# License: Public domain code
import htmlentitydefs
import httplib
+import locale
import math
import netrc
import os
"""
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):
- sys.stdout.write('%s%s' % (message, ['\n', ''][skip_eol]))
+ print u'%s%s' % (message, [u'\n', u''][skip_eol]),
sys.stdout.flush()
def to_stderr(self, message):
"""Print message to stderr."""
- sys.stderr.write('%s\n' % message)
+ print >>sys.stderr, message
def fixed_template(self):
"""Checks if the output template is fixed."""
def report_destination(self, filename):
"""Report destination filename."""
- self.to_stdout('[download] Destination: %s' % filename)
+ self.to_stdout(u'[download] Destination: %s' % filename)
def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
"""Report download progress."""
- self.to_stdout('\r[download] %s of %s at %s ETA %s' %
+ self.to_stdout(u'\r[download] %s of %s at %s ETA %s' %
(percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
def report_finish(self):
"""Report download finished."""
- self.to_stdout('')
+ self.to_stdout(u'')
def download(self, url_list):
"""Download a given list of URLs."""
filename = self._params['outtmpl'] % result
self.report_destination(filename)
except (ValueError, KeyError), err:
- retcode = self.trouble('ERROR: invalid output template: %s' % str(err))
+ retcode = self.trouble('ERROR: invalid output template or system charset: %s' % str(err))
continue
try:
self.pmkdir(filename)
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)
def to_stderr(self, message):
"""Print message to stderr."""
- sys.stderr.write('%s\n' % message)
+ print >>sys.stderr, message
def _real_initialize(self):
"""Real initialization process. Redefine in subclasses."""
"""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=/'
+ _LOGIN_URL = 'http://uk.youtube.com/login?next=/'
+ _AGE_URL = 'http://uk.youtube.com/verify_age?next_url=/'
_NETRC_MACHINE = 'youtube'
@staticmethod
def report_login(self):
"""Report attempt to log in."""
- self.to_stdout('[youtube] Logging in')
+ self.to_stdout(u'[youtube] Logging in')
def report_age_confirmation(self):
"""Report attempt to confirm age."""
- self.to_stdout('[youtube] Confirming age')
+ self.to_stdout(u'[youtube] Confirming age')
def report_webpage_download(self, video_id):
"""Report attempt to download webpage."""
- self.to_stdout('[youtube] %s: Downloading video webpage' % video_id)
+ self.to_stdout(u'[youtube] %s: Downloading video webpage' % video_id)
def report_information_extraction(self, video_id):
"""Report attempt to extract video information."""
- self.to_stdout('[youtube] %s: Extracting video information' % video_id)
+ self.to_stdout(u'[youtube] %s: Extracting video information' % video_id)
def report_video_url(self, video_id, video_real_url):
"""Report extracted video URL."""
- self.to_stdout('[youtube] %s: URL: %s' % (video_id, video_real_url))
+ self.to_stdout(u'[youtube] %s: URL: %s' % (video_id, video_real_url))
def _real_initialize(self):
if self._downloader is None:
else:
raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
except (IOError, netrc.NetrcParseError), err:
- self.to_stderr('WARNING: parsing .netrc: %s' % str(err))
+ self.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))
return
# No authentication to be performed
self.report_login()
login_results = urllib2.urlopen(request).read()
if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None:
- self.to_stderr('WARNING: unable to log in: bad username or password')
+ self.to_stderr(u'WARNING: unable to log in: bad username or password')
return
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self.to_stderr('WARNING: unable to log in: %s' % str(err))
+ self.to_stderr(u'WARNING: unable to log in: %s' % str(err))
return
# Confirm age
self.report_age_confirmation()
age_results = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self.to_stderr('ERROR: unable to confirm age: %s' % str(err))
+ self.to_stderr(u'ERROR: unable to confirm age: %s' % str(err))
return
def _real_extract(self, url):
# Extract video id from URL
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self.to_stderr('ERROR: invalid URL: %s' % url)
+ self.to_stderr(u'ERROR: invalid URL: %s' % url)
return [None]
video_id = mobj.group(2)
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://uk.youtube.com/watch?v=%s' % 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_webpage_download(video_id)
video_webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self.to_stderr('ERROR: unable to download video webpage: %s' % str(err))
+ self.to_stderr(u'ERROR: unable to download video webpage: %s' % str(err))
return [None]
self.report_information_extraction(video_id)
# "t" param
mobj = re.search(r', "t": "([^"]+)"', video_webpage)
if mobj is None:
- self.to_stderr('ERROR: unable to extract "t" parameter')
