Fix the DailymotionIE to parse the new title of a webpage

[youtube-dl] / youtube-dl

diff --git a/youtube-dl b/youtube-dl
index 36ca6baf949e9f312ccb8b3130cc8f387daf127e..042b852671b01e5f12092d5a980337360129199d 100755 (executable)
--- a/youtube-dl
+++ b/youtube-dl
@@ -1,19 +1,32 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-

-# Author: Ricardo Garcia Gonzalez
-# Author: Danny Colligan
-# Author: Benjamin Johnson
-# Author: Vasyl' Vavrychuk
-# Author: Witold Baryluk
-# Author: Paweł Paprota
-# Author: Gergely Imreh
-# License: Public domain code
+
+__author__  = (
+       'Ricardo Garcia Gonzalez',
+       'Danny Colligan',
+       'Benjamin Johnson',
+       'Vasyl\' Vavrychuk',
+       'Witold Baryluk',
+       'Paweł Paprota',
+       'Gergely Imreh',
+       'Rogério Brito',
+       'Philipp Hagemeister',
+       'Sören Schulze',
+       'Kevin Ngo',
+       'Ori Avtalion',
+       'shizeeg',
+       )
+
+__license__ = 'Public Domain'
+__version__ = '2011.11.23'
+
+UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl'
+

 import cookielib
 import cookielib

-import ctypes

 import datetime
 import datetime

-import email.utils

 import gzip
 import htmlentitydefs
 import gzip
 import htmlentitydefs

+import HTMLParser

 import httplib
 import locale
 import math
 import httplib
 import locale
 import math


@@ -23,20 +36,42 @@ import os.path
 import re
 import socket
 import string
 import re
 import socket
 import string

-import StringIO

 import subprocess
 import sys
 import time
 import urllib
 import urllib2
 import subprocess
 import sys
 import time
 import urllib
 import urllib2

+import warnings

 import zlib
 
 import zlib
 

+if os.name == 'nt':
+       import ctypes
+
+try:
+       import email.utils
+except ImportError: # Python 2.4
+       import email.Utils
+try:
+       import cStringIO as StringIO
+except ImportError:
+       import StringIO
+

 # parse_qs was moved from the cgi module to the urlparse module recently.
 try:
        from urlparse import parse_qs
 except ImportError:
        from cgi import parse_qs
 
 # parse_qs was moved from the cgi module to the urlparse module recently.
 try:
        from urlparse import parse_qs
 except ImportError:
        from cgi import parse_qs
 

+try:
+       import lxml.etree
+except ImportError:
+       pass # Handled below
+
+try:
+       import xml.etree.ElementTree
+except ImportError: # Python<2.5: Not officially supported, but let it slip
+       warnings.warn('xml.etree.ElementTree support is missing. Consider upgrading to Python >= 2.5 if you get related errors.')
+

 std_headers = {
        'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:5.0.1) Gecko/20100101 Firefox/5.0.1',
        'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
 std_headers = {
        'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:5.0.1) Gecko/20100101 Firefox/5.0.1',
        'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',


@@ -45,8 +80,118 @@ std_headers = {
        'Accept-Language': 'en-us,en;q=0.5',
 }
 
        'Accept-Language': 'en-us,en;q=0.5',
 }
 

-simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii')
-
+try:
+       import json
+except ImportError: # Python <2.6, use trivialjson (https://github.com/phihag/trivialjson):
+       import re
+       class json(object):
+               @staticmethod
+               def loads(s):
+                       s = s.decode('UTF-8')
+                       def raiseError(msg, i):
+                               raise ValueError(msg + ' at position ' + str(i) + ' of ' + repr(s) + ': ' + repr(s[i:]))
+                       def skipSpace(i, expectMore=True):
+                               while i < len(s) and s[i] in ' \t\r\n':
+                                       i += 1
+                               if expectMore:
+                                       if i >= len(s):
+                                               raiseError('Premature end', i)
+                               return i
+                       def decodeEscape(match):
+                               esc = match.group(1)
+                               _STATIC = {
+                                       '"': '"',
+                                       '\\': '\\',
+                                       '/': '/',
+                                       'b': unichr(0x8),
+                                       'f': unichr(0xc),
+                                       'n': '\n',
+                                       'r': '\r',
+                                       't': '\t',
+                               }
+                               if esc in _STATIC:
+                                       return _STATIC[esc]
+                               if esc[0] == 'u':
+                                       if len(esc) == 1+4:
+                                               return unichr(int(esc[1:5], 16))
+                                       if len(esc) == 5+6 and esc[5:7] == '\\u':
+                                               hi = int(esc[1:5], 16)
+                                               low = int(esc[7:11], 16)
+                                               return unichr((hi - 0xd800) * 0x400 + low - 0xdc00 + 0x10000)
+                               raise ValueError('Unknown escape ' + str(esc))
+                       def parseString(i):
+                               i += 1
+                               e = i
+                               while True:
+                                       e = s.index('"', e)
+                                       bslashes = 0
+                                       while s[e-bslashes-1] == '\\':
+                                               bslashes += 1
+                                       if bslashes % 2 == 1:
+                                               e += 1
+                                               continue
+                                       break
+                               rexp = re.compile(r'\\(u[dD][89aAbB][0-9a-fA-F]{2}\\u[0-9a-fA-F]{4}|u[0-9a-fA-F]{4}|.|$)')
+                               stri = rexp.sub(decodeEscape, s[i:e])
+                               return (e+1,stri)
+                       def parseObj(i):
+                               i += 1
+                               res = {}
+                               i = skipSpace(i)
+                               if s[i] == '}': # Empty dictionary
+                                       return (i+1,res)
+                               while True:
+                                       if s[i] != '"':
+                                               raiseError('Expected a string object key', i)
+                                       i,key = parseString(i)
+                                       i = skipSpace(i)
+                                       if i >= len(s) or s[i] != ':':
+                                               raiseError('Expected a colon', i)
+                                       i,val = parse(i+1)
+                                       res[key] = val
+                                       i = skipSpace(i)
+                                       if s[i] == '}':
+                                               return (i+1, res)
+                                       if s[i] != ',':
+                                               raiseError('Expected comma or closing curly brace', i)
+                                       i = skipSpace(i+1)
+                       def parseArray(i):
+                               res = []
+                               i = skipSpace(i+1)
+                               if s[i] == ']': # Empty array
+                                       return (i+1,res)
+                               while True:
+                                       i,val = parse(i)
+                                       res.append(val)
+                                       i = skipSpace(i) # Raise exception if premature end
+                                       if s[i] == ']':
+                                               return (i+1, res)
+                                       if s[i] != ',':
+                                               raiseError('Expected a comma or closing bracket', i)
+                                       i = skipSpace(i+1)
+                       def parseDiscrete(i):
+                               for k,v in {'true': True, 'false': False, 'null': None}.items():
+                                       if s.startswith(k, i):
+                                               return (i+len(k), v)
+                               raiseError('Not a boolean (or null)', i)
+                       def parseNumber(i):
+                               mobj = re.match('^(-?(0|[1-9][0-9]*)(\.[0-9]*)?([eE][+-]?[0-9]+)?)', s[i:])
+                               if mobj is None:
+                                       raiseError('Not a number', i)
+                               nums = mobj.group(1)
+                               if '.' in nums or 'e' in nums or 'E' in nums:
+                                       return (i+len(nums), float(nums))
+                               return (i+len(nums), int(nums))
+                       CHARMAP = {'{': parseObj, '[': parseArray, '"': parseString, 't': parseDiscrete, 'f': parseDiscrete, 'n': parseDiscrete}
+                       def parse(i):
+                               i = skipSpace(i)
+                               i,res = CHARMAP.get(s[i], parseNumber)(i)
+                               i = skipSpace(i, False)
+                               return (i,res)
+                       i,res = parse(0)
+                       if i < len(s):
+                               raise ValueError('Extra data at end of input (index ' + str(i) + ' of ' + repr(s) + ': ' + repr(s[i:]) + ')')
+                       return res

 
 def preferredencoding():
        """Get preferred encoding.
 
 def preferredencoding():
        """Get preferred encoding.


@@ -133,6 +278,9 @@ def timeconvert(timestr):
                timestamp = email.utils.mktime_tz(timetuple)
        return timestamp
 
                timestamp = email.utils.mktime_tz(timetuple)
        return timestamp
 

+def _simplify_title(title):
+       expr = re.compile(ur'[^\w\d_\-]+', flags=re.UNICODE)
+       return expr.sub(u'_', title).strip(u'_')

 
 class DownloadError(Exception):
        """Download Error exception.
 
 class DownloadError(Exception):
        """Download Error exception.


@@ -294,10 +442,14 @@ class FileDownloader(object):
        noprogress:       Do not print the progress bar.
        playliststart:    Playlist item to start at.
        playlistend:      Playlist item to end at.
        noprogress:       Do not print the progress bar.
        playliststart:    Playlist item to start at.
        playlistend:      Playlist item to end at.

+       matchtitle:       Download only matching titles.
+       rejecttitle:      Reject downloads for matching titles.

        logtostderr:      Log messages to stderr instead of stdout.
        consoletitle:     Display progress in console window's titlebar.
        nopart:           Do not use temporary .part files.
        updatetime:       Use the Last-modified header to set output file timestamps.
        logtostderr:      Log messages to stderr instead of stdout.
        consoletitle:     Display progress in console window's titlebar.
        nopart:           Do not use temporary .part files.
        updatetime:       Use the Last-modified header to set output file timestamps.

+       writedescription: Write the video description to a .description file
+       writeinfojson:    Write the video description to a .info.json file

        """
 
        params = None
        """
 
        params = None


@@ -316,16 +468,6 @@ class FileDownloader(object):
                self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
                self.params = params
 
                self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
                self.params = params
 

-       @staticmethod
-       def pmkdir(filename):
-               """Create directory components in filename. Similar to Unix "mkdir -p"."""
-               components = filename.split(os.sep)
-               aggregate = [os.sep.join(components[0:x]) for x in xrange(1, len(components))]
-               aggregate = ['%s%s' % (x, os.sep) for x in aggregate] # Finish names with separator
-               for dir in aggregate:
-                       if not os.path.exists(dir):
-                               os.mkdir(dir)
-

        @staticmethod
        def format_bytes(bytes):
                if bytes is None:
        @staticmethod
        def format_bytes(bytes):
                if bytes is None:


@@ -487,11 +629,20 @@ class FileDownloader(object):
                        return
                filetime = timeconvert(timestr)
                if filetime is None:
                        return
                filetime = timeconvert(timestr)
                if filetime is None:

-                       return
+                       return filetime

                try:
                        os.utime(filename, (time.time(), filetime))
                except:
                        pass
                try:
                        os.utime(filename, (time.time(), filetime))
                except:
                        pass

+               return filetime
+
+       def report_writedescription(self, descfn):
+               """ Report that the description file is being written """
+               self.to_screen(u'[info] Writing video description to: %s' % descfn, ignore_encoding_errors=True)
+
+       def report_writeinfojson(self, infofn):
+               """ Report that the metadata file has been written """
+               self.to_screen(u'[info] Video description metadata as JSON to: %s' % infofn, ignore_encoding_errors=True)

 
        def report_destination(self, filename):
                """Report destination filename."""
 
        def report_destination(self, filename):
                """Report destination filename."""


@@ -548,54 +699,117 @@ class FileDownloader(object):
                        self.trouble(u'ERROR: invalid system charset or erroneous output template')
                        return None
 
                        self.trouble(u'ERROR: invalid system charset or erroneous output template')
                        return None
 

+       def _match_entry(self, info_dict):
+               """ Returns None iff the file should be downloaded """
+
+               title = info_dict['title']
+               matchtitle = self.params.get('matchtitle', False)
+               if matchtitle and not re.search(matchtitle, title, re.IGNORECASE):
+                       return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"'
+               rejecttitle = self.params.get('rejecttitle', False)
+               if rejecttitle and re.search(rejecttitle, title, re.IGNORECASE):
+                       return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"'
+               return None
+

        def process_info(self, info_dict):
                """Process a single dictionary returned by an InfoExtractor."""
        def process_info(self, info_dict):
                """Process a single dictionary returned by an InfoExtractor."""

+
+               reason = self._match_entry(info_dict)
+               if reason is not None:
+                       self.to_screen(u'[download] ' + reason)
+                       return
+
+               max_downloads = self.params.get('max_downloads')
+               if max_downloads is not None:
+                       if self._num_downloads > int(max_downloads):
+                               self.to_screen(u'[download] Maximum number of downloads reached. Skipping ' + info_dict['title'])
+                               return
+

                filename = self.prepare_filename(info_dict)
                filename = self.prepare_filename(info_dict)

+               
+               # Forced printings
+               if self.params.get('forcetitle', False):
+                       print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')
+               if self.params.get('forceurl', False):
+                       print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace')
+               if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict:
+                       print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace')
+               if self.params.get('forcedescription', False) and 'description' in info_dict:
+                       print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace')
+               if self.params.get('forcefilename', False) and filename is not None:
+                       print filename.encode(preferredencoding(), 'xmlcharrefreplace')
+               if self.params.get('forceformat', False):
+                       print info_dict['format'].encode(preferredencoding(), 'xmlcharrefreplace')
+

                # Do nothing else if in simulate mode
                if self.params.get('simulate', False):
                # Do nothing else if in simulate mode
                if self.params.get('simulate', False):

-                       # Forced printings
-                       if self.params.get('forcetitle', False):
-                               print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')
-                       if self.params.get('forceurl', False):
-                               print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace')
-                       if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict:
-                               print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace')
-                       if self.params.get('forcedescription', False) and 'description' in info_dict:
-                               print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace')
-                       if self.params.get('forcefilename', False) and filename is not None:
-                               print filename.encode(preferredencoding(), 'xmlcharrefreplace')
-

                        return
 
                if filename is None:
                        return
                        return
 
                if filename is None:
                        return

+

                if self.params.get('nooverwrites', False) and os.path.exists(filename):
                        self.to_stderr(u'WARNING: file exists and will be skipped')
                        return
 
                try:
                if self.params.get('nooverwrites', False) and os.path.exists(filename):
                        self.to_stderr(u'WARNING: file exists and will be skipped')
                        return
 
                try:

-                       self.pmkdir(filename)
+                       dn = os.path.dirname(filename)
+                       if dn != '' and not os.path.exists(dn):
+                               os.makedirs(dn)

                except (OSError, IOError), err:
                except (OSError, IOError), err:

-                       self.trouble(u'ERROR: unable to create directories: %s' % str(err))
+                       self.trouble(u'ERROR: unable to create directory ' + unicode(err))

