|
|
|
@ -52,6 +52,13 @@ class PostProcessingError(Exception):
|
|
|
|
|
"""
|
|
|
|
|
pass
|
|
|
|
|
|
|
|
|
|
class UnavailableFormatError(Exception):
|
|
|
|
|
"""Unavailable Format exception.
|
|
|
|
|
|
|
|
|
|
This exception will be thrown when a video is requested
|
|
|
|
|
in a format that is not available for that video.
|
|
|
|
|
"""
|
|
|
|
|
|
|
|
|
|
class FileDownloader(object):
|
|
|
|
|
"""File Downloader class.
|
|
|
|
|
|
|
|
|
@ -260,33 +267,38 @@ class FileDownloader(object):
|
|
|
|
|
if self.params['nooverwrites'] and os.path.exists(filename):
|
|
|
|
|
self.to_stderr('WARNING: file exists: %s; skipping' % filename)
|
|
|
|
|
return
|
|
|
|
|
|
|
|
|
|
try:
|
|
|
|
|
self.pmkdir(filename)
|
|
|
|
|
except (OSError, IOError), err:
|
|
|
|
|
self.trouble('ERROR: unable to create directories: %s' % str(err))
|
|
|
|
|
return
|
|
|
|
|
|
|
|
|
|
try:
|
|
|
|
|
outstream = open(filename, 'wb')
|
|
|
|
|
except (OSError, IOError), err:
|
|
|
|
|
self.trouble('ERROR: unable to open for writing: %s' % str(err))
|
|
|
|
|
return
|
|
|
|
|
|
|
|
|
|
try:
|
|
|
|
|
self._do_download(outstream, info_dict['url'])
|
|
|
|
|
outstream.close()
|
|
|
|
|
except (OSError, IOError), err:
|
|
|
|
|
self.trouble('ERROR: unable to write video data: %s' % str(err))
|
|
|
|
|
return
|
|
|
|
|
if info_dict['best_quality']:
|
|
|
|
|
raise UnavailableFormatError
|
|
|
|
|
else:
|
|
|
|
|
self.trouble('ERROR: unable to write video data: %s' % str(err))
|
|
|
|
|
return
|
|
|
|
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
|
|
|
|
self.trouble('ERROR: unable to download video data: %s' % str(err))
|
|
|
|
|
return
|
|
|
|
|
|
|
|
|
|
try:
|
|
|
|
|
self.post_process(filename, info_dict)
|
|
|
|
|
except (PostProcessingError), err:
|
|
|
|
|
self.trouble('ERROR: postprocessing: %s' % str(err))
|
|
|
|
|
return
|
|
|
|
|
|
|
|
|
|
return
|
|
|
|
|
|
|
|
|
|
def download(self, url_list):
|
|
|
|
|
"""Download a given list of URLs."""
|
|
|
|
|
if len(url_list) > 1 and self.fixed_template():
|
|
|
|
@ -424,6 +436,13 @@ class YoutubeIE(InfoExtractor):
|
|
|
|
|
_LOGIN_URL = 'http://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'
|
|
|
|
|
_available_formats = ['22', '18', '17', '13'] # listed in order of priority for -b flag
|
|
|
|
|
_video_extensions = {
|
|
|
|
|
'13': '3gp',
|
|
|
|
|
'17': 'mp4',
|
|
|
|
|
'18': 'mp4',
|
|
|
|
|
'22': 'mp4',
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
@staticmethod
|
|
|
|
|
def suitable(url):
|
|
|
|
@ -476,6 +495,10 @@ class YoutubeIE(InfoExtractor):
|
|
|
|
|
"""Report extracted video URL."""
