# License: Public domain code
import htmlentitydefs
import httplib
+import locale
import math
import netrc
import os
import urllib2
std_headers = {
- 'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.1) Gecko/2008070208 Firefox/3.0.1',
+ 'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.5) Gecko/2008120122 Firefox/3.0.5',
'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',
"""
pass
+class PostProcessingError(Exception):
+ """Post Processing exception.
+
+ This exception may be raised by PostProcessor's .run() method to
+ indicate an error in the postprocessing task.
+ """
+ pass
+
class FileDownloader(object):
"""File Downloader class.
_params = None
_ies = []
+ _pps = []
def __init__(self, params):
"""Create a FileDownloader object with the given options."""
self._ies = []
+ self._pps = []
self.set_params(params)
@staticmethod
self._ies.append(ie)
ie.set_downloader(self)
+ def add_post_processor(self, pp):
+ """Add a PostProcessor object to the end of the chain."""
+ self._pps.append(pp)
+ pp.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):
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
retcode = self.trouble('ERROR: unable to download video data: %s' % str(err))
continue
+ try:
+ self.post_process(filename, result)
+ except (PostProcessingError), err:
+ retcode = self.trouble('ERROR: postprocessing: %s' % str(err))
+ continue
+
break
if not suitable_found:
retcode = self.trouble('ERROR: no suitable InfoExtractor: %s' % url)
return retcode
+
+ def post_process(self, filename, ie_info):
+ """Run the postprocessing chain on the given file."""
+ info = dict(ie_info)
+ info['filepath'] = filename
+ for pp in self._pps:
+ info = pp.run(info)
+ if info is None:
+ break
def _do_download(self, stream, url):
request = urllib2.Request(url, None, std_headers)
"""Information extractor for youtube.com."""
_VALID_URL = r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:\.php)?)?\?(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$'
- _LOGIN_URL = 'http://www.youtube.com/login?next=/'
- _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/'
+ _LANG_URL = r'http://uk.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'
+ _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
_NETRC_MACHINE = 'youtube'
@staticmethod
def suitable(url):
return (re.match(YoutubeIE._VALID_URL, url) is not None)
+ def report_lang(self):
+ """Report attempt to set language."""
+ self.to_stdout(u'[youtube] Setting language')
+
def report_login(self):
"""Report attempt to log in."""
self.to_stdout(u'[youtube] Logging in')
if username is None:
return
+ # Set language
+ request = urllib2.Request(self._LOGIN_URL, None, std_headers)
+ try:
+ self.report_lang()
+ urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self.to_stderr(u'WARNING: unable to set language: %s' % str(err))
+ return
+
# Log in
login_form = {
'current_form': 'loginForm',
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 = '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)
self.report_video_url(video_id, video_real_url)
# uploader
- mobj = re.search(r'More From: ([^<]*)<', video_webpage)
+ mobj = re.search(r"var watchUsername = '([^']+)';", video_webpage)
if mobj is None:
self.to_stderr(u'ERROR: unable to extract uploader nickname')
return [None]
"""Information Extractor for metacafe.com."""
_VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
- _DISCLAIMER = 'http://www.metacafe.com/disclaimer'
+ _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
_youtube_ie = None
def __init__(self, youtube_ie, downloader=None):
# Confirm age
disclaimer_form = {
- 'allowAdultContent': '1',
+ 'filters': '0',
'submit': "Continue - I'm over 18",
}
- request = urllib2.Request('http://www.metacafe.com/watch/', urllib.urlencode(disclaimer_form), std_headers)
+ request = urllib2.Request('http://www.metacafe.com/', urllib.urlencode(disclaimer_form), std_headers)
try:
self.report_age_confirmation()
disclaimer = urllib2.urlopen(request).read()
video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
- mobj = re.search(r'(?im)<meta name="title" content="Metacafe - ([^"]+)"', webpage)
+ mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
if mobj is None:
self.to_stderr(u'ERROR: unable to extract title')
return [None]
'ext': video_extension.decode('utf-8'),
}]
+
+class YoutubeSearchIE(InfoExtractor):
+ """Information Extractor for YouTube search queries."""
+ _VALID_QUERY = r'ytsearch(\d+|all)?:[\s\S]+'
+ _TEMPLATE_URL = 'http://www.youtube.com/results?search_query=%s&page=%s&gl=US&hl=en'
+ _VIDEO_INDICATOR = r'href="/watch\?v=.+?"'
+ _MORE_PAGES_INDICATOR = r'>Next</a>'
+ _youtube_ie = None
+
+ def __init__(self, youtube_ie, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+ self._youtube_ie = youtube_ie
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(YoutubeSearchIE._VALID_QUERY, url) is not None)
+
+ def report_download_page(self, query, pagenum):
+ """Report attempt to download playlist page with given number."""
