# Author: Benjamin Johnson
# License: Public domain code
import cookielib
+import datetime
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',
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.
"""
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 attempt to resume at given byte."""
- self.to_stdout(u'[download] Resuming download at byte %s' % resume_len)
+ 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 5xx"""
- self.to_stdout(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries))
+ 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."""
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')
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(u'\nERROR: rtmpdump exited with code %d' % retval)
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:
# 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'),
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
'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'),
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
'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'),
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
'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'),
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
'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'),
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
'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'),
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
'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'),
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()
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
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()
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)
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...')
- latest_url = 'http://bitbucket.org/rg3/youtube-dl/raw/tip/LATEST_VERSION'
+ downloader.to_screen('Updating to latest stable version...')
+ latest_url = 'http://github.com/rg3/youtube-dl/raw/master/LATEST_VERSION'
latest_version = urllib.urlopen(latest_url).read().strip()
- prog_url = 'http://bitbucket.org/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version
+ prog_url = 'http://github.com/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version
newcontent = urllib.urlopen(prog_url).read()
stream = open(filename, 'w')
stream.write(newcontent)
stream.close()
- downloader.to_stdout('Updated to version %s' % latest_version)
+ downloader.to_screen('Updated to version %s' % latest_version)
# Parse command line
parser = optparse.OptionParser(
usage='Usage: %prog [options] url...',
- version='2010.10.03',
+ version='2010.10.24',
conflict_handler='resolve',
)
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',
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')
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)
fd.add_info_extractor(youtube_pl_ie)
projects / youtube-dl.git / blobdiff