X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube-dl;h=46d45d37d95630d5fd742ee16d182530a3dcb34f;hb=1c5e23021ed23a1d143d7b0a9554574d1e7050fb;hp=6a79bf93a2a520ed2cf6418e42b2200918577ed9;hpb=7414bdf11d0382e1a7206caa9def3da999510b6b;p=youtube-dl diff --git a/youtube-dl b/youtube-dl index 6a79bf93a..46d45d37d 100755 --- a/youtube-dl +++ b/youtube-dl @@ -55,15 +55,19 @@ 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. """ _params = None _ies = [] def __init__(self, params): + """Create a FileDownloader object with the given options.""" self._ies = [] self.set_params(params) @@ -157,8 +161,24 @@ 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 exit the program or + not when errors are found, after printing the message. If it + doesn't exit, 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) + return 1 + 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') @@ -169,42 +189,55 @@ 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') - if self._params.get('simulate', False): - continue - 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 (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) @@ -273,7 +306,7 @@ 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 @@ -288,10 +321,12 @@ 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): @@ -349,10 +384,10 @@ class YoutubeIE(InfoExtractor): self.to_stdout('[youtube] Logging in') 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 @@ -365,13 +400,13 @@ class YoutubeIE(InfoExtractor): self.to_stdout('[youtube] Confirming age') age_results = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: - sys.exit('ERROR: Unable to confirm age: %s' % str(err)) + sys.exit('ERROR: unable to confirm age: %s' % str(err)) 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) @@ -382,7 +417,7 @@ class YoutubeIE(InfoExtractor): format_param = params.get('format', None) # Extension - video_extension = {18: 'mp4'}.get(format_param, 'flv') + video_extension = {'18': 'mp4'}.get(format_param, 'flv') # Normalize URL, including format normalized_url = 'http://www.youtube.com/watch?v=%s' % video_id @@ -393,13 +428,13 @@ class YoutubeIE(InfoExtractor): self.to_stdout('[youtube] %s: Downloading video webpage' % 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)) + sys.exit('ERROR: unable to download video: %s' % str(err)) self.to_stdout('[youtube] %s: Extracting video information' % 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: @@ -409,17 +444,18 @@ class YoutubeIE(InfoExtractor): # 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) @@ -437,29 +473,89 @@ class YoutubeIE(InfoExtractor): if __name__ == '__main__': try: + # Modules needed only when running the main program + import getpass + import optparse + # General configuration urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler())) urllib2.install_opener(urllib2.build_opener(urllib2.HTTPCookieProcessor())) + socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words) + + # Parse command line + parser = optparse.OptionParser( + usage='Usage: %prog [options] url...', + version='INTERNAL', + conflict_handler='resolve', + ) + parser.add_option('-h', '--help', + action='help', help='print this help text and exit') + parser.add_option('-v', '--version', + action='version', help='print program version and exit') + parser.add_option('-u', '--username', + dest='username', metavar='UN', help='account username') + parser.add_option('-p', '--password', + dest='password', metavar='PW', help='account password') + parser.add_option('-o', '--output', + dest='outtmpl', metavar='TPL', help='output filename template') + parser.add_option('-q', '--quiet', + action='store_true', dest='quiet', help='activates quiet mode', default=False) + parser.add_option('-s', '--simulate', + action='store_true', dest='simulate', help='do not download video', default=False) + parser.add_option('-t', '--title', + action='store_true', dest='usetitle', help='use title in file name', default=False) + parser.add_option('-l', '--literal', + action='store_true', dest='useliteral', help='use literal title in file name', default=False) + parser.add_option('-n', '--netrc', + action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False) + parser.add_option('-g', '--get-url', + action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False) + parser.add_option('-e', '--get-title', + action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False) + 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') + 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 + if len(args) < 1: + sys.exit('ERROR: you must provide at least one URL') + if opts.usenetrc and (opts.username is not None or opts.password is not None): + sys.exit('ERROR: using .netrc conflicts with giving username/password') + if opts.password is not None and opts.username is None: + sys.exit('ERROR: account username missing') + if opts.outtmpl is not None and (opts.useliteral or opts.usetitle): + sys.exit('ERROR: using output template conflicts with using title or literal title') + if opts.usetitle and opts.useliteral: + 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:') # Information extractors youtube_ie = YoutubeIE() # File downloader fd = FileDownloader({ - 'usenetrc': False, - 'username': None, - 'password': None, - 'quiet': False, - 'simulate': False, - 'format': None, - 'outtmpl': '%(ext)s/%(ext)s/%(id)s.%(ext)s' + 'usenetrc': opts.usenetrc, + 'username': opts.username, + 'password': opts.password, + 'quiet': (opts.quiet or opts.geturl or opts.gettitle), + 'forceurl': opts.geturl, + 'forcetitle': opts.gettitle, + 'simulate': (opts.simulate or opts.geturl or opts.gettitle), + 'format': opts.format, + 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl) + 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([ - 'http://www.youtube.com/watch?v=t7qdwI7TVe8', - 'http://www.youtube.com/watch?v=IJyn3pRcy_Q', - 'http://www.youtube.com/watch?v=DZRXe1wtC-M', - ]) + retcode = fd.download(args) + sys.exit(retcode) except KeyboardInterrupt: sys.exit('\nERROR: Interrupted by user')