X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/2c7340935c5a1d278a0d4b141b0e27b4c3218946..7e9c858ce0f2ba4d261737f5566f927487d9f917:/youtube-dl?ds=sidebyside
diff --git a/youtube-dl b/youtube-dl
index 6d53fa3..43566b6 100755
--- a/youtube-dl
+++ b/youtube-dl
@@ -1,328 +1,1849 @@
#!/usr/bin/env python
-#
-# Copyright (c) 2006 Ricardo Garcia Gonzalez
-#
-# Permission is hereby granted, free of charge, to any person obtaining a
-# copy of this software and associated documentation files (the "Software"),
-# to deal in the Software without restriction, including without limitation
-# the rights to use, copy, modify, merge, publish, distribute, sublicense,
-# and/or sell copies of the Software, and to permit persons to whom the
-# Software is furnished to do so, subject to the following conditions:
-#
-# The above copyright notice and this permission notice shall be included
-# in all copies or substantial portions of the Software.
-#
-# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
-# THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
-# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
-# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
-# OTHER DEALINGS IN THE SOFTWARE.
-#
-# Except as contained in this notice, the name(s) of the above copyright
-# holders shall not be used in advertising or otherwise to promote the
-# sale, use or other dealings in this Software without prior written
-# authorization.
-#
-import getpass
+# -*- coding: utf-8 -*-
+# Author: Ricardo Garcia Gonzalez
+# Author: Danny Colligan
+# Author: Benjamin Johnson
+# License: Public domain code
+import htmlentitydefs
import httplib
+import locale
+import math
import netrc
-import optparse
import os
+import os.path
import re
import socket
import string
+import subprocess
import sys
import time
+import urllib
import urllib2
-# Global constants
-const_video_url_str = 'http://www.youtube.com/watch?v=%s'
-const_video_url_re = re.compile(r'(?:http://)?(?:www\d*\.)?youtube\.com/(?:v/|(?:watch(?:\.php)?)?\?v=)([^&]+).*')
-const_login_url_str = 'http://www.youtube.com/login?next=/watch%%3Fv%%3D%s'
-const_login_post_str = 'current_form=loginForm&next=%%2Fwatch%%3Fv%%3D%s&username=%s&password=%s&action_login=Log+In'
-const_age_url_str = 'http://www.youtube.com/verify_age?next_url=/watch%%3Fv%%3D%s'
-const_age_post_str = 'next_url=%%2Fwatch%%3Fv%%3D%s&action_confirm=Confirm'
-const_video_url_params_re = re.compile(r'player2\.swf\?([^"]+)"', re.M)
-const_video_url_real_str = 'http://www.youtube.com/get_video?%s'
-const_video_title_re = re.compile(r'YouTube - ([^<]*)', re.M | re.I)
-const_1k = 1024
-const_initial_block_size = 10 * const_1k
-
-# Print error message, followed by standard advice information, and then exit
-def error_advice_exit(error_text):
- sys.stderr.write('Error: %s.\n' % error_text)
- sys.stderr.write('Try again several times. It may be a temporary problem.\n')
- sys.stderr.write('Other typical problems:\n\n')
- sys.stderr.write('\tVideo no longer exists.\n')
- sys.stderr.write('\tVideo requires age confirmation but you did not provide an account.\n')
- sys.stderr.write('\tYou provided the account data, but it is not valid.\n')
- sys.stderr.write('\tThe connection was cut suddenly for some reason.\n')
- sys.stderr.write('\tYouTube changed their system, and the program no longer works.\n')
- sys.stderr.write('\nTry to confirm you are able to view the video using a web browser.\n')
- sys.stderr.write('Use the same video URL and account information, if needed, with this program.\n')
- sys.stderr.write('When using a proxy, make sure http_proxy has http://host:port format.\n')
- sys.stderr.write('Try again several times and contact me if the problem persists.\n')
- sys.exit('\n')
-
-# Wrapper to create custom requests with typical headers
-def request_create(url, data=None):
- retval = urllib2.Request(url)
- if data is not None:
- retval.add_data(data)
- # Try to mimic Firefox, at least a little bit
- retval.add_header('User-Agent', 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1) Gecko/20061010 Firefox/2.0')
- retval.add_header('Accept-Charset', 'ISO-8859-1,utf-8;q=0.7,*;q=0.7')
- retval.add_header('Accept', 'text/xml,application/xml,application/xhtml+xml,text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5')
- retval.add_header('Accept-Language', 'en-us,en;q=0.5')