+ self.to_stderr(u'ERROR: unable to extract "t" parameter')
return [None]
- video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s' % (video_id, mobj.group(1))
+ video_real_url = 'http://uk.youtube.com/get_video?video_id=%s&t=%s' % (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'More From: ([^<]*)<', video_webpage)
+ mobj = re.search(r"var watchUsername = '([^']+)';", video_webpage)
if mobj is None:
- self.to_stderr('ERROR: unable to extract uploader nickname')
+ self.to_stderr(u'ERROR: unable to extract uploader nickname')
return [None]
video_uploader = mobj.group(1)
# title
mobj = re.search(r'(?im)<title>YouTube - ([^<]*)</title>', video_webpage)
if mobj is None:
- self.to_stderr('ERROR: unable to extract video title')
+ self.to_stderr(u'ERROR: unable to extract video title')
return [None]
video_title = mobj.group(1).decode('utf-8')
video_title = re.sub(ur'(?u)&(.+?);', lambda x: unichr(htmlentitydefs.name2codepoint[x.group(1)]), video_title)
# Return information
return [{
- 'id': video_id,
- 'url': video_real_url,
- 'uploader': video_uploader,
+ '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,
+ 'ext': video_extension.decode('utf-8'),
}]
class MetacafeIE(InfoExtractor):
"""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):
def report_disclaimer(self):
"""Report disclaimer retrieval."""
- self.to_stdout('[metacafe] Retrieving disclaimer')
+ self.to_stdout(u'[metacafe] Retrieving disclaimer')
def report_age_confirmation(self):
"""Report attempt to confirm age."""
- self.to_stdout('[metacafe] Confirming age')
+ self.to_stdout(u'[metacafe] Confirming age')
def report_download_webpage(self, video_id):
"""Report webpage download."""
- self.to_stdout('[metacafe] %s: Downloading webpage' % video_id)
+ self.to_stdout(u'[metacafe] %s: Downloading webpage' % video_id)
def report_extraction(self, video_id):
"""Report information extraction."""
- self.to_stdout('[metacafe] %s: Extracting information' % video_id)
+ self.to_stdout(u'[metacafe] %s: Extracting information' % video_id)
def _real_initialize(self):
# Retrieve disclaimer
self.report_disclaimer()
disclaimer = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self.to_stderr('ERROR: unable to retrieve disclaimer: %s' % str(err))
+ self.to_stderr(u'ERROR: unable to retrieve disclaimer: %s' % str(err))
return
# 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()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self.to_stderr('ERROR: unable to confirm age: %s' % str(err))
+ self.to_stderr(u'ERROR: unable to confirm age: %s' % str(err))
return
def _real_extract(self, url):
# Extract id and simplified title from URL
mobj = re.match(self._VALID_URL, url)
if mobj is None:
- self.to_stderr('ERROR: invalid URL: %s' % url)
+ self.to_stderr(u'ERROR: invalid URL: %s' % url)
return [None]
video_id = mobj.group(1)
# Check if video comes from YouTube
mobj2 = re.match(r'^yt-(.*)$', video_id)
if mobj2 is not None:
- return self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1))
+ return self._youtube_ie.extract('http://uk.youtube.com/watch?v=%s' % mobj2.group(1))
simple_title = mobj.group(2).decode('utf-8')
video_extension = 'flv'
self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self.to_stderr('ERROR: unable retrieve video webpage: %s' % str(err))
+ self.to_stderr(u'ERROR: unable retrieve video webpage: %s' % str(err))
return [None]
# Extract URL, uploader and title from webpage
self.report_extraction(video_id)
mobj = re.search(r'(?m)"mediaURL":"(http.*?\.flv)"', webpage)
if mobj is None:
- self.to_stderr('ERROR: unable to extract media URL')
+ self.to_stderr(u'ERROR: unable to extract media URL')
return [None]
mediaURL = mobj.group(1).replace('\\', '')
mobj = re.search(r'(?m)"gdaKey":"(.*?)"', webpage)
if mobj is None:
- self.to_stderr('ERROR: unable to extract gdaKey')
+ self.to_stderr(u'ERROR: unable to extract gdaKey')
return [None]
gdaKey = mobj.group(1)
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('ERROR: unable to extract title')
+ self.to_stderr(u'ERROR: unable to extract title')
return [None]
video_title = mobj.group(1).decode('utf-8')
mobj = re.search(r'(?m)<li id="ChnlUsr">.*?Submitter:<br />(.*?)</li>', webpage)
if mobj is None:
- self.to_stderr('ERROR: unable to extract uploader nickname')
+ self.to_stderr(u'ERROR: unable to extract uploader nickname')
return [None]
video_uploader = re.sub(r'<.*?>', '', mobj.group(1))
# Return information
return [{
- 'id': video_id,
- 'url': video_url,
- 'uploader': video_uploader,
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url.decode('utf-8'),
+ 'uploader': video_uploader.decode('utf-8'),
'title': video_title,
'stitle': simple_title,
- 'ext': video_extension,
+ 'ext': video_extension.decode('utf-8'),
}]
+class YoutubePlaylistIE(InfoExtractor):
+ """Information Extractor for YouTube playlists."""
