report_extraction was never called for GenericIE

[youtube-dl] / youtube-dl

diff --git a/youtube-dl b/youtube-dl
index 1894317b0e667b8200d2680083fc397033ff111d..d0584a3126c6818e86ed96821e8bbabcfc2a9c7c 100755 (executable)
--- a/youtube-dl
+++ b/youtube-dl
@@ -1,7 +1,11 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 # Author: Ricardo Garcia Gonzalez
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 # Author: Ricardo Garcia Gonzalez

+# Author: Danny Colligan
+# Author: Benjamin Johnson

 # License: Public domain code
 # License: Public domain code

+import cookielib
+import datetime

 import htmlentitydefs
 import httplib
 import locale
 import htmlentitydefs
 import httplib
 import locale


@@ -12,20 +16,101 @@ import os.path
 import re
 import socket
 import string
 import re
 import socket
 import string

+import subprocess

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

-std_headers = {        
-       'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.1) Gecko/2008070208 Firefox/3.0.1',
+# 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
+
+std_headers = {
+       'User-Agent': 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.12) Gecko/20101028 Firefox/3.6.12',

        'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
        'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',

-       'Accept': 'text/xml,application/xml,application/xhtml+xml,text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5',
+       'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',

        'Accept-Language': 'en-us,en;q=0.5',
 }
 
 simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii')
 
        'Accept-Language': 'en-us,en;q=0.5',
 }
 
 simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii')
 

+def preferredencoding():
+       """Get preferred encoding.
+
+       Returns the best encoding scheme for the system, based on
+       locale.getpreferredencoding() and some further tweaks.
+       """
+       def yield_preferredencoding():
+               try:
+                       pref = locale.getpreferredencoding()
+                       u'TEST'.encode(pref)
+               except:
+                       pref = 'UTF-8'
+               while True:
+                       yield pref
+       return yield_preferredencoding().next()
+
+def htmlentity_transform(matchobj):
+       """Transforms an HTML entity to a Unicode character.
+       
+       This function receives a match object and is intended to be used with
+       the re.sub() function.
+       """
+       entity = matchobj.group(1)
+
+       # Known non-numeric HTML entity
+       if entity in htmlentitydefs.name2codepoint:
+               return unichr(htmlentitydefs.name2codepoint[entity])
+
+       # Unicode character
+       mobj = re.match(ur'(?u)#(x?\d+)', entity)
+       if mobj is not None:
+               numstr = mobj.group(1)
+               if numstr.startswith(u'x'):
+                       base = 16
+                       numstr = u'0%s' % numstr
+               else:
+                       base = 10
+               return unichr(long(numstr, base))
+
+       # Unknown entity in name, return its literal representation
+       return (u'&%s;' % entity)
+
+def sanitize_title(utitle):
+       """Sanitizes a video title so it could be used as part of a filename."""
+       utitle = re.sub(ur'(?u)&(.+?);', htmlentity_transform, utitle)
+       return utitle.replace(unicode(os.sep), u'%')
+
+def sanitize_open(filename, open_mode):
+       """Try to open the given filename, and slightly tweak it if this fails.
+
+       Attempts to open the given filename. If this fails, it tries to change
+       the filename slightly, step by step, until it's either able to open it
+       or it fails and raises a final exception, like the standard open()
+       function.
+
+       It returns the tuple (stream, definitive_file_name).
+       """
+       try:
+               if filename == u'-':
+                       if sys.platform == 'win32':
+                               import msvcrt
+                               msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
+                       return (sys.stdout, filename)
+               stream = open(filename, open_mode)
+               return (stream, filename)
+       except (IOError, OSError), err:
+               # In case of error, try to remove win32 forbidden chars
+               filename = re.sub(ur'[/<>:"\|\?\*]', u'#', filename)
+
+               # An exception here should be caught in the caller
+               stream = open(filename, open_mode)
+               return (stream, filename)
+
+

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


@@ -51,6 +136,29 @@ class PostProcessingError(Exception):
        """
        pass
 
        """
        pass
 

+class UnavailableVideoError(Exception):
+       """Unavailable Format exception.
+
+       This exception will be thrown when a video is requested
+       in a format that is not available for that video.
+       """
+       pass
+
+class ContentTooShortError(Exception):
+       """Content Too Short exception.
+
+       This exception may be raised by FileDownloader objects when a file they
+       download is too small for what the server announced first, indicating
+       the connection was probably interrupted.
+       """
+       # Both in bytes
+       downloaded = None
+       expected = None
+
+       def __init__(self, downloaded, expected):
+               self.downloaded = downloaded
+               self.expected = expected
+

 class FileDownloader(object):
        """File Downloader class.
 
 class FileDownloader(object):
        """File Downloader class.
 


@@ -64,41 +172,58 @@ class FileDownloader(object):
        For this, file downloader objects have a method that allows
        InfoExtractors to be registered in a given order. When it is passed
        a URL, the file downloader handles it to the first InfoExtractor it
        For this, file downloader objects have a method that allows
        InfoExtractors to be registered in a given order. When it is passed
        a URL, the file downloader handles it to the first InfoExtractor it

-       finds that reports being able to handle it. The InfoExtractor returns
-       all the information to the FileDownloader and the latter downloads the
-       file or does whatever it's instructed to do.
+       finds that reports being able to handle it. The InfoExtractor extracts
+       all the information about the video or videos the URL refers to, and
+       asks the FileDownloader to process the video information, possibly
+       downloading the video.

 
        File downloaders accept a lot of parameters. In order not to saturate
        the object constructor with arguments, it receives a dictionary of
 
        File downloaders accept a lot of parameters. In order not to saturate
        the object constructor with arguments, it receives a dictionary of

-       options instead. These options are available through the get_params()
-       method for the InfoExtractors to use. The FileDownloader also registers
-       itself as the downloader in charge for the InfoExtractors that are
-       added to it, so this is a "mutual registration".
+       options instead. These options are available through the params
+       attribute for the InfoExtractors to use. The FileDownloader also
+       registers itself as the downloader in charge for the InfoExtractors
+       that are added to it, so this is a "mutual registration".

 
        Available options:
 
 
        Available options:
 

-       username:       Username for authentication purposes.
-       password:       Password for authentication purposes.
-       usenetrc:       Use netrc for authentication instead.
-       quiet:          Do not print messages to stdout.
-       forceurl:       Force printing final URL.
-       forcetitle:     Force printing title.
-       simulate:       Do not download the video files.
-       format:         Video format code.
-       outtmpl:        Template for output names.
-       ignoreerrors:   Do not stop on download errors.
-       ratelimit:      Download speed limit, in bytes/sec.
+       username:         Username for authentication purposes.
+       password:         Password for authentication purposes.
+       usenetrc:         Use netrc for authentication instead.
+       quiet:            Do not print messages to stdout.
+       forceurl:         Force printing final URL.
+       forcetitle:       Force printing title.
+       forcethumbnail:   Force printing thumbnail URL.
+       forcedescription: Force printing description.
+       simulate:         Do not download the video files.
+       format:           Video format code.
+       format_limit:     Highest quality format to try.
+       outtmpl:          Template for output names.
+       ignoreerrors:     Do not stop on download errors.
+       ratelimit:        Download speed limit, in bytes/sec.
+       nooverwrites:     Prevent overwriting files.
+       retries:          Number of times to retry for HTTP error 5xx
+       continuedl:       Try to continue downloads if possible.
+       noprogress:       Do not print the progress bar.
+       playliststart:    Playlist item to start at.
+       playlistend:      Playlist item to end at.
+       logtostderr:      Log messages to stderr instead of stdout.

        """
 
        """
 

-       _params = None
+       params = None

        _ies = []
        _pps = []
        _ies = []
        _pps = []

+       _download_retcode = None
+       _num_downloads = None
+       _screen_file = None

 
        def __init__(self, params):
                """Create a FileDownloader object with the given options."""
                self._ies = []
                self._pps = []
 
        def __init__(self, params):
                """Create a FileDownloader object with the given options."""
                self._ies = []
                self._pps = []

-               self.set_params(params)
+               self._download_retcode = 0
+               self._num_downloads = 0
+               self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
+               self.params = params

        
        @staticmethod
        def pmkdir(filename):
        
        @staticmethod
        def pmkdir(filename):


@@ -110,14 +235,21 @@ class FileDownloader(object):
                        if not os.path.exists(dir):
                                os.mkdir(dir)
        
                        if not os.path.exists(dir):
                                os.mkdir(dir)
        

+       @staticmethod
+       def temp_name(filename):
+               """Returns a temporary filename for the given filename."""
+               return filename + '.part'
+       

        @staticmethod
        def format_bytes(bytes):
                if bytes is None:
                        return 'N/A'
        @staticmethod
        def format_bytes(bytes):
                if bytes is None:
                        return 'N/A'

-               if bytes == 0:
+               if type(bytes) is str:
+                       bytes = float(bytes)
+               if bytes == 0.0:

                        exponent = 0
                else:
                        exponent = 0
                else:

-                       exponent = long(math.log(float(bytes), 1024.0))
+                       exponent = long(math.log(bytes, 1024.0))

                suffix = 'bkMGTPEZY'[exponent]
                converted = float(bytes) / float(1024**exponent)
                return '%.2f%s' % (converted, suffix)
                suffix = 'bkMGTPEZY'[exponent]
                converted = float(bytes) / float(1024**exponent)
                return '%.2f%s' % (converted, suffix)


@@ -142,7 +274,7 @@ class FileDownloader(object):
                        return '--:--'
                return '%02d:%02d' % (eta_mins, eta_secs)
 
                        return '--:--'
                return '%02d:%02d' % (eta_mins, eta_secs)
 

-       @staticmethod
+       @staticmethod

        def calc_speed(start, now, bytes):
                dif = now - start
                if bytes == 0 or dif < 0.001: # One millisecond
        def calc_speed(start, now, bytes):
                dif = now - start
                if bytes == 0 or dif < 0.001: # One millisecond


@@ -154,13 +286,13 @@ class FileDownloader(object):
                new_min = max(bytes / 2.0, 1.0)
                new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB
                if elapsed_time < 0.001:
                new_min = max(bytes / 2.0, 1.0)
                new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB
                if elapsed_time < 0.001:

-                       return int(new_max)
+                       return long(new_max)

                rate = bytes / elapsed_time
                if rate > new_max:
                rate = bytes / elapsed_time
                if rate > new_max:

-                       return int(new_max)
+                       return long(new_max)

                if rate < new_min:
                if rate < new_min:

-                       return int(new_min)
-               return int(rate)
+                       return long(new_min)
+               return long(rate)

 
        @staticmethod
        def parse_bytes(bytestr):
 
        @staticmethod
        def parse_bytes(bytestr):


@@ -172,16 +304,6 @@ class FileDownloader(object):
                multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
                return long(round(number * multiplier))
 
                multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
                return long(round(number * multiplier))
 

-       def set_params(self, params):
-               """Sets parameters."""
-               if type(params) != dict:
-                       raise ValueError('params: dictionary expected')
-               self._params = params
-       
-       def get_params(self):
-               """Get parameters."""
-               return self._params
-

        def add_info_extractor(self, ie):
                """Add an InfoExtractor object to the end of the list."""
                self._ies.append(ie)
        def add_info_extractor(self, ie):
                """Add an InfoExtractor object to the end of the list."""
                self._ies.append(ie)


@@ -192,38 +314,41 @@ class FileDownloader(object):
                self._pps.append(pp)
                pp.set_downloader(self)
        
                self._pps.append(pp)
                pp.set_downloader(self)
        

-       def to_stdout(self, message, skip_eol=False):
+       def to_screen(self, message, skip_eol=False, ignore_encoding_errors=False):

                """Print message to stdout if not in quiet mode."""
                """Print message to stdout if not in quiet mode."""

-               if not self._params.get('quiet', False):
-                       print u'%s%s' % (message, [u'\n', u''][skip_eol]),
-                       sys.stdout.flush()
+               try:
+                       if not self.params.get('quiet', False):
+                               terminator = [u'\n', u''][skip_eol]
+                               print >>self._screen_file, (u'%s%s' % (message, terminator)).encode(preferredencoding()),
+                       self._screen_file.flush()
+               except (UnicodeEncodeError), err:
+                       if not ignore_encoding_errors:
+                               raise

        
        def to_stderr(self, message):
                """Print message to stderr."""
        
        def to_stderr(self, message):
                """Print message to stderr."""

-               print >>sys.stderr, message
+               print >>sys.stderr, message.encode(preferredencoding())

        
        def fixed_template(self):
                """Checks if the output template is fixed."""
        
        def fixed_template(self):
                """Checks if the output template is fixed."""

-               return (re.search(ur'(?u)%\(.+?\)s', self._params['outtmpl']) is None)
+               return (re.search(ur'(?u)%\(.+?\)s', self.params['outtmpl']) is None)

 
        def trouble(self, message=None):
                """Determine action to take when a download problem appears.
 
                Depending on if the downloader has been configured to ignore
                download errors or not, this method may throw an exception or
 
        def trouble(self, message=None):
                """Determine action to take when a download problem appears.
 
                Depending on if the downloader has been configured to ignore
                download errors or not, this method may throw an exception or

-               not when errors are found, after printing the message. If it
-               doesn't raise, it returns an error code suitable to be returned
-               later as a program exit code to indicate error.
+               not when errors are found, after printing the message.

                """
                if message is not None:
                        self.to_stderr(message)
                """
                if message is not None:
                        self.to_stderr(message)

-               if not self._params.get('ignoreerrors', False):
+               if not self.params.get('ignoreerrors', False):

                        raise DownloadError(message)
                        raise DownloadError(message)

-               return 1
+               self._download_retcode = 1

 
        def slow_down(self, start_time, byte_counter):
                """Sleep if the download speed is over the rate limit."""
 
        def slow_down(self, start_time, byte_counter):
                """Sleep if the download speed is over the rate limit."""

-               rate_limit = self._params.get('ratelimit', None)
+               rate_limit = self.params.get('ratelimit', None)

                if rate_limit is None or byte_counter == 0:
                        return
                now = time.time()
                if rate_limit is None or byte_counter == 0:
                        return
                now = time.time()


@@ -233,88 +358,131 @@ class FileDownloader(object):
                speed = float(byte_counter) / elapsed
                if speed > rate_limit:
                        time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit)
                speed = float(byte_counter) / elapsed
                if speed > rate_limit:
                        time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit)

+       
+       def try_rename(self, old_filename, new_filename):
+               try:
+                       os.rename(old_filename, new_filename)
+               except (IOError, OSError), err:
+                       self.trouble(u'ERROR: unable to rename file')

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

-               self.to_stdout(u'[download] Destination: %s' % filename)
+               self.to_screen(u'[download] Destination: %s' % filename, ignore_encoding_errors=True)

        
        def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
                """Report download progress."""
        
        def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
                """Report download progress."""

-               self.to_stdout(u'\r[download] %s of %s at %s ETA %s' %
+               if self.params.get('noprogress', False):
+                       return
+               self.to_screen(u'\r[download] %s of %s at %s ETA %s' %

                                (percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
                                (percent_str, data_len_str, speed_str, eta_str), skip_eol=True)

+
+       def report_resuming_byte(self, resume_len):
+               """Report attempt to resume at given byte."""
+               self.to_screen(u'[download] Resuming download at byte %s' % resume_len)
+       
+       def report_retry(self, count, retries):
+               """Report retry in case of HTTP error 5xx"""
+               self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries))
+       
+       def report_file_already_downloaded(self, file_name):
+               """Report file has already been fully downloaded."""
+               try:
+                       self.to_screen(u'[download] %s has already been downloaded' % file_name)
+               except (UnicodeEncodeError), err:
+                       self.to_screen(u'[download] The file has already been downloaded')
+       
+       def report_unable_to_resume(self):
+               """Report it was impossible to resume download."""
+               self.to_screen(u'[download] Unable to resume')

        
        def report_finish(self):
                """Report download finished."""
        
        def report_finish(self):
                """Report download finished."""

-               self.to_stdout(u'')
+               if self.params.get('noprogress', False):
+                       self.to_screen(u'[download] Download completed')
+               else:
+                       self.to_screen(u'')
+       
+       def increment_downloads(self):
+               """Increment the ordinal that assigns a number to each file."""
+               self._num_downloads += 1
+
+       def process_info(self, info_dict):
+               """Process a single dictionary returned by an InfoExtractor."""
+               # 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')
+
+                       return
+                       
+               try:
+                       template_dict = dict(info_dict)
+                       template_dict['epoch'] = unicode(long(time.time()))
+                       template_dict['autonumber'] = unicode('%05d' % self._num_downloads)
+                       filename = self.params['outtmpl'] % template_dict
+               except (ValueError, KeyError), err:
+                       self.trouble(u'ERROR: invalid system charset or erroneous output template')
+                       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:
+                       self.pmkdir(filename)
+               except (OSError, IOError), err:
+                       self.trouble(u'ERROR: unable to create directories: %s' % str(err))
+                       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 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."""

-               retcode = 0

                if len(url_list) > 1 and self.fixed_template():
                if len(url_list) > 1 and self.fixed_template():

-                       raise SameFileError(self._params['outtmpl'])
+                       raise SameFileError(self.params['outtmpl'])

 
                for url in url_list:
                        suitable_found = False
                        for ie in self._ies:
 
                for url in url_list:
                        suitable_found = False
                        for ie in self._ies:

+                               # Go to next InfoExtractor if not suitable

                                if not ie.suitable(url):
                                        continue
                                if not ie.suitable(url):
                                        continue

+

                                # Suitable InfoExtractor found
                                suitable_found = True
                                # Suitable InfoExtractor found
                                suitable_found = True

-                               all_results = ie.extract(url)
-                               results = [x for x in all_results if x is not None]
-                               if len(results) != len(all_results):
-                                       retcode = self.trouble()
-
-                               if len(results) > 1 and self.fixed_template():
-                                       raise SameFileError(self._params['outtmpl'])
-
-                               for result in results:
-                                       # Forced printings
-                                       if self._params.get('forcetitle', False):
-                                               print result['title']
-                                       if self._params.get('forceurl', False):
-                                               print result['url']
-                                               
-                                       # Do nothing else if in simulate mode
-                                       if self._params.get('simulate', False):
-                                               continue

 
 

-                                       try:
-                                               filename = self._params['outtmpl'] % result
-                                               self.report_destination(filename)
-                                       except (ValueError, KeyError), err:
-                                               retcode = self.trouble('ERROR: invalid output template or system charset: %s' % str(err))
-                                               continue
-                                       try:
-                                               self.pmkdir(filename)
-                                       except (OSError, IOError), err:
-                                               retcode = self.trouble('ERROR: unable to create directories: %s' % str(err))
-                                               continue
-                                       try:
-                                               outstream = open(filename, 'wb')
-                                       except (OSError, IOError), err:
-                                               retcode = self.trouble('ERROR: unable to open for writing: %s' % str(err))
-                                               continue
-                                       try:
-                                               self._do_download(outstream, result['url'])
-                                               outstream.close()
-                                       except (OSError, IOError), err:
-                                               retcode = self.trouble('ERROR: unable to write video data: %s' % str(err))
-                                               continue
-                                       except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-                                               retcode = self.trouble('ERROR: unable to download video data: %s' % str(err))
-                                               continue
-                                       try:
-                                               self.post_process(filename, result)
-                                       except (PostProcessingError), err:
-                                               retcode = self.trouble('ERROR: postprocessing: %s' % str(err))
-                                               continue
+                               # Extract information from URL and process it
+                               ie.extract(url)

 
 

+                               # Suitable InfoExtractor had been found; go to next URL

                                break
                                break

+

                        if not suitable_found:
                        if not suitable_found:

-                               retcode = self.trouble('ERROR: no suitable InfoExtractor: %s' % url)
+                               self.trouble(u'ERROR: no suitable InfoExtractor: %s' % url)

 
 

-               return retcode
+               return self._download_retcode

 
        def post_process(self, filename, ie_info):
                """Run the postprocessing chain on the given file."""
 
        def post_process(self, filename, ie_info):
                """Run the postprocessing chain on the given file."""


@@ -325,21 +493,120 @@ class FileDownloader(object):
                        if info is None:
                                break
        
                        if info is None:
                                break
        

-       def _do_download(self, stream, url):
+       def _download_with_rtmpdump(self, filename, url, player_url):
+               self.report_destination(filename)
+               tmpfilename = self.temp_name(filename)
+
+               # Check for rtmpdump first
+               try:
+                       subprocess.call(['rtmpdump', '-h'], stdout=(file(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
+               except (OSError, IOError):
+                       self.trouble(u'ERROR: RTMP download detected but "rtmpdump" could not be run')
+                       return False
+
+               # Download using rtmpdump. rtmpdump returns exit code 2 when
+               # the connection was interrumpted and resuming appears to be
+               # possible. This is part of rtmpdump's normal usage, AFAIK.
+               basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', tmpfilename]
+               retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)])
+               while retval == 2 or retval == 1:
+                       prevsize = os.path.getsize(tmpfilename)
+                       self.to_screen(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True)
+                       time.sleep(5.0) # This seems to be needed
+                       retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])
+                       cursize = os.path.getsize(tmpfilename)
+                       if prevsize == cursize and retval == 1:
+                               break
+               if retval == 0:
+                       self.to_screen(u'\r[rtmpdump] %s bytes' % os.path.getsize(tmpfilename))
+                       self.try_rename(tmpfilename, filename)
+                       return True
+               else:
+                       self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval)
+                       return False
+
+       def _do_download(self, filename, url, player_url):
+               # Check file already present
+               if self.params.get('continuedl', False) and os.path.isfile(filename):
+                       self.report_file_already_downloaded(filename)
+                       return True
+
+               # Attempt to download using rtmpdump
+               if url.startswith('rtmp'):
+                       return self._download_with_rtmpdump(filename, url, player_url)
+
+               tmpfilename = self.temp_name(filename)
+               stream = None
+               open_mode = 'wb'
+               basic_request = urllib2.Request(url, None, std_headers)

                request = urllib2.Request(url, None, std_headers)
                request = urllib2.Request(url, None, std_headers)

-               data = urllib2.urlopen(request)
+
+               # Establish possible resume length
+               if os.path.isfile(tmpfilename):
+                       resume_len = os.path.getsize(tmpfilename)
+               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'
+
+               count = 0
+               retries = self.params.get('retries', 0)
+               while count <= retries:
+                       # Establish connection
+                       try:
+                               data = urllib2.urlopen(request)
+                               break
+                       except (urllib2.HTTPError, ), err:
+                               if (err.code < 500 or err.code >= 600) and err.code != 416:
+                                       # Unexpected HTTP error
+                                       raise
+                               elif err.code == 416:
+                                       # Unable to resume (requested range not satisfiable)
+                                       try:
+                                               # Open the connection again without the range header
+                                               data = urllib2.urlopen(basic_request)
+                                               content_length = data.info()['Content-Length']
+                                       except (urllib2.HTTPError, ), err:
+                                               if err.code < 500 or err.code >= 600:
+                                                       raise
+                                       else:
+                                               # Examine the reported length
+                                               if (content_length is not None and
+                                                   (resume_len - 100 < long(content_length) < resume_len + 100)):
+                                                       # The file had already been fully downloaded.
+                                                       # Explanation to the above condition: in issue #175 it was revealed that
+                                                       # YouTube sometimes adds or removes a few bytes from the end of the file,
+                                                       # changing the file size slightly and causing problems for some users. So
+                                                       # I decided to implement a suggested change and consider the file
+                                                       # completely downloaded if the file size differs less than 100 bytes from
+                                                       # the one in the hard drive.
+                                                       self.report_file_already_downloaded(filename)
+                                                       self.try_rename(tmpfilename, filename)
+                                                       return True
+                                               else:
+                                                       # The length does not match, we start the download over
+                                                       self.report_unable_to_resume()
+                                                       open_mode = 'wb'
+                                                       break
+                       # Retry
+                       count += 1
+                       if count <= retries:
+                               self.report_retry(count, retries)
+
+               if count > retries:
+                       self.trouble(u'ERROR: giving up after %s retries' % retries)
+                       return False
+

                data_len = data.info().get('Content-length', None)
                data_len_str = self.format_bytes(data_len)
                byte_counter = 0
                block_size = 1024
                start = time.time()
                while True:
                data_len = data.info().get('Content-length', None)
                data_len_str = self.format_bytes(data_len)
                byte_counter = 0
                block_size = 1024
                start = time.time()
                while True:

-                       # Progress message
-                       percent_str = self.calc_percent(byte_counter, data_len)
-                       eta_str = self.calc_eta(start, time.time(), data_len, byte_counter)
-                       speed_str = self.calc_speed(start, time.time(), byte_counter)
-                       self.report_progress(percent_str, data_len_str, speed_str, eta_str)
-

                        # Download and write
                        before = time.time()
                        data_block = data.read(block_size)
                        # Download and write
                        before = time.time()
                        data_block = data.read(block_size)


@@ -348,15 +615,36 @@ class FileDownloader(object):
                        if data_block_len == 0:
                                break
                        byte_counter += data_block_len
                        if data_block_len == 0:
                                break
                        byte_counter += data_block_len

-                       stream.write(data_block)
+
+                       # Open file just in time
+                       if stream is None:
+                               try:
+                                       (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode)
+                                       self.report_destination(filename)
+                               except (OSError, IOError), err:
+                                       self.trouble(u'ERROR: unable to open for writing: %s' % str(err))
+                                       return False
+                       try:
+                               stream.write(data_block)
+                       except (IOError, OSError), err:
+                               self.trouble(u'\nERROR: unable to write data: %s' % str(err))
+                               return False

                        block_size = self.best_block_size(after - before, data_block_len)
 
                        block_size = self.best_block_size(after - before, data_block_len)
 

+                       # Progress message
+                       percent_str = self.calc_percent(byte_counter, data_len)
+                       eta_str = self.calc_eta(start, time.time(), data_len, byte_counter)
+                       speed_str = self.calc_speed(start, time.time(), byte_counter)
+                       self.report_progress(percent_str, data_len_str, speed_str, eta_str)
+

                        # Apply rate limit
                        self.slow_down(start, byte_counter)
 
                self.report_finish()
                if data_len is not None and str(byte_counter) != data_len:
                        # Apply rate limit
                        self.slow_down(start, byte_counter)
 
                self.report_finish()
                if data_len is not None and str(byte_counter) != data_len:

-                       raise ValueError('Content too short: %s/%s bytes' % (byte_counter, data_len))
+                       raise ContentTooShortError(byte_counter, long(data_len))
+               self.try_rename(tmpfilename, filename)
+               return True

 
 class InfoExtractor(object):
        """Information Extractor class.
 
 class InfoExtractor(object):
        """Information Extractor class.


@@ -364,9 +652,10 @@ class InfoExtractor(object):
        Information extractors are the classes that, given a URL, extract
        information from the video (or videos) the URL refers to. This
        information includes the real video URL, the video title and simplified
        Information extractors are the classes that, given a URL, extract
        information from the video (or videos) the URL refers to. This
        information includes the real video URL, the video title and simplified

-       title, author and others. It is returned in a list of dictionaries when
-       calling its extract() method. It is a list because a URL can refer to
-       more than one video (think of playlists). The dictionaries must include
+       title, author and others. The information is stored in a dictionary
+       which is then passed to the FileDownloader. The FileDownloader
+       processes this information possibly downloading the video to the file
+       system, among other possible outcomes. The dictionaries must include

        the following fields:
 
        id:             Video identifier.
        the following fields:
 
        id:             Video identifier.


@@ -375,6 +664,16 @@ class InfoExtractor(object):
        title:          Literal title.
        stitle:         Simplified title.
        ext:            Video filename extension.
        title:          Literal title.
        stitle:         Simplified title.
        ext:            Video filename extension.

+       format:         Video format.
+       player_url:     SWF Player URL (may be None).
+
+       The following fields are optional. Their primary purpose is to allow
+       youtube-dl to serve as the backend for a video search function, such
+       as the one in youtube2mp3.  They are only used when their respective
+       forced printing functions are called:
+
+       thumbnail:      Full URL to a video thumbnail image.
+       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.
 
        Subclasses of this one should re-define the _real_initialize() and
        _real_extract() methods, as well as the suitable() static method.


@@ -410,15 +709,6 @@ class InfoExtractor(object):
                """Sets the downloader for this IE."""
                self._downloader = downloader
        
                """Sets the downloader for this IE."""
                self._downloader = downloader
        

-       def to_stdout(self, message):
-               """Print message to stdout if downloader is not in quiet mode."""
-               if self._downloader is None or not self._downloader.get_params().get('quiet', False):
-                       print message
-       
-       def to_stderr(self, message):
-               """Print message to stderr."""
-               print >>sys.stderr, message
-

        def _real_initialize(self):
                """Real initialization process. Redefine in subclasses."""
                pass
        def _real_initialize(self):
                """Real initialization process. Redefine in subclasses."""
                pass


@@ -430,11 +720,23 @@ class InfoExtractor(object):
 class YoutubeIE(InfoExtractor):
        """Information extractor for youtube.com."""
 
 class YoutubeIE(InfoExtractor):
        """Information extractor for youtube.com."""
 

-       _VALID_URL = r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:\.php)?)?\?(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$'
-       _LANG_URL = r'http://uk.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
-       _LOGIN_URL = 'http://www.youtube.com/signup?next=/&gl=US&hl=en'
+       _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/(?:(?:v/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))))?([0-9A-Za-z_-]+)(?(1).+)?$'
+       _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'
        _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']
+       _video_extensions = {
+               '13': '3gp',
+               '17': 'mp4',
+               '18': 'mp4',
+               '22': 'mp4',
+               '37': 'mp4',
+               '38': 'video', # You actually don't know if this will be MOV, AVI or whatever
+               '43': 'webm',
+               '45': 'webm',
+       }

 
        @staticmethod
        def suitable(url):
 
        @staticmethod
        def suitable(url):


@@ -442,35 +744,43 @@ class YoutubeIE(InfoExtractor):
 
        def report_lang(self):
                """Report attempt to set language."""
 
        def report_lang(self):
                """Report attempt to set language."""