- return retval
-
-# Perform a request, process headers and return response
-def perform_request(url, data=None):
- request = request_create(url, data)
- response = urllib2.urlopen(request)
- return response
-
-# Convert bytes to KiB
-def to_k(bytes):
- global const_1k
- return bytes / const_1k
-
-# Conditional print
-def cond_print(str):
- global cmdl_opts
- if not cmdl_opts.quiet:
- sys.stdout.write(str)
- sys.stdout.flush()
-
-# Title string normalization
-def title_string_norm(title):
- title = ''.join((x in string.ascii_letters or x in string.digits) and x or ' ' for x in title)
- title = '_'.join(title.split())
- title = title.lower()
- return title
-
-# Generic download step
-def download_step(return_data_flag, step_title, step_error, url, post_data=None):
- try:
- cond_print('%s... ' % step_title)
- data = perform_request(url, post_data).read()
- cond_print('done.\n')
- if return_data_flag:
- return data
- return None
+# 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
- except (urllib2.URLError, ValueError, httplib.HTTPException, TypeError, socket.error):
- cond_print('failed.\n')
- error_advice_exit(step_error)
+std_headers = {
+ 'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.2) Gecko/20100115 Firefox/3.6',
+ 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
+ 'Accept': 'text/xml,application/xml,application/xhtml+xml,text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5',
+ 'Accept-Language': 'en-us,en;q=0.5',
+}
- except KeyboardInterrupt:
- sys.exit('\n')
+simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii')
-# Generic extract step
-def extract_step(step_title, step_error, regexp, data):
- try:
- cond_print('%s... ' % step_title)
- match = regexp.search(data)
-
- if match is None:
- cond_print('failed.\n')
- error_advice_exit(step_error)
-
- extracted_data = match.group(1)
- cond_print('done.\n')
- return extracted_data
+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.
- except KeyboardInterrupt:
- sys.exit('\n')
-
-# Calculate new block size based on previous block size
-def new_block_size(before, after, bytes):
- new_min = max(bytes / 2, 1)
- new_max = max(bytes * 2, 1)
- dif = after - before
- if dif < 0.0001:
- return new_max
- rate = int(bytes / dif)
- if rate > new_max:
- return new_max
- if rate < new_min:
- return new_min
- return rate
-
-# Create the command line options parser and parse command line
-cmdl_usage = 'usage: %prog [options] video_url'
-cmdl_version = '2007.02.18'
-cmdl_parser = optparse.OptionParser(usage=cmdl_usage, version=cmdl_version, conflict_handler='resolve')
-cmdl_parser.add_option('-h', '--help', action='help', help='print this help text and exit')
-cmdl_parser.add_option('-v', '--version', action='version', help='print program version and exit')
-cmdl_parser.add_option('-u', '--username', dest='username', metavar='USERNAME', help='account username')
-cmdl_parser.add_option('-p', '--password', dest='password', metavar='PASSWORD', help='account password')
-cmdl_parser.add_option('-o', '--output', dest='outfile', metavar='FILE', help='output video file name')
-cmdl_parser.add_option('-q', '--quiet', action='store_true', dest='quiet', help='activates quiet mode')
-cmdl_parser.add_option('-s', '--simulate', action='store_true', dest='simulate', help='do not download video')
-cmdl_parser.add_option('-t', '--title', action='store_true', dest='use_title', help='use title in file name')
-cmdl_parser.add_option('-n', '--netrc', action='store_true', dest='use_netrc', help='use .netrc authentication data')
-(cmdl_opts, cmdl_args) = cmdl_parser.parse_args()
-
-# Get video URL
-if len(cmdl_args) != 1:
- cmdl_parser.print_help()
- sys.exit('\n')
-video_url_cmdl = cmdl_args[0]
-
-# Verify video URL format and convert to "standard" format
-video_url_mo = const_video_url_re.match(video_url_cmdl)
-if video_url_mo is None:
- sys.exit('Error: URL does not seem to be a youtube video URL. If it is, report a bug.')
-video_url_id = video_url_mo.group(1)
-video_url = const_video_url_str % video_url_id
-
-# Check conflicting options
-if cmdl_opts.outfile is not None and cmdl_opts.simulate:
- sys.stderr.write('Warning: video file name given but will not be used.\n')
-
-if cmdl_opts.outfile is not None and cmdl_opts.use_title:
- sys.exit('Error: using the video title conflicts with using a given file name.')
-
-if cmdl_opts.use_netrc and cmdl_opts.password is not None:
- sys.exit('Error: using netrc conflicts with giving command line password.')
-
-# Incorrect option formatting
-if cmdl_opts.username is None and cmdl_opts.password is not None:
- sys.exit('Error: password give but username is missing.')
-
-# Get account information if any
-account_username = None
-account_password = None
-
-if cmdl_opts.use_netrc:
- try:
- info = netrc.netrc().authenticators('youtube')
- if info is None:
- sys.exit('Error: no authenticators for machine youtube.')
- netrc_username = info[0]
- netrc_password = info[2]
- except IOError:
- sys.exit('Error: unable to read .netrc file.')
- except netrc.NetrcParseError:
- sys.exit('Error: unable to parse .netrc file.')
-
-if cmdl_opts.password is not None:
- account_username = cmdl_opts.username
- account_password = cmdl_opts.password
-else:
- if cmdl_opts.username is not None and cmdl_opts.use_netrc:
- if cmdl_opts.username != netrc_username:
- sys.exit('Error: conflicting username from .netrc and command line options.')
- account_username = cmdl_opts.username
- account_password = netrc_password
- elif cmdl_opts.username is not None:
- account_username = cmdl_opts.username
- account_password = getpass.getpass('Type YouTube password and press return: ')
- elif cmdl_opts.use_netrc:
- if len(netrc_username) == 0:
- sys.exit('Error: empty username in .netrc file.')
- account_username = netrc_username
- account_password = netrc_password
-
-# Get output file name
-if cmdl_opts.outfile is None:
- video_filename = '%s.flv' % video_url_id
-else:
- video_filename = cmdl_opts.outfile
-
-# Check name
-if not video_filename.lower().endswith('.flv'):
- sys.stderr.write('Warning: video file name does not end in .flv\n')
-
-# Test writable file
-if not cmdl_opts.simulate:
+ 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:
- disk_test = open(video_filename, 'wb')
- disk_test.close()
+ if filename == u'-':
+ 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)
- except (OSError, IOError):
- sys.exit('Error: unable to open %s for writing.' % video_filename)
+ # An exception here should be caught in the caller
+ stream = open(filename, open_mode)
+ return (stream, filename)
-# Install cookie and proxy handlers
-urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler()))
-urllib2.install_opener(urllib2.build_opener(urllib2.HTTPCookieProcessor()))
-# Log in and confirm age if needed
-if account_username is not None:
- url = const_login_url_str % video_url_id
- post = const_login_post_str % (video_url_id, account_username, account_password)
- download_step(False, 'Logging in', 'unable to log in', url, post)
+class DownloadError(Exception):
+ """Download Error exception.
+
+ This exception may be thrown by FileDownloader objects if they are not
+ configured to continue on errors. They will contain the appropriate
+ error message.
+ """
+ pass
- url = const_age_url_str % video_url_id
- post = const_age_post_str % video_url_id
- download_step(False, 'Confirming age', 'unable to confirm age', url, post)
+class SameFileError(Exception):
+ """Same File exception.
-# Retrieve video webpage
-video_webpage = download_step(True, 'Retrieving video webpage', 'unable to retrieve video webpage', video_url)
+ This exception will be thrown by FileDownloader objects if they detect
+ multiple files would have to be downloaded to the same file on disk.
+ """
+ pass
-# Extract video title if needed
-if cmdl_opts.use_title:
- video_title = extract_step('Extracting video title', 'unable to extract video title', const_video_title_re, video_webpage)
+class PostProcessingError(Exception):
+ """Post Processing exception.
-# Extract needed video URL parameters
-video_url_params = extract_step('Extracting video URL parameters', 'unable to extract URL parameters', const_video_url_params_re, video_webpage)
-video_url_real = const_video_url_real_str % video_url_params
+ This exception may be raised by PostProcessor's .run() method to
+ indicate an error in the postprocessing task.
+ """
+ pass
-# Retrieve video data
-try:
- video_data = perform_request(video_url_real)
- cond_print('Video data found at %s\n' % video_data.geturl())
+class UnavailableFormatError(Exception):
+ """Unavailable Format exception.
- # Abort here if in simulate mode
- if cmdl_opts.simulate:
- sys.exit()
+ This exception will be thrown when a video is requested
+ in a format that is not available for that video.
+ """
+ pass
- video_file = open(video_filename, 'wb')
- try:
- video_len_str = '%sk' % to_k(long(video_data.info()['Content-length']))
- except KeyError:
- video_len_str = '(unknown)'
-
- byte_counter = 0
- block_size = const_initial_block_size
- while True:
- cond_print('\rRetrieving video data... %sk of %s ' % (to_k(byte_counter), video_len_str))
- before = time.time()
- video_block = video_data.read(block_size)
- after = time.time()
- dl_bytes = len(video_block)
- if dl_bytes == 0:
- break
- byte_counter += dl_bytes
- video_file.write(video_block)
- block_size = new_block_size(before, after, dl_bytes)
-
- video_file.close()
- cond_print('done.\n')
- cond_print('Video data saved to %s\n' % video_filename)
-
-except (urllib2.URLError, ValueError, httplib.HTTPException, TypeError, socket.error):
- cond_print('failed.\n')
- error_advice_exit('unable to download video data')
-
-except KeyboardInterrupt:
- sys.exit('\n')
-
-# Rename video file if needed
-if cmdl_opts.use_title:
- try:
- final_filename = '%s-%s.flv' % (title_string_norm(video_title), video_url_id)
- os.rename(video_filename, final_filename)
- cond_print('Video file renamed to %s\n' % final_filename)
+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.
+
+ File downloader objects are the ones responsible of downloading the
+ actual video file and writing it to disk if the user has requested
+ it, among some other tasks. In most cases there should be one per
+ program. As, given a video URL, the downloader doesn't know how to
+ extract all the needed information, task that InfoExtractors do, it
+ has to pass the URL to one of them.
+
+ 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 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
+ 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:
+
+ 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.
+ nooverwrites: Prevent overwriting files.
+ continuedl: Try to continue downloads if possible.
+ noprogress: Do not print the progress bar.
+ """
+
+ params = None
+ _ies = []
+ _pps = []
+ _download_retcode = None
+ _num_downloads = None
+
+ def __init__(self, params):
+ """Create a FileDownloader object with the given options."""
+ self._ies = []
+ self._pps = []
+ self._download_retcode = 0
+ self._num_downloads = 0
+ self.params = params
- except OSError:
- sys.stderr.write('Warning: unable to rename file.\n')
+ @staticmethod
+ def pmkdir(filename):
+ """Create directory components in filename. Similar to Unix "mkdir -p"."""
+ components = filename.split(os.sep)
+ aggregate = [os.sep.join(components[0:x]) for x in xrange(1, len(components))]
+ aggregate = ['%s%s' % (x, os.sep) for x in aggregate] # Finish names with separator
+ for dir in aggregate:
+ if not os.path.exists(dir):
+ os.mkdir(dir)
+
+ @staticmethod
+ def format_bytes(bytes):
+ if bytes is None:
+ return 'N/A'
+ if type(bytes) is str:
+ bytes = float(bytes)
+ if bytes == 0.0:
+ exponent = 0
+ else:
+ exponent = long(math.log(bytes, 1024.0))
+ suffix = 'bkMGTPEZY'[exponent]
+ converted = float(bytes) / float(1024**exponent)
+ return '%.2f%s' % (converted, suffix)
- except KeyboardInterrupt:
- sys.exit('\n')
+ @staticmethod
+ def calc_percent(byte_counter, data_len):
+ if data_len is None:
+ return '---.-%'
+ return '%6s' % ('%3.1f%%' % (float(byte_counter) / float(data_len) * 100.0))
+
+ @staticmethod
+ def calc_eta(start, now, total, current):
+ if total is None:
+ return '--:--'
+ dif = now - start
+ if current == 0 or dif < 0.001: # One millisecond
+ return '--:--'
+ rate = float(current) / dif
+ eta = long((float(total) - float(current)) / rate)
+ (eta_mins, eta_secs) = divmod(eta, 60)
+ if eta_mins > 99:
+ return '--:--'
+ return '%02d:%02d' % (eta_mins, eta_secs)
+
+ @staticmethod
+ def calc_speed(start, now, bytes):
+ dif = now - start
+ if bytes == 0 or dif < 0.001: # One millisecond
+ return '%10s' % '---b/s'
+ return '%10s' % ('%s/s' % FileDownloader.format_bytes(float(bytes) / dif))
+
+ @staticmethod
+ def best_block_size(elapsed_time, bytes):
+ 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 long(new_max)
+ rate = bytes / elapsed_time
+ if rate > new_max:
+ return long(new_max)
+ if rate < new_min:
+ return long(new_min)
+ return long(rate)
+
+ @staticmethod
+ def parse_bytes(bytestr):
+ """Parse a string indicating a byte quantity into a long integer."""
+ matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr)
+ if matchobj is None:
+ return None
+ number = float(matchobj.group(1))
+ multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
+ return long(round(number * multiplier))
+
+ @staticmethod
+ def verify_url(url):
+ """Verify a URL is valid and data could be downloaded. Return real data URL."""
+ request = urllib2.Request(url, None, std_headers)
+ data = urllib2.urlopen(request)
+ data.read(1)
+ url = data.geturl()
+ data.close()
+ return url
+
+ def add_info_extractor(self, ie):
+ """Add an InfoExtractor object to the end of the list."""
+ self._ies.append(ie)
+ ie.set_downloader(self)
+
+ def add_post_processor(self, pp):
+ """Add a PostProcessor object to the end of the chain."""
+ self._pps.append(pp)
+ pp.set_downloader(self)
+
+ def to_stdout(self, message, skip_eol=False, ignore_encoding_errors=False):
+ """Print message to stdout if not in quiet mode."""
+ try:
+ if not self.params.get('quiet', False):
+ print (u'%s%s' % (message, [u'\n', u''][skip_eol])).encode(preferredencoding()),
+ sys.stdout.flush()
+ except (UnicodeEncodeError), err:
+ if not ignore_encoding_errors:
+ raise
+
+ def to_stderr(self, message):
+ """Print message to stderr."""
+ print >>sys.stderr, message.encode(preferredencoding())
+
+ def fixed_template(self):
+ """Checks if the output template is fixed."""
+ 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
+ not when errors are found, after printing the message.
+ """
+ if message is not None:
+ self.to_stderr(message)
+ if not self.params.get('ignoreerrors', False):
+ raise DownloadError(message)
+ self._download_retcode = 1
+
+ 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)
+ if rate_limit is None or byte_counter == 0:
+ return
+ now = time.time()
+ elapsed = now - start_time
+ if elapsed <= 0.0:
+ return
+ speed = float(byte_counter) / elapsed
+ if speed > rate_limit:
+ time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit)
+
+ def report_destination(self, filename):
+ """Report destination filename."""
+ self.to_stdout(u'[download] Destination: %s' % filename, ignore_encoding_errors=True)
+
+ def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
+ """Report download progress."""
+ if self.params.get('noprogress', False):
+ return
+ self.to_stdout(u'\r[download] %s of %s at %s ETA %s' %
+ (percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
+
+ def report_resuming_byte(self, resume_len):
+ """Report attemtp to resume at given byte."""
+ self.to_stdout(u'[download] Resuming download at byte %s' % resume_len)
+
+ def report_file_already_downloaded(self, file_name):
+ """Report file has already been fully downloaded."""
+ try:
+ self.to_stdout(u'[download] %s has already been downloaded' % file_name)
+ except (UnicodeEncodeError), err:
+ self.to_stdout(u'[download] The file has already been downloaded')
+
+ def report_unable_to_resume(self):
+ """Report it was impossible to resume download."""
+ self.to_stdout(u'[download] Unable to resume')
+
+ def report_finish(self):
+ """Report download finished."""
