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',
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.
For this, file downloader objects have a method that allows
InfoExtractors to be registered in a given order. When it is passed
a URL, the file downloader handles it to the first InfoExtractor it
- finds that reports it's able to handle it. The InfoExtractor returns
+ finds that reports being able to handle it. The InfoExtractor returns
all the information to the FileDownloader and the latter downloads the
file or does whatever it's instructed to do.
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)
else:
exponent = long(math.log(float(bytes), 1024.0))
suffix = 'bkMGTPEZY'[exponent]
- if exponent == 0:
- return '%s%s' % (bytes, suffix)
converted = float(bytes) / float(1024**exponent)
return '%.2f%s' % (converted, suffix)
def calc_speed(start, now, bytes):
dif = now - start
if bytes == 0 or dif < 0.001: # One millisecond
- return '%9s' % 'N/A b/s'
+ return '%10s' % '---b/s'
return '%10s' % ('%s/s' % FileDownloader.format_bytes(float(bytes) / dif))
@staticmethod
self._ies.append(ie)
ie.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]))
+ sys.stdout.flush()
+
+ 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 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:
continue
# Suitable InfoExtractor found
suitable_found = True
- for result in ie.extract(url):
- if result is 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():
+ 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:
- sys.stderr.write('ERROR: invalid output template: %s\n' % 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:
- sys.stderr.write('ERROR: unable to create directories: %s\n' % str(err))
+ retcode = self.trouble('ERROR: unable to create directories: %s' % str(err))
continue
try:
outstream = open(filename, 'wb')
except (OSError, IOError), err:
- sys.stderr.write('ERROR: unable to open for writing: %s\n' % 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:
- sys.stderr.write('ERROR: unable to write video data: %s\n' % str(err))
+ retcode = self.trouble('ERROR: unable to write video data: %s' % str(err))
continue
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- sys.stderr.write('ERROR: unable to download video data: %s\n' % str(err))
+ retcode = self.trouble('ERROR: unable to download video data: %s' % str(err))
continue
break
if not suitable_found:
- sys.stderr.write('ERROR: no suitable InfoExtractor: %s\n' % 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)
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.report_progress(percent_str, data_len_str, speed_str, eta_str)
- if not self._params.get('quiet', False):
- sys.stdout.write('\r[download] %s of %s at %s ETA %s' %
- (percent_str, data_len_str, speed_str, eta_str))
- sys.stdout.flush()
-
+ # Download and write
before = time.time()
data_block = data.read(block_size)
after = time.time()
stream.write(data_block)
block_size = self.best_block_size(after - before, data_block_len)
- if not self._params.get('quiet', False):
- print
-
+ 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))
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
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):
_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
self.to_stderr('WARNING: parsing .netrc: %s' % str(err))
return
+ # No authentication to be performed
if username is None:
return
# Log in
- login_form = { 'current_form': 'loginForm',
+ login_form = {
+ 'current_form': 'loginForm',
'next': '/',
'action_login': 'Log In',
'username': username,
- 'password': password, }
+ 'password': password,
+ }
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)<form[^>]* 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
- age_form = { 'next_url': '/',
- 'action_confirm': 'Confirm', }
+ age_form = {
+ 'next_url': '/',
+ 'action_confirm': 'Confirm',
+ }
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)
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
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.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)<title>YouTube - ([^<]*)</title>', 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(u'&(.+?);', lambda x: unichr(htmlentitydefs.name2codepoint[x.group(1)]), video_title)
+ 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(u'([^%s]+)' % simple_title_chars, u'_', video_title)
- simple_title = simple_title.strip(u'_')
+ simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+ simple_title = simple_title.strip(ur'_')
# Return information
- return [{ 'id': video_id,
- 'url': video_real_url,
- 'uploader': video_uploader,
- 'title': video_title,
- 'stitle': simple_title,
- 'ext': video_extension,
- }]
+ return [{
+ 'id': video_id,
+ 'url': video_real_url,
+ 'uploader': video_uploader,
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension,
+ }]
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('-m', '--mobile-version',
+ action='store_const', dest='video_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
+ 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,
- 'format': None,
- 'outtmpl': '%(id)s.%(ext)s'
- })
+ fd = FileDownloader({
+ '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 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')