                        return
 
                        return
 

-               try:
-                       success = self._do_download(filename, info_dict['url'].encode('utf-8'), info_dict.get('player_url', None))
-               except (OSError, IOError), err:
-                       raise UnavailableVideoError
-               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-                       self.trouble(u'ERROR: unable to download video data: %s' % str(err))
-                       return
-               except (ContentTooShortError, ), err:
-                       self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
-                       return
+               if self.params.get('writedescription', False):
+                       try:
+                               descfn = filename + '.description'
+                               self.report_writedescription(descfn)
+                               descfile = open(descfn, 'wb')
+                               try:
+                                       descfile.write(info_dict['description'].encode('utf-8'))
+                               finally:
+                                       descfile.close()
+                       except (OSError, IOError):
+                               self.trouble(u'ERROR: Cannot write description file ' + descfn)
+                               return

 
 

-               if success:
+               if self.params.get('writeinfojson', False):
+                       infofn = filename + '.info.json'
+                       self.report_writeinfojson(infofn)

                        try:
                        try:

-                               self.post_process(filename, info_dict)
-                       except (PostProcessingError), err:
-                               self.trouble(u'ERROR: postprocessing: %s' % str(err))
+                               json.dump
+                       except (NameError,AttributeError):
+                               self.trouble(u'ERROR: No JSON encoder found. Update to Python 2.6+, setup a json module, or leave out --write-info-json.')
+                               return
+                       try:
+                               infof = open(infofn, 'wb')
+                               try:
+                                       json_info_dict = dict((k,v) for k,v in info_dict.iteritems() if not k in ('urlhandle',))
+                                       json.dump(json_info_dict, infof)
+                               finally:
+                                       infof.close()
+                       except (OSError, IOError):
+                               self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn)
+                               return
+
+               if not self.params.get('skip_download', False):
+                       try:
+                               success = self._do_download(filename, info_dict)
+                       except (OSError, IOError), err:
+                               raise UnavailableVideoError
+                       except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                               self.trouble(u'ERROR: unable to download video data: %s' % str(err))
+                               return
+                       except (ContentTooShortError, ), err:
+                               self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))

                                return
                                return

+       
+                       if success:
+                               try:
+                                       self.post_process(filename, info_dict)
+                               except (PostProcessingError), err:
+                                       self.trouble(u'ERROR: postprocessing: %s' % str(err))
+                                       return

 
        def download(self, url_list):
                """Download a given list of URLs."""
 
        def download(self, url_list):
                """Download a given list of URLs."""


@@ -656,6 +870,11 @@ class FileDownloader(object):
                        cursize = os.path.getsize(tmpfilename)
                        if prevsize == cursize and retval == 1:
                                break
                        cursize = os.path.getsize(tmpfilename)
                        if prevsize == cursize and retval == 1:
                                break

+                        # Some rtmp streams seem abort after ~ 99.8%. Don't complain for those
+                       if prevsize == cursize and retval == 2 and cursize > 1024:
+                               self.to_screen(u'\r[rtmpdump] Could not download the whole video. This can happen for some advertisements.')
+                               retval = 0
+                               break

                if retval == 0:
                        self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(tmpfilename))
                        self.try_rename(tmpfilename, filename)
                if retval == 0:
                        self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(tmpfilename))
                        self.try_rename(tmpfilename, filename)


@@ -664,7 +883,10 @@ class FileDownloader(object):
                        self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval)
                        return False
 
                        self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval)
                        return False
 

-       def _do_download(self, filename, url, player_url):
+       def _do_download(self, filename, info_dict):
+               url = info_dict['url']
+               player_url = info_dict.get('player_url', None)
+

                # Check file already present
                if self.params.get('continuedl', False) and os.path.isfile(filename) and not self.params.get('nopart', False):
                        self.report_file_already_downloaded(filename)
                # Check file already present
                if self.params.get('continuedl', False) and os.path.isfile(filename) and not self.params.get('nopart', False):
                        self.report_file_already_downloaded(filename)


@@ -676,7 +898,6 @@ class FileDownloader(object):
 
                tmpfilename = self.temp_name(filename)
                stream = None
 
                tmpfilename = self.temp_name(filename)
                stream = None

-               open_mode = 'wb'

 
                # Do not include the Accept-Encoding header
                headers = {'Youtubedl-no-compression': 'True'}
 
                # Do not include the Accept-Encoding header
                headers = {'Youtubedl-no-compression': 'True'}


@@ -689,17 +910,22 @@ class FileDownloader(object):
                else:
                        resume_len = 0
 
                else:
                        resume_len = 0
 

-               # Request parameters in case of being able to resume
-               if self.params.get('continuedl', False) and resume_len != 0:
-                       self.report_resuming_byte(resume_len)
-                       request.add_header('Range', 'bytes=%d-' % resume_len)
-                       open_mode = 'ab'
+               open_mode = 'wb'
+               if resume_len != 0:
+                       if self.params.get('continuedl', False):
+                               self.report_resuming_byte(resume_len)
+                               request.add_header('Range','bytes=%d-' % resume_len)
+                               open_mode = 'ab'
+                       else:
+                               resume_len = 0

 
                count = 0
                retries = self.params.get('retries', 0)
                while count <= retries:
                        # Establish connection
                        try:
 
                count = 0
                retries = self.params.get('retries', 0)
                while count <= retries:
                        # Establish connection
                        try:

+                               if count == 0 and 'urlhandle' in info_dict:
+                                       data = info_dict['urlhandle']

                                data = urllib2.urlopen(request)
                                break
                        except (urllib2.HTTPError, ), err:
                                data = urllib2.urlopen(request)
                                break
                        except (urllib2.HTTPError, ), err:


@@ -763,6 +989,7 @@ class FileDownloader(object):
                        if stream is None:
                                try:
                                        (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode)
                        if stream is None:
                                try:
                                        (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode)

+                                       assert stream is not None

                                        filename = self.undo_temp_name(tmpfilename)
                                        self.report_destination(filename)
                                except (OSError, IOError), err:
                                        filename = self.undo_temp_name(tmpfilename)
                                        self.report_destination(filename)
                                except (OSError, IOError), err:


@@ -776,14 +1003,20 @@ class FileDownloader(object):
                        block_size = self.best_block_size(after - before, len(data_block))
 
                        # Progress message
                        block_size = self.best_block_size(after - before, len(data_block))
 
                        # Progress message

-                       percent_str = self.calc_percent(byte_counter, data_len)
-                       eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)

                        speed_str = self.calc_speed(start, time.time(), byte_counter - resume_len)
                        speed_str = self.calc_speed(start, time.time(), byte_counter - resume_len)

-                       self.report_progress(percent_str, data_len_str, speed_str, eta_str)
+                       if data_len is None:
+                               self.report_progress('Unknown %', data_len_str, speed_str, 'Unknown ETA')
+                       else:
+                               percent_str = self.calc_percent(byte_counter, data_len)
+                               eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)
+                               self.report_progress(percent_str, data_len_str, speed_str, eta_str)

 
                        # Apply rate limit
                        self.slow_down(start, byte_counter - resume_len)
 
 
                        # Apply rate limit
                        self.slow_down(start, byte_counter - resume_len)
 

+               if stream is None:
+                       self.trouble(u'\nERROR: Did not get any data blocks')
+                       return False

                stream.close()
                self.report_finish()
                if data_len is not None and byte_counter != data_len:
                stream.close()
                self.report_finish()
                if data_len is not None and byte_counter != data_len:


@@ -792,7 +1025,7 @@ class FileDownloader(object):
 
                # Update file modification time
                if self.params.get('updatetime', True):
 
                # Update file modification time
                if self.params.get('updatetime', True):

-                       self.try_utime(filename, data.info().get('last-modified', None))
+                       info_dict['filetime'] = self.try_utime(filename, data.info().get('last-modified', None))

 
                return True
 
 
                return True
 


@@ -827,9 +1060,8 @@ class InfoExtractor(object):
        description:    One-line video description.
 
        Subclasses of this one should re-define the _real_initialize() and
        description:    One-line video description.
 
        Subclasses of this one should re-define the _real_initialize() and

-       _real_extract() methods, as well as the suitable() static method.
-       Probably, they should also be instantiated and added to the main
-       downloader.
+       _real_extract() methods and define a _VALID_URL regexp.
+       Probably, they should also be added to the list of extractors.

        """
 
        _ready = False
        """
 
        _ready = False


@@ -840,10 +1072,9 @@ class InfoExtractor(object):
                self._ready = False
                self.set_downloader(downloader)
 
                self._ready = False
                self.set_downloader(downloader)
 

-       @staticmethod
-       def suitable(url):
+       def suitable(self, url):

                """Receives a URL and returns True if suitable for this IE."""
                """Receives a URL and returns True if suitable for this IE."""

-               return False
+               return re.match(self._VALID_URL, url) is not None

 
        def initialize(self):
                """Initializes an instance (authentication, etc)."""
 
        def initialize(self):
                """Initializes an instance (authentication, etc)."""


@@ -872,13 +1103,13 @@ class InfoExtractor(object):
 class YoutubeIE(InfoExtractor):
        """Information extractor for youtube.com."""
 
 class YoutubeIE(InfoExtractor):
        """Information extractor for youtube.com."""
 

-       _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$'
+       _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$'

        _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
        _LOGIN_URL = 'https://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'
        # Listed in order of quality
        _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
        _LOGIN_URL = 'https://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'
        # Listed in order of quality

-       _available_formats = ['38', '37', '22', '45', '35', '34', '43', '18', '6', '5', '17', '13']
+       _available_formats = ['38', '37', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13']

        _video_extensions = {
                '13': '3gp',
                '17': 'mp4',
        _video_extensions = {
                '13': '3gp',
                '17': 'mp4',


@@ -887,12 +1118,25 @@ class YoutubeIE(InfoExtractor):
                '37': 'mp4',
                '38': 'video', # You actually don't know if this will be MOV, AVI or whatever
                '43': 'webm',
                '37': 'mp4',
                '38': 'video', # You actually don't know if this will be MOV, AVI or whatever
                '43': 'webm',

+               '44': 'webm',

                '45': 'webm',
        }
                '45': 'webm',
        }

-
-       @staticmethod
-       def suitable(url):
-               return (re.match(YoutubeIE._VALID_URL, url) is not None)
+       _video_dimensions = {
+               '5': '240x400',
+               '6': '???',
+               '13': '???',
+               '17': '144x176',
+               '18': '360x640',
+               '22': '720x1280',
+               '34': '360x640',
+               '35': '480x854',
+               '37': '1080x1920',
+               '38': '3072x4096',
+               '43': '360x640',
+               '44': '480x854',
+               '45': '720x1280',
+       }       
+       IE_NAME = u'youtube'

 
        def report_lang(self):
                """Report attempt to set language."""
 
        def report_lang(self):
                """Report attempt to set language."""


@@ -926,6 +1170,11 @@ class YoutubeIE(InfoExtractor):
                """Indicate the download will use the RTMP protocol."""
                self._downloader.to_screen(u'[youtube] RTMP download detected')
 
                """Indicate the download will use the RTMP protocol."""
                self._downloader.to_screen(u'[youtube] RTMP download detected')
 

+       def _print_formats(self, formats):
+               print 'Available formats:'
+               for x in formats:
+                       print '%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???'))
+

        def _real_initialize(self):
                if self._downloader is None:
                        return
        def _real_initialize(self):
                if self._downloader is None:
                        return


@@ -1005,7 +1254,7 @@ class YoutubeIE(InfoExtractor):
 
                # Get video webpage
                self.report_video_webpage_download(video_id)
 
                # Get video webpage
                self.report_video_webpage_download(video_id)

-               request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&amp;has_verified=1' % video_id)
+               request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id)

                try:
                        video_webpage = urllib2.urlopen(request).read()
                except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                try:
                        video_webpage = urllib2.urlopen(request).read()
                except (urllib2.URLError, httplib.HTTPException, socket.error), err:


@@ -1058,8 +1307,7 @@ class YoutubeIE(InfoExtractor):
                video_title = sanitize_title(video_title)
 
                # simplified title
                video_title = sanitize_title(video_title)
 
                # simplified title

-               simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
-               simple_title = simple_title.strip(ur'_')
+               simple_title = _simplify_title(video_title)

 
                # thumbnail image
                if 'thumbnail_url' not in video_info:
 
                # thumbnail image
                if 'thumbnail_url' not in video_info:


@@ -1081,11 +1329,19 @@ class YoutubeIE(InfoExtractor):
                                        pass
 
                # description
                                        pass
 
                # description

-               video_description = 'No description available.'
-               if self._downloader.params.get('forcedescription', False):
-                       mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', video_webpage)
-                       if mobj is not None:
-                               video_description = mobj.group(1)
+               try:
+                       lxml.etree
+               except NameError:
+                       video_description = u'No description available.'
+                       if self._downloader.params.get('forcedescription', False) or self._downloader.params.get('writedescription', False):
+                               mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', video_webpage)
+                               if mobj is not None:
+                                       video_description = mobj.group(1).decode('utf-8')
+               else:
+                       html_parser = lxml.etree.HTMLParser(encoding='utf-8')
+                       vwebpage_doc = lxml.etree.parse(StringIO.StringIO(video_webpage), html_parser)
+                       video_description = u''.join(vwebpage_doc.xpath('id("eow-description")//text()'))
+                       # TODO use another parser

 
                # token
                video_token = urllib.unquote_plus(video_info['token'][0])
 
                # token
                video_token = urllib.unquote_plus(video_info['token'][0])


@@ -1093,10 +1349,15 @@ class YoutubeIE(InfoExtractor):
                # Decide which formats to download
                req_format = self._downloader.params.get('format', None)
 
                # Decide which formats to download
                req_format = self._downloader.params.get('format', None)
 

-               if 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1:
+               if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
+                       self.report_rtmp_download()
+                       video_url_list = [(None, video_info['conn'][0])]
+               elif 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1:

                        url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',')
                        url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',')

-                       url_data = [dict(pairStr.split('=') for pairStr in uds.split('&')) for uds in url_data_strs]
-                       url_map = dict((ud['itag'], urllib.unquote(ud['url'])) for ud in url_data)
+                       url_data = [parse_qs(uds) for uds in url_data_strs]
+                       url_data = filter(lambda ud: 'itag' in ud and 'url' in ud, url_data)
+                       url_map = dict((ud['itag'][0], ud['url'][0]) for ud in url_data)
+

                        format_limit = self._downloader.params.get('format_limit', None)
                        if format_limit is not None and format_limit in self._available_formats:
                                format_list = self._available_formats[self._available_formats.index(format_limit):]
                        format_limit = self._downloader.params.get('format_limit', None)
                        if format_limit is not None and format_limit in self._available_formats:
                                format_list = self._available_formats[self._available_formats.index(format_limit):]


