# Author: Benjamin Johnson
# License: Public domain code
import cookielib
+import datetime
import htmlentitydefs
import httplib
import locale
continuedl: Try to continue downloads if possible.
noprogress: Do not print the progress bar.
playliststart: Playlist item to start at.
+ playlistend: Playlist item to end at.
logtostderr: Log messages to stderr instead of stdout.
"""
try:
template_dict = dict(info_dict)
template_dict['epoch'] = unicode(long(time.time()))
- template_dict['ord'] = unicode('%05d' % self._num_downloads)
+ template_dict['autonumber'] = unicode('%05d' % self._num_downloads)
filename = self.params['outtmpl'] % template_dict
except (ValueError, KeyError), err:
self.trouble(u'ERROR: invalid system charset or erroneous output template')
# Get video webpage
self.report_video_webpage_download(video_id)
- request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id, None, std_headers)
+ request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id, None, std_headers)
try:
video_webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
return
# Attempt to extract SWF player URL
- mobj = re.search(r'swfConfig.*"(http://.*?watch.*?-.*?\.swf)"', video_webpage)
+ mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
if mobj is not None:
- player_url = mobj.group(1)
+ player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
else:
player_url = None
else: # don't panic if we can't find it
video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0])
+ # upload date
+ upload_date = u'NA'
+ mobj = re.search(r'id="eow-date".*?>(.*?)</span>', video_webpage, re.DOTALL)
+ if mobj is not None:
+ upload_date = mobj.group(1).split()
+ format_expressions = ['%d %B %Y', '%B %d, %Y']
+ for expression in format_expressions:
+ try:
+ upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d')
+ except:
+ pass
+
# description
video_description = 'No description available.'
if self._downloader.params.get('forcedescription', False):
'id': video_id.decode('utf-8'),
'url': video_real_url.decode('utf-8'),
'uploader': video_uploader.decode('utf-8'),
+ 'uploaddate': upload_date,
'title': video_title,
'stitle': simple_title,
'ext': video_extension.decode('utf-8'),
'id': video_id.decode('utf-8'),
'url': video_url.decode('utf-8'),
'uploader': video_uploader.decode('utf-8'),
+ 'uploaddate': u'NA',
'title': video_title,
'stitle': simple_title,
'ext': video_extension.decode('utf-8'),
'id': video_id.decode('utf-8'),
'url': video_url.decode('utf-8'),
'uploader': video_uploader.decode('utf-8'),
+ 'uploaddate': u'NA',
'title': video_title,
'stitle': simple_title,
'ext': video_extension.decode('utf-8'),
'id': video_id.decode('utf-8'),
'url': video_url.decode('utf-8'),
'uploader': u'NA',
+ 'uploaddate': u'NA',
'title': video_title,
'stitle': simple_title,
'ext': video_extension.decode('utf-8'),
'id': video_id.decode('utf-8'),
'url': video_url.decode('utf-8'),
'uploader': video_uploader,
+ 'uploaddate': u'NA',
'title': video_title,
'stitle': simple_title,
'ext': video_extension.decode('utf-8'),
'id': video_id.decode('utf-8'),
'url': video_url,
'uploader': video_uploader,
+ 'uploaddate': u'NA',
'title': video_title,
'stitle': simple_title,
'ext': video_extension.decode('utf-8'),
'id': video_id.decode('utf-8'),
'url': video_url.decode('utf-8'),
'uploader': video_uploader,
+ 'uploaddate': u'NA',
'title': video_title,
'stitle': simple_title,
'ext': video_extension.decode('utf-8'),
break
pagenum = pagenum + 1
- playliststart = self._downloader.params.get('playliststart', 1)
- playliststart -= 1 #our arrays are zero-based but the playlist is 1-based
- if playliststart > 0:
- video_ids = video_ids[playliststart:]
-
+ playliststart = self._downloader.params.get('playliststart', 1) - 1
+ playlistend = self._downloader.params.get('playlistend', -1)
+ video_ids = video_ids[playliststart:playlistend]
+
for id in video_ids:
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
return
ids_in_page.append(mobj.group(1))
video_ids.extend(ids_in_page)
- playliststart = self._downloader.params.get('playliststart', 1)
