X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube-dl;h=135d14809554a592101ef6b9100dd41bb3dcce7f;hb=bb028346923a1b53bb8852ded546e08a1516dd49;hp=814e1b68b33ff285efba820ee4a34313b4593a88;hpb=e8e20c76f23e73c8f4f864667b03515ab5d7523f;p=youtube-dl diff --git a/youtube-dl b/youtube-dl index 814e1b68b..135d14809 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. @@ -60,12 +77,14 @@ class FileDownloader(object): simulate: Do not download the video files. format: Video format code. outtmpl: Template for output names. + ignoreerrors: Do not stop on download errors. """ _params = None _ies = [] def __init__(self, params): + """Create a FileDownloader object with the given options.""" self._ies = [] self.set_params(params) @@ -159,10 +178,39 @@ class FileDownloader(object): """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 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 @@ -171,10 +219,13 @@ class FileDownloader(object): continue # Suitable InfoExtractor found suitable_found = True - results = [x for x in ie.extract(url) if x is not None] + 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 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: @@ -190,31 +241,34 @@ class FileDownloader(object): try: filename = self._params['outtmpl'] % result + self.report_destination(filename) except (ValueError, KeyError), err: - self.to_stderr('ERROR: invalid output template: %s' % str(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) @@ -225,12 +279,13 @@ 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() @@ -241,7 +296,7 @@ class FileDownloader(object): stream.write(data_block) block_size = self.best_block_size(after - before, data_block_len) - self.to_stdout('') + 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)) @@ -283,7 +338,7 @@ 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 @@ -298,10 +353,12 @@ 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): @@ -319,6 +376,26 @@ 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 @@ -343,6 +420,7 @@ class YoutubeIE(InfoExtractor): self.to_stderr('WARNING: parsing .netrc: %s' % str(err)) return + # No authentication to be performed if username is None: return @@ -356,13 +434,13 @@ 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)]* name="loginForm"', login_results) is not None: - self.to_stderr('WARNING: Unable to log in: bad username or password') + self.to_stderr('WARNING: unable to log in: bad username or password') return except (urllib2.URLError, httplib.HTTPException, socket.error), err: - self.to_stderr('WARNING: Unable to log in: %s' % str(err)) + self.to_stderr('WARNING: unable to log in: %s' % str(err)) return # Confirm age @@ -372,16 +450,17 @@ 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: - sys.exit('ERROR: Unable to confirm age: %s' % str(err)) + self.to_stderr('ERROR: unable to confirm age: %s' % str(err)) + return 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) if mobj is None: - self.to_stderr('ERROR: Invalid URL: %s' % url) + self.to_stderr('ERROR: invalid URL: %s' % url) return [None] video_id = mobj.group(2) @@ -392,7 +471,7 @@ class YoutubeIE(InfoExtractor): format_param = params.get('format', None) # Extension - video_extension = {'18': 'mp4'}.get(format_param, 'flv') + video_extension = {'18': 'mp4', '17': '3gp'}.get(format_param, 'flv') # Normalize URL, including format normalized_url = 'http://www.youtube.com/watch?v=%s' % video_id @@ -400,36 +479,38 @@ 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: - sys.exit('ERROR: Unable to download video: %s' % str(err)) - self.to_stdout('[youtube] %s: Extracting video information' % video_id) + self.to_stderr('ERROR: unable to download video webpage: %s' % str(err)) + return [None] + self.report_information_extraction(video_id) # "t" param mobj = re.search(r', "t": "([^"]+)"', video_webpage) if mobj is None: - self.to_stderr('ERROR: Unable to extract "t" parameter') + self.to_stderr('ERROR: unable to extract "t" parameter') return [None] 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) if mobj is None: - self.to_stderr('ERROR: Unable to extract uploader nickname') + self.to_stderr('ERROR: unable to extract uploader nickname') return [None] video_uploader = mobj.group(1) # title mobj = re.search(r'(?im)YouTube - ([^<]*)', video_webpage) if mobj is None: - self.to_stderr('ERROR: Unable to extract video title') + self.to_stderr('ERROR: unable to extract video title') return [None] video_title = mobj.group(1).decode('utf-8') video_title = re.sub(ur'(?u)&(.+?);', lambda x: unichr(htmlentitydefs.name2codepoint[x.group(1)]), video_title) + video_title = video_title.replace(os.sep, u'%') # simplified title simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title) @@ -459,7 +540,7 @@ 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', @@ -489,7 +570,11 @@ 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='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) (opts, args) = parser.parse_args() # Conflicting, missing and erroneous options @@ -523,9 +608,15 @@ if __name__ == '__main__': or (opts.usetitle and '%(stitle)s-%(id)s.%(ext)s') or (opts.useliteral and '%(title)s-%(id)s.%(ext)s') or '%(id)s.%(ext)s'), + 'ignoreerrors': opts.ignoreerrors, }) fd.add_info_extractor(youtube_ie) - fd.download(args) + retcode = fd.download(args) + sys.exit(retcode) + except DownloadError: + sys.exit(1) + except SameFileError: + sys.exit('ERROR: fixed output name but more than one file to download') except KeyboardInterrupt: sys.exit('\nERROR: Interrupted by user')