X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube-dl;h=3e7f13956d534fd76478a68594f31f8e552e62ed;hb=a9633f14577db35ce1bed3f8d623a7be8f287e87;hp=135d14809554a592101ef6b9100dd41bb3dcce7f;hpb=d7bc253bb82ac4f8a6ffef568c5b6eee508c7206;p=youtube-dl.git diff --git a/youtube-dl b/youtube-dl index 135d14809..3e7f13956 100755 --- a/youtube-dl +++ b/youtube-dl @@ -4,6 +4,7 @@ # License: Public domain code import htmlentitydefs import httplib +import locale import math import netrc import os @@ -17,7 +18,7 @@ import urllib import urllib2 std_headers = { - 'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.1) Gecko/2008070208 Firefox/3.0.1', + 'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.5) Gecko/2008120122 Firefox/3.0.5', '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', @@ -42,6 +43,14 @@ class SameFileError(Exception): """ pass +class PostProcessingError(Exception): + """Post Processing exception. + + This exception may be raised by PostProcessor's .run() method to + indicate an error in the postprocessing task. + """ + pass + class FileDownloader(object): """File Downloader class. @@ -78,14 +87,17 @@ 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 _ies = [] + _pps = [] def __init__(self, params): """Create a FileDownloader object with the given options.""" self._ies = [] + self._pps = [] self.set_params(params) @staticmethod @@ -93,6 +105,7 @@ 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 +162,16 @@ 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: @@ -164,15 +187,20 @@ class FileDownloader(object): self._ies.append(ie) ie.set_downloader(self) + def add_post_processor(self, pp): + """Add a PostProcessor object to the end of the chain.""" + self._pps.append(pp) + pp.set_downloader(self) + def to_stdout(self, message, skip_eol=False): """Print message to stdout if not in quiet mode.""" if not self._params.get('quiet', False): - sys.stdout.write('%s%s' % (message, ['\n', ''][skip_eol])) + print u'%s%s' % (message, [u'\n', u''][skip_eol]), sys.stdout.flush() def to_stderr(self, message): """Print message to stderr.""" - sys.stderr.write('%s\n' % message) + print >>sys.stderr, message def fixed_template(self): """Checks if the output template is fixed.""" @@ -193,18 +221,31 @@ 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) + self.to_stdout(u'[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' % + 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) def report_finish(self): """Report download finished.""" - self.to_stdout('') + self.to_stdout(u'') def download(self, url_list): """Download a given list of URLs.""" @@ -228,7 +269,6 @@ class FileDownloader(object): raise SameFileError(self._params['outtmpl']) for result in results: - # Forced printings if self._params.get('forcetitle', False): print result['title'] @@ -243,7 +283,7 @@ class FileDownloader(object): filename = self._params['outtmpl'] % result self.report_destination(filename) except (ValueError, KeyError), err: - retcode = self.trouble('ERROR: invalid output template: %s' % str(err)) + retcode = self.trouble('ERROR: invalid output template or system charset: %s' % str(err)) continue try: self.pmkdir(filename) @@ -264,11 +304,26 @@ class FileDownloader(object): except (urllib2.URLError, httplib.HTTPException, socket.error), err: retcode = self.trouble('ERROR: unable to download video data: %s' % str(err)) continue + try: + self.post_process(filename, result) + except (PostProcessingError), err: + retcode = self.trouble('ERROR: postprocessing: %s' % str(err)) + continue + break if not suitable_found: retcode = self.trouble('ERROR: no suitable InfoExtractor: %s' % url) return retcode + + def post_process(self, filename, ie_info): + """Run the postprocessing chain on the given file.""" + info = dict(ie_info) + info['filepath'] = filename + for pp in self._pps: + info = pp.run(info) + if info is None: + break def _do_download(self, stream, url): request = urllib2.Request(url, None, std_headers) @@ -296,6 +351,9 @@ class FileDownloader(object): stream.write(data_block) block_size = self.best_block_size(after - before, data_block_len) + # 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)) @@ -335,7 +393,7 @@ 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).""" @@ -359,7 +417,7 @@ class InfoExtractor(object): def to_stderr(self, message): """Print message to stderr.""" - sys.stderr.write('%s\n' % message) + print >>sys.stderr, message def _real_initialize(self): """Real initialization process. Redefine in subclasses.""" @@ -372,29 +430,39 @@ class InfoExtractor(object): class YoutubeIE(InfoExtractor): """Information extractor for youtube.com.""" - _LOGIN_URL = 'http://www.youtube.com/login?next=/' - _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/' + _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' + @staticmethod + def suitable(url): + return (re.match(YoutubeIE._VALID_URL, url) is not None) + + def report_lang(self): + """Report attempt to set language.""" + self.to_stdout(u'[youtube] Setting language') + def report_login(self): """Report attempt to log in.""" - self.to_stdout('[youtube] Logging in') + self.to_stdout(u'[youtube] Logging in') def report_age_confirmation(self): """Report attempt to confirm age.""" - self.to_stdout('[youtube] Confirming age') + self.to_stdout(u'[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) + self.to_stdout(u'[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) + self.to_stdout(u'[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)) + self.to_stdout(u'[youtube] %s: URL: %s' % (video_id, video_real_url)) def _real_initialize(self): if self._downloader is None: @@ -417,13 +485,22 @@ class YoutubeIE(InfoExtractor): else: raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) except (IOError, netrc.NetrcParseError), err: - self.to_stderr('WARNING: parsing .netrc: %s' % str(err)) + self.to_stderr(u'WARNING: parsing .netrc: %s' % str(err)) return # No authentication to be performed if username is None: return + # Set language + request = urllib2.Request(self._LOGIN_URL, None, std_headers) + try: + self.report_lang() + urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self.to_stderr(u'WARNING: unable to set language: %s' % str(err)) + return + # Log in login_form = { 'current_form': 'loginForm', @@ -437,10 +514,10 @@ class YoutubeIE(InfoExtractor): self.report_login() login_results = urllib2.urlopen(request).read() if re.search(r'(?i)