+
+ _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/view_play_list\?p=(.+)'
+ _TEMPLATE_URL = 'http://uk.youtube.com/view_play_list?p=%s&page=%s'
+ _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
+ _MORE_PAGES_INDICATOR = r'/view_play_list?p=%s&page=%s'
+ _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(YoutubePlaylistIE._VALID_URL, url) is not None)
+
+ def report_download_page(self, playlist_id, pagenum):
+ """Report attempt to download playlist page with given number."""
+ self.to_stdout(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
+
+ def _real_initialize(self):
+ self._youtube_ie.initialize()
+
+ def _real_extract(self, url):
+ # Extract playlist id
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self.to_stderr(u'ERROR: invalid url: %s' % url)
+ return [None]
+
+ # Download playlist pages
+ playlist_id = mobj.group(1)
+ video_ids = []
+ pagenum = 1
+
+ while True:
+ self.report_download_page(playlist_id, pagenum)
+ request = urllib2.Request(self._TEMPLATE_URL % (playlist_id, pagenum), 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
+ ids_in_page = []
+ for mobj in re.finditer(self._VIDEO_INDICATOR, 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 % (playlist_id, pagenum + 1)) not in page:
+ break
+ pagenum = pagenum + 1
+
+ information = []
+ for id in video_ids:
+ information.extend(self._youtube_ie.extract('http://uk.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='2008.11.01',
conflict_handler='resolve',
)
parser.add_option('-h', '--help',
# Conflicting, missing and erroneous options
if len(args) < 1:
- sys.exit('ERROR: you must provide at least one URL')
+ 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('ERROR: using .netrc conflicts with giving username/password')
+ sys.exit(u'ERROR: using .netrc conflicts with giving username/password')
if opts.password is not None and opts.username is None:
- sys.exit('ERROR: account username missing')
+ sys.exit(u'ERROR: account username missing')
if opts.outtmpl is not None and (opts.useliteral or opts.usetitle):
- sys.exit('ERROR: using output template conflicts with using title or literal title')
+ sys.exit(u'ERROR: using output template conflicts with using title or literal title')
if opts.usetitle and opts.useliteral:
- sys.exit('ERROR: using title conflicts with using literal title')
+ sys.exit(u'ERROR: using title conflicts with using literal title')
if opts.username is not None and opts.password is None:
- opts.password = getpass.getpass('Type account password and press return:')
+ opts.password = getpass.getpass(u'Type account password and press return:')
if opts.ratelimit is not None:
numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
if numeric_limit is None:
- sys.exit('ERROR: invalid rate limit specified')
+ sys.exit(u'ERROR: invalid rate limit specified')
opts.ratelimit = numeric_limit
# Information extractors
youtube_ie = YoutubeIE()
metacafe_ie = MetacafeIE(youtube_ie)
+ youtube_pl_ie = YoutubePlaylistIE(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)
- or (opts.usetitle and '%(stitle)s-%(id)s.%(ext)s')
- or (opts.useliteral and '%(title)s-%(id)s.%(ext)s')
- or '%(id)s.%(ext)s'),
+ '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_pl_ie)
fd.add_info_extractor(metacafe_ie)
fd.add_info_extractor(youtube_ie)
retcode = fd.download(args)
except DownloadError:
sys.exit(1)
except SameFileError:
- sys.exit('ERROR: fixed output name but more than one file to download')
+ sys.exit(u'ERROR: fixed output name but more than one file to download')
except KeyboardInterrupt:
- sys.exit('\nERROR: Interrupted by user')
+ sys.exit(u'\nERROR: Interrupted by user')
projects / youtube-dl.git / blobdiff