|
|
|
|
|
self._downloader.to_stdout(u'[youtube] %s: URL: %s' % (video_id, video_real_url))
|
|
|
|
|
|
|
|
|
|
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))
|
|
|
|
|
|
|
|
|
|
def _real_initialize(self):
|
|
|
|
|
if self._downloader is None:
|
|
|
|
|
return
|
|
|
|
@ -554,71 +577,87 @@ class YoutubeIE(InfoExtractor):
|
|
|
|
|
video_id = mobj.group(2)
|
|
|
|
|
|
|
|
|
|
# Downloader parameters
|
|
|
|
|
best_quality = False
|
|
|
|
|
format_param = None
|
|
|
|
|
quality_index = 0
|
|
|
|
|
if self._downloader is not None:
|
|
|
|
|
params = self._downloader.params
|
|
|
|
|
format_param = params.get('format', None)
|
|
|
|
|
if format_param == '0':
|
|
|
|
|
format_param = self._available_formats[quality_index]
|
|
|
|
|
best_quality = True
|
|
|
|
|
|
|
|
|
|
# Extension
|
|
|
|
|
video_extension = {
|
|
|
|
|
'13': '3gp',
|
|
|
|
|
'17': 'mp4',
|
|
|
|
|
'18': 'mp4',
|
|
|
|
|
'22': 'mp4',
|
|
|
|
|
}.get(format_param, 'flv')
|
|
|
|
|
|
|
|
|
|
# Normalize URL, including format
|
|
|
|
|
normalized_url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id
|
|
|
|
|
if format_param is not None:
|
|
|
|
|
normalized_url = '%s&fmt=%s' % (normalized_url, format_param)
|
|
|
|
|
request = urllib2.Request(normalized_url, None, std_headers)
|
|
|
|
|
try:
|
|
|
|
|
self.report_webpage_download(video_id)
|
|
|
|
|
video_webpage = urllib2.urlopen(request).read()
|
|
|
|
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
|
|
|
|
self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
|
|
|
|
|
return
|
|
|
|
|
self.report_information_extraction(video_id)
|
|
|
|
|
|
|
|
|
|
# "t" param
|
|
|
|
|
mobj = re.search(r', "t": "([^"]+)"', video_webpage)
|
|
|
|
|
if mobj is None:
|
|
|
|
|
self._downloader.trouble(u'ERROR: unable to extract "t" parameter')
|
|
|
|
|
return
|
|
|
|
|
video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&el=detailpage&ps=' % (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)
|
|
|
|
|
while True:
|
|
|
|
|
try:
|
|
|
|
|
# Extension
|
|
|
|
|
video_extension = self._video_extensions.get(format_param, 'flv')
|
|
|
|
|
|
|
|
|
|
# Normalize URL, including format
|
|
|
|
|
normalized_url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id
|
|
|
|
|
if format_param is not None:
|
|
|
|
|
normalized_url = '%s&fmt=%s' % (normalized_url, format_param)
|
|
|
|
|
request = urllib2.Request(normalized_url, None, std_headers)
|
|
|
|
|
try:
|
|
|
|
|
self.report_webpage_download(video_id)
|
|
|
|
|
video_webpage = urllib2.urlopen(request).read()
|
|
|
|
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
|
|
|
|
self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
|
|
|
|
|
return
|
|
|
|
|
self.report_information_extraction(video_id)
|
|
|
|
|
|
|
|
|
|
# uploader
|
|
|
|
|
mobj = re.search(r"var watchUsername = '([^']+)';", video_webpage)
|
|
|
|
|
if mobj is None:
|
|
|
|
|
self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
|
|
|
|
|
return
|
|
|
|
|