@@ -1106,23 +1367,29 @@ class YoutubeIE(InfoExtractor):
                        if len(existing_formats) == 0:
                                self._downloader.trouble(u'ERROR: no known formats available for video')
                                return
                        if len(existing_formats) == 0:
                                self._downloader.trouble(u'ERROR: no known formats available for video')
                                return

-                       if req_format is None:
+                       if self._downloader.params.get('listformats', None):
+                               self._print_formats(existing_formats)
+                               return
+                       if req_format is None or req_format == 'best':

                                video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
                                video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality

-                       elif req_format == '-1':
+                       elif req_format == 'worst':
+                               video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality
+                       elif req_format in ('-1', 'all'):

                                video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
                        else:
                                video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
                        else:

-                               # Specific format
-                               if req_format not in url_map:
+                               # Specific formats. We pick the first in a slash-delimeted sequence.
+                               # For example, if '1/2/3/4' is requested and '2' and '4' are available, we pick '2'.
+                               req_formats = req_format.split('/')
+                               video_url_list = None
+                               for rf in req_formats:
+                                       if rf in url_map:
+                                               video_url_list = [(rf, url_map[rf])]
+                                               break
+                               if video_url_list is None:

                                        self._downloader.trouble(u'ERROR: requested format not available')
                                        return
                                        self._downloader.trouble(u'ERROR: requested format not available')
                                        return

-                               video_url_list = [(req_format, url_map[req_format])] # Specific format
-
-               elif 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
-                       self.report_rtmp_download()
-                       video_url_list = [(None, video_info['conn'][0])]
-

                else:
                else:

-                       self._downloader.trouble(u'ERROR: no fmt_url_map or conn information found in video info')
+                       self._downloader.trouble(u'ERROR: no conn or url_encoded_fmt_stream_map information found in video info')

                        return
 
                for format_param, video_real_url in video_url_list:
                        return
 
                for format_param, video_real_url in video_url_list:


@@ -1132,7 +1399,6 @@ class YoutubeIE(InfoExtractor):
                        # Extension
                        video_extension = self._video_extensions.get(format_param, 'flv')
 
                        # Extension
                        video_extension = self._video_extensions.get(format_param, 'flv')
 

-                       # Find the video URL in fmt_url_map or conn paramters

                        try:
                                # Process video information
                                self._downloader.process_info({
                        try:
                                # Process video information
                                self._downloader.process_info({


@@ -1145,7 +1411,7 @@ class YoutubeIE(InfoExtractor):
                                        'ext':          video_extension.decode('utf-8'),
                                        'format':       (format_param is None and u'NA' or format_param.decode('utf-8')),
                                        'thumbnail':    video_thumbnail.decode('utf-8'),
                                        'ext':          video_extension.decode('utf-8'),
                                        'format':       (format_param is None and u'NA' or format_param.decode('utf-8')),
                                        'thumbnail':    video_thumbnail.decode('utf-8'),

-                                       'description':  video_description.decode('utf-8'),
+                                       'description':  video_description,

                                        'player_url':   player_url,
                                })
                        except UnavailableVideoError, err:
                                        'player_url':   player_url,
                                })
                        except UnavailableVideoError, err:


@@ -1159,15 +1425,12 @@ class MetacafeIE(InfoExtractor):
        _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
        _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
        _youtube_ie = None
        _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
        _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
        _youtube_ie = None

+       IE_NAME = u'metacafe'

 
        def __init__(self, youtube_ie, downloader=None):
                InfoExtractor.__init__(self, downloader)
                self._youtube_ie = youtube_ie
 
 
        def __init__(self, youtube_ie, downloader=None):
                InfoExtractor.__init__(self, downloader)
                self._youtube_ie = youtube_ie
 

-       @staticmethod
-       def suitable(url):
-               return (re.match(MetacafeIE._VALID_URL, url) is not None)
-

        def report_disclaimer(self):
                """Report disclaimer retrieval."""
                self._downloader.to_screen(u'[metacafe] Retrieving disclaimer')
        def report_disclaimer(self):
                """Report disclaimer retrieval."""
                self._downloader.to_screen(u'[metacafe] Retrieving disclaimer')


@@ -1301,14 +1564,11 @@ class DailymotionIE(InfoExtractor):
        """Information Extractor for Dailymotion"""
 
        _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)'
        """Information Extractor for Dailymotion"""
 
        _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)'

+       IE_NAME = u'dailymotion'

 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 
 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 

-       @staticmethod
-       def suitable(url):
-               return (re.match(DailymotionIE._VALID_URL, url) is not None)
-

        def report_download_webpage(self, video_id):
                """Report webpage download."""
                self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id)
        def report_download_webpage(self, video_id):
                """Report webpage download."""
                self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id)


@@ -1317,9 +1577,6 @@ class DailymotionIE(InfoExtractor):
                """Report information extraction."""
                self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id)
 
                """Report information extraction."""
                self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id)
 

-       def _real_initialize(self):
-               return
-

        def _real_extract(self, url):
                # Extract id and simplified title from URL
                mobj = re.match(self._VALID_URL, url)
        def _real_extract(self, url):
                # Extract id and simplified title from URL
                mobj = re.match(self._VALID_URL, url)


@@ -1336,6 +1593,7 @@ class DailymotionIE(InfoExtractor):
 
                # Retrieve video webpage to extract further information
                request = urllib2.Request(url)
 
                # Retrieve video webpage to extract further information
                request = urllib2.Request(url)

+               request.add_header('Cookie', 'family_filter=off')

                try:
                        self.report_download_webpage(video_id)
                        webpage = urllib2.urlopen(request).read()
                try:
                        self.report_download_webpage(video_id)
                        webpage = urllib2.urlopen(request).read()


@@ -1345,25 +1603,29 @@ class DailymotionIE(InfoExtractor):
 
                # Extract URL, uploader and title from webpage
                self.report_extraction(video_id)
 
                # Extract URL, uploader and title from webpage
                self.report_extraction(video_id)

-               mobj = re.search(r'(?i)addVariable\(\"video\"\s*,\s*\"([^\"]*)\"\)', webpage)
+               mobj = re.search(r'(?i)addVariable\(\"sequence\"\s*,\s*\"([^\"]+?)\"\)', webpage)

                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract media URL')
                        return
                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract media URL')
                        return

-               mediaURL = urllib.unquote(mobj.group(1))
+               sequence = urllib.unquote(mobj.group(1))
+               mobj = re.search(r',\"sdURL\"\:\"([^\"]+?)\",', sequence)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract media URL')
+                       return
+               mediaURL = urllib.unquote(mobj.group(1)).replace('\\', '')

 
                # if needed add http://www.dailymotion.com/ if relative URL
 
                video_url = mediaURL
 
 
                # if needed add http://www.dailymotion.com/ if relative URL
 
                video_url = mediaURL
 

-               # '<meta\s+name="title"\s+content="Dailymotion\s*[:\-]\s*(.*?)"\s*\/\s*>'
-               mobj = re.search(r'(?im)<title>Dailymotion\s*[\-:]\s*(.+?)</title>', webpage)
+               mobj = re.search(r'(?im)<title>\s*(.+)\s*-\s*Video\s+Dailymotion</title>', webpage)

                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract title')
                        return
                video_title = mobj.group(1).decode('utf-8')
                video_title = sanitize_title(video_title)
 
                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract title')
                        return
                video_title = mobj.group(1).decode('utf-8')
                video_title = sanitize_title(video_title)
 

-               mobj = re.search(r'(?im)<Attribute name="owner">(.+?)</Attribute>', webpage)
+               mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a></span>', webpage)

                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
                        return
                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
                        return


@@ -1390,14 +1652,11 @@ class GoogleIE(InfoExtractor):
        """Information extractor for video.google.com."""
 
        _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*'
        """Information extractor for video.google.com."""
 
        _VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*'

+       IE_NAME = u'video.google'

 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 
 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 

-       @staticmethod
-       def suitable(url):
-               return (re.match(GoogleIE._VALID_URL, url) is not None)
-

        def report_download_webpage(self, video_id):
                """Report webpage download."""
                self._downloader.to_screen(u'[video.google] %s: Downloading webpage' % video_id)
        def report_download_webpage(self, video_id):
                """Report webpage download."""
                self._downloader.to_screen(u'[video.google] %s: Downloading webpage' % video_id)


@@ -1406,9 +1665,6 @@ class GoogleIE(InfoExtractor):
                """Report information extraction."""
                self._downloader.to_screen(u'[video.google] %s: Extracting information' % video_id)
 
                """Report information extraction."""
                self._downloader.to_screen(u'[video.google] %s: Extracting information' % video_id)
 

-       def _real_initialize(self):
-               return
-

        def _real_extract(self, url):
                # Extract id from URL
                mobj = re.match(self._VALID_URL, url)
        def _real_extract(self, url):
                # Extract id from URL
                mobj = re.match(self._VALID_URL, url)


@@ -1452,7 +1708,7 @@ class GoogleIE(InfoExtractor):
                        return
                video_title = mobj.group(1).decode('utf-8')
                video_title = sanitize_title(video_title)
                        return
                video_title = mobj.group(1).decode('utf-8')
                video_title = sanitize_title(video_title)

-               simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+               simple_title = _simplify_title(video_title)

 
                # Extract video description
                mobj = re.search(r'<span id=short-desc-content>([^<]*)</span>', webpage)
 
                # Extract video description
                mobj = re.search(r'<span id=short-desc-content>([^<]*)</span>', webpage)


@@ -1500,14 +1756,11 @@ class PhotobucketIE(InfoExtractor):
        """Information extractor for photobucket.com."""
 
        _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
        """Information extractor for photobucket.com."""
 
        _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'

+       IE_NAME = u'photobucket'

 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 
 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 

-       @staticmethod
-       def suitable(url):
-               return (re.match(PhotobucketIE._VALID_URL, url) is not None)
-

        def report_download_webpage(self, video_id):
                """Report webpage download."""
                self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id)
        def report_download_webpage(self, video_id):
                """Report webpage download."""
                self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id)


@@ -1516,9 +1769,6 @@ class PhotobucketIE(InfoExtractor):
                """Report information extraction."""
                self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id)
 
                """Report information extraction."""
                self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id)
 

-       def _real_initialize(self):
-               return
-

        def _real_extract(self, url):
                # Extract id from URL
                mobj = re.match(self._VALID_URL, url)
        def _real_extract(self, url):
                # Extract id from URL
                mobj = re.match(self._VALID_URL, url)


@@ -1557,7 +1807,7 @@ class PhotobucketIE(InfoExtractor):
                        return
                video_title = mobj.group(1).decode('utf-8')
                video_title = sanitize_title(video_title)
                        return
                video_title = mobj.group(1).decode('utf-8')
                video_title = sanitize_title(video_title)

-               simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+               simple_title = _simplify_title(vide_title)

 
                video_uploader = mobj.group(2).decode('utf-8')
 
 
                video_uploader = mobj.group(2).decode('utf-8')
 


@@ -1585,14 +1835,11 @@ class YahooIE(InfoExtractor):
        # _VPAGE_URL matches only the extractable '/watch/' URLs
        _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?'
        _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?'
        # _VPAGE_URL matches only the extractable '/watch/' URLs
        _VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?'
        _VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?'

+       IE_NAME = u'video.yahoo'

 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 
 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 

-       @staticmethod
-       def suitable(url):
-               return (re.match(YahooIE._VALID_URL, url) is not None)
-

        def report_download_webpage(self, video_id):
                """Report webpage download."""
                self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id)
        def report_download_webpage(self, video_id):
                """Report webpage download."""
                self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id)


@@ -1601,9 +1848,6 @@ class YahooIE(InfoExtractor):
                """Report information extraction."""
                self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id)
 
                """Report information extraction."""
                self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id)
 

-       def _real_initialize(self):
-               return
-

        def _real_extract(self, url, new_video=True):
                # Extract ID from URL
                mobj = re.match(self._VALID_URL, url)
        def _real_extract(self, url, new_video=True):
                # Extract ID from URL
                mobj = re.match(self._VALID_URL, url)


@@ -1657,7 +1901,7 @@ class YahooIE(InfoExtractor):
                        self._downloader.trouble(u'ERROR: unable to extract video title')
                        return
                video_title = mobj.group(1).decode('utf-8')
                        self._downloader.trouble(u'ERROR: unable to extract video title')
                        return
                video_title = mobj.group(1).decode('utf-8')

-               simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+               simple_title = _simplify_title(video_title)

 
                mobj = re.search(r'<h2 class="ti-5"><a href="http://video\.yahoo\.com/(people|profile)/[0-9]+" beacon=".*">(.*)</a></h2>', webpage)
                if mobj is None:
 
                mobj = re.search(r'<h2 class="ti-5"><a href="http://video\.yahoo\.com/(people|profile)/[0-9]+" beacon=".*">(.*)</a></h2>', webpage)
                if mobj is None:


@@ -1730,23 +1974,143 @@ class YahooIE(InfoExtractor):
                                'thumbnail':    video_thumbnail.decode('utf-8'),
                                'description':  video_description,
                                'thumbnail':    video_thumbnail,
                                'thumbnail':    video_thumbnail.decode('utf-8'),
                                'description':  video_description,
                                'thumbnail':    video_thumbnail,

-                               'description':  video_description,

                                'player_url':   None,
                        })
                except UnavailableVideoError:
                        self._downloader.trouble(u'\nERROR: unable to download video')
 
 
                                'player_url':   None,
                        })
                except UnavailableVideoError:
                        self._downloader.trouble(u'\nERROR: unable to download video')
 
 

+class VimeoIE(InfoExtractor):
+       """Information extractor for vimeo.com."""
+
+       # _VALID_URL matches Vimeo URLs
+       _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:groups/[^/]+/)?(?:videos?/)?([0-9]+)'
+       IE_NAME = u'vimeo'
+
+       def __init__(self, downloader=None):
+               InfoExtractor.__init__(self, downloader)
+
+       def report_download_webpage(self, video_id):
+               """Report webpage download."""
+               self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id)
+
+       def report_extraction(self, video_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id)
+
+       def _real_extract(self, url, new_video=True):
+               # Extract ID from URL
+               mobj = re.match(self._VALID_URL, url)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+                       return
+
+               # At this point we have a new video
+               self._downloader.increment_downloads()
+               video_id = mobj.group(1)
+
+               # Retrieve video webpage to extract further information
+               request = urllib2.Request("http://vimeo.com/moogaloop/load/clip:%s" % video_id, None, std_headers)
+               try:
+                       self.report_download_webpage(video_id)
+                       webpage = urllib2.urlopen(request).read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+                       return
+
+               # Now we begin extracting as much information as we can from what we
+               # retrieved. First we extract the information common to all extractors,
+               # and latter we extract those that are Vimeo specific.
+               self.report_extraction(video_id)
+
+               # Extract title
+               mobj = re.search(r'<caption>(.*?)</caption>', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract video title')
+                       return
+               video_title = mobj.group(1).decode('utf-8')
+               simple_title = _simplify_title(video_title)
+
+               # Extract uploader
+               mobj = re.search(r'<uploader_url>http://vimeo.com/(.*?)</uploader_url>', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract video uploader')
+                       return
+               video_uploader = mobj.group(1).decode('utf-8')
+
+               # Extract video thumbnail
+               mobj = re.search(r'<thumbnail>(.*?)</thumbnail>', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
+                       return
+               video_thumbnail = mobj.group(1).decode('utf-8')
+
+               # # Extract video description
+               # mobj = re.search(r'<meta property="og:description" content="(.*)" />', webpage)
+               # if mobj is None:
+               #       self._downloader.trouble(u'ERROR: unable to extract video description')
+               #       return
+               # video_description = mobj.group(1).decode('utf-8')
+               # if not video_description: video_description = 'No description available.'
+               video_description = 'Foo.'
+
+               # Vimeo specific: extract request signature
+               mobj = re.search(r'<request_signature>(.*?)</request_signature>', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract request signature')
+                       return
+               sig = mobj.group(1).decode('utf-8')
+
+               # Vimeo specific: extract video quality information
+               mobj = re.search(r'<isHD>(\d+)</isHD>', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract video quality information')
+                       return
+               quality = mobj.group(1).decode('utf-8')
+
+               if int(quality) == 1:
+                       quality = 'hd'
+               else:
+                       quality = 'sd'
+
+               # Vimeo specific: Extract request signature expiration
+               mobj = re.search(r'<request_signature_expires>(.*?)</request_signature_expires>', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract request signature expiration')
+                       return
+               sig_exp = mobj.group(1).decode('utf-8')
+
+               video_url = "http://vimeo.com/moogaloop/play/clip:%s/%s/%s/?q=%s" % (video_id, sig, sig_exp, quality)
+
+               try:
+                       # Process video information
+                       self._downloader.process_info({
+                               'id':           video_id.decode('utf-8'),
+                               'url':          video_url,
+                               'uploader':     video_uploader,
+                               'upload_date':  u'NA',
+                               'title':        video_title,
+                               'stitle':       simple_title,
+                               'ext':          u'mp4',
+                               'thumbnail':    video_thumbnail.decode('utf-8'),
+                               'description':  video_description,
+                               'thumbnail':    video_thumbnail,
+                               'description':  video_description,
+                               'player_url':   None,
+                       })
+               except UnavailableVideoError:
+                       self._downloader.trouble(u'ERROR: unable to download video')
+
+

 class GenericIE(InfoExtractor):
        """Generic last-resort information extractor."""
 
 class GenericIE(InfoExtractor):
        """Generic last-resort information extractor."""
 

+       _VALID_URL = r'.*'
+       IE_NAME = u'generic'
+

        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 

-       @staticmethod
-       def suitable(url):
-               return True
-

        def report_download_webpage(self, video_id):
                """Report webpage download."""
                self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.')
        def report_download_webpage(self, video_id):
                """Report webpage download."""
                self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.')


@@ -1756,9 +2120,6 @@ class GenericIE(InfoExtractor):
                """Report information extraction."""
                self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id)
 
                """Report information extraction."""
                self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id)
 

-       def _real_initialize(self):
-               return
-

        def _real_extract(self, url):
                # At this point we have a new video
                self._downloader.increment_downloads()
        def _real_extract(self, url):
                # At this point we have a new video
                self._downloader.increment_downloads()


@@ -1812,7 +2173,7 @@ class GenericIE(InfoExtractor):
                        return
                video_title = mobj.group(1).decode('utf-8')
                video_title = sanitize_title(video_title)
                        return
                video_title = mobj.group(1).decode('utf-8')
                video_title = sanitize_title(video_title)

-               simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+               simple_title = _simplify_title(video_title)

 
                # video uploader is domain name
                mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
 
                # video uploader is domain name
                mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)


@@ -1840,21 +2201,18 @@ class GenericIE(InfoExtractor):
 
 class YoutubeSearchIE(InfoExtractor):
        """Information Extractor for YouTube search queries."""
 
 class YoutubeSearchIE(InfoExtractor):
        """Information Extractor for YouTube search queries."""

-       _VALID_QUERY = r'ytsearch(\d+|all)?:[\s\S]+'
+       _VALID_URL = 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'(?m)>\s*Next\s*</a>'
        _youtube_ie = None
        _max_youtube_results = 1000
        _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'(?m)>\s*Next\s*</a>'
        _youtube_ie = None
        _max_youtube_results = 1000

+       IE_NAME = u'youtube:search'

 
        def __init__(self, youtube_ie, downloader=None):
                InfoExtractor.__init__(self, downloader)
                self._youtube_ie = youtube_ie
 
 
        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."""
                query = query.decode(preferredencoding())
        def report_download_page(self, query, pagenum):
                """Report attempt to download playlist page with given number."""
                query = query.decode(preferredencoding())


@@ -1864,7 +2222,7 @@ class YoutubeSearchIE(InfoExtractor):
                self._youtube_ie.initialize()
 
        def _real_extract(self, query):
                self._youtube_ie.initialize()
 
        def _real_extract(self, query):

-               mobj = re.match(self._VALID_QUERY, query)
+               mobj = re.match(self._VALID_URL, query)

                if mobj is None:
                        self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
                        return
                if mobj is None:
                        self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
                        return


@@ -1932,21 +2290,18 @@ class YoutubeSearchIE(InfoExtractor):
 
 class GoogleSearchIE(InfoExtractor):
        """Information Extractor for Google Video search queries."""
 
 class GoogleSearchIE(InfoExtractor):
        """Information Extractor for Google Video search queries."""

-       _VALID_QUERY = r'gvsearch(\d+|all)?:[\s\S]+'
+       _VALID_URL = r'gvsearch(\d+|all)?:[\s\S]+'

        _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en'
        _VIDEO_INDICATOR = r'videoplay\?docid=([^\&>]+)\&'
        _MORE_PAGES_INDICATOR = r'<span>Next</span>'
        _google_ie = None
        _max_google_results = 1000
        _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en'
        _VIDEO_INDICATOR = r'videoplay\?docid=([^\&>]+)\&'
        _MORE_PAGES_INDICATOR = r'<span>Next</span>'
        _google_ie = None
        _max_google_results = 1000

+       IE_NAME = u'video.google:search'

 
        def __init__(self, google_ie, downloader=None):
                InfoExtractor.__init__(self, downloader)
                self._google_ie = google_ie
 
 
        def __init__(self, google_ie, downloader=None):
                InfoExtractor.__init__(self, downloader)
                self._google_ie = google_ie
 

-       @staticmethod
-       def suitable(url):
-               return (re.match(GoogleSearchIE._VALID_QUERY, url) is not None)
-

        def report_download_page(self, query, pagenum):
                """Report attempt to download playlist page with given number."""
                query = query.decode(preferredencoding())
        def report_download_page(self, query, pagenum):
                """Report attempt to download playlist page with given number."""
                query = query.decode(preferredencoding())


@@ -1956,7 +2311,7 @@ class GoogleSearchIE(InfoExtractor):
                self._google_ie.initialize()
 
        def _real_extract(self, query):
                self._google_ie.initialize()
 
        def _real_extract(self, query):

-               mobj = re.match(self._VALID_QUERY, query)
+               mobj = re.match(self._VALID_URL, query)

                if mobj is None:
                        self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
                        return
                if mobj is None:
                        self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
                        return


@@ -2024,21 +2379,18 @@ class GoogleSearchIE(InfoExtractor):
 
 class YahooSearchIE(InfoExtractor):
        """Information Extractor for Yahoo! Video search queries."""
 
 class YahooSearchIE(InfoExtractor):
        """Information Extractor for Yahoo! Video search queries."""

-       _VALID_QUERY = r'yvsearch(\d+|all)?:[\s\S]+'
+       _VALID_URL = r'yvsearch(\d+|all)?:[\s\S]+'

        _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s'
        _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"'
        _MORE_PAGES_INDICATOR = r'\s*Next'
        _yahoo_ie = None
        _max_yahoo_results = 1000
        _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s'
        _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"'
        _MORE_PAGES_INDICATOR = r'\s*Next'
        _yahoo_ie = None
        _max_yahoo_results = 1000

+       IE_NAME = u'video.yahoo:search'

 
        def __init__(self, yahoo_ie, downloader=None):
                InfoExtractor.__init__(self, downloader)
                self._yahoo_ie = yahoo_ie
 
 
        def __init__(self, yahoo_ie, downloader=None):
                InfoExtractor.__init__(self, downloader)
                self._yahoo_ie = yahoo_ie
 

-       @staticmethod
-       def suitable(url):
-               return (re.match(YahooSearchIE._VALID_QUERY, url) is not None)
-

        def report_download_page(self, query, pagenum):
                """Report attempt to download playlist page with given number."""
                query = query.decode(preferredencoding())
        def report_download_page(self, query, pagenum):
                """Report attempt to download playlist page with given number."""
                query = query.decode(preferredencoding())


@@ -2048,7 +2400,7 @@ class YahooSearchIE(InfoExtractor):
                self._yahoo_ie.initialize()
 
        def _real_extract(self, query):
                self._yahoo_ie.initialize()
 
        def _real_extract(self, query):

-               mobj = re.match(self._VALID_QUERY, query)
+               mobj = re.match(self._VALID_URL, query)

                if mobj is None:
                        self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
                        return
                if mobj is None:
                        self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
                        return


@@ -2117,20 +2469,17 @@ class YahooSearchIE(InfoExtractor):
 class YoutubePlaylistIE(InfoExtractor):
        """Information Extractor for YouTube playlists."""
 
 class YoutubePlaylistIE(InfoExtractor):
        """Information Extractor for YouTube playlists."""
 

-       _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists|artist)\?.*?(p|a)=|user/.*?/user/|p/|user/.*?#[pg]/c/)([0-9A-Za-z]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
+       _VALID_URL = r'(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL)?([0-9A-Za-z-_]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'

        _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
        _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
        _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
        _youtube_ie = None
        _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
        _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
        _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
        _youtube_ie = None

+       IE_NAME = u'youtube:playlist'

 
        def __init__(self, youtube_ie, downloader=None):
                InfoExtractor.__init__(self, downloader)
                self._youtube_ie = youtube_ie
 
 
        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._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
        def report_download_page(self, playlist_id, pagenum):
                """Report attempt to download playlist page with given number."""
                self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))


@@ -2164,7 +2513,8 @@ class YoutubePlaylistIE(InfoExtractor):
 
                while True:
                        self.report_download_page(playlist_id, pagenum)
 
                while True:
                        self.report_download_page(playlist_id, pagenum)

-                       request = urllib2.Request(self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum))
+                       url = self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum)
+                       request = urllib2.Request(url)

                        try:
                                page = urllib2.urlopen(request).read()
                        except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                        try:
                                page = urllib2.urlopen(request).read()
                        except (urllib2.URLError, httplib.HTTPException, socket.error), err:


@@ -2194,21 +2544,18 @@ class YoutubePlaylistIE(InfoExtractor):
 class YoutubeUserIE(InfoExtractor):
        """Information Extractor for YouTube users."""
 
 class YoutubeUserIE(InfoExtractor):
        """Information Extractor for YouTube users."""
 

-       _VALID_URL = r'(?:(?:(?:http://)?(?:\w+\.)?youtube.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
+       _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/user/)|ytuser:)([A-Za-z0-9_-]+)'

        _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
        _GDATA_PAGE_SIZE = 50
        _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d'
        _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
        _GDATA_PAGE_SIZE = 50
        _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d'

-       _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
+       _VIDEO_INDICATOR = r'/watch\?v=(.+?)[\<&]'

        _youtube_ie = None
        _youtube_ie = None

+       IE_NAME = u'youtube:user'

 
        def __init__(self, youtube_ie, downloader=None):
                InfoExtractor.__init__(self, downloader)
                self._youtube_ie = youtube_ie
 
 
        def __init__(self, youtube_ie, downloader=None):
                InfoExtractor.__init__(self, downloader)
                self._youtube_ie = youtube_ie
 

-       @staticmethod
-       def suitable(url):
-               return (re.match(YoutubeUserIE._VALID_URL, url) is not None)
-

        def report_download_page(self, username, start_index):
                """Report attempt to download user page."""
                self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' %
        def report_download_page(self, username, start_index):
                """Report attempt to download user page."""
                self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' %


@@ -2285,15 +2632,12 @@ class YoutubeUserIE(InfoExtractor):
 class DepositFilesIE(InfoExtractor):
        """Information extractor for depositfiles.com"""
 
 class DepositFilesIE(InfoExtractor):
        """Information extractor for depositfiles.com"""
 

-       _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles.com/(?:../(?#locale))?files/(.+)'
+       _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)'
+       IE_NAME = u'DepositFiles'

 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 
 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 

-       @staticmethod
-       def suitable(url):
-               return (re.match(DepositFilesIE._VALID_URL, url) is not None)
-

        def report_download_webpage(self, file_id):
                """Report webpage download."""
                self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id)
        def report_download_webpage(self, file_id):
                """Report webpage download."""
                self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id)


@@ -2302,9 +2646,6 @@ class DepositFilesIE(InfoExtractor):
                """Report information extraction."""
                self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id)
 
                """Report information extraction."""
                self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id)
 

-       def _real_initialize(self):
-               return
-

        def _real_extract(self, url):
                # At this point we have a new file
                self._downloader.increment_downloads()
        def _real_extract(self, url):
                # At this point we have a new file
                self._downloader.increment_downloads()


@@ -2365,22 +2706,20 @@ class DepositFilesIE(InfoExtractor):
 class FacebookIE(InfoExtractor):
        """Information Extractor for Facebook"""
 
 class FacebookIE(InfoExtractor):
        """Information Extractor for Facebook"""
 

-       _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook.com/video/video.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
+       _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'

        _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&'
        _NETRC_MACHINE = 'facebook'
        _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&'
        _NETRC_MACHINE = 'facebook'

-       _available_formats = ['highqual', 'lowqual']
+       _available_formats = ['video', 'highqual', 'lowqual']