-               self.to_stdout(u'[youtube] Setting language')
+               self._downloader.to_screen(u'[youtube] Setting language')

 
        def report_login(self):
                """Report attempt to log in."""
 
        def report_login(self):
                """Report attempt to log in."""

-               self.to_stdout(u'[youtube] Logging in')
+               self._downloader.to_screen(u'[youtube] Logging in')

        
        def report_age_confirmation(self):
                """Report attempt to confirm age."""
        
        def report_age_confirmation(self):
                """Report attempt to confirm age."""

-               self.to_stdout(u'[youtube] Confirming age')
+               self._downloader.to_screen(u'[youtube] Confirming age')
+       
+       def report_video_webpage_download(self, video_id):
+               """Report attempt to download video webpage."""
+               self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id)

        
        

-       def report_webpage_download(self, video_id):
-               """Report attempt to download webpage."""
-               self.to_stdout(u'[youtube] %s: Downloading video webpage' % video_id)
+       def report_video_info_webpage_download(self, video_id):
+               """Report attempt to download video info webpage."""
+               self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id)

        
        def report_information_extraction(self, video_id):
                """Report attempt to extract video information."""
        
        def report_information_extraction(self, video_id):
                """Report attempt to extract video information."""

-               self.to_stdout(u'[youtube] %s: Extracting video information' % video_id)
+               self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id)

        
        

-       def report_video_url(self, video_id, video_real_url):
+       def report_unavailable_format(self, video_id, format):

                """Report extracted video URL."""
                """Report extracted video URL."""

-               self.to_stdout(u'[youtube] %s: URL: %s' % (video_id, video_real_url))
-
+               self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format))
+       
+       def report_rtmp_download(self):
+               """Indicate the download will use the RTMP protocol."""
+               self._downloader.to_screen(u'[youtube] RTMP download detected')
+       

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

-               downloader_params = self._downloader.get_params()
+               downloader_params = self._downloader.params

 
                # Attempt to use provided username and password or .netrc data
                if downloader_params.get('username', None) is not None:
 
                # Attempt to use provided username and password or .netrc data
                if downloader_params.get('username', None) is not None:


@@ -485,20 +795,20 @@ class YoutubeIE(InfoExtractor):
                                else:
                                        raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
                        except (IOError, netrc.NetrcParseError), err:
                                else:
                                        raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
                        except (IOError, netrc.NetrcParseError), err:

-                               self.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))
+                               self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))

                                return
 
                                return
 

-               # No authentication to be performed
-               if username is None:
-                       return
-

                # Set language
                # Set language

-               request = urllib2.Request(self._LOGIN_URL, None, std_headers)
+               request = urllib2.Request(self._LANG_URL, None, std_headers)

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

-                       self.to_stderr(u'WARNING: unable to set language: %s' % str(err))
+                       self._downloader.to_stderr(u'WARNING: unable to set language: %s' % str(err))
+                       return
+
+               # No authentication to be performed
+               if username is None:

                        return
 
                # Log in
                        return
 
                # Log in


@@ -514,10 +824,10 @@ class YoutubeIE(InfoExtractor):
                        self.report_login()
                        login_results = urllib2.urlopen(request).read()
                        if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None:
                        self.report_login()
                        login_results = urllib2.urlopen(request).read()
                        if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None:

-                               self.to_stderr(u'WARNING: unable to log in: bad username or password')
+                               self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password')

                                return
                except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                                return
                except (urllib2.URLError, httplib.HTTPException, socket.error), err:

-                       self.to_stderr(u'WARNING: unable to log in: %s' % str(err))
+                       self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err))

                        return
        
                # Confirm age
                        return
        
                # Confirm age


@@ -530,84 +840,167 @@ class YoutubeIE(InfoExtractor):
                        self.report_age_confirmation()
                        age_results = urllib2.urlopen(request).read()
                except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                        self.report_age_confirmation()
                        age_results = urllib2.urlopen(request).read()
                except (urllib2.URLError, httplib.HTTPException, socket.error), err:

-                       self.to_stderr(u'ERROR: unable to confirm age: %s' % str(err))
+                       self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))

                        return
 
        def _real_extract(self, url):
                # Extract video id from URL
                mobj = re.match(self._VALID_URL, url)
                if mobj is None:
                        return
 
        def _real_extract(self, url):
                # Extract video id from URL
                mobj = re.match(self._VALID_URL, url)
                if mobj is None:

-                       self.to_stderr(u'ERROR: invalid URL: %s' % url)
-                       return [None]
+                       self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+                       return

                video_id = mobj.group(2)
 
                video_id = mobj.group(2)
 

-               # Downloader parameters
-               format_param = None
-               if self._downloader is not None:
-                       params = self._downloader.get_params()
-                       format_param = params.get('format', None)
-
-               # Extension
-               video_extension = {'18': 'mp4', '17': '3gp'}.get(format_param, 'flv')
-
-               # Normalize URL, including format
-               normalized_url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id
-               if format_param is not None:
-                       normalized_url = '%s&fmt=%s' % (normalized_url, format_param)
-               request = urllib2.Request(normalized_url, None, std_headers)
+               # 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, None, std_headers)

                try:
                try:

-                       self.report_webpage_download(video_id)

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

-                       self.to_stderr(u'ERROR: unable to download video webpage: %s' % str(err))
-                       return [None]
+                       self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+                       return
+
+               # Attempt to extract SWF player URL
+               mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
+               if mobj is not None:
+                       player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
+               else:
+                       player_url = None
+
+               # Get video info
+               self.report_video_info_webpage_download(video_id)
+               for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
+                       video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
+                                          % (video_id, el_type))
+                       request = urllib2.Request(video_info_url, None, std_headers)
+                       try:
+                               video_info_webpage = urllib2.urlopen(request).read()
+                               video_info = parse_qs(video_info_webpage)
+                               if 'token' in video_info:
+                                       break
+                       except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                               self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
+                               return
+               if 'token' not in video_info:
+                       if 'reason' in video_info:
+                               self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0].decode('utf-8'))
+                       else:
+                               self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason')
+                       return
+
+               # Start extracting information

                self.report_information_extraction(video_id)
                self.report_information_extraction(video_id)

-               
-               # "t" param
-               mobj = re.search(r', "t": "([^"]+)"', video_webpage)
-               if mobj is None:
-                       self.to_stderr(u'ERROR: unable to extract "t" parameter')
-                       return [None]
-               video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s' % (video_id, mobj.group(1))
-               if format_param is not None:
-                       video_real_url = '%s&fmt=%s' % (video_real_url, format_param)
-               self.report_video_url(video_id, video_real_url)

 
                # uploader
 
                # uploader

-               mobj = re.search(r"var watchUsername = '([^']+)';", video_webpage)
-               if mobj is None:
-                       self.to_stderr(u'ERROR: unable to extract uploader nickname')
-                       return [None]
-               video_uploader = mobj.group(1)
+               if 'author' not in video_info:
+                       self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
+                       return
+               video_uploader = urllib.unquote_plus(video_info['author'][0])

 
                # title
 
                # title

-               mobj = re.search(r'(?im)<title>YouTube - ([^<]*)</title>', video_webpage)
-               if mobj is None:
-                       self.to_stderr(u'ERROR: unable to extract video title')
-                       return [None]
-               video_title = mobj.group(1).decode('utf-8')
-               video_title = re.sub(ur'(?u)&(.+?);', lambda x: unichr(htmlentitydefs.name2codepoint[x.group(1)]), video_title)
-               video_title = video_title.replace(os.sep, u'%')
+               if 'title' not in video_info:
+                       self._downloader.trouble(u'ERROR: unable to extract video title')
+                       return
+               video_title = urllib.unquote_plus(video_info['title'][0])
+               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'_')
 
 
                # simplified title
                simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
                simple_title = simple_title.strip(ur'_')
 

-               # Return information
-               return [{
-                       'id':           video_id.decode('utf-8'),
-                       'url':          video_real_url.decode('utf-8'),
-                       'uploader':     video_uploader.decode('utf-8'),
-                       'title':        video_title,
-                       'stitle':       simple_title,
-                       'ext':          video_extension.decode('utf-8'),
-                       }]
+               # thumbnail image
+               if 'thumbnail_url' not in video_info:
+                       self._downloader.trouble(u'WARNING: unable to extract video thumbnail')
+                       video_thumbnail = ''
+               else:   # don't panic if we can't find it
+                       video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0])
+
+               # upload date
+               upload_date = u'NA'
+               mobj = re.search(r'id="eow-date".*?>(.*?)</span>', video_webpage, re.DOTALL)
+               if mobj is not None:
+                       upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
+                       format_expressions = ['%d %B %Y', '%B %d %Y']
+                       for expression in format_expressions:
+                               try:
+                                       upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d')
+                               except:
+                                       pass
+
+               # description
+               video_description = 'No description available.'
+               if self._downloader.params.get('forcedescription', False):
+                       mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', video_webpage)
+                       if mobj is not None:
+                               video_description = mobj.group(1)
+
+               # token
+               video_token = urllib.unquote_plus(video_info['token'][0])
+
+               # Decide which formats to download
+               requested_format = self._downloader.params.get('format', None)
+               get_video_template = 'http://www.youtube.com/get_video?video_id=%s&t=%s&eurl=&el=&ps=&asv=&fmt=%%s' % (video_id, video_token)
+
+               if 'fmt_url_map' in video_info:
+                       url_map = dict(tuple(pair.split('|')) for pair in video_info['fmt_url_map'][0].split(','))
+                       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):]
+                       else:
+                               format_list = self._available_formats
+                       existing_formats = [x for x in format_list if x in url_map]
+                       if len(existing_formats) == 0:
+                               self._downloader.trouble(u'ERROR: no known formats available for video')
+                               return
+                       if requested_format is None:
+                               video_url_list = [(existing_formats[0], get_video_template % existing_formats[0])] # Best quality
+                       elif requested_format == '-1':
+                               video_url_list = [(f, get_video_template % f) for f in existing_formats] # All formats
+                       else:
+                               video_url_list = [(requested_format, get_video_template % requested_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:
+                       self._downloader.trouble(u'ERROR: no fmt_url_map or conn information found in video info')
+                       return
+
+               for format_param, video_real_url in video_url_list:
+                       # At this point we have a new video
+                       self._downloader.increment_downloads()
+
+                       # 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({
+                                       'id':           video_id.decode('utf-8'),
+                                       'url':          video_real_url.decode('utf-8'),
+                                       'uploader':     video_uploader.decode('utf-8'),
+                                       'upload_date':  upload_date,
+                                       'title':        video_title,
+                                       'stitle':       simple_title,
+                                       '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'),
+                                       'player_url':   player_url,
+                               })
+                       except UnavailableVideoError, err:
+                               self._downloader.trouble(u'ERROR: unable to download video (format may not be available)')
+

 
 class MetacafeIE(InfoExtractor):
        """Information Extractor for metacafe.com."""
 