- playliststart = playliststart-1 #our arrays are zero-based but the playlist is 1-based
- if playliststart > 0:
- video_ids = video_ids[playliststart:]
+ playliststart = self._downloader.params.get('playliststart', 1) - 1
+ playlistend = self._downloader.params.get('playlistend', -1)
+ video_ids = video_ids[playliststart:playlistend]
for id in video_ids:
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
dest='retries', metavar='RETRIES', help='number of retries (default is 10)', default=10)
parser.add_option('--playlist-start',
dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1)
+ parser.add_option('--playlist-end',
+ dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1)
authentication = optparse.OptionGroup(parser, 'Authentication Options')
authentication.add_option('-u', '--username',
action='store_true', dest='usetitle', help='use title in file name', default=False)
filesystem.add_option('-l', '--literal',
action='store_true', dest='useliteral', help='use literal title in file name', default=False)
+ filesystem.add_option('-A', '--auto-number',
+ action='store_true', dest='autonumber', help='number downloaded files starting from 00000', default=False)
filesystem.add_option('-o', '--output',
dest='outtmpl', metavar='TEMPLATE', help='output filename template')
filesystem.add_option('-a', '--batch-file',
batchfd = open(opts.batchfile, 'r')
batchurls = batchfd.readlines()
batchurls = [x.strip() for x in batchurls]
- batchurls = [x for x in batchurls if len(x) > 0]
+ batchurls = [x for x in batchurls if len(x) > 0 and not re.search(r'^[#/;]', x)]
except IOError:
sys.exit(u'ERROR: batch file could not be read')
all_urls = batchurls + args
parser.error(u'using .netrc conflicts with giving username/password')
if opts.password is not None and opts.username is None:
parser.error(u'account username missing')
- if opts.outtmpl is not None and (opts.useliteral or opts.usetitle):
- parser.error(u'using output template conflicts with using title or literal title')
+ if opts.outtmpl is not None and (opts.useliteral or opts.usetitle or opts.autonumber):
+ parser.error(u'using output template conflicts with using title, literal title or auto number')
if opts.usetitle and opts.useliteral:
parser.error(u'using title conflicts with using literal title')
if opts.username is not None and opts.password is None:
opts.retries = long(opts.retries)
except (TypeError, ValueError), err:
parser.error(u'invalid retry count specified')
- if opts.playliststart is not None:
- try:
- opts.playliststart = long(opts.playliststart)
- except (TypeError, ValueError), err:
- parser.error(u'invalid playlist page specified')
+ try:
+ opts.playliststart = long(opts.playliststart)
+ if opts.playliststart <= 0:
+ raise ValueError
+ except (TypeError, ValueError), err:
+ parser.error(u'invalid playlist start number specified')
+ try:
+ opts.playlistend = long(opts.playlistend)
+ if opts.playlistend != -1 and (opts.playlistend <= 0 or opts.playlistend < opts.playliststart):
+ raise ValueError
+ except (TypeError, ValueError), err:
+ parser.error(u'invalid playlist end number specified')
# Information extractors
youtube_ie = YoutubeIE()
or (opts.format == '-1' and opts.usetitle and u'%(stitle)s-%(id)s-%(format)s.%(ext)s')
or (opts.format == '-1' and opts.useliteral and u'%(title)s-%(id)s-%(format)s.%(ext)s')
or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s')
+ or (opts.usetitle and opts.autonumber and u'%(autonumber)s-%(stitle)s-%(id)s.%(ext)s')
+ or (opts.useliteral and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s')
or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s')
or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s')
+ or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s')
or u'%(id)s.%(ext)s'),
'ignoreerrors': opts.ignoreerrors,
'ratelimit': opts.ratelimit,
'continuedl': opts.continue_dl,
'noprogress': opts.noprogress,
'playliststart': opts.playliststart,
+ 'playlistend': opts.playlistend,
'logtostderr': opts.outtmpl == '-',
})
fd.add_info_extractor(youtube_search_ie)