+ self.to_stdout(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
+
+ def _real_initialize(self):
+ self._youtube_ie.initialize()
+
+ def _real_extract(self, query):
+ mobj = re.match(self._VALID_QUERY, query)
+ if mobj is None:
+ self.to_stderr(u'ERROR: invalid search query "%s"' % query)
+ return [None]
+
+ prefix, query = query.split(':')
+ prefix = prefix[8:]
+ if prefix == '':
+ return self._download_n_results(query, 1)
+ elif prefix == 'all':
+ return self._download_n_results(query, -1)
+ else:
+ try:
+ n = int(prefix)
+ if n <= 0:
+ self.to_stderr(u'ERROR: invalid download number %s for query "%s"' % (n, query))
+ return [None]
+ return self._download_n_results(query, n)
+ except ValueError: # parsing prefix as int fails
+ return self._download_n_results(query, 1)
+
+ def _download_n_results(self, query, n):
+ """Downloads a specified number of results for a query"""
+
+ video_ids = []
+ already_seen = set()
+ pagenum = 1
+
+ while True:
+ self.report_download_page(query, pagenum)
+ result_url = self._TEMPLATE_URL % (urllib.quote(query.replace(' ', '+')), pagenum)
+ request = urllib2.Request(result_url, None, std_headers)
+ try:
+ page = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self.to_stderr(u'ERROR: unable to download webpage: %s' % str(err))
+ return [None]
+
+ # Extract video identifiers
+ for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+ video_id = page[mobj.span()[0]:mobj.span()[1]].split('=')[2][:-1]
+ if video_id not in already_seen:
+ video_ids.append(video_id)
+ already_seen.add(video_id)
+ if len(video_ids) == n:
+ # Specified n videos reached
+ information = []
+ for id in video_ids:
+ information.extend(self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id))
+ return information
+
+ if self._MORE_PAGES_INDICATOR not in page:
+ information = []
+ for id in video_ids:
+ information.extend(self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id))
+ return information
+
+ pagenum = pagenum + 1
+
class YoutubePlaylistIE(InfoExtractor):
"""Information Extractor for YouTube playlists."""
_VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/view_play_list\?p=(.+)'
- _TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s'
+ _TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en'
_VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
- _MORE_PAGES_INDICATOR = r'class="pagerNotCurrent">Next</a>'
+ _MORE_PAGES_INDICATOR = r'/view_play_list?p=%s&page=%s'
_youtube_ie = None
def __init__(self, youtube_ie, downloader=None):
return [None]
# Extract video identifiers
- ids_in_page = set()
+ ids_in_page = []
for mobj in re.finditer(self._VIDEO_INDICATOR, page):
- ids_in_page.add(mobj.group(1))
- video_ids.extend(list(ids_in_page))
+ if mobj.group(1) not in ids_in_page:
+ ids_in_page.append(mobj.group(1))
+ video_ids.extend(ids_in_page)
- if self._MORE_PAGES_INDICATOR not in page:
+ if (self._MORE_PAGES_INDICATOR % (playlist_id, pagenum + 1)) not in page:
break
pagenum = pagenum + 1
information.extend(self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id))
return information
+class PostProcessor(object):
+ """Post Processor class.
+
+ PostProcessor objects can be added to downloaders with their
+ add_post_processor() method. When the downloader has finished a
+ successful download, it will take its internal chain of PostProcessors
+ and start calling the run() method on each one of them, first with
+ an initial argument and then with the returned value of the previous
+ PostProcessor.
+
+ The chain will be stopped if one of them ever returns None or the end
+ of the chain is reached.
+
+ PostProcessor objects follow a "mutual registration" process similar
+ to InfoExtractor objects.
+ """
+
+ _downloader = None
+
+ def __init__(self, downloader=None):
+ 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."""
+ print >>sys.stderr, message
+
+ def set_downloader(self, downloader):
+ """Sets the downloader for this PP."""
+ self._downloader = downloader
+
+ def run(self, information):
+ """Run the PostProcessor.
+
+ The "information" argument is a dictionary like the ones
+ returned by InfoExtractors. The only difference is that this
+ one has an extra field called "filepath" that points to the
+ downloaded file.
+
+ When this method returns None, the postprocessing chain is
+ stopped. However, this method may return an information
+ dictionary that will be passed to the next postprocessing
+ object in the chain. It can be the one it received after
+ changing some fields.
+
+ In addition, this method may raise a PostProcessingError
+ exception that will be taken into account by the downloader
+ it was called from.
+ """
+ return information # by default, do nothing
+
+### MAIN PROGRAM ###
if __name__ == '__main__':
try:
# Modules needed only when running the main program
# Parse command line
parser = optparse.OptionParser(
usage='Usage: %prog [options] url...',
- version='2008.07.22',
+ version='2009.01.31',
conflict_handler='resolve',
)
parser.add_option('-h', '--help',
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',
+ dest='batchfile', metavar='F', help='file containing URLs to download')
(opts, args) = parser.parse_args()
+ # Batch file verification
+ batchurls = []
+ if opts.batchfile is not None:
+ try:
+ batchurls = [line.strip() for line in open(opts.batchfile, 'r')]
+ except IOError:
+ sys.exit(u'ERROR: batch file could not be read')
+ all_urls = batchurls + args
+
# Conflicting, missing and erroneous options
- if len(args) < 1:
+ if len(all_urls) < 1:
sys.exit(u'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(u'ERROR: using .netrc conflicts with giving username/password')
youtube_ie = YoutubeIE()
metacafe_ie = MetacafeIE(youtube_ie)
youtube_pl_ie = YoutubePlaylistIE(youtube_ie)
+ youtube_search_ie = YoutubeSearchIE(youtube_ie)
# File downloader
+ charset = locale.getdefaultlocale()[1]
+ if charset is None:
+ charset = 'ascii'
fd = FileDownloader({
'usenetrc': opts.usenetrc,
'username': opts.username,
'forcetitle': opts.gettitle,
'simulate': (opts.simulate or opts.geturl or opts.gettitle),
'format': opts.format,
- 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode())
+ 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(charset))
or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s')
or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s')
or u'%(id)s.%(ext)s'),
'ignoreerrors': opts.ignoreerrors,
'ratelimit': opts.ratelimit,
})
+ fd.add_info_extractor(youtube_search_ie)
fd.add_info_extractor(youtube_pl_ie)
fd.add_info_extractor(metacafe_ie)
fd.add_info_extractor(youtube_ie)
- retcode = fd.download(args)
+ retcode = fd.download(all_urls)
sys.exit(retcode)
except DownloadError: