# Author: Danny Colligan
# Author: Benjamin Johnson
# License: Public domain code
+import cookielib
import htmlentitydefs
import httplib
import locale
from cgi import parse_qs
std_headers = {
- 'User-Agent': 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.8) Gecko/20100723 Firefox/3.6.8',
+ 'User-Agent': 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.11) Gecko/20101019 Firefox/3.6.11',
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Language': 'en-us,en;q=0.5',
"""
try:
if filename == u'-':
+ if sys.platform == 'win32':
+ import msvcrt
+ msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
return (sys.stdout, filename)
stream = open(filename, open_mode)
return (stream, filename)
Available options:
- username: Username for authentication purposes.
- 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.
- format_limit: Highest quality format to try.
- outtmpl: Template for output names.
- ignoreerrors: Do not stop on download errors.
- ratelimit: Download speed limit, in bytes/sec.
- nooverwrites: Prevent overwriting files.
- retries: Number of times to retry for HTTP error 503
- continuedl: Try to continue downloads if possible.
- noprogress: Do not print the progress bar.
+ username: Username for authentication purposes.
+ 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.
+ forcethumbnail: Force printing thumbnail URL.
+ forcedescription: Force printing description.
+ simulate: Do not download the video files.
+ format: Video format code.
+ format_limit: Highest quality format to try.
+ outtmpl: Template for output names.
+ ignoreerrors: Do not stop on download errors.
+ ratelimit: Download speed limit, in bytes/sec.
+ nooverwrites: Prevent overwriting files.
+ retries: Number of times to retry for HTTP error 5xx
+ continuedl: Try to continue downloads if possible.
+ noprogress: Do not print the progress bar.
+ playliststart: Playlist item to start at.
+ logtostderr: Log messages to stderr instead of stdout.
"""
params = None
_pps = []
_download_retcode = None
_num_downloads = None
+ _screen_file = None
def __init__(self, params):
"""Create a FileDownloader object with the given options."""
self._pps = []
self._download_retcode = 0
self._num_downloads = 0
+ self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
self.params = params
@staticmethod
self._pps.append(pp)
pp.set_downloader(self)
- def to_stdout(self, message, skip_eol=False, ignore_encoding_errors=False):
+ def to_screen(self, message, skip_eol=False, ignore_encoding_errors=False):
"""Print message to stdout if not in quiet mode."""
try:
if not self.params.get('quiet', False):
- print (u'%s%s' % (message, [u'\n', u''][skip_eol])).encode(preferredencoding()),
- sys.stdout.flush()
+ terminator = [u'\n', u''][skip_eol]
+ print >>self._screen_file, (u'%s%s' % (message, terminator)).encode(preferredencoding()),
+ self._screen_file.flush()
except (UnicodeEncodeError), err:
if not ignore_encoding_errors:
raise
def report_destination(self, filename):
"""Report destination filename."""
- self.to_stdout(u'[download] Destination: %s' % filename, ignore_encoding_errors=True)
+ self.to_screen(u'[download] Destination: %s' % filename, ignore_encoding_errors=True)
def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
"""Report download progress."""
if self.params.get('noprogress', False):
return
- self.to_stdout(u'\r[download] %s of %s at %s ETA %s' %
+ self.to_screen(u'\r[download] %s of %s at %s ETA %s' %
(percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
def report_resuming_byte(self, resume_len):
- """Report attemtp to resume at given byte."""
- self.to_stdout(u'[download] Resuming download at byte %s' % resume_len)
+ """Report attempt to resume at given byte."""
+ self.to_screen(u'[download] Resuming download at byte %s' % resume_len)
def report_retry(self, count, retries):
- """Report retry in case of HTTP error 503"""
- self.to_stdout(u'[download] Got HTTP error 503. Retrying (attempt %d of %d)...' % (count, retries))
+ """Report retry in case of HTTP error 5xx"""
+ self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries))
def report_file_already_downloaded(self, file_name):
"""Report file has already been fully downloaded."""
try:
- self.to_stdout(u'[download] %s has already been downloaded' % file_name)
+ self.to_screen(u'[download] %s has already been downloaded' % file_name)
except (UnicodeEncodeError), err:
- self.to_stdout(u'[download] The file has already been downloaded')
+ self.to_screen(u'[download] The file has already been downloaded')
def report_unable_to_resume(self):
"""Report it was impossible to resume download."""
- self.to_stdout(u'[download] Unable to resume')
+ self.to_screen(u'[download] Unable to resume')
def report_finish(self):
"""Report download finished."""
if self.params.get('noprogress', False):
- self.to_stdout(u'[download] Download completed')
+ self.to_screen(u'[download] Download completed')
else:
- self.to_stdout(u'')
+ self.to_screen(u'')
def increment_downloads(self):
"""Increment the ordinal that assigns a number to each file."""
template_dict['ord'] = unicode('%05d' % self._num_downloads)
filename = self.params['outtmpl'] % template_dict
except (ValueError, KeyError), err:
- self.trouble('ERROR: invalid output template or system charset: %s' % str(err))
+ self.trouble(u'ERROR: invalid system charset or erroneous output template')
+ return
if self.params.get('nooverwrites', False) and os.path.exists(filename):
- self.to_stderr(u'WARNING: file exists: %s; skipping' % filename)
+ self.to_stderr(u'WARNING: file exists and will be skipped')
return
try:
self.pmkdir(filename)
except (OSError, IOError), err:
- self.trouble('ERROR: unable to create directories: %s' % str(err))
+ self.trouble(u'ERROR: unable to create directories: %s' % str(err))
return
try:
except (OSError, IOError), err:
raise UnavailableVideoError
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self.trouble('ERROR: unable to download video data: %s' % str(err))
+ self.trouble(u'ERROR: unable to download video data: %s' % str(err))
return
except (ContentTooShortError, ), err:
- self.trouble('ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
+ self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
return
if success:
try:
self.post_process(filename, info_dict)
except (PostProcessingError), err:
- self.trouble('ERROR: postprocessing: %s' % str(err))
+ self.trouble(u'ERROR: postprocessing: %s' % str(err))
return
def download(self, url_list):
break
if not suitable_found:
- self.trouble('ERROR: no suitable InfoExtractor: %s' % url)
+ self.trouble(u'ERROR: no suitable InfoExtractor: %s' % url)
return self._download_retcode
retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)])
while retval == 2 or retval == 1:
prevsize = os.path.getsize(filename)
- self.to_stdout(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True)
+ self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True)
time.sleep(5.0) # This seems to be needed
retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])
cursize = os.path.getsize(filename)
if prevsize == cursize and retval == 1:
break
if retval == 0:
- self.to_stdout(u'\r[rtmpdump] %s bytes' % os.path.getsize(filename))
+ self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(filename))
return True
else:
- self.trouble('\nERROR: rtmpdump exited with code %d' % retval)
+ self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval)
return False
def _do_download(self, filename, url, player_url):
data = urllib2.urlopen(request)
break
except (urllib2.HTTPError, ), err:
- if err.code != 503 and err.code != 416:
+ if (err.code < 500 or err.code >= 600) and err.code != 416:
# Unexpected HTTP error
raise
elif err.code == 416:
data = urllib2.urlopen(basic_request)
content_length = data.info()['Content-Length']
except (urllib2.HTTPError, ), err:
- if err.code != 503:
+ if err.code < 500 or err.code >= 600:
raise
else:
# Examine the reported length
(stream, filename) = sanitize_open(filename, open_mode)
self.report_destination(filename)
except (OSError, IOError), err:
- self.trouble('ERROR: unable to open for writing: %s' % str(err))
+ self.trouble(u'ERROR: unable to open for writing: %s' % str(err))
return False
try:
stream.write(data_block)
except (IOError, OSError), err:
- self.trouble('\nERROR: unable to write data: %s' % str(err))
+ self.trouble(u'\nERROR: unable to write data: %s' % str(err))
+ return False
block_size = self.best_block_size(after - before, data_block_len)
# Progress message
class YoutubeIE(InfoExtractor):
"""Information extractor for youtube.com."""
- _VALID_URL = r'^((?:http://)?(?:youtu\.be/|(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:_popup)?(?:\.php)?)?[\?#](?:.+&)?v=))))?([0-9A-Za-z_-]+)(?(1).+)?$'
+ _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/(?:(?:v/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))))?([0-9A-Za-z_-]+)(?(1).+)?$'
_LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
- _LOGIN_URL = 'http://www.youtube.com/signup?next=/&gl=US&hl=en'
+ _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en'
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
_NETRC_MACHINE = 'youtube'
# Listed in order of quality
def report_lang(self):
"""Report attempt to set language."""
- self._downloader.to_stdout(u'[youtube] Setting language')
+ self._downloader.to_screen(u'[youtube] Setting language')
def report_login(self):
"""Report attempt to log in."""
- self._downloader.to_stdout(u'[youtube] Logging in')
+ self._downloader.to_screen(u'[youtube] Logging in')
def report_age_confirmation(self):
"""Report attempt to confirm age."""
- self._downloader.to_stdout(u'[youtube] Confirming age')
+ self._downloader.to_screen(u'[youtube] Confirming age')
def report_video_webpage_download(self, video_id):
"""Report attempt to download video webpage."""
- self._downloader.to_stdout(u'[youtube] %s: Downloading video webpage' % video_id)
+ self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id)
def report_video_info_webpage_download(self, video_id):
"""Report attempt to download video info webpage."""
- self._downloader.to_stdout(u'[youtube] %s: Downloading video info webpage' % video_id)
+ self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id)
def report_information_extraction(self, video_id):
"""Report attempt to extract video information."""
- self._downloader.to_stdout(u'[youtube] %s: Extracting video information' % video_id)
+ self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id)
def report_unavailable_format(self, video_id, format):
"""Report extracted video URL."""
- self._downloader.to_stdout(u'[youtube] %s: Format %s not available' % (video_id, format))
+ self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format))
def report_rtmp_download(self):
"""Indicate the download will use the RTMP protocol."""
- self._downloader.to_stdout(u'[youtube] RTMP download detected')
+ self._downloader.to_screen(u'[youtube] RTMP download detected')
def _real_initialize(self):
if self._downloader is None:
return
if 'token' not in video_info:
if 'reason' in video_info:
- self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0])
+ self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0].decode('utf-8'))
else:
self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason')
return
def report_disclaimer(self):
"""Report disclaimer retrieval."""
- self._downloader.to_stdout(u'[metacafe] Retrieving disclaimer')
+ self._downloader.to_screen(u'[metacafe] Retrieving disclaimer')
def report_age_confirmation(self):
"""Report attempt to confirm age."""
- self._downloader.to_stdout(u'[metacafe] Confirming age')
+ self._downloader.to_screen(u'[metacafe] Confirming age')
def report_download_webpage(self, video_id):
"""Report webpage download."""
- self._downloader.to_stdout(u'[metacafe] %s: Downloading webpage' % video_id)
+ self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id)
def report_extraction(self, video_id):
"""Report information extraction."""
- self._downloader.to_stdout(u'[metacafe] %s: Extracting information' % video_id)
+ self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id)
def _real_initialize(self):
# Retrieve disclaimer
self._downloader.increment_downloads()
simple_title = mobj.group(2).decode('utf-8')
- video_extension = 'flv'
# Retrieve video webpage to extract further information
request = urllib2.Request('http://www.metacafe.com/watch/%s/' % video_id)
# Extract URL, uploader and title from webpage
self.report_extraction(video_id)
mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
- mediaURL = urllib.unquote(mobj.group(1))
-
- # Extract gdaKey if available
- mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
- if mobj is None:
- video_url = mediaURL
- #self._downloader.trouble(u'ERROR: unable to extract gdaKey')
- #return
+ if mobj is not None:
+ mediaURL = urllib.unquote(mobj.group(1))
+ video_extension = mediaURL[-3:]
+
+ # Extract gdaKey if available
+ mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
+ if mobj is None:
+ video_url = mediaURL
+ else:
+ gdaKey = mobj.group(1)
+ video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
else:
- gdaKey = mobj.group(1)
- video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
+ mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract media URL')
+ return
+ vardict = parse_qs(mobj.group(1))
+ if 'mediaData' not in vardict:
+ self._downloader.trouble(u'ERROR: unable to extract media URL')
+ return
+ mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0])
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract media URL')
+ return
+ mediaURL = mobj.group(1).replace('\\/', '/')
+ video_extension = mediaURL[-3:]
+ video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2))
mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
if mobj is None:
def report_download_webpage(self, video_id):
"""Report webpage download."""
- self._downloader.to_stdout(u'[dailymotion] %s: Downloading webpage' % video_id)
+ self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id)
def report_extraction(self, video_id):
"""Report information extraction."""
- self._downloader.to_stdout(u'[dailymotion] %s: Extracting information' % video_id)
+ self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id)
def _real_initialize(self):
return
video_title = mobj.group(1).decode('utf-8')
video_title = sanitize_title(video_title)
- mobj = re.search(r'(?im)<div class="dmco_html owner">.*?<a class="name" href="/.+?">(.+?)</a></div>', webpage)
+ mobj = re.search(r'(?im)<div class="dmco_html owner">.*?<a class="name" href="/.+?">(.+?)</a>', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
return
def report_download_webpage(self, video_id):
"""Report webpage download."""
- self._downloader.to_stdout(u'[video.google] %s: Downloading webpage' % video_id)
+ self._downloader.to_screen(u'[video.google] %s: Downloading webpage' % video_id)
def report_extraction(self, video_id):
"""Report information extraction."""
- self._downloader.to_stdout(u'[video.google] %s: Extracting information' % video_id)
+ self._downloader.to_screen(u'[video.google] %s: Extracting information' % video_id)
def _real_initialize(self):
return
def report_download_webpage(self, video_id):
"""Report webpage download."""
- self._downloader.to_stdout(u'[photobucket] %s: Downloading webpage' % video_id)
+ self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id)
def report_extraction(self, video_id):
"""Report information extraction."""
- self._downloader.to_stdout(u'[photobucket] %s: Extracting information' % video_id)
+ self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id)
def _real_initialize(self):
return
def report_download_webpage(self, video_id):
"""Report webpage download."""
- self._downloader.to_stdout(u'[video.yahoo] %s: Downloading webpage' % video_id)
+ self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id)
def report_extraction(self, video_id):
"""Report information extraction."""
- self._downloader.to_stdout(u'[video.yahoo] %s: Extracting information' % video_id)
+ self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id)
def _real_initialize(self):
return
def report_download_webpage(self, video_id):
"""Report webpage download."""
- self._downloader.to_stdout(u'WARNING: Falling back on generic information extractor.')
- self._downloader.to_stdout(u'[generic] %s: Downloading webpage' % video_id)
+ self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.')
+ self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id)
def report_extraction(self, video_id):
"""Report information extraction."""
- self._downloader.to_stdout(u'[generic] %s: Extracting information' % video_id)
+ self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id)
def _real_initialize(self):
return
def report_download_page(self, query, pagenum):
"""Report attempt to download playlist page with given number."""
query = query.decode(preferredencoding())
- self._downloader.to_stdout(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
+ self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
def _real_initialize(self):
self._youtube_ie.initialize()
def report_download_page(self, query, pagenum):
"""Report attempt to download playlist page with given number."""
query = query.decode(preferredencoding())
- self._downloader.to_stdout(u'[video.google] query "%s": Downloading page %s' % (query, pagenum))
+ self._downloader.to_screen(u'[video.google] query "%s": Downloading page %s' % (query, pagenum))
def _real_initialize(self):
self._google_ie.initialize()
def report_download_page(self, query, pagenum):
"""Report attempt to download playlist page with given number."""
query = query.decode(preferredencoding())
- self._downloader.to_stdout(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum))
+ self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum))
def _real_initialize(self):
self._yahoo_ie.initialize()
def report_download_page(self, playlist_id, pagenum):
"""Report attempt to download playlist page with given number."""
- self._downloader.to_stdout(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
+ self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
def _real_initialize(self):
self._youtube_ie.initialize()
def report_download_page(self, username):
"""Report attempt to download user page."""
- self._downloader.to_stdout(u'[youtube] user %s: Downloading page ' % (username))
+ self._downloader.to_screen(u'[youtube] user %s: Downloading page ' % (username))
def _real_initialize(self):
self._youtube_ie.initialize()
if not os.access (filename, os.W_OK):
sys.exit('ERROR: no write permissions on %s' % filename)
- downloader.to_stdout('Updating to latest stable version...')
+ downloader.to_screen('Updating to latest stable version...')
latest_url = 'http://bitbucket.org/rg3/youtube-dl/raw/tip/LATEST_VERSION'
latest_version = urllib.urlopen(latest_url).read().strip()
prog_url = 'http://bitbucket.org/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version
stream = open(filename, 'w')
stream.write(newcontent)
stream.close()
- downloader.to_stdout('Updated to version %s' % latest_version)
-
- # 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)
+ downloader.to_screen('Updated to version %s' % latest_version)
# Parse command line
parser = optparse.OptionParser(
usage='Usage: %prog [options] url...',
- version='2010.08.04',
+ version='2010.10.24',
conflict_handler='resolve',
)
action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
filesystem.add_option('-c', '--continue',
action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False)
+ filesystem.add_option('--cookies',
+ dest='cookiefile', metavar='FILE', help='file to dump cookie jar to')
parser.add_option_group(filesystem)
(opts, args) = parser.parse_args()
+ # Open appropriate CookieJar
+ if opts.cookiefile is None:
+ jar = cookielib.CookieJar()
+ else:
+ try:
+ jar = cookielib.MozillaCookieJar(opts.cookiefile)
+ if os.path.isfile(opts.cookiefile) and os.access(opts.cookiefile, os.R_OK):
+ jar.load()
+ except (IOError, OSError), err:
+ sys.exit(u'ERROR: unable to open cookie file')
+
+ # General configuration
+ cookie_processor = urllib2.HTTPCookieProcessor(jar)
+ urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler()))
+ urllib2.install_opener(urllib2.build_opener(cookie_processor))
+ socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
+
# Batch file verification
batchurls = []
if opts.batchfile is not None:
'continuedl': opts.continue_dl,
'noprogress': opts.noprogress,
'playliststart': opts.playliststart,
+ 'logtostderr': opts.outtmpl == '-',
})
fd.add_info_extractor(youtube_search_ie)
fd.add_info_extractor(youtube_pl_ie)
else:
sys.exit()
retcode = fd.download(all_urls)
+
+ # Dump cookie jar if requested
+ if opts.cookiefile is not None:
+ try:
+ jar.save()
+ except (IOError, OSError), err:
+ sys.exit(u'ERROR: unable to save cookie jar')
+
sys.exit(retcode)
except DownloadError:
Rapsys Git / youtubedl / blobdiff