video_uploader = mobj.group(1)
|
|
|
|
|
# "t" param
|
|
|
|
|
mobj = re.search(r', "t": "([^"]+)"', video_webpage)
|
|
|
|
|
if mobj is None:
|
|
|
|
|
self._downloader.trouble(u'ERROR: unable to extract "t" parameter')
|
|
|
|
|
return
|
|
|
|
|
video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&el=detailpage&ps=' % (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"var watchUsername = '([^']+)';", video_webpage)
|
|
|
|
|
if mobj is None:
|
|
|
|
|
self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
|
|
|
|
|
return
|
|
|
|
|
video_uploader = mobj.group(1)
|
|
|
|
|
|
|
|
|
|
# title
|
|
|
|
|
mobj = re.search(r'(?im)<title>YouTube - ([^<]*)</title>', video_webpage)
|
|
|
|
|
if mobj is None:
|
|
|
|
|
self._downloader.trouble(u'ERROR: unable to extract video title')
|
|
|
|
|
return
|
|
|
|
|
video_title = mobj.group(1).decode('utf-8')
|
|
|
|
|
video_title = re.sub(ur'(?u)&(.+?);', self.htmlentity_transform, video_title)
|
|
|
|
|
video_title = video_title.replace(os.sep, u'%')
|
|
|
|
|
# title
|
|
|
|
|
mobj = re.search(r'(?im)<title>YouTube - ([^<]*)</title>', video_webpage)
|
|
|
|
|
if mobj is None:
|
|
|
|
|
self._downloader.trouble(u'ERROR: unable to extract video title')
|
|
|
|
|
return
|
|
|
|
|
video_title = mobj.group(1).decode('utf-8')
|
|
|
|
|
video_title = re.sub(ur'(?u)&(.+?);', self.htmlentity_transform, 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)
|
|
|
|
|
simple_title = simple_title.strip(ur'_')
|
|
|
|
|
|
|
|
|
|
# Process video information
|
|
|
|
|
self._downloader.process_info({
|
|
|
|
|
'id': video_id.decode('utf-8'),
|
|
|
|
|
'url': video_real_url.decode('utf-8'),
|
|
|
|
|
'uploader': video_uploader.decode('utf-8'),
|
|
|
|
|
'title': video_title,
|
|
|
|
|
'stitle': simple_title,
|
|
|
|
|
'ext': video_extension.decode('utf-8'),
|
|
|
|
|
'best_quality': best_quality,
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
# simplified title
|
|
|
|
|
simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
|
|
|
|
|
simple_title = simple_title.strip(ur'_')
|
|
|
|
|
return
|
|
|
|
|
|
|
|
|
|
# Process video information
|
|
|
|
|
self._downloader.process_info({
|
|
|
|
|
'id': video_id.decode('utf-8'),
|
|
|
|
|
'url': video_real_url.decode('utf-8'),
|
|
|
|
|
'uploader': video_uploader.decode('utf-8'),
|
|
|
|
|
'title': video_title,
|
|
|
|
|
'stitle': simple_title,
|
|
|
|
|
'ext': video_extension.decode('utf-8'),
|
|
|
|
|
})
|
|
|
|
|
except UnavailableFormatError:
|
|
|
|
|
if quality_index == len(self._available_formats) - 1:
|
|
|
|
|
# I don't ever expect this to happen
|
|
|
|
|
self._downloader.trouble(u'ERROR: no known formats available for video')
|
|
|
|
|
return
|
|
|
|
|
else:
|
|
|
|
|
self.report_unavailable_format(video_id, format_param)
|
|
|
|
|
quality_index += 1
|
|
|
|
|
format_param = self._available_formats[quality_index]
|
|
|
|
|
continue
|
|
|
|
|
|
|
|
|
|
class MetacafeIE(InfoExtractor):
|
|
|
|
|
"""Information Extractor for metacafe.com."""
|
|
|
|
@ -738,7 +777,8 @@ class MetacafeIE(InfoExtractor):
|
|
|
|
|
'title': video_title,
|
|
|
|
|
'stitle': simple_title,
|
|
|
|
|
'ext': video_extension.decode('utf-8'),
|
|
|
|
|
})
|
|
|
|
|
'best_quality': False, # TODO
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class YoutubeSearchIE(InfoExtractor):
|
|
|
|
@ -950,48 +990,64 @@ if __name__ == '__main__':
|
|
|
|
|
|
|
|
|
|
# Parse command line
|
|
|
|
|
parser = optparse.OptionParser(
|
|
|
|
|
usage='Usage: %prog [options] url...',
|
|
|
|
|
version='INTERNAL',
|
|
|
|
|
conflict_handler='resolve',
|
|
|
|
|
)
|
|
|
|
|
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',
|
|
|
|
|
parser.add_option('-i', '--ignore-errors',
|
|
|
|
|
action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
|
|
|
|
|
parser.add_option('-r', '--rate-limit',
|
|
|
|
|
dest='ratelimit', metavar='L', help='download rate limit (e.g. 50k or 44.6m)')
|
|
|
|
|
|
|
|
|
|
authentication = optparse.OptionGroup(parser, 'Authentication Options')
|
|
|
|
|
authentication.add_option('-u', '--username',
|
|
|
|
|
dest='username', metavar='UN', help='account username')
|
|
|
|
|
parser.add_option('-p', '--password',
|
|
|
|
|
authentication.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',
|
|
|
|
|
authentication.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',
|
|
|
|
|
parser.add_option_group(authentication)
|
|
|
|
|
|
|
|
|
|
video_format = optparse.OptionGroup(parser, 'Video Format Options')
|
|
|
|
|
video_format.add_option('-f', '--format',
|
|
|
|
|
dest='format', metavar='FMT', help='video format code')
|
|
|
|
|
parser.add_option('-m', '--mobile-version',
|
|
|
|
|
video_format.add_option('-b', '--best-quality',
|
|
|
|
|
action='store_const', dest='format', help='download the best quality video possible', const='0')
|
|
|
|
|
video_format.add_option('-m', '--mobile-version',
|
|
|
|
|
action='store_const', dest='format', help='alias for -f 17', const='17')
|
|
|
|
|
parser.add_option('-d', '--high-def',
|
|
|
|
|
video_format.add_option('-d', '--high-def',
|
|
|
|
|
action='store_const', dest='format', help='alias for -f 22', const='22')
|
|
|
|
|
parser.add_option('-i', '--ignore-errors',
|
|
|
|
|
action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
|
|
|
|
|
parser.add_option('-r', '--rate-limit',
|
|
|
|
|
dest='ratelimit', metavar='L', help='download rate limit (e.g. 50k or 44.6m)')
|
|
|
|
|
parser.add_option('-a', '--batch-file',
|
|
|
|
|
parser.add_option_group(video_format)
|
|
|
|
|
|
|
|
|
|
verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
|
|
|
|
|
verbosity.add_option('-q', '--quiet',
|
|
|
|
|
action='store_true', dest='quiet', help='activates quiet mode', default=False)
|
|
|
|
|
verbosity.add_option('-s', '--simulate',
|
|
|
|
|
action='store_true', dest='simulate', help='do not download video', default=False)
|
|
|
|
|
verbosity.add_option('-g', '--get-url',
|
|
|
|
|
action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
|
|
|
|
|
verbosity.add_option('-e', '--get-title',
|
|
|
|
|
action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
|
|
|
|
|
verbosity.add_option('-t', '--title',
|
|
|
|
|
action='store_true', dest='usetitle', help='use title in file name', default=False)
|
|
|
|
|
verbosity.add_option('-l', '--literal',
|
|
|
|
|
action='store_true', dest='useliteral', help='use literal title in file name', default=False)
|
|
|
|
|
parser.add_option_group(verbosity)
|
|
|
|
|
|
|
|
|
|
filesystem = optparse.OptionGroup(parser, 'Filesystem Options')
|
|
|
|
|
filesystem.add_option('-o', '--output',
|
|
|
|
|
dest='outtmpl', metavar='TPL', help='output filename template')
|
|
|
|
|
filesystem.add_option('-a', '--batch-file',
|
|
|
|
|
dest='batchfile', metavar='F', help='file containing URLs to download')
|
|
|
|
|
parser.add_option('-w', '--no-overwrites',
|
|
|
|
|
filesystem.add_option('-w', '--no-overwrites',
|
|
|
|
|
action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
|
|
|
|
|
parser.add_option_group(filesystem)
|
|
|
|
|
|
|
|
|
|
(opts, args) = parser.parse_args()
|
|
|
|
|
|
|
|
|
|
# Batch file verification
|
|
|
|
|