        _video_extensions = {
        _video_extensions = {

+               'video': 'mp4',

                'highqual': 'mp4',
                'lowqual': 'mp4',
        }
                'highqual': 'mp4',
                'lowqual': 'mp4',
        }

+       IE_NAME = u'facebook'

 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 
 
        def __init__(self, downloader=None):
                InfoExtractor.__init__(self, downloader)
 

-       @staticmethod
-       def suitable(url):
-               return (re.match(FacebookIE._VALID_URL, url) is not None)
-

        def _reporter(self, message):
                """Add header and report message."""
                self._downloader.to_screen(u'[facebook] %s' % message)
        def _reporter(self, message):
                """Add header and report message."""
                self._downloader.to_screen(u'[facebook] %s' % message)


@@ -2400,10 +2739,9 @@ class FacebookIE(InfoExtractor):
        def _parse_page(self, video_webpage):
                """Extract video information from page"""
                # General data
        def _parse_page(self, video_webpage):
                """Extract video information from page"""
                # General data

-               data = {'title': r'class="video_title datawrap">(.*?)</',
+               data = {'title': r'\("video_title", "(.*?)"\)',

                        'description': r'<div class="datawrap">(.*?)</div>',
                        'owner': r'\("video_owner_name", "(.*?)"\)',
                        'description': r'<div class="datawrap">(.*?)</div>',
                        'owner': r'\("video_owner_name", "(.*?)"\)',

-                       'upload_date': r'data-date="(.*?)"',

                        'thumbnail':  r'\("thumb_url", "(?P<THUMB>.*?)"\)',
                        }
                video_info = {}
                        'thumbnail':  r'\("thumb_url", "(?P<THUMB>.*?)"\)',
                        }
                video_info = {}


@@ -2505,9 +2843,7 @@ class FacebookIE(InfoExtractor):
                video_title = video_title.decode('utf-8')
                video_title = sanitize_title(video_title)
 
                video_title = video_title.decode('utf-8')
                video_title = sanitize_title(video_title)
 

-               # simplified title
-               simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
-               simple_title = simple_title.strip(ur'_')
+               simple_title = _simplify_title(video_title)

 
                # thumbnail image
                if 'thumbnail' not in video_info:
 
                # thumbnail image
                if 'thumbnail' not in video_info:


@@ -2528,10 +2864,7 @@ class FacebookIE(InfoExtractor):
                                        pass
 
                # description
                                        pass
 
                # description

-               video_description = 'No description available.'
-               if (self._downloader.params.get('forcedescription', False) and
-                       'description' in video_info):
-                       video_description = video_info['description']
+               video_description = video_info.get('description', 'No description available.')

 
                url_map = video_info['video_urls']
                if len(url_map.keys()) > 0:
 
                url_map = video_info['video_urls']
                if len(url_map.keys()) > 0:


@@ -2549,6 +2882,8 @@ class FacebookIE(InfoExtractor):
                                return
                        if req_format is None:
                                video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
                                return
                        if req_format is None:
                                video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality

+                       elif req_format == 'worst':
+                               video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality

                        elif req_format == '-1':
                                video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
                        else:
                        elif req_format == '-1':
                                video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
                        else:


@@ -2566,7 +2901,6 @@ class FacebookIE(InfoExtractor):
                        # Extension
                        video_extension = self._video_extensions.get(format_param, 'mp4')
 
                        # Extension
                        video_extension = self._video_extensions.get(format_param, 'mp4')
 

-                       # Find the video URL in fmt_url_map or conn paramters

                        try:
                                # Process video information
                                self._downloader.process_info({
                        try:
                                # Process video information
                                self._downloader.process_info({


@@ -2585,37 +2919,863 @@ class FacebookIE(InfoExtractor):
                        except UnavailableVideoError, err:
                                self._downloader.trouble(u'\nERROR: unable to download video')
 
                        except UnavailableVideoError, err:
                                self._downloader.trouble(u'\nERROR: unable to download video')
 

+class BlipTVIE(InfoExtractor):
+       """Information extractor for blip.tv"""

 
 

-class PostProcessor(object):
-       """Post Processor class.
+       _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv(/.+)$'
+       _URL_EXT = r'^.*\.([a-z0-9]+)$'
+       IE_NAME = u'blip.tv'

 
 

-       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.
+       def report_extraction(self, file_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id))

 
 

-       The chain will be stopped if one of them ever returns None or the end
-       of the chain is reached.
+       def report_direct_download(self, title):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[%s] %s: Direct download detected' % (self.IE_NAME, title))

 
 

-       PostProcessor objects follow a "mutual registration" process similar
-       to InfoExtractor objects.
-       """
+       def _real_extract(self, url):
+               mobj = re.match(self._VALID_URL, url)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+                       return

 
 

-       _downloader = None
+               if '?' in url:
+                       cchar = '&'
+               else:
+                       cchar = '?'
+               json_url = url + cchar + 'skin=json&version=2&no_wrap=1'
+               request = urllib2.Request(json_url)
+               self.report_extraction(mobj.group(1))
+               info = None
+               try:
+                       urlh = urllib2.urlopen(request)
+                       if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download
+                               basename = url.split('/')[-1]
+                               title,ext = os.path.splitext(basename)
+                               title = title.decode('UTF-8')
+                               ext = ext.replace('.', '')
+                               self.report_direct_download(title)
+                               info = {
+                                       'id': title,
+                                       'url': url,
+                                       'title': title,
+                                       'stitle': _simplify_title(title),
+                                       'ext': ext,
+                                       'urlhandle': urlh
+                               }
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
+                       return
+               if info is None: # Regular URL
+                       try:
+                               json_code = urlh.read()
+                       except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                               self._downloader.trouble(u'ERROR: unable to read video info webpage: %s' % str(err))
+                               return

 
 

-       def __init__(self, downloader=None):
-               self._downloader = downloader
+                       try:
+                               json_data = json.loads(json_code)
+                               if 'Post' in json_data:
+                                       data = json_data['Post']
+                               else:
+                                       data = json_data
+       
+                               upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d')
+                               video_url = data['media']['url']
+                               umobj = re.match(self._URL_EXT, video_url)
+                               if umobj is None:
+                                       raise ValueError('Can not determine filename extension')
+                               ext = umobj.group(1)
+       
+                               info = {
+                                       'id': data['item_id'],
+                                       'url': video_url,
+                                       'uploader': data['display_name'],
+                                       'upload_date': upload_date,
+                                       'title': data['title'],
+                                       'stitle': _simplify_title(data['title']),
+                                       'ext': ext,
+                                       'format': data['media']['mimeType'],
+                                       'thumbnail': data['thumbnailUrl'],
+                                       'description': data['description'],
+                                       'player_url': data['embedUrl']
+                               }
+                       except (ValueError,KeyError), err:
+                               self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err))
+                               return

 
 

-       def set_downloader(self, downloader):
-               """Sets the downloader for this PP."""
-               self._downloader = downloader
+               self._downloader.increment_downloads()

 
 

-       def run(self, information):
-               """Run the PostProcessor.
+               try:
+                       self._downloader.process_info(info)
+               except UnavailableVideoError, err:
+                       self._downloader.trouble(u'\nERROR: unable to download video')

 
 

-               The "information" argument is a dictionary like the ones
+
+class MyVideoIE(InfoExtractor):
+       """Information Extractor for myvideo.de."""
+
+       _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*'
+       IE_NAME = u'myvideo'
+
+       def __init__(self, downloader=None):
+               InfoExtractor.__init__(self, downloader)
+       
+       def report_download_webpage(self, video_id):
+               """Report webpage download."""
+               self._downloader.to_screen(u'[myvideo] %s: Downloading webpage' % video_id)
+
+       def report_extraction(self, video_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[myvideo] %s: Extracting information' % video_id)
+
+       def _real_extract(self,url):
+               mobj = re.match(self._VALID_URL, url)
+               if mobj is None:
+                       self._download.trouble(u'ERROR: invalid URL: %s' % url)
+                       return
+
+               video_id = mobj.group(1)
+
+               # Get video webpage
+               request = urllib2.Request('http://www.myvideo.de/watch/%s' % video_id)
+               try:
+                       self.report_download_webpage(video_id)
+                       webpage = urllib2.urlopen(request).read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+                       return
+
+               self.report_extraction(video_id)
+               mobj = re.search(r'<link rel=\'image_src\' href=\'(http://is[0-9].myvideo\.de/de/movie[0-9]+/[a-f0-9]+)/thumbs/[^.]+\.jpg\' />',
+                                webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract media URL')
+                       return
+               video_url = mobj.group(1) + ('/%s.flv' % video_id)
+
+               mobj = re.search('<title>([^<]+)</title>', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract title')
+                       return
+
+               video_title = mobj.group(1)
+               video_title = sanitize_title(video_title)
+
+               simple_title = _simplify_title(video_title)
+
+               try:
+                       self._downloader.process_info({
+                               'id':           video_id,
+                               'url':          video_url,
+                               'uploader':     u'NA',
+                               'upload_date':  u'NA',
+                               'title':        video_title,
+                               'stitle':       simple_title,
+                               'ext':          u'flv',
+                               'format':       u'NA',
+                               'player_url':   None,
+                       })
+               except UnavailableVideoError:
+                       self._downloader.trouble(u'\nERROR: Unable to download video')
+
+class ComedyCentralIE(InfoExtractor):
+       """Information extractor for The Daily Show and Colbert Report """
+
+       _VALID_URL = r'^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport))|(https?://)?(www\.)?(?P<showname>thedailyshow|colbertnation)\.com/full-episodes/(?P<episode>.*)$'
+       IE_NAME = u'comedycentral'
+
+       def report_extraction(self, episode_id):
+               self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id)
+       
+       def report_config_download(self, episode_id):
+               self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration' % episode_id)
+
+       def report_index_download(self, episode_id):
+               self._downloader.to_screen(u'[comedycentral] %s: Downloading show index' % episode_id)
+
+       def report_player_url(self, episode_id):
+               self._downloader.to_screen(u'[comedycentral] %s: Determining player URL' % episode_id)
+
+       def _real_extract(self, url):
+               mobj = re.match(self._VALID_URL, url)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+                       return
+
+               if mobj.group('shortname'):
+                       if mobj.group('shortname') in ('tds', 'thedailyshow'):
+                               url = u'http://www.thedailyshow.com/full-episodes/'
+                       else:
+                               url = u'http://www.colbertnation.com/full-episodes/'
+                       mobj = re.match(self._VALID_URL, url)
+                       assert mobj is not None
+
+               dlNewest = not mobj.group('episode')
+               if dlNewest:
+                       epTitle = mobj.group('showname')
+               else:
+                       epTitle = mobj.group('episode')
+
+               req = urllib2.Request(url)
+               self.report_extraction(epTitle)
+               try:
+                       htmlHandle = urllib2.urlopen(req)
+                       html = htmlHandle.read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err))
+                       return
+               if dlNewest:
+                       url = htmlHandle.geturl()
+                       mobj = re.match(self._VALID_URL, url)
+                       if mobj is None:
+                               self._downloader.trouble(u'ERROR: Invalid redirected URL: ' + url)
+                               return
+                       if mobj.group('episode') == '':
+                               self._downloader.trouble(u'ERROR: Redirected URL is still not specific: ' + url)
+                               return
+                       epTitle = mobj.group('episode')
+
+               mMovieParams = re.findall('<param name="movie" value="(http://media.mtvnservices.com/([^"]*episode.*?:.*?))"/>', html)
+               if len(mMovieParams) == 0:
+                       self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url)
+                       return
+
+               playerUrl_raw = mMovieParams[0][0]
+               self.report_player_url(epTitle)
+               try:
+                       urlHandle = urllib2.urlopen(playerUrl_raw)
+                       playerUrl = urlHandle.geturl()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to find out player URL: ' + unicode(err))
+                       return
+
+               uri = mMovieParams[0][1]
+               indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + urllib.urlencode({'uri': uri})
+               self.report_index_download(epTitle)
+               try:
+                       indexXml = urllib2.urlopen(indexUrl).read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to download episode index: ' + unicode(err))
+                       return
+
+               idoc = xml.etree.ElementTree.fromstring(indexXml)
+               itemEls = idoc.findall('.//item')
+               for itemEl in itemEls:
+                       mediaId = itemEl.findall('./guid')[0].text
+                       shortMediaId = mediaId.split(':')[-1]
+                       showId = mediaId.split(':')[-2].replace('.com', '')
+                       officialTitle = itemEl.findall('./title')[0].text
+                       officialDate = itemEl.findall('./pubDate')[0].text
+
+                       configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' +
+                                               urllib.urlencode({'uri': mediaId}))
+                       configReq = urllib2.Request(configUrl)
+                       self.report_config_download(epTitle)
+                       try:
+                               configXml = urllib2.urlopen(configReq).read()
+                       except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                               self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err))
+                               return
+
+                       cdoc = xml.etree.ElementTree.fromstring(configXml)
+                       turls = []
+                       for rendition in cdoc.findall('.//rendition'):
+                               finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text)
+                               turls.append(finfo)
+
+                       if len(turls) == 0:
+                               self._downloader.trouble(u'\nERROR: unable to download ' + mediaId + ': No videos found')
+                               continue
+
+                       # For now, just pick the highest bitrate
+                       format,video_url = turls[-1]
+
+                       self._downloader.increment_downloads()
+
+                       effTitle = showId + u'-' + epTitle
+                       info = {
+                               'id': shortMediaId,
+                               'url': video_url,
+                               'uploader': showId,
+                               'upload_date': officialDate,
+                               'title': effTitle,
+                               'stitle': _simplify_title(effTitle),
+                               'ext': 'mp4',
+                               'format': format,
+                               'thumbnail': None,
+                               'description': officialTitle,
+                               'player_url': playerUrl
+                       }
+
+                       try:
+                               self._downloader.process_info(info)
+                       except UnavailableVideoError, err:
+                               self._downloader.trouble(u'\nERROR: unable to download ' + mediaId)
+                               continue
+
+
+class EscapistIE(InfoExtractor):
+       """Information extractor for The Escapist """
+
+       _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
+       IE_NAME = u'escapist'
+
+       def report_extraction(self, showName):
+               self._downloader.to_screen(u'[escapist] %s: Extracting information' % showName)
+
+       def report_config_download(self, showName):
+               self._downloader.to_screen(u'[escapist] %s: Downloading configuration' % showName)
+
+       def _real_extract(self, url):
+               htmlParser = HTMLParser.HTMLParser()
+
+               mobj = re.match(self._VALID_URL, url)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+                       return
+               showName = mobj.group('showname')
+               videoId = mobj.group('episode')
+
+               self.report_extraction(showName)
+               try:
+                       webPage = urllib2.urlopen(url).read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to download webpage: ' + unicode(err))
+                       return
+
+               descMatch = re.search('<meta name="description" content="([^"]*)"', webPage)
+               description = htmlParser.unescape(descMatch.group(1))
+               imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage)
+               imgUrl = htmlParser.unescape(imgMatch.group(1))
+               playerUrlMatch = re.search('<meta property="og:video" content="([^"]*)"', webPage)
+               playerUrl = htmlParser.unescape(playerUrlMatch.group(1))
+               configUrlMatch = re.search('config=(.*)$', playerUrl)
+               configUrl = urllib2.unquote(configUrlMatch.group(1))
+
+               self.report_config_download(showName)
+               try:
+                       configJSON = urllib2.urlopen(configUrl).read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to download configuration: ' + unicode(err))
+                       return
+
+               # Technically, it's JavaScript, not JSON
+               configJSON = configJSON.replace("'", '"')
+
+               try:
+                       config = json.loads(configJSON)
+               except (ValueError,), err:
+                       self._downloader.trouble(u'ERROR: Invalid JSON in configuration file: ' + unicode(err))
+                       return
+
+               playlist = config['playlist']
+               videoUrl = playlist[1]['url']
+
+               self._downloader.increment_downloads()
+               info = {
+                       'id': videoId,
+                       'url': videoUrl,
+                       'uploader': showName,
+                       'upload_date': None,
+                       'title': showName,
+                       'stitle': _simplify_title(showName),
+                       'ext': 'flv',
+                       'format': 'flv',
+                       'thumbnail': imgUrl,
+                       'description': description,
+                       'player_url': playerUrl,
+               }
+
+               try:
+                       self._downloader.process_info(info)
+               except UnavailableVideoError, err:
+                       self._downloader.trouble(u'\nERROR: unable to download ' + videoId)
+
+
+class CollegeHumorIE(InfoExtractor):
+       """Information extractor for collegehumor.com"""
+
+       _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/video/(?P<videoid>[0-9]+)/(?P<shorttitle>.*)$'
+       IE_NAME = u'collegehumor'
+
+       def report_webpage(self, video_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
+
+       def report_extraction(self, video_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+
+       def _real_extract(self, url):
+               htmlParser = HTMLParser.HTMLParser()
+
+               mobj = re.match(self._VALID_URL, url)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+                       return
+               video_id = mobj.group('videoid')
+
+               self.report_webpage(video_id)
+               request = urllib2.Request(url)
+               try:
+                       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
+
+               m = re.search(r'id="video:(?P<internalvideoid>[0-9]+)"', webpage)
+               if m is None:
+                       self._downloader.trouble(u'ERROR: Cannot extract internal video ID')
+                       return
+               internal_video_id = m.group('internalvideoid')
+
+               info = {
+                       'id': video_id,
+                       'internal_id': internal_video_id,
+               }
+
+               self.report_extraction(video_id)
+               xmlUrl = 'http://www.collegehumor.com/moogaloop/video:' + internal_video_id
+               try:
+                       metaXml = urllib2.urlopen(xmlUrl).read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % str(err))
+                       return
+
+               mdoc = xml.etree.ElementTree.fromstring(metaXml)
+               try:
+                       videoNode = mdoc.findall('./video')[0]
+                       info['description'] = videoNode.findall('./description')[0].text
+                       info['title'] = videoNode.findall('./caption')[0].text
+                       info['stitle'] = _simplify_title(info['title'])
+                       info['url'] = videoNode.findall('./file')[0].text
+                       info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
+                       info['ext'] = info['url'].rpartition('.')[2]
+                       info['format'] = info['ext']
+               except IndexError:
+                       self._downloader.trouble(u'\nERROR: Invalid metadata XML file')
+                       return
+
+               self._downloader.increment_downloads()
+
+               try:
+                       self._downloader.process_info(info)
+               except UnavailableVideoError, err:
+                       self._downloader.trouble(u'\nERROR: unable to download video')
+
+
+class XVideosIE(InfoExtractor):
+       """Information extractor for xvideos.com"""
+
+       _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
+       IE_NAME = u'xvideos'
+
+       def report_webpage(self, video_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
+
+       def report_extraction(self, video_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+
+       def _real_extract(self, url):
+               htmlParser = HTMLParser.HTMLParser()
+
+               mobj = re.match(self._VALID_URL, url)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+                       return
+               video_id = mobj.group(1).decode('utf-8')
+
+               self.report_webpage(video_id)
+
+               request = urllib2.Request(r'http://www.xvideos.com/video' + video_id)
+               try:
+                       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_extraction(video_id)
+
+
+               # Extract video URL
+               mobj = re.search(r'flv_url=(.+?)&', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract video url')
+                       return
+               video_url = urllib2.unquote(mobj.group(1).decode('utf-8'))
+
+
+               # Extract title
+               mobj = re.search(r'<title>(.*?)\s+-\s+XVID', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract video title')
+                       return
+               video_title = mobj.group(1).decode('utf-8')
+
+
+               # Extract video thumbnail
+               mobj = re.search(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]/[a-fA-F0-9]/[a-fA-F0-9]/([a-fA-F0-9.]+jpg)', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
+                       return
+               video_thumbnail = mobj.group(1).decode('utf-8')
+
+
+
+               self._downloader.increment_downloads()
+               info = {
+                       'id': video_id,
+                       'url': video_url,
+                       'uploader': None,
+                       'upload_date': None,
+                       'title': video_title,
+                       'stitle': _simplify_title(video_title),
+                       'ext': 'flv',
+                       'format': 'flv',
+                       'thumbnail': video_thumbnail,
+                       'description': None,
+                       'player_url': None,
+               }
+
+               try:
+                       self._downloader.process_info(info)
+               except UnavailableVideoError, err:
+                       self._downloader.trouble(u'\nERROR: unable to download ' + video_id)
+
+
+class SoundcloudIE(InfoExtractor):
+       """Information extractor for soundcloud.com
+          To access the media, the uid of the song and a stream token
+          must be extracted from the page source and the script must make
+          a request to media.soundcloud.com/crossdomain.xml. Then
+          the media can be grabbed by requesting from an url composed
+          of the stream token and uid
+        """
+
+       _VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)'
+       IE_NAME = u'soundcloud'
+
+       def __init__(self, downloader=None):
+               InfoExtractor.__init__(self, downloader)
+
+       def report_webpage(self, video_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
+
+       def report_extraction(self, video_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+
+       def _real_extract(self, url):
+               htmlParser = HTMLParser.HTMLParser()
+
+               mobj = re.match(self._VALID_URL, url)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+                       return
+
+               # extract uploader (which is in the url)
+               uploader = mobj.group(1).decode('utf-8')
+               # extract simple title (uploader + slug of song title)
+               slug_title =  mobj.group(2).decode('utf-8')
+               simple_title = uploader + '-' + slug_title
+
+               self.report_webpage('%s/%s' % (uploader, slug_title))
+
+               request = urllib2.Request('http://soundcloud.com/%s/%s' % (uploader, slug_title))
+               try:
+                       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_extraction('%s/%s' % (uploader, slug_title))
+
+               # extract uid and stream token that soundcloud hands out for access
+               mobj = re.search('"uid":"([\w\d]+?)".*?stream_token=([\w\d]+)', webpage)
+               if mobj:
+                       video_id = mobj.group(1)
+                       stream_token = mobj.group(2)
+
+               # extract unsimplified title
+               mobj = re.search('"title":"(.*?)",', webpage)
+               if mobj:
+                       title = mobj.group(1)
+
+               # construct media url (with uid/token)
+               mediaURL = "http://media.soundcloud.com/stream/%s?stream_token=%s"
+               mediaURL = mediaURL % (video_id, stream_token)
+
+               # description
+               description = u'No description available'
+               mobj = re.search('track-description-value"><p>(.*?)</p>', webpage)
+               if mobj:
+                       description = mobj.group(1)
+               
+               # upload date
+               upload_date = None
+               mobj = re.search("pretty-date'>on ([\w]+ [\d]+, [\d]+ \d+:\d+)</abbr></h2>", webpage)
+               if mobj:
+                       try:
+                               upload_date = datetime.datetime.strptime(mobj.group(1), '%B %d, %Y %H:%M').strftime('%Y%m%d')
+                       except Exception, e:
+                               print str(e)
+
+               # for soundcloud, a request to a cross domain is required for cookies
+               request = urllib2.Request('http://media.soundcloud.com/crossdomain.xml', std_headers)
+
+               try:
+                       self._downloader.process_info({
+                               'id':           video_id.decode('utf-8'),
+                               'url':          mediaURL,
+                               'uploader':     uploader.decode('utf-8'),
+                               'upload_date':  upload_date,
+                               'title':        simple_title.decode('utf-8'),
+                               'stitle':       simple_title.decode('utf-8'),
+                               'ext':          u'mp3',
+                               'format':       u'NA',
+                               'player_url':   None,
+                               'description': description.decode('utf-8')
+                       })
+               except UnavailableVideoError:
+                       self._downloader.trouble(u'\nERROR: unable to download video')
+
+
+class InfoQIE(InfoExtractor):
+       """Information extractor for infoq.com"""
+
+       _VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$'
+       IE_NAME = u'infoq'
+
+       def report_webpage(self, video_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
+
+       def report_extraction(self, video_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+
+       def _real_extract(self, url):
+               htmlParser = HTMLParser.HTMLParser()
+
+               mobj = re.match(self._VALID_URL, url)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+                       return
+
+               self.report_webpage(url)
+
+               request = urllib2.Request(url)
+               try:
+                       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_extraction(url)
+
+
+               # Extract video URL
+               mobj = re.search(r"jsclassref='([^']*)'", webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract video url')
+                       return
+               video_url = 'rtmpe://video.infoq.com/cfx/st/' + urllib2.unquote(mobj.group(1).decode('base64'))
+
+
+               # Extract title
+               mobj = re.search(r'contentTitle = "(.*?)";', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract video title')
+                       return
+               video_title = mobj.group(1).decode('utf-8')
+
+               # Extract description
+               video_description = u'No description available.'
+               mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', webpage)
+               if mobj is not None:
+                       video_description = mobj.group(1).decode('utf-8')
+
+               video_filename = video_url.split('/')[-1]
+               video_id, extension = video_filename.split('.')
+
+               self._downloader.increment_downloads()
+               info = {
+                       'id': video_id,
+                       'url': video_url,
+                       'uploader': None,
+                       'upload_date': None,
+                       'title': video_title,
+                       'stitle': _simplify_title(video_title),
+                       'ext': extension,
+                       'format': extension, # Extension is always(?) mp4, but seems to be flv
+                       'thumbnail': None,
+                       'description': video_description,
+                       'player_url': None,
+               }
+
+               try:
+                       self._downloader.process_info(info)
+               except UnavailableVideoError, err:
+                       self._downloader.trouble(u'\nERROR: unable to download ' + video_url)
+
+class MixcloudIE(InfoExtractor):
+       """Information extractor for www.mixcloud.com"""
+       _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)'
+       IE_NAME = u'mixcloud'
+
+       def __init__(self, downloader=None):
+               InfoExtractor.__init__(self, downloader)
+
+       def report_download_json(self, file_id):
+               """Report JSON download."""
+               self._downloader.to_screen(u'[%s] Downloading json' % self.IE_NAME)
+
+       def report_extraction(self, file_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id))
+
+       def get_urls(self, jsonData, fmt, bitrate='best'):
+               """Get urls from 'audio_formats' section in json"""
+               file_url = None
+               try:
+                       bitrate_list = jsonData[fmt]
+                       if bitrate is None or bitrate == 'best' or bitrate not in bitrate_list:
+                               bitrate = max(bitrate_list) # select highest
+
+                       url_list = jsonData[fmt][bitrate]
+               except TypeError: # we have no bitrate info.
+                       url_list = jsonData[fmt]
+                               
+               return url_list
+
+       def check_urls(self, url_list):
+               """Returns 1st active url from list"""
+               for url in url_list:
+                       try:
+                               urllib2.urlopen(url)
+                               return url
+                       except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                               url = None
+
+               return None
+
+       def _print_formats(self, formats):
+               print 'Available formats:'
+               for fmt in formats.keys():
+                       for b in formats[fmt]:
+                               try:
+                                       ext = formats[fmt][b][0]
+                                       print '%s\t%s\t[%s]' % (fmt, b, ext.split('.')[-1])
+                               except TypeError: # we have no bitrate info
+                                       ext = formats[fmt][0]
+                                       print '%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1])
+                                       break
+
+       def _real_extract(self, url):
+               mobj = re.match(self._VALID_URL, url)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+                       return
+               # extract uploader & filename from url
+               uploader = mobj.group(1).decode('utf-8')
+               file_id = uploader + "-" + mobj.group(2).decode('utf-8')
+
+               # construct API request
+               file_url = 'http://www.mixcloud.com/api/1/cloudcast/' + '/'.join(url.split('/')[-3:-1]) + '.json'
+               # retrieve .json file with links to files
+               request = urllib2.Request(file_url)
+               try:
+                       self.report_download_json(file_url)
+                       jsonData = urllib2.urlopen(request).read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: Unable to retrieve file: %s' % str(err))
+                       return
+
+               # parse JSON
+               json_data = json.loads(jsonData)
+               player_url = json_data['player_swf_url']
+               formats = dict(json_data['audio_formats'])
+
+               req_format = self._downloader.params.get('format', None)
+               bitrate = None
+
+               if self._downloader.params.get('listformats', None):
+                       self._print_formats(formats)
+                       return
+
+               if req_format is None or req_format == 'best':
+                       for format_param in formats.keys():
+                               url_list = self.get_urls(formats, format_param)
+                               # check urls
+                               file_url = self.check_urls(url_list)
+                               if file_url is not None:
+                                       break # got it!
+               else:
+                       if req_format not in formats.keys():
+                               self._downloader.trouble(u'ERROR: format is not available')
+                               return
+
+                       url_list = self.get_urls(formats, req_format)
+                       file_url = self.check_urls(url_list)
+                       format_param = req_format
+
+               # We have audio
+               self._downloader.increment_downloads()
+               try:
+                       # Process file information
+                       self._downloader.process_info({
+                               'id':           file_id.decode('utf-8'),
+                               'url':          file_url.decode('utf-8'),
+                               'uploader':     uploader.decode('utf-8'),
+                               'upload_date':  u'NA',
+                               'title':        json_data['name'],
+                               'stitle':       _simplify_title(json_data['name']),
+                               'ext':          file_url.split('.')[-1].decode('utf-8'),
+                               'format':       (format_param is None and u'NA' or format_param.decode('utf-8')),
+                               'thumbnail':    json_data['thumbnail_url'],
+                               'description':  json_data['description'],
+                               'player_url':   player_url.decode('utf-8'),
+                       })
+               except UnavailableVideoError, err:
+                       self._downloader.trouble(u'ERROR: unable to download file')
+
+
+
+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 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

                composed by InfoExtractors. The only difference is that this
                one has an extra field called "filepath" that points to the
                downloaded file.
                composed by InfoExtractors. The only difference is that this
                one has an extra field called "filepath" that points to the
                downloaded file.