        _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
        _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
 
 class MetacafeIE(InfoExtractor):
        """Information Extractor for metacafe.com."""
 
        _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
        _DISCLAIMER = 'http://www.metacafe.com/family_filter/'

+       _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'

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


@@ -620,19 +1013,19 @@ class MetacafeIE(InfoExtractor):
 
        def report_disclaimer(self):
                """Report disclaimer retrieval."""
 
        def report_disclaimer(self):
                """Report disclaimer retrieval."""

-               self.to_stdout(u'[metacafe] Retrieving disclaimer')
+               self._downloader.to_screen(u'[metacafe] Retrieving disclaimer')

 
        def report_age_confirmation(self):
                """Report attempt to confirm age."""
 
        def report_age_confirmation(self):
                """Report attempt to confirm age."""

-               self.to_stdout(u'[metacafe] Confirming age')
+               self._downloader.to_screen(u'[metacafe] Confirming age')

        
        def report_download_webpage(self, video_id):
                """Report webpage download."""
        
        def report_download_webpage(self, video_id):
                """Report webpage download."""

-               self.to_stdout(u'[metacafe] %s: Downloading webpage' % video_id)
+               self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id)

        
        def report_extraction(self, video_id):
                """Report information extraction."""
        
        def report_extraction(self, video_id):
                """Report information extraction."""

-               self.to_stdout(u'[metacafe] %s: Extracting information' % video_id)
+               self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id)

 
        def _real_initialize(self):
                # Retrieve disclaimer
 
        def _real_initialize(self):
                # Retrieve disclaimer


@@ -641,7 +1034,7 @@ class MetacafeIE(InfoExtractor):
                        self.report_disclaimer()
                        disclaimer = urllib2.urlopen(request).read()
                except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                        self.report_disclaimer()
                        disclaimer = urllib2.urlopen(request).read()
                except (urllib2.URLError, httplib.HTTPException, socket.error), err:

-                       self.to_stderr(u'ERROR: unable to retrieve disclaimer: %s' % str(err))
+                       self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % str(err))

                        return
 
                # Confirm age
                        return
 
                # Confirm age


@@ -649,30 +1042,33 @@ class MetacafeIE(InfoExtractor):
                        'filters': '0',
                        'submit': "Continue - I'm over 18",
                        }
                        'filters': '0',
                        'submit': "Continue - I'm over 18",
                        }

-               request = urllib2.Request('http://www.metacafe.com/', urllib.urlencode(disclaimer_form), std_headers)
+               request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form), std_headers)

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

-                       self.to_stderr(u'ERROR: unable to confirm age: %s' % str(err))
+                       self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))

                        return
        
        def _real_extract(self, url):
                # Extract id and simplified title from URL
                mobj = re.match(self._VALID_URL, url)
                if mobj is None:
                        return
        
        def _real_extract(self, url):
                # Extract id and simplified title from URL
                mobj = re.match(self._VALID_URL, url)
                if mobj is None:

-                       self.to_stderr(u'ERROR: invalid URL: %s' % url)
-                       return [None]
+                       self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+                       return

 
                video_id = mobj.group(1)
 
                # Check if video comes from YouTube
                mobj2 = re.match(r'^yt-(.*)$', video_id)
                if mobj2 is not None:
 
                video_id = mobj.group(1)
 
                # Check if video comes from YouTube
                mobj2 = re.match(r'^yt-(.*)$', video_id)
                if mobj2 is not None:

-                       return self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1))
+                       self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1))
+                       return
+
+               # At this point we have a new video
+               self._downloader.increment_downloads()

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

-               video_extension = 'flv'

 
                # Retrieve video webpage to extract further information
                request = urllib2.Request('http://www.metacafe.com/watch/%s/' % video_id)
 
                # Retrieve video webpage to extract further information
                request = urllib2.Request('http://www.metacafe.com/watch/%s/' % video_id)


@@ -680,154 +1076,1043 @@ class MetacafeIE(InfoExtractor):
                        self.report_download_webpage(video_id)
                        webpage = urllib2.urlopen(request).read()
                except (urllib2.URLError, httplib.HTTPException, socket.error), err:
                        self.report_download_webpage(video_id)
                        webpage = urllib2.urlopen(request).read()
                except (urllib2.URLError, httplib.HTTPException, socket.error), err:

-                       self.to_stderr(u'ERROR: unable retrieve video webpage: %s' % str(err))
-                       return [None]
+                       self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err))
+                       return

 
                # 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'(?m)"mediaURL":"(http.*?\.flv)"', webpage)
-               if mobj is None:
-                       self.to_stderr(u'ERROR: unable to extract media URL')
-                       return [None]
-               mediaURL = mobj.group(1).replace('\\', '')
-
-               mobj = re.search(r'(?m)"gdaKey":"(.*?)"', webpage)
-               if mobj is None:
-                       self.to_stderr(u'ERROR: unable to extract gdaKey')
-                       return [None]
-               gdaKey = mobj.group(1)
-
-               video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
+               mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
+               if mobj is not None:
+                       mediaURL = urllib.unquote(mobj.group(1))
+                       video_extension = mediaURL[-3:]
+                       
+                       # Extract gdaKey if available
+                       mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
+                       if mobj is None:
+                               video_url = mediaURL
+                       else:
+                               gdaKey = mobj.group(1)
+                               video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
+               else:
+                       mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
+                       if mobj is None:
+                               self._downloader.trouble(u'ERROR: unable to extract media URL')
+                               return
+                       vardict = parse_qs(mobj.group(1))
+                       if 'mediaData' not in vardict:
+                               self._downloader.trouble(u'ERROR: unable to extract media URL')
+                               return
+                       mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0])
+                       if mobj is None:
+                               self._downloader.trouble(u'ERROR: unable to extract media URL')
+                               return
+                       mediaURL = mobj.group(1).replace('\\/', '/')
+                       video_extension = mediaURL[-3:]
+                       video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2))

 
                mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
                if mobj is None:
 
                mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
                if mobj is None:

-                       self.to_stderr(u'ERROR: unable to extract title')
-                       return [None]
+                       self._downloader.trouble(u'ERROR: unable to extract title')
+                       return

                video_title = mobj.group(1).decode('utf-8')
                video_title = mobj.group(1).decode('utf-8')

+               video_title = sanitize_title(video_title)

 
 

-               mobj = re.search(r'(?m)<li id="ChnlUsr">.*?Submitter:<br />(.*?)</li>', webpage)
+               mobj = re.search(r'(?ms)By:\s*<a .*?>(.+?)<', webpage)

                if mobj is None:
                if mobj is None:

-                       self.to_stderr(u'ERROR: unable to extract uploader nickname')
-                       return [None]
-               video_uploader = re.sub(r'<.*?>', '', mobj.group(1))
+                       self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
+                       return
+               video_uploader = mobj.group(1)
+
+               try:
+                       # Process video information
+                       self._downloader.process_info({
+                               'id':           video_id.decode('utf-8'),
+                               'url':          video_url.decode('utf-8'),
+                               'uploader':     video_uploader.decode('utf-8'),
+                               'upload_date':  u'NA',
+                               'title':        video_title,
+                               'stitle':       simple_title,
+                               'ext':          video_extension.decode('utf-8'),
+                               'format':       u'NA',
+                               'player_url':   None,
+                       })
+               except UnavailableVideoError:
+                       self._downloader.trouble(u'ERROR: unable to download video')

 
 

-               # Return information
-               return [{
-                       'id':           video_id.decode('utf-8'),
-                       'url':          video_url.decode('utf-8'),
-                       'uploader':     video_uploader.decode('utf-8'),
-                       'title':        video_title,
-                       'stitle':       simple_title,
-                       'ext':          video_extension.decode('utf-8'),
-                       }]

 
 

-class YoutubePlaylistIE(InfoExtractor):
-       """Information Extractor for YouTube playlists."""
+class DailymotionIE(InfoExtractor):
+       """Information Extractor for Dailymotion"""

 
 

-       _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/view_play_list\?p=(.+)'
-       _TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en'
-       _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
-       _MORE_PAGES_INDICATOR = r'/view_play_list?p=%s&amp;page=%s'
-       _youtube_ie = None
+       _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)'

 
 

-       def __init__(self, youtube_ie, downloader=None):
+       def __init__(self, downloader=None):

                InfoExtractor.__init__(self, downloader)
                InfoExtractor.__init__(self, downloader)

-               self._youtube_ie = youtube_ie
-       
+

        @staticmethod
        def suitable(url):
        @staticmethod
        def suitable(url):

-               return (re.match(YoutubePlaylistIE._VALID_URL, url) is not None)
+               return (re.match(DailymotionIE._VALID_URL, url) is not None)

 
 

-       def report_download_page(self, playlist_id, pagenum):
-               """Report attempt to download playlist page with given number."""
-               self.to_stdout(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
+       def report_download_webpage(self, video_id):
+               """Report webpage download."""
+               self._downloader.to_screen(u'[dailymotion] %s: Downloading webpage' % video_id)
+       
+       def report_extraction(self, video_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id)

 
        def _real_initialize(self):
 
        def _real_initialize(self):

-               self._youtube_ie.initialize()
-       
+               return
+

        def _real_extract(self, url):
        def _real_extract(self, url):

-               # Extract playlist id
+               # Extract id and simplified title from URL

                mobj = re.match(self._VALID_URL, url)
                if mobj is None:
                mobj = re.match(self._VALID_URL, url)
                if mobj is None:

-                       self.to_stderr(u'ERROR: invalid url: %s' % url)
-                       return [None]
+                       self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+                       return

 
 

-               # Download playlist pages
-               playlist_id = mobj.group(1)
-               video_ids = []
-               pagenum = 1
+               # At this point we have a new video
+               self._downloader.increment_downloads()
+               video_id = mobj.group(1)

 
 

-               while True:
-                       self.report_download_page(playlist_id, pagenum)
-                       request = urllib2.Request(self._TEMPLATE_URL % (playlist_id, pagenum), None, std_headers)
-                       try:
-                               page = urllib2.urlopen(request).read()
-                       except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-                               self.to_stderr(u'ERROR: unable to download webpage: %s' % str(err))
-                               return [None]
+               simple_title = mobj.group(2).decode('utf-8')
+               video_extension = 'flv'

 
 

-                       # Extract video identifiers
-                       ids_in_page = []
-                       for mobj in re.finditer(self._VIDEO_INDICATOR, page):
-                               if mobj.group(1) not in ids_in_page:
-                                       ids_in_page.append(mobj.group(1))
-                       video_ids.extend(ids_in_page)
+               # Retrieve video webpage to extract further information
+               request = urllib2.Request(url)
+               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 retrieve video webpage: %s' % str(err))
+                       return

 
 

-                       if (self._MORE_PAGES_INDICATOR % (playlist_id, pagenum + 1)) not in page:
-                               break
-                       pagenum = pagenum + 1
+               # Extract URL, uploader and title from webpage
+               self.report_extraction(video_id)
+               mobj = re.search(r'(?i)addVariable\(\"video\"\s*,\s*\"([^\"]*)\"\)', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract media URL')
+                       return
+               mediaURL = urllib.unquote(mobj.group(1))

 
 

-               information = []
-               for id in video_ids:
-                       information.extend(self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id))
-               return information
+               # if needed add http://www.dailymotion.com/ if relative URL

 
 

-class PostProcessor(object):
-       """Post Processor class.
+               video_url = mediaURL

 
 

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

 
 

-       The chain will be stopped if one of them ever returns None or the end
-       of the chain is reached.
+               mobj = re.search(r'(?im)<div class="dmco_html owner">.*?<a class="name" href="/.+?">(.+?)</a>', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
+                       return
+               video_uploader = mobj.group(1)

 
 

-       PostProcessor objects follow a "mutual registration" process similar
-       to InfoExtractor objects.
-       """
+               try:
+                       # Process video information
+                       self._downloader.process_info({
+                               'id':           video_id.decode('utf-8'),
+                               'url':          video_url.decode('utf-8'),
+                               'uploader':     video_uploader.decode('utf-8'),
+                               'upload_date':  u'NA',
+                               'title':        video_title,
+                               'stitle':       simple_title,
+                               'ext':          video_extension.decode('utf-8'),
+                               'format':       u'NA',
+                               'player_url':   None,
+                       })
+               except UnavailableVideoError:
+                       self._downloader.trouble(u'ERROR: unable to download video')

 
 

-       _downloader = None
+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=([^\&]+).*'

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

-               self._downloader = downloader
+               InfoExtractor.__init__(self, downloader)

 
 

-       def to_stdout(self, message):
-               """Print message to stdout if downloader is not in quiet mode."""
-               if self._downloader is None or not self._downloader.get_params().get('quiet', False):
-                       print message
-       
-       def to_stderr(self, message):
-               """Print message to stderr."""
-               print >>sys.stderr, message
+       @staticmethod
+       def suitable(url):
+               return (re.match(GoogleIE._VALID_URL, url) is not None)

 
 

-       def set_downloader(self, downloader):
-               """Sets the downloader for this PP."""
-               self._downloader = downloader
-       
-       def run(self, information):
-               """Run the PostProcessor.
+       def report_download_webpage(self, video_id):
+               """Report webpage download."""
+               self._downloader.to_screen(u'[video.google] %s: Downloading webpage' % video_id)

 
 

-               The "information" argument is a dictionary like the ones
-               returned by InfoExtractors. The only difference is that this
-               one has an extra field called "filepath" that points to the
-               downloaded file.
+       def report_extraction(self, video_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[video.google] %s: Extracting information' % video_id)

 
 

-               When this method returns None, the postprocessing chain is
-               stopped. However, this method may return an information
-               dictionary that will be passed to the next postprocessing
+       def _real_initialize(self):
+               return
+
+       def _real_extract(self, url):
+               # 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)
+
+               video_extension = 'mp4'
+
+               # Retrieve video webpage to extract further information
+               request = urllib2.Request('http://video.google.com/videoplay?docid=%s&hl=en&oe=utf-8' % 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
+
+               # Extract URL, uploader, and title from webpage
+               self.report_extraction(video_id)
+               mobj = re.search(r"download_url:'([^']+)'", webpage)
+               if mobj is None:
+                       video_extension = 'flv'
+                       mobj = re.search(r"(?i)videoUrl\\x3d(.+?)\\x26", webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract media URL')
+                       return
+               mediaURL = urllib.unquote(mobj.group(1))
+               mediaURL = mediaURL.replace('\\x3d', '\x3d')
+               mediaURL = mediaURL.replace('\\x26', '\x26')
+
+               video_url = mediaURL
+
+               mobj = re.search(r'<title>(.*)</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)
+               simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+
+               # Extract video description
+               mobj = re.search(r'<span id=short-desc-content>([^<]*)</span>', 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.'
+
+               # Extract video thumbnail
+               if self._downloader.params.get('forcethumbnail', False):
+                       request = urllib2.Request('http://video.google.com/videosearch?q=%s+site:video.google.com&hl=en' % abs(int(video_id)))
+                       try:
+                               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
+                       mobj = re.search(r'<img class=thumbnail-img (?:.* )?src=(http.*)>', webpage)
+                       if mobj is None:
+                               self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
+                               return
+                       video_thumbnail = mobj.group(1)
+               else:   # we need something to pass to process_info
+                       video_thumbnail = ''
+
+
+               try:
+                       # Process video information
+                       self._downloader.process_info({
+                               'id':           video_id.decode('utf-8'),
+                               'url':          video_url.decode('utf-8'),
+                               'uploader':     u'NA',
+                               'upload_date':  u'NA',
+                               'title':        video_title,
+                               'stitle':       simple_title,
+                               'ext':          video_extension.decode('utf-8'),
+                               'format':       u'NA',
+                               'player_url':   None,
+                       })
+               except UnavailableVideoError:
+                       self._downloader.trouble(u'ERROR: unable to download video')
+
+
+class PhotobucketIE(InfoExtractor):
+       """Information extractor for photobucket.com."""
+
+       _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
+
+       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_extraction(self, 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)
+               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)
+
+               video_extension = 'flv'
+
+               # Retrieve video webpage to extract further information
+               request = urllib2.Request(url)
+               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
+
+               # Extract URL, uploader, and title from webpage
+               self.report_extraction(video_id)
+               mobj = re.search(r'<link rel="video_src" href=".*\?file=([^"]+)" />', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract media URL')
+                       return
+               mediaURL = urllib.unquote(mobj.group(1))
+
+               video_url = mediaURL
+
+               mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</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)
+               simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+
+               video_uploader = mobj.group(2).decode('utf-8')
+
+               try:
+                       # Process video information
+                       self._downloader.process_info({
+                               'id':           video_id.decode('utf-8'),
+                               'url':          video_url.decode('utf-8'),
+                               'uploader':     video_uploader,
+                               'upload_date':  u'NA',
+                               'title':        video_title,
+                               'stitle':       simple_title,
+                               'ext':          video_extension.decode('utf-8'),
+                               'format':       u'NA',
+                               'player_url':   None,
+                       })
+               except UnavailableVideoError:
+                       self._downloader.trouble(u'ERROR: unable to download video')
+
+
+class YahooIE(InfoExtractor):
+       """Information extractor for video.yahoo.com."""
+
+       # _VALID_URL matches all Yahoo! Video URLs
+       # _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]+)(?:[#\?].*)?'
+
+       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_extraction(self, 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)
+               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(2)
+               video_extension = 'flv'
+
+               # Rewrite valid but non-extractable URLs as
+               # extractable English language /watch/ URLs
+               if re.match(self._VPAGE_URL, url) is None:
+                       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 retrieve video webpage: %s' % str(err))
+                               return
+
+                       mobj = re.search(r'\("id", "([0-9]+)"\);', webpage)
+                       if mobj is None:
+                               self._downloader.trouble(u'ERROR: Unable to extract id field')
+                               return
+                       yahoo_id = mobj.group(1)
+
+                       mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage)
+                       if mobj is None:
+                               self._downloader.trouble(u'ERROR: Unable to extract vid field')
+                               return
+                       yahoo_vid = mobj.group(1)
+
+                       url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id)
+                       return self._real_extract(url, new_video=False)
+
+               # Retrieve video webpage to extract further information
+               request = urllib2.Request(url)
+               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
+
+               # Extract uploader and title from webpage
+               self.report_extraction(video_id)
+               mobj = re.search(r'<meta name="title" content="(.*)" />', 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 = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', 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:
+                       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'<link rel="image_src" href="(.*)" />', 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 name="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.'
+
+               # Extract video height and width
+               mobj = re.search(r'<meta name="video_height" content="([0-9]+)" />', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract video height')
+                       return
+               yv_video_height = mobj.group(1)
+
+               mobj = re.search(r'<meta name="video_width" content="([0-9]+)" />', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract video width')
+                       return
+               yv_video_width = mobj.group(1)
+
+               # Retrieve video playlist to extract media URL
+               # I'm not completely sure what all these options are, but we
+               # seem to need most of them, otherwise the server sends a 401.
+               yv_lg = 'R0xx6idZnW2zlrKP8xxAIR'  # not sure what this represents
+               yv_bitrate = '700'  # according to Wikipedia this is hard-coded
+               request = urllib2.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id +
+                                         '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height +
+                                         '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797')
+               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
+
+               # Extract media URL from playlist XML
+               mobj = re.search(r'<STREAM APP="(http://.*)" FULLPATH="/?(/.*\.flv\?[^"]*)"', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: Unable to extract media URL')
+                       return
+               video_url = urllib.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8')
+               video_url = re.sub(r'(?u)&(.+?);', htmlentity_transform, video_url)
+
+               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':          video_extension.decode('utf-8'),
+                               '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."""
+
+       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.')
+               self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id)
+
+       def report_extraction(self, 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()
+
+               video_id = url.split('/')[-1]
+               request = urllib2.Request(url)
+               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
+               except ValueError, err:
+                       # since this is the last-resort InfoExtractor, if
+                       # this error is thrown, it'll be thrown here
+                       self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+                       return
+
+               self.report_extraction(video_id)
+               # Start with something easy: JW Player in SWFObject
+               mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
+               if mobj is None:
+                       # Broaden the search a little bit
+                       mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+                       return
+
+               # It's possible that one of the regexes
+               # matched, but returned an empty group:
+               if mobj.group(1) is None:
+                       self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+                       return
+
+               video_url = urllib.unquote(mobj.group(1))
+               video_id  = os.path.basename(video_url)
+
+               # here's a fun little line of code for you:
+               video_extension = os.path.splitext(video_id)[1][1:]
+               video_id        = os.path.splitext(video_id)[0]
+
+               # it's tempting to parse this further, but you would
+               # have to take into account all the variations like
+               #   Video Title - Site Name
+               #   Site Name | Video Title
+               #   Video Title - Tagline | Site Name
+               # and so on and so forth; it's just not practical
+               mobj = re.search(r'<title>(.*)</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)
+               simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+
+               # video uploader is domain name
+               mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: unable to extract title')
+                       return
+               video_uploader = mobj.group(1).decode('utf-8')
+
+               try:
+                       # Process video information
+                       self._downloader.process_info({
+                               'id':           video_id.decode('utf-8'),
+                               'url':          video_url.decode('utf-8'),
+                               'uploader':     video_uploader,
+                               'upload_date':  u'NA',
+                               'title':        video_title,
+                               'stitle':       simple_title,
+                               'ext':          video_extension.decode('utf-8'),
+                               'format':       u'NA',
+                               'player_url':   None,
+                       })
+               except UnavailableVideoError, err:
+                       self._downloader.trouble(u'ERROR: unable to download video')
+
+
+class YoutubeSearchIE(InfoExtractor):
+       """Information Extractor for YouTube search queries."""
+       _VALID_QUERY = r'ytsearch(\d+|all)?:[\s\S]+'
+       _TEMPLATE_URL = 'http://www.youtube.com/results?search_query=%s&page=%s&gl=US&hl=en'
+       _VIDEO_INDICATOR = r'href="/watch\?v=.+?"'
+       _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
+       _youtube_ie = None
+       _max_youtube_results = 1000
+
+       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())
+               self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
+
+       def _real_initialize(self):
+               self._youtube_ie.initialize()
+       
+       def _real_extract(self, query):
+               mobj = re.match(self._VALID_QUERY, query)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
+                       return
+
+               prefix, query = query.split(':')
+               prefix = prefix[8:]
+               query  = query.encode('utf-8')
+               if prefix == '':
+                       self._download_n_results(query, 1)
+                       return
+               elif prefix == 'all':
+                       self._download_n_results(query, self._max_youtube_results)
+                       return
+               else:
+                       try:
+                               n = long(prefix)
+                               if n <= 0:
+                                       self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
+                                       return
+                               elif n > self._max_youtube_results:
+                                       self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)'  % (self._max_youtube_results, n))
+                                       n = self._max_youtube_results
+                               self._download_n_results(query, n)
+                               return
+                       except ValueError: # parsing prefix as integer fails
+                               self._download_n_results(query, 1)
+                               return
+
+       def _download_n_results(self, query, n):
+               """Downloads a specified number of results for a query"""
+
+               video_ids = []
+               already_seen = set()
+               pagenum = 1
+
+               while True:
+                       self.report_download_page(query, pagenum)
+                       result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
+                       request = urllib2.Request(result_url, None, std_headers)
+                       try:
+                               page = urllib2.urlopen(request).read()
+                       except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                               self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+                               return
+
+                       # Extract video identifiers
+                       for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+                               video_id = page[mobj.span()[0]:mobj.span()[1]].split('=')[2][:-1]
+                               if video_id not in already_seen:
+                                       video_ids.append(video_id)
+                                       already_seen.add(video_id)
+                                       if len(video_ids) == n:
+                                               # Specified n videos reached
+                                               for id in video_ids:
+                                                       self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
+                                               return
+
+                       if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+                               for id in video_ids:
+                                       self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
+                               return
+
+                       pagenum = pagenum + 1
+
+class GoogleSearchIE(InfoExtractor):
+       """Information Extractor for Google Video search queries."""
+       _VALID_QUERY = 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
+
+       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())
+               self._downloader.to_screen(u'[video.google] query "%s": Downloading page %s' % (query, pagenum))
+
+       def _real_initialize(self):
+               self._google_ie.initialize()
+       
+       def _real_extract(self, query):
+               mobj = re.match(self._VALID_QUERY, query)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
+                       return
+
+               prefix, query = query.split(':')
+               prefix = prefix[8:]
+               query  = query.encode('utf-8')
+               if prefix == '':
+                       self._download_n_results(query, 1)
+                       return
+               elif prefix == 'all':
+                       self._download_n_results(query, self._max_google_results)
+                       return
+               else:
+                       try:
+                               n = long(prefix)
+                               if n <= 0:
+                                       self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
+                                       return
+                               elif n > self._max_google_results:
+                                       self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)'  % (self._max_google_results, n))
+                                       n = self._max_google_results
+                               self._download_n_results(query, n)
+                               return
+                       except ValueError: # parsing prefix as integer fails
+                               self._download_n_results(query, 1)
+                               return
+
+       def _download_n_results(self, query, n):
+               """Downloads a specified number of results for a query"""
+
+               video_ids = []
+               already_seen = set()
+               pagenum = 1
+
+               while True:
+                       self.report_download_page(query, pagenum)
+                       result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
+                       request = urllib2.Request(result_url, None, std_headers)
+                       try:
+                               page = urllib2.urlopen(request).read()
+                       except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                               self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+                               return
+
+                       # Extract video identifiers
+                       for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+                               video_id = mobj.group(1)
+                               if video_id not in already_seen:
+                                       video_ids.append(video_id)
+                                       already_seen.add(video_id)
+                                       if len(video_ids) == n:
+                                               # Specified n videos reached
+                                               for id in video_ids:
+                                                       self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id)
+                                               return
+
+                       if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+                               for id in video_ids:
+                                       self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id)
+                               return
+
+                       pagenum = pagenum + 1
+
+class YahooSearchIE(InfoExtractor):
+       """Information Extractor for Yahoo! Video search queries."""
+       _VALID_QUERY = 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
+
+       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())
+               self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum))
+
+       def _real_initialize(self):
+               self._yahoo_ie.initialize()
+       
+       def _real_extract(self, query):
+               mobj = re.match(self._VALID_QUERY, query)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
+                       return
+
+               prefix, query = query.split(':')
+               prefix = prefix[8:]
+               query  = query.encode('utf-8')
+               if prefix == '':
+                       self._download_n_results(query, 1)
+                       return
+               elif prefix == 'all':
+                       self._download_n_results(query, self._max_yahoo_results)
+                       return
+               else:
+                       try:
+                               n = long(prefix)
+                               if n <= 0:
+                                       self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
+                                       return
+                               elif n > self._max_yahoo_results:
+                                       self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)'  % (self._max_yahoo_results, n))
+                                       n = self._max_yahoo_results
+                               self._download_n_results(query, n)
+                               return
+                       except ValueError: # parsing prefix as integer fails
+                               self._download_n_results(query, 1)
+                               return
+
+       def _download_n_results(self, query, n):
+               """Downloads a specified number of results for a query"""
+
+               video_ids = []
+               already_seen = set()
+               pagenum = 1
+
+               while True:
+                       self.report_download_page(query, pagenum)
+                       result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
+                       request = urllib2.Request(result_url, None, std_headers)
+                       try:
+                               page = urllib2.urlopen(request).read()
+                       except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                               self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+                               return
+
+                       # Extract video identifiers
+                       for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+                               video_id = mobj.group(1)
+                               if video_id not in already_seen:
+                                       video_ids.append(video_id)
+                                       already_seen.add(video_id)
+                                       if len(video_ids) == n:
+                                               # Specified n videos reached
+                                               for id in video_ids:
+                                                       self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id)
+                                               return
+
+                       if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+                               for id in video_ids:
+                                       self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id)
+                               return
+
+                       pagenum = pagenum + 1
+
+class YoutubePlaylistIE(InfoExtractor):
+       """Information Extractor for YouTube playlists."""
+
+       _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists)\?.*?p=|user/.*?/user/)([^&]+).*'
+       _TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en'
+       _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
+       _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
+       _youtube_ie = None
+
+       def __init__(self, youtube_ie, downloader=None):
+               InfoExtractor.__init__(self, downloader)
+               self._youtube_ie = youtube_ie
+       
+       @staticmethod
+       def suitable(url):
+               return (re.match(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 _real_initialize(self):
+               self._youtube_ie.initialize()
+       
+       def _real_extract(self, url):
+               # Extract playlist id
+               mobj = re.match(self._VALID_URL, url)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: invalid url: %s' % url)
+                       return
+
+               # Download playlist pages
+               playlist_id = mobj.group(1)
+               video_ids = []
+               pagenum = 1
+
+               while True:
+                       self.report_download_page(playlist_id, pagenum)
+                       request = urllib2.Request(self._TEMPLATE_URL % (playlist_id, pagenum), None, std_headers)
+                       try:
+                               page = urllib2.urlopen(request).read()
+                       except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                               self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+                               return
+
+                       # Extract video identifiers
+                       ids_in_page = []
+                       for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+                               if mobj.group(1) not in ids_in_page:
+                                       ids_in_page.append(mobj.group(1))
+                       video_ids.extend(ids_in_page)
+
+                       if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+                               break
+                       pagenum = pagenum + 1
+
+               playliststart = self._downloader.params.get('playliststart', 1) - 1
+               playlistend = self._downloader.params.get('playlistend', -1)
+               video_ids = video_ids[playliststart:playlistend]
+
+               for id in video_ids:
+                       self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
+               return
+
+class YoutubeUserIE(InfoExtractor):
+       """Information Extractor for YouTube users."""
+
+       _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/user/(.*)'
+       _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
+       _VIDEO_INDICATOR = r'http://gdata.youtube.com/feeds/api/videos/(.*)' # XXX Fix this.
+       _youtube_ie = None
+
+       def __init__(self, youtube_ie, downloader=None):
+               InfoExtractor.__init__(self, downloader)
+               self._youtube_ie = youtube_ie
+       
+       @staticmethod
+       def suitable(url):
+               return (re.match(YoutubeUserIE._VALID_URL, url) is not None)
+
+       def report_download_page(self, username):
+               """Report attempt to download user page."""
+               self._downloader.to_screen(u'[youtube] user %s: Downloading page ' % (username))
+
+       def _real_initialize(self):
+               self._youtube_ie.initialize()
+       
+       def _real_extract(self, url):
+               # Extract username
+               mobj = re.match(self._VALID_URL, url)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: invalid url: %s' % url)
+                       return
+
+               # Download user page
+               username = mobj.group(1)
+               video_ids = []
+               pagenum = 1
+
+               self.report_download_page(username)
+               request = urllib2.Request(self._TEMPLATE_URL % (username), None, std_headers)
+               try:
+                       page = urllib2.urlopen(request).read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+                       self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+                       return
+
+               # Extract video identifiers
+               ids_in_page = []
+
+               for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+                       if mobj.group(1) not in ids_in_page:
+                               ids_in_page.append(mobj.group(1))
+               video_ids.extend(ids_in_page)
+
+               playliststart = self._downloader.params.get('playliststart', 1) - 1
+               playlistend = self._downloader.params.get('playlistend', -1)
+               video_ids = video_ids[playliststart:playlistend]
+
+               for id in video_ids:
+                       self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
+               return
+
+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.
+
+               When this method returns None, the postprocessing chain is
+               stopped. However, this method may return an information
+               dictionary that will be passed to the next postprocessing

                object in the chain. It can be the one it received after
                changing some fields.
 
                object in the chain. It can be the one it received after
                changing some fields.
 


@@ -844,111 +2129,256 @@ if __name__ == '__main__':
                import getpass
                import optparse
 
                import getpass
                import optparse
 

-               # General configuration
-               urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler()))
-               urllib2.install_opener(urllib2.build_opener(urllib2.HTTPCookieProcessor()))
-               socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
+               # Function to update the program file with the latest version from bitbucket.org
+               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)
+
+                       downloader.to_screen('Updating to latest stable version...')
+                       latest_url = 'http://github.com/rg3/youtube-dl/raw/master/LATEST_VERSION'
+                       latest_version = urllib.urlopen(latest_url).read().strip()
+                       prog_url = 'http://github.com/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version
+                       newcontent = urllib.urlopen(prog_url).read()
+                       stream = open(filename, 'w')
+                       stream.write(newcontent)
+                       stream.close()
+                       downloader.to_screen('Updated to version %s' % latest_version)

 
                # Parse command line
                parser = optparse.OptionParser(
 
                # Parse command line
                parser = optparse.OptionParser(

-                               usage='Usage: %prog [options] url...',
-                               version='2008.11.01',
-                               conflict_handler='resolve',
-                               )
+                       usage='Usage: %prog [options] url...',
+                       version='2010.11.19',
+                       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('-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', '--username',
-                               dest='username', metavar='UN', help='account username')
-               parser.add_option('-p', '--password',
-                               dest='password', metavar='PW', help='account password')
-               parser.add_option('-o', '--output',
-                               dest='outtmpl', metavar='TPL', help='output filename template')
-               parser.add_option('-q', '--quiet',
+               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)
+
+               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('-m', '--mobile-version',
+                               action='store_const', dest='format', help='alias for -f 17', const='17')
+               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')
+               video_format.add_option('-b', '--best-quality',
+                               action='store_true', dest='bestquality', help='download the best video quality (DEPRECATED)')
+               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)
                                action='store_true', dest='quiet', help='activates quiet mode', default=False)

-               parser.add_option('-s', '--simulate',
+               verbosity.add_option('-s', '--simulate',

                                action='store_true', dest='simulate', help='do not download video', default=False)
                                action='store_true', dest='simulate', help='do not download video', default=False)

-               parser.add_option('-t', '--title',
-                               action='store_true', dest='usetitle', help='use title in file name', default=False)
-               parser.add_option('-l', '--literal',
-                               action='store_true', dest='useliteral', help='use literal title in file name', default=False)
-               parser.add_option('-n', '--netrc',
-                               action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
-               parser.add_option('-g', '--get-url',
+               verbosity.add_option('-g', '--get-url',

                                action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
                                action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)

-               parser.add_option('-e', '--get-title',
+               verbosity.add_option('-e', '--get-title',

                                action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
                                action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)

-               parser.add_option('-f', '--format',
-                               dest='format', metavar='FMT', help='video format code')
-               parser.add_option('-b', '--best-quality',
-                               action='store_const', dest='format', help='alias for -f 18', const='18')
-               parser.add_option('-m', '--mobile-version',
-                               action='store_const', dest='format', help='alias for -f 17', const='17')
-               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='L', help='download rate limit (e.g. 50k or 44.6m)')
-               parser.add_option('-a', '--batch-file',
-                               dest='batchfile', metavar='F', help='file containing URLs to download')
+               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('--no-progress',
+                               action='store_true', dest='noprogress', help='do not print progress bar', 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')
+               parser.add_option_group(filesystem)
+

                (opts, args) = parser.parse_args()
 
                (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')
+
+               # General configuration
+               cookie_processor = urllib2.HTTPCookieProcessor(jar)
+               urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler()))
+               urllib2.install_opener(urllib2.build_opener(cookie_processor))
+               socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
+

                # Batch file verification
                # Batch file verification

+               batchurls = []

                if opts.batchfile is not None:
                        try:
                if opts.batchfile is not None:
                        try:

-                               batchurls = [line.strip() for line in open(opts.batchfile, 'r')]
+                               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
                        except IOError:
                                sys.exit(u'ERROR: batch file could not be read')
                all_urls = batchurls + args
 
                # Conflicting, missing and erroneous options

-               if len(all_urls) < 1:
-                       sys.exit(u'ERROR: you must provide at least one URL')
+               if opts.bestquality:
+                       print >>sys.stderr, u'\nWARNING: -b/--best-quality IS DEPRECATED AS IT IS THE DEFAULT BEHAVIOR NOW\n'

                if opts.usenetrc and (opts.username is not None or opts.password is not None):
                if opts.usenetrc and (opts.username is not None or opts.password is not None):

-                       sys.exit(u'ERROR: using .netrc conflicts with giving username/password')
+                       parser.error(u'using .netrc conflicts with giving username/password')

                if opts.password is not None and opts.username is None:
                if opts.password is not None and opts.username is None:

-                       sys.exit(u'ERROR: account username missing')
-               if opts.outtmpl is not None and (opts.useliteral or opts.usetitle):
-                       sys.exit(u'ERROR: using output template conflicts with using title or literal title')
+                       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:
                if opts.usetitle and opts.useliteral:

-                       sys.exit(u'ERROR: using title conflicts with using literal title')
+                       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:
                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:

-                               sys.exit(u'ERROR: invalid rate limit specified')
+                               parser.error(u'invalid rate limit specified')

                        opts.ratelimit = numeric_limit
                        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 = long(opts.playliststart)
+                       if opts.playliststart <= 0:
+                               raise ValueError
+               except (TypeError, ValueError), err:
+                       parser.error(u'invalid playlist start number specified')
+               try:
+                       opts.playlistend = long(opts.playlistend)
+                       if opts.playlistend != -1 and (opts.playlistend <= 0 or opts.playlistend < opts.playliststart):
+                               raise ValueError
+               except (TypeError, ValueError), err:
+                       parser.error(u'invalid playlist end number specified')

 
                # Information extractors
                youtube_ie = YoutubeIE()
                metacafe_ie = MetacafeIE(youtube_ie)
 
                # Information extractors
                youtube_ie = YoutubeIE()
                metacafe_ie = MetacafeIE(youtube_ie)

+               dailymotion_ie = DailymotionIE()

                youtube_pl_ie = YoutubePlaylistIE(youtube_ie)
                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)
+               generic_ie = GenericIE()

 
                # File downloader
 
                # File downloader

-               charset = locale.getdefaultlocale()[1]
-               if charset is None:
-                       charset = 'ascii'

                fd = FileDownloader({
                        'usenetrc': opts.usenetrc,
                        'username': opts.username,
                        'password': opts.password,
                fd = FileDownloader({
                        'usenetrc': opts.usenetrc,
                        'username': opts.username,
                        'password': opts.password,

-                       'quiet': (opts.quiet or opts.geturl or opts.gettitle),
+                       'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription),

                        'forceurl': opts.geturl,
                        'forcetitle': opts.gettitle,
                        'forceurl': opts.geturl,
                        'forcetitle': opts.gettitle,

-                       'simulate': (opts.simulate or opts.geturl or opts.gettitle),
+                       'forcethumbnail': opts.getthumbnail,
+                       'forcedescription': opts.getdescription,
+                       'simulate': (opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription),

                        'format': opts.format,
                        'format': opts.format,

-                       'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(charset))
+                       '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.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,
                                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 == '-',

                        })
                        })

+               fd.add_info_extractor(youtube_search_ie)

                fd.add_info_extractor(youtube_pl_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(metacafe_ie)

+               fd.add_info_extractor(dailymotion_ie)

                fd.add_info_extractor(youtube_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)
+
+               # This must come last since it's the
+               # fallback if none of the others work
+               fd.add_info_extractor(generic_ie)
+
+               # 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')
+                       else:
+                               sys.exit()

                retcode = fd.download(all_urls)
                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')
+

                sys.exit(retcode)
 
        except DownloadError:
                sys.exit(retcode)
 
        except DownloadError: