X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube-dl;h=4dea34376bba4b87dfcf4ff7a47fd570ec906549;hb=acd3d842987ee4c407093aaa4dedf4f301895adc;hp=1c4a05471e1eb7533cd2906b7dc2fee9d8bf0491;hpb=7e5cab673024e93a706afa64f9fc38e25e8df085;p=youtube-dl.git diff --git a/youtube-dl b/youtube-dl index 1c4a05471..4dea34376 100755 --- a/youtube-dl +++ b/youtube-dl @@ -17,7 +17,7 @@ import urllib import urllib2 std_headers = { - 'User-Agent': 'UserAgent: Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9) Gecko/2008052906 Firefox/3.0', + 'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.1) Gecko/2008070208 Firefox/3.0.1', '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', @@ -25,6 +25,23 @@ std_headers = { simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii') +class DownloadError(Exception): + """Download Error exception. + + This exception may be thrown by FileDownloader objects if they are not + configured to continue on errors. They will contain the appropriate + error message. + """ + pass + +class SameFileError(Exception): + """Same File exception. + + This exception will be thrown by FileDownloader objects if they detect + multiple files would have to be downloaded to the same file on disk. + """ + pass + class FileDownloader(object): """File Downloader class. @@ -55,15 +72,20 @@ class FileDownloader(object): 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. outtmpl: Template for output names. + ignoreerrors: Do not stop on download errors. + ratelimit: Download speed limit, in bytes/sec. """ _params = None _ies = [] def __init__(self, params): + """Create a FileDownloader object with the given options.""" self._ies = [] self.set_params(params) @@ -128,6 +150,16 @@ 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: @@ -152,9 +184,58 @@ class FileDownloader(object): def to_stderr(self, message): """Print message to stderr.""" sys.stderr.write('%s\n' % message) + + def fixed_template(self): + """Checks if the output template is fixed.""" + return (re.search(ur'(?u)%\(.+?\)s', self._params['outtmpl']) is None) + + def trouble(self, message=None): + """Determine action to take when a download problem appears. + + Depending on if the downloader has been configured to ignore + download errors or not, this method may throw an exception or + not when errors are found, after printing the message. If it + doesn't raise, it returns an error code suitable to be returned + later as a program exit code to indicate error. + """ + if message is not None: + self.to_stderr(message) + if not self._params.get('ignoreerrors', False): + 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 + if len(url_list) > 1 and self.fixed_template(): + raise SameFileError(self._params['outtmpl']) + for url in url_list: suitable_found = False for ie in self._ies: @@ -162,42 +243,56 @@ class FileDownloader(object): continue # Suitable InfoExtractor found suitable_found = True - results = [x for x in ie.extract(url) if x is not None] - - if (len(url_list) > 1 or len(results) > 1) and re.search(r'%\(.+?\)s', self._params['outtmpl']) is None: - sys.exit('ERROR: fixed output name but more than one file to download') + all_results = ie.extract(url) + results = [x for x in all_results if x is not None] + if len(results) != len(all_results): + retcode = self.trouble() - if self._params.get('simulate', False): - continue + if len(results) > 1 and self.fixed_template(): + raise SameFileError(self._params['outtmpl']) for result in results: + + # Forced printings + if self._params.get('forcetitle', False): + print result['title'] + if self._params.get('forceurl', False): + print result['url'] + + # Do nothing else if in simulate mode + if self._params.get('simulate', False): + continue + try: filename = self._params['outtmpl'] % result - except (KeyError), err: - self.to_stderr('ERROR: invalid output template: %s' % str(err)) + self.report_destination(filename) + except (ValueError, KeyError), err: + retcode = self.trouble('ERROR: invalid output template: %s' % str(err)) continue try: self.pmkdir(filename) except (OSError, IOError), err: - self.to_stderr('ERROR: unable to create directories: %s' % str(err)) + retcode = self.trouble('ERROR: unable to create directories: %s' % str(err)) continue try: outstream = open(filename, 'wb') except (OSError, IOError), err: - self.to_stderr('ERROR: unable to open for writing: %s' % str(err)) + retcode = self.trouble('ERROR: unable to open for writing: %s' % str(err)) continue try: self._do_download(outstream, result['url']) outstream.close() except (OSError, IOError), err: - self.to_stderr('ERROR: unable to write video data: %s' % str(err)) + retcode = self.trouble('ERROR: unable to write video data: %s' % str(err)) continue except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self.to_stderr('ERROR: unable to download video data: %s' % str(err)) + retcode = self.trouble('ERROR: unable to download video data: %s' % str(err)) continue break if not suitable_found: - self.to_stderr('ERROR: no suitable InfoExtractor: %s' % url) + retcode = self.trouble('ERROR: no suitable InfoExtractor: %s' % url) + + return retcode def _do_download(self, stream, url): request = urllib2.Request(url, None, std_headers) @@ -208,12 +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() @@ -224,7 +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)) @@ -266,7 +365,7 @@ class InfoExtractor(object): return True def initialize(self): - """Initializes an instance (login, etc).""" + """Initializes an instance (authentication, etc).""" if not self._ready: self._real_initialize() self._ready = True @@ -281,10 +380,12 @@ class InfoExtractor(object): self._downloader = downloader def to_stdout(self, message): + """Print message to stdout if downloader is not in quiet mode.""" if self._downloader is None or not self._downloader.get_params().get('quiet', False): print message def to_stderr(self, message): + """Print message to stderr.""" sys.stderr.write('%s\n' % message) def _real_initialize(self): @@ -302,6 +403,26 @@ class YoutubeIE(InfoExtractor): _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/' _NETRC_MACHINE = 'youtube' + 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 @@ -326,6 +447,7 @@ class YoutubeIE(InfoExtractor): self.to_stderr('WARNING: parsing .netrc: %s' % str(err)) return + # No authentication to be performed if username is None: return @@ -339,13 +461,13 @@ 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)