@@ -2635,11 +3795,13 @@ class PostProcessor(object):
 
 class FFmpegExtractAudioPP(PostProcessor):
 
 
 class FFmpegExtractAudioPP(PostProcessor):
 

-       def __init__(self, downloader=None, preferredcodec=None):
+       def __init__(self, downloader=None, preferredcodec=None, preferredquality=None, keepvideo=False):

                PostProcessor.__init__(self, downloader)
                if preferredcodec is None:
                        preferredcodec = 'best'
                self._preferredcodec = preferredcodec
                PostProcessor.__init__(self, downloader)
                if preferredcodec is None:
                        preferredcodec = 'best'
                self._preferredcodec = preferredcodec

+               self._preferredquality = preferredquality
+               self._keepvideo = keepvideo

 
        @staticmethod
        def get_audio_codec(path):
 
        @staticmethod
        def get_audio_codec(path):


@@ -2678,24 +3840,32 @@ class FFmpegExtractAudioPP(PostProcessor):
 
                more_opts = []
                if self._preferredcodec == 'best' or self._preferredcodec == filecodec:
 
                more_opts = []
                if self._preferredcodec == 'best' or self._preferredcodec == filecodec:

-                       if filecodec == 'aac' or filecodec == 'mp3':
+                       if filecodec in ['aac', 'mp3', 'vorbis']:

                                # Lossless if possible
                                acodec = 'copy'
                                extension = filecodec
                                if filecodec == 'aac':
                                        more_opts = ['-f', 'adts']
                                # Lossless if possible
                                acodec = 'copy'
                                extension = filecodec
                                if filecodec == 'aac':
                                        more_opts = ['-f', 'adts']

+                               if filecodec == 'vorbis':
+                                       extension = 'ogg'

                        else:
                                # MP3 otherwise.
                                acodec = 'libmp3lame'
                                extension = 'mp3'
                        else:
                                # MP3 otherwise.
                                acodec = 'libmp3lame'
                                extension = 'mp3'

-                               more_opts = ['-ab', '128k']
+                               more_opts = []
+                               if self._preferredquality is not None:
+                                       more_opts += ['-ab', self._preferredquality]

                else:
                        # We convert the audio (lossy)
                else:
                        # We convert the audio (lossy)

-                       acodec = {'mp3': 'libmp3lame', 'aac': 'aac'}[self._preferredcodec]
+                       acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'vorbis': 'libvorbis'}[self._preferredcodec]

                        extension = self._preferredcodec
                        extension = self._preferredcodec

-                       more_opts = ['-ab', '128k']
+                       more_opts = []
+                       if self._preferredquality is not None:
+                               more_opts += ['-ab', self._preferredquality]

                        if self._preferredcodec == 'aac':
                                more_opts += ['-f', 'adts']
                        if self._preferredcodec == 'aac':
                                more_opts += ['-f', 'adts']

+                       if self._preferredcodec == 'vorbis':
+                               extension = 'ogg'

 
                (prefix, ext) = os.path.splitext(path)
                new_path = prefix + '.' + extension
 
                (prefix, ext) = os.path.splitext(path)
                new_path = prefix + '.' + extension


@@ -2706,320 +3876,472 @@ class FFmpegExtractAudioPP(PostProcessor):
                        self._downloader.to_stderr(u'WARNING: error running ffmpeg')
                        return None
 
                        self._downloader.to_stderr(u'WARNING: error running ffmpeg')
                        return None
 

-               try:
-                       os.remove(path)
-               except (IOError, OSError):
-                       self._downloader.to_stderr(u'WARNING: Unable to remove downloaded video file')
-                       return None
+               # Try to update the date time for extracted audio file.
+               if information.get('filetime') is not None:
+                       try:
+                               os.utime(new_path, (time.time(), information['filetime']))
+                       except:
+                               self._downloader.to_stderr(u'WARNING: Cannot update utime of audio file')
+
+               if not self._keepvideo:
+                       try:
+                               os.remove(path)
+                       except (IOError, OSError):
+                               self._downloader.to_stderr(u'WARNING: Unable to remove downloaded video file')
+                               return None

 
                information['filepath'] = new_path
                return information
 
 
                information['filepath'] = new_path
                return information
 

-### MAIN PROGRAM ###
-if __name__ == '__main__':
+
+def updateSelf(downloader, filename):
+       ''' Update the program file with the latest version from the repository '''
+       # Note: downloader only used for options
+       if not os.access(filename, os.W_OK):
+               sys.exit('ERROR: no write permissions on %s' % filename)
+
+       downloader.to_screen('Updating to latest version...')
+

        try:
        try:

-               # Modules needed only when running the main program
-               import getpass
-               import optparse
+               try:
+                       urlh = urllib.urlopen(UPDATE_URL)
+                       newcontent = urlh.read()
+                       
+                       vmatch = re.search("__version__ = '([^']+)'", newcontent)
+                       if vmatch is not None and vmatch.group(1) == __version__:
+                               downloader.to_screen('youtube-dl is up-to-date (' + __version__ + ')')
+                               return
+               finally:
+                       urlh.close()
+       except (IOError, OSError), err:
+               sys.exit('ERROR: unable to download latest version')

 
 

-               # Function to update the program file with the latest version from the repository.
-               def update_self(downloader, filename):
-                       # Note: downloader only used for options
-                       if not os.access(filename, os.W_OK):
-                               sys.exit('ERROR: no write permissions on %s' % filename)
+       try:
+               outf = open(filename, 'wb')
+               try:
+                       outf.write(newcontent)
+               finally:
+                       outf.close()
+       except (IOError, OSError), err:
+               sys.exit('ERROR: unable to overwrite current version')

 
 

-                       downloader.to_screen('Updating to latest stable version...')
-                       try:
-                               latest_url = 'http://github.com/rg3/youtube-dl/raw/master/LATEST_VERSION'
-                               latest_version = urllib.urlopen(latest_url).read().strip()
-                               prog_url = 'http://github.com/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version
-                               newcontent = urllib.urlopen(prog_url).read()
-                       except (IOError, OSError), err:
-                               sys.exit('ERROR: unable to download latest version')
-                       try:
-                               stream = open(filename, 'w')
-                               stream.write(newcontent)
-                               stream.close()
-                       except (IOError, OSError), err:
-                               sys.exit('ERROR: unable to overwrite current version')
-                       downloader.to_screen('Updated to version %s' % latest_version)
-
-               # Parse command line
-               parser = optparse.OptionParser(
-                       usage='Usage: %prog [options] url...',
-                       version='2011.08.04',
-                       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', '--update',
-                               action='store_true', dest='update_self', help='update this program to latest stable version')
-               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='LIMIT', help='download rate limit (e.g. 50k or 44.6m)')
-               parser.add_option('-R', '--retries',
-                               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)
-               parser.add_option('--dump-user-agent',
-                               action='store_true', dest='dump_user_agent',
-                               help='display the current browser identification', default=False)
-
-               authentication = optparse.OptionGroup(parser, 'Authentication Options')
-               authentication.add_option('-u', '--username',
-                               dest='username', metavar='USERNAME', help='account username')
-               authentication.add_option('-p', '--password',
-                               dest='password', metavar='PASSWORD', help='account password')
-               authentication.add_option('-n', '--netrc',
-                               action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
-               parser.add_option_group(authentication)
-
-               video_format = optparse.OptionGroup(parser, 'Video Format Options')
-               video_format.add_option('-f', '--format',
-                               action='store', dest='format', metavar='FORMAT', help='video format code')
-               video_format.add_option('--all-formats',
-                               action='store_const', dest='format', help='download all available video formats', const='-1')
-               video_format.add_option('--max-quality',
-                               action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
-               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('--get-thumbnail',
-                               action='store_true', dest='getthumbnail',
-                               help='simulate, quiet but print thumbnail URL', default=False)
-               verbosity.add_option('--get-description',
-                               action='store_true', dest='getdescription',
-                               help='simulate, quiet but print video description', default=False)
-               verbosity.add_option('--get-filename',
-                               action='store_true', dest='getfilename',
-                               help='simulate, quiet but print output filename', default=False)
-               verbosity.add_option('--no-progress',
-                               action='store_true', dest='noprogress', help='do not print progress bar', default=False)
-               verbosity.add_option('--console-title',
-                               action='store_true', dest='consoletitle',
-                               help='display progress in console titlebar', default=False)
-               parser.add_option_group(verbosity)
-
-               filesystem = optparse.OptionGroup(parser, 'Filesystem Options')
-               filesystem.add_option('-t', '--title',
-                               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',
-                               dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
-               filesystem.add_option('-w', '--no-overwrites',
-                               action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
-               filesystem.add_option('-c', '--continue',
-                               action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False)
-               filesystem.add_option('--cookies',
-                               dest='cookiefile', metavar='FILE', help='file to dump cookie jar to')
-               filesystem.add_option('--no-part',
-                               action='store_true', dest='nopart', help='do not use .part files', default=False)
-               filesystem.add_option('--no-mtime',
-                               action='store_false', dest='updatetime',
-                               help='do not use the Last-modified header to set the file modification time', default=True)
-               parser.add_option_group(filesystem)
-
-               postproc = optparse.OptionGroup(parser, 'Post-processing Options')
-               postproc.add_option('--extract-audio', action='store_true', dest='extractaudio', default=False,
-                               help='convert video files to audio-only files (requires ffmpeg and ffprobe)')
-               postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best',
-                               help='"best", "aac" or "mp3"; best by default')
-               parser.add_option_group(postproc)
-
-               (opts, args) = parser.parse_args()
-
-               # Open appropriate CookieJar
-               if opts.cookiefile is None:
-                       jar = cookielib.CookieJar()
-               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')
+       downloader.to_screen('Updated youtube-dl. Restart youtube-dl to use the new version.')

 
 

-               # Dump user agent
-               if opts.dump_user_agent:
-                       print std_headers['User-Agent']
-                       sys.exit(0)
+def parseOpts():
+       # Deferred imports
+       import getpass
+       import optparse
+       import shlex

 
 

-               # General configuration
-               cookie_processor = urllib2.HTTPCookieProcessor(jar)
-               urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler(), cookie_processor, YoutubeDLHandler()))
-               socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
+       def _readOptions(filename):
+               try:
+                       optionf = open(filename)
+               except IOError:
+                       return [] # silently skip if file is not present
+               try:
+                       res = []
+                       for l in optionf:
+                               res += shlex.split(l, comments=True)
+               finally:
+                       optionf.close()
+               return res
+
+       def _format_option_string(option):
+               ''' ('-o', '--option') -> -o, --format METAVAR'''
+
+               opts = []
+
+               if option._short_opts: opts.append(option._short_opts[0])
+               if option._long_opts: opts.append(option._long_opts[0])
+               if len(opts) > 1: opts.insert(1, ', ')
+
+               if option.takes_value(): opts.append(' %s' % option.metavar)
+
+               return "".join(opts)
+
+       def _find_term_columns():
+               columns = os.environ.get('COLUMNS', None)
+               if columns:
+                       return int(columns)

 
 

-               # Batch file verification
-               batchurls = []
-               if opts.batchfile is not None:
-                       try:
-                               if opts.batchfile == '-':
-                                       batchfd = sys.stdin
-                               else:
-                                       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 and not re.search(r'^[#/;]', x)]
-                       except IOError:
-                               sys.exit(u'ERROR: batch file could not be read')
-               all_urls = batchurls + args
-
-               # Conflicting, missing and erroneous options
-               if opts.usenetrc and (opts.username is not None or opts.password is not None):
-                       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 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.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:
-                               parser.error(u'invalid rate limit specified')
-                       opts.ratelimit = numeric_limit
-               if opts.retries is not None:
-                       try:
-                               opts.retries = long(opts.retries)
-                       except (TypeError, ValueError), err:
-                               parser.error(u'invalid retry count specified')

                try:
                try:

-                       opts.playliststart = long(opts.playliststart)
-                       if opts.playliststart <= 0:
-                               raise ValueError
-               except (TypeError, ValueError), err:
-                       parser.error(u'invalid playlist start number specified')
+                       sp = subprocess.Popen(['stty', 'size'], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+                       out,err = sp.communicate()
+                       return int(out.split()[1])
+               except:
+                       pass
+               return None
+
+       max_width = 80
+       max_help_position = 80
+
+       # No need to wrap help messages if we're on a wide console
+       columns = _find_term_columns()
+       if columns: max_width = columns
+
+       fmt = optparse.IndentedHelpFormatter(width=max_width, max_help_position=max_help_position)
+       fmt.format_option_strings = _format_option_string
+
+       kw = {
+               'version'   : __version__,
+               'formatter' : fmt,
+               'usage' : '%prog [options] url [url...]',
+               'conflict_handler' : 'resolve',
+       }
+
+       parser = optparse.OptionParser(**kw)
+
+       # option groups
+       general        = optparse.OptionGroup(parser, 'General Options')
+       selection      = optparse.OptionGroup(parser, 'Video Selection')
+       authentication = optparse.OptionGroup(parser, 'Authentication Options')
+       video_format   = optparse.OptionGroup(parser, 'Video Format Options')
+       postproc       = optparse.OptionGroup(parser, 'Post-processing Options')
+       filesystem     = optparse.OptionGroup(parser, 'Filesystem Options')
+       verbosity      = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
+
+       general.add_option('-h', '--help',
+                       action='help', help='print this help text and exit')
+       general.add_option('-v', '--version',
+                       action='version', help='print program version and exit')
+       general.add_option('-U', '--update',
+                       action='store_true', dest='update_self', help='update this program to latest version')
+       general.add_option('-i', '--ignore-errors',
+                       action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
+       general.add_option('-r', '--rate-limit',
+                       dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)')
+       general.add_option('-R', '--retries',
+                       dest='retries', metavar='RETRIES', help='number of retries (default is 10)', default=10)
+       general.add_option('--dump-user-agent',
+                       action='store_true', dest='dump_user_agent',
+                       help='display the current browser identification', default=False)
+       general.add_option('--list-extractors',
+                       action='store_true', dest='list_extractors',
+                       help='List all supported extractors and the URLs they would handle', default=False)
+
+       selection.add_option('--playlist-start',
+                       dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1)
+       selection.add_option('--playlist-end',
+                       dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1)
+       selection.add_option('--match-title', dest='matchtitle', metavar='REGEX',help='download only matching titles (regex or caseless sub-string)')
+       selection.add_option('--reject-title', dest='rejecttitle', metavar='REGEX',help='skip download for matching titles (regex or caseless sub-string)')
+       selection.add_option('--max-downloads', metavar='NUMBER', dest='max_downloads', help='Abort after downloading NUMBER files', default=None)
+
+       authentication.add_option('-u', '--username',
+                       dest='username', metavar='USERNAME', help='account username')
+       authentication.add_option('-p', '--password',
+                       dest='password', metavar='PASSWORD', help='account password')
+       authentication.add_option('-n', '--netrc',
+                       action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
+
+
+       video_format.add_option('-f', '--format',
+                       action='store', dest='format', metavar='FORMAT', help='video format code')
+       video_format.add_option('--all-formats',
+                       action='store_const', dest='format', help='download all available video formats', const='all')
+       video_format.add_option('--max-quality',
+                       action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
+       video_format.add_option('-F', '--list-formats',
+                       action='store_true', dest='listformats', help='list all available formats (currently youtube only)')
+
+
+       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 the video and do not write anything to disk', default=False)
+       verbosity.add_option('--skip-download',
+                       action='store_true', dest='skip_download', help='do not download the 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('--get-thumbnail',
+                       action='store_true', dest='getthumbnail',
+                       help='simulate, quiet but print thumbnail URL', default=False)
+       verbosity.add_option('--get-description',
+                       action='store_true', dest='getdescription',
+                       help='simulate, quiet but print video description', default=False)
+       verbosity.add_option('--get-filename',
+                       action='store_true', dest='getfilename',
+                       help='simulate, quiet but print output filename', default=False)
+       verbosity.add_option('--get-format',
+                       action='store_true', dest='getformat',
+                       help='simulate, quiet but print output format', default=False)
+       verbosity.add_option('--no-progress',
+                       action='store_true', dest='noprogress', help='do not print progress bar', default=False)
+       verbosity.add_option('--console-title',
+                       action='store_true', dest='consoletitle',
+                       help='display progress in console titlebar', default=False)
+
+
+       filesystem.add_option('-t', '--title',
+                       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. Use %(stitle)s to get the title, %(uploader)s for the uploader name, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(upload_date)s for the upload date (YYYYMMDD), and %% for a literal percent. Use - to output to stdout.')
+       filesystem.add_option('-a', '--batch-file',
+                       dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
+       filesystem.add_option('-w', '--no-overwrites',
+                       action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
+       filesystem.add_option('-c', '--continue',
+                       action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False)
+       filesystem.add_option('--no-continue',
+                       action='store_false', dest='continue_dl',
+                       help='do not resume partially downloaded files (restart from beginning)')
+       filesystem.add_option('--cookies',
+                       dest='cookiefile', metavar='FILE', help='file to read cookies from and dump cookie jar in')
+       filesystem.add_option('--no-part',
+                       action='store_true', dest='nopart', help='do not use .part files', default=False)
+       filesystem.add_option('--no-mtime',
+                       action='store_false', dest='updatetime',
+                       help='do not use the Last-modified header to set the file modification time', default=True)
+       filesystem.add_option('--write-description',
+                       action='store_true', dest='writedescription',
+                       help='write video description to a .description file', default=False)
+       filesystem.add_option('--write-info-json',
+                       action='store_true', dest='writeinfojson',
+                       help='write video metadata to a .info.json file', default=False)
+
+
+       postproc.add_option('--extract-audio', action='store_true', dest='extractaudio', default=False,
+                       help='convert video files to audio-only files (requires ffmpeg and ffprobe)')
+       postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best',
+                       help='"best", "aac", "vorbis" or "mp3"; best by default')
+       postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='128K',
+                       help='ffmpeg audio bitrate specification, 128k by default')
+       postproc.add_option('-k', '--keep-video', action='store_true', dest='keepvideo', default=False,
+                       help='keeps the video file on disk after the post-processing; the video is erased by default')
+
+
+       parser.add_option_group(general)
+       parser.add_option_group(selection)
+       parser.add_option_group(filesystem)
+       parser.add_option_group(verbosity)
+       parser.add_option_group(video_format)
+       parser.add_option_group(authentication)
+       parser.add_option_group(postproc)
+
+       xdg_config_home = os.environ.get('XDG_CONFIG_HOME')
+       if xdg_config_home:
+               userConf = os.path.join(xdg_config_home, 'youtube-dl.conf')
+       else:
+               userConf = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf')
+       argv = _readOptions('/etc/youtube-dl.conf') + _readOptions(userConf) + sys.argv[1:]
+       opts, args = parser.parse_args(argv)
+
+       return parser, opts, args
+
+def gen_extractors():
+       """ Return a list of an instance of every supported extractor.
+       The order does matter; the first extractor matched is the one handling the URL.
+       """
+       youtube_ie = YoutubeIE()
+       google_ie = GoogleIE()
+       yahoo_ie = YahooIE()
+       return [
+               YoutubePlaylistIE(youtube_ie),
+               YoutubeUserIE(youtube_ie),
+               YoutubeSearchIE(youtube_ie),
+               youtube_ie,
+               MetacafeIE(youtube_ie),
+               DailymotionIE(),
+               google_ie,
+               GoogleSearchIE(google_ie),
+               PhotobucketIE(),
+               yahoo_ie,
+               YahooSearchIE(yahoo_ie),
+               DepositFilesIE(),
+               FacebookIE(),
+               BlipTVIE(),
+               VimeoIE(),
+               MyVideoIE(),
+               ComedyCentralIE(),
+               EscapistIE(),
+               CollegeHumorIE(),
+               XVideosIE(),
+               SoundcloudIE(),
+               InfoQIE(),
+               MixcloudIE(),
+
+               GenericIE()
+       ]
+
+def _real_main():
+       parser, opts, args = parseOpts()
+
+       # Open appropriate CookieJar
+       if opts.cookiefile is None:
+               jar = cookielib.CookieJar()
+       else:

                try:
                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')
-               if opts.extractaudio:
-                       if opts.audioformat not in ['best', 'aac', 'mp3']:
-                               parser.error(u'invalid audio format specified')
-
-               # Information extractors
-               youtube_ie = YoutubeIE()
-               metacafe_ie = MetacafeIE(youtube_ie)
-               dailymotion_ie = DailymotionIE()
-               youtube_pl_ie = YoutubePlaylistIE(youtube_ie)
-               youtube_user_ie = YoutubeUserIE(youtube_ie)
-               youtube_search_ie = YoutubeSearchIE(youtube_ie)
-               google_ie = GoogleIE()
-               google_search_ie = GoogleSearchIE(google_ie)
-               photobucket_ie = PhotobucketIE()
-               yahoo_ie = YahooIE()
-               yahoo_search_ie = YahooSearchIE(yahoo_ie)
-               deposit_files_ie = DepositFilesIE()
-               facebook_ie = FacebookIE()
-               generic_ie = GenericIE()
-
-               # File downloader
-               fd = FileDownloader({
-                       'usenetrc': opts.usenetrc,
-                       'username': opts.username,
-                       'password': opts.password,
-                       'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename),
-                       'forceurl': opts.geturl,
-                       'forcetitle': opts.gettitle,
-                       'forcethumbnail': opts.getthumbnail,
-                       'forcedescription': opts.getdescription,
-                       'forcefilename': opts.getfilename,
-                       'simulate': (opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename),
-                       'format': opts.format,
-                       'format_limit': opts.format_limit,
-                       'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding()))
-                               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,
-                       'nooverwrites': opts.nooverwrites,
-                       'retries': opts.retries,
-                       'continuedl': opts.continue_dl,
-                       'noprogress': opts.noprogress,
-                       'playliststart': opts.playliststart,
-                       'playlistend': opts.playlistend,
-                       'logtostderr': opts.outtmpl == '-',
-                       'consoletitle': opts.consoletitle,
-                       'nopart': opts.nopart,
-                       'updatetime': opts.updatetime,
-                       })
-               fd.add_info_extractor(youtube_search_ie)
-               fd.add_info_extractor(youtube_pl_ie)
-               fd.add_info_extractor(youtube_user_ie)
-               fd.add_info_extractor(metacafe_ie)
-               fd.add_info_extractor(dailymotion_ie)
-               fd.add_info_extractor(youtube_ie)
-               fd.add_info_extractor(google_ie)
-               fd.add_info_extractor(google_search_ie)
-               fd.add_info_extractor(photobucket_ie)
-               fd.add_info_extractor(yahoo_ie)
-               fd.add_info_extractor(yahoo_search_ie)
-               fd.add_info_extractor(deposit_files_ie)
-               fd.add_info_extractor(facebook_ie)
-
-               # This must come last since it's the
-               # fallback if none of the others work
-               fd.add_info_extractor(generic_ie)
-
-               # PostProcessors
-               if opts.extractaudio:
-                       fd.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat))
-
-               # Update version
-               if opts.update_self:
-                       update_self(fd, sys.argv[0])
-
-               # Maybe do nothing
-               if len(all_urls) < 1:
-                       if not opts.update_self:
-                               parser.error(u'you must provide at least one URL')
+                       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')
+
+       # Dump user agent
+       if opts.dump_user_agent:
+               print std_headers['User-Agent']
+               sys.exit(0)
+
+       # Batch file verification
+       batchurls = []
+       if opts.batchfile is not None:
+               try:
+                       if opts.batchfile == '-':
+                               batchfd = sys.stdin

                        else:
                        else:

-                               sys.exit()
-               retcode = fd.download(all_urls)
+                               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 and not re.search(r'^[#/;]', x)]
+               except IOError:
+                       sys.exit(u'ERROR: batch file could not be read')
+       all_urls = batchurls + args
+
+       # General configuration
+       cookie_processor = urllib2.HTTPCookieProcessor(jar)
+       opener = urllib2.build_opener(urllib2.ProxyHandler(), cookie_processor, YoutubeDLHandler())
+       urllib2.install_opener(opener)
+       socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
+
+       extractors = gen_extractors()
+
+       if opts.list_extractors:
+               for ie in extractors:
+                       print(ie.IE_NAME)
+                       matchedUrls = filter(lambda url: ie.suitable(url), all_urls)
+                       all_urls = filter(lambda url: url not in matchedUrls, all_urls)
+                       for mu in matchedUrls:
+                               print(u'  ' + mu)
+               sys.exit(0)
+
+       # Conflicting, missing and erroneous options
+       if opts.usenetrc and (opts.username is not None or opts.password is not None):
+               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 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.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:
+                       parser.error(u'invalid rate limit specified')
+               opts.ratelimit = numeric_limit
+       if opts.retries is not None:
+               try:
+                       opts.retries = long(opts.retries)
+               except (TypeError, ValueError), err:
+                       parser.error(u'invalid retry count specified')
+       try:
+               opts.playliststart = int(opts.playliststart)
+               if opts.playliststart <= 0:
+                       raise ValueError(u'Playlist start must be positive')
+       except (TypeError, ValueError), err:
+               parser.error(u'invalid playlist start number specified')
+       try:
+               opts.playlistend = int(opts.playlistend)
+               if opts.playlistend != -1 and (opts.playlistend <= 0 or opts.playlistend < opts.playliststart):
+                       raise ValueError(u'Playlist end must be greater than playlist start')
+       except (TypeError, ValueError), err:
+               parser.error(u'invalid playlist end number specified')
+       if opts.extractaudio:
+               if opts.audioformat not in ['best', 'aac', 'mp3', 'vorbis']:
+                       parser.error(u'invalid audio format specified')
+
+       # File downloader
+       fd = FileDownloader({
+               'usenetrc': opts.usenetrc,
+               'username': opts.username,
+               'password': opts.password,
+               'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
+               'forceurl': opts.geturl,
+               'forcetitle': opts.gettitle,
+               'forcethumbnail': opts.getthumbnail,
+               'forcedescription': opts.getdescription,
+               'forcefilename': opts.getfilename,
+               'forceformat': opts.getformat,
+               'simulate': opts.simulate,
+               'skip_download': (opts.skip_download or opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
+               'format': opts.format,
+               'format_limit': opts.format_limit,
+               'listformats': opts.listformats,
+               'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding()))
+                       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,
+               'nooverwrites': opts.nooverwrites,
+               'retries': opts.retries,
+               'continuedl': opts.continue_dl,
+               'noprogress': opts.noprogress,
+               'playliststart': opts.playliststart,
+               'playlistend': opts.playlistend,
+               'logtostderr': opts.outtmpl == '-',
+               'consoletitle': opts.consoletitle,
+               'nopart': opts.nopart,
+               'updatetime': opts.updatetime,
+               'writedescription': opts.writedescription,
+               'writeinfojson': opts.writeinfojson,
+               'matchtitle': opts.matchtitle,
+               'rejecttitle': opts.rejecttitle,
+               'max_downloads': opts.max_downloads,
+               })
+       for extractor in extractors:
+               fd.add_info_extractor(extractor)
+
+       # PostProcessors
+       if opts.extractaudio:
+               fd.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, keepvideo=opts.keepvideo))
+
+       # Update version
+       if opts.update_self:
+               updateSelf(fd, sys.argv[0])
+
+       # Maybe do nothing
+       if len(all_urls) < 1:
+               if not opts.update_self:
+                       parser.error(u'you must provide at least one URL')
+               else:
+                       sys.exit()
+       retcode = fd.download(all_urls)

 
 

-               # Dump cookie jar if requested
-               if opts.cookiefile is not None:
-                       try:
-                               jar.save()
-                       except (IOError, OSError), err:
-                               sys.exit(u'ERROR: unable to save cookie jar')
+       # Dump cookie jar if requested
+       if opts.cookiefile is not None:
+               try:
+                       jar.save()
+               except (IOError, OSError), err:
+                       sys.exit(u'ERROR: unable to save cookie jar')

 
 

-               sys.exit(retcode)
+       sys.exit(retcode)

 
 

+def main():
+       try:
+               _real_main()

        except DownloadError:
                sys.exit(1)
        except SameFileError:
                sys.exit(u'ERROR: fixed output name but more than one file to download')
        except KeyboardInterrupt:
                sys.exit(u'\nERROR: Interrupted by user')
        except DownloadError:
                sys.exit(1)
        except SameFileError:
                sys.exit(u'ERROR: fixed output name but more than one file to download')
        except KeyboardInterrupt:
                sys.exit(u'\nERROR: Interrupted by user')

+
+if __name__ == '__main__':
+       main()
+
+# vim: set ts=4 sw=4 sts=4 noet ai si filetype=python: