X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube-dl;h=7eaafdcd5f2c6ea8d55949850716c71f47c87a3c;hb=0c2dc87d9e299fb413d103f08df0d03fed55adb1;hp=633c87e5d1a370a813cec1839ccfba8b292f1967;hpb=38acff0e77d773de0b14b95a21ea4cafd43a98c9;p=youtube-dl diff --git a/youtube-dl b/youtube-dl index 633c87e5d..7eaafdcd5 100755 --- a/youtube-dl +++ b/youtube-dl @@ -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. @@ -61,6 +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 @@ -76,6 +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) @@ -132,6 +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: @@ -165,22 +194,48 @@ class FileDownloader(object): """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 exit the program or + download errors or not, this method may throw an exception or not when errors are found, after printing the message. If it - doesn't exit, it returns an error code suitable to be returned + 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): - sys.exit(1) + 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(): - sys.exit('ERROR: fixed output name but more than one file to download') + raise SameFileError(self._params['outtmpl']) for url in url_list: suitable_found = False @@ -195,10 +250,9 @@ class FileDownloader(object): retcode = self.trouble() if len(results) > 1 and self.fixed_template(): - sys.exit('ERROR: fixed output name but more than one file to download') + raise SameFileError(self._params['outtmpl']) for result in results: - # Forced printings if self._params.get('forcetitle', False): print result['title'] @@ -211,6 +265,7 @@ class FileDownloader(object): try: filename = self._params['outtmpl'] % result + self.report_destination(filename) except (ValueError, KeyError), err: retcode = self.trouble('ERROR: invalid output template: %s' % str(err)) continue @@ -248,12 +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() @@ -264,7 +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)) @@ -303,7 +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).""" @@ -340,10 +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 @@ -382,7 +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)