list(ids_in_page)) + + if self._MORE_PAGES_INDICATOR not in page: + break + pagenum = pagenum + 1 + + information = [] + for id in video_ids: + information.extend(self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)) + return information + if __name__ == '__main__': try: # Modules needed only when running the main program @@ -506,7 +750,7 @@ if __name__ == '__main__': # Parse command line parser = optparse.OptionParser( usage='Usage: %prog [options] url...', - version='INTERNAL', + version='2008.07.22', conflict_handler='resolve', ) parser.add_option('-h', '--help', @@ -536,11 +780,13 @@ if __name__ == '__main__': parser.add_option('-f', '--format', dest='format', metavar='FMT', help='video format code') parser.add_option('-b', '--best-quality', - action='store_const', dest='video_format', help='alias for -f 18', const='18') + action='store_const', dest='format', help='alias for -f 18', const='18') parser.add_option('-m', '--mobile-version', - action='store_const', dest='video_format', help='alias for -f 17', const='17') + action='store_const', dest='format', help='alias for -f 17', const='17') parser.add_option('-i', '--ignore-errors', action='store_true', dest='ignoreerrors', help='continue on download errors', default=False) + parser.add_option('-r', '--rate-limit', + dest='ratelimit', metavar='L', help='download rate limit (e.g. 50k or 44.6m)') (opts, args) = parser.parse_args() # Conflicting, missing and erroneous options @@ -556,9 +802,16 @@ if __name__ == '__main__': sys.exit('ERROR: using title conflicts with using literal title') if opts.username is not None and opts.password is None: opts.password = getpass.getpass('Type account password and press return:') + if opts.ratelimit is not None: + numeric_limit = FileDownloader.parse_bytes(opts.ratelimit) + if numeric_limit is None: + sys.exit('ERROR: invalid rate limit specified') + opts.ratelimit = numeric_limit # Information extractors youtube_ie = YoutubeIE() + metacafe_ie = MetacafeIE(youtube_ie) + youtube_pl_ie = YoutubePlaylistIE(youtube_ie) # File downloader fd = FileDownloader({ @@ -575,7 +828,10 @@ if __name__ == '__main__': or (opts.useliteral and '%(title)s-%(id)s.%(ext)s') or '%(id)s.%(ext)s'), 'ignoreerrors': opts.ignoreerrors, + 'ratelimit': opts.ratelimit, }) + fd.add_info_extractor(youtube_pl_ie) + fd.add_info_extractor(metacafe_ie) fd.add_info_extractor(youtube_ie) retcode = fd.download(args) sys.exit(retcode)