+ if self.params.get('noprogress', False):
+ self.to_stdout(u'[download] Download completed')
+ else:
+ self.to_stdout(u'')
+
+ 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):
+ # Verify URL if it's an HTTP one
+ if info_dict['url'].startswith('http'):
+ try:
+ self.verify_url(info_dict['url'].encode('utf-8')).decode('utf-8')
+ except (OSError, IOError, urllib2.URLError, httplib.HTTPException, socket.error), err:
+ raise UnavailableFormatError
+
+ # 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')
+
+ return
+
+ try:
+ template_dict = dict(info_dict)
+ template_dict['epoch'] = unicode(long(time.time()))
+ template_dict['ord'] = unicode('%05d' % self._num_downloads)
+ filename = self.params['outtmpl'] % template_dict
+ except (ValueError, KeyError), err:
+ self.trouble('ERROR: invalid output template or system charset: %s' % str(err))
+ if self.params.get('nooverwrites', False) and os.path.exists(filename):
+ self.to_stderr(u'WARNING: file exists: %s; skipping' % filename)
+ return
+
+ try:
+ self.pmkdir(filename)
+ except (OSError, IOError), err:
+ self.trouble('ERROR: unable to create directories: %s' % str(err))
+ return
+
+ try:
+ success = self._do_download(filename, info_dict['url'].encode('utf-8'))
+ except (OSError, IOError), err:
+ raise UnavailableFormatError
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self.trouble('ERROR: unable to download video data: %s' % str(err))
+ return
+ except (ContentTooShortError, ), err:
+ self.trouble('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('ERROR: postprocessing: %s' % str(err))
+ return
+
+ def download(self, url_list):
+ """Download a given list of URLs."""
+ if len(url_list) > 1 and self.fixed_template():
+ raise SameFileError(self.params['outtmpl'])
+
+ 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
+
+ # Suitable InfoExtractor found
+ suitable_found = True
+
+ # Extract information from URL and process it
+ ie.extract(url)
+
+ # Suitable InfoExtractor had been found; go to next URL
+ break
+
+ if not suitable_found:
+ self.trouble('ERROR: no suitable InfoExtractor: %s' % url)
+
+ return self._download_retcode
+
+ def post_process(self, filename, ie_info):
+ """Run the postprocessing chain on the given file."""
+ info = dict(ie_info)
+ info['filepath'] = filename
+ for pp in self._pps:
+ info = pp.run(info)
+ if info is None:
+ break
+
+ def _download_with_rtmpdump(self, filename, url):
+ self.report_destination(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', '-r', url, '-o', filename]
+ retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)])
+ while retval == 2 or retval == 1:
+ self.to_stdout(u'\r[rtmpdump] %s bytes' % os.path.getsize(filename), skip_eol=True)
+ time.sleep(2.0) # This seems to be needed
+ retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])
+ if retval == 0:
+ self.to_stdout(u'\r[rtmpdump] %s bytes' % os.path.getsize(filename))
+ return True
+ else:
+ self.trouble('\nERROR: rtmpdump exited with code %d' % retval)
+ return False
+
+ def _do_download(self, filename, url):
+ # Attempt to download using rtmpdump
+ if url.startswith('rtmp'):
+ return self._download_with_rtmpdump(filename, url)
+
+ stream = None
+ open_mode = 'wb'
+ basic_request = urllib2.Request(url, None, std_headers)
+ request = urllib2.Request(url, None, std_headers)
+
+ # Establish possible resume length
+ if os.path.isfile(filename):
+ resume_len = os.path.getsize(filename)
+ 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'
+
+ # Establish connection
+ try:
+ data = urllib2.urlopen(request)
+ except (urllib2.HTTPError, ), err:
+ if err.code != 416: # 416 is 'Requested range not satisfiable'
+ raise
+ # Unable to resume
+ data = urllib2.urlopen(basic_request)
+ content_length = data.info()['Content-Length']
+
+ if content_length is not None and long(content_length) == resume_len:
+ # Because the file had already been fully downloaded
+ self.report_file_already_downloaded(filename)
+ return True
+ else:
+ # Because the server didn't let us
+ self.report_unable_to_resume()
+ open_mode = 'wb'
+
+ 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:
+ # Download and write
+ before = time.time()
+ data_block = data.read(block_size)
+ after = time.time()
+ data_block_len = len(data_block)
+ if data_block_len == 0:
+ break
+ byte_counter += data_block_len
+
+ # Open file just in time
+ if stream is None:
+ try:
+ (stream, filename) = sanitize_open(filename, open_mode)
+ self.report_destination(filename)
+ self._num_downloads += 1
+ except (OSError, IOError), err:
+ self.trouble('ERROR: unable to open for writing: %s' % str(err))
+ return False
+ stream.write(data_block)
+ 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:
+ raise ContentTooShortError(byte_counter, long(data_len))
+ return True
+
+class InfoExtractor(object):
+ """Information Extractor class.
+
+ 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. 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.
+ url: Final video URL.
+ uploader: Nickname of the video uploader.
+ title: Literal title.
+ stitle: Simplified title.
+ ext: Video filename extension.
+ format: Video format.
+
+ Subclasses of this one should re-define the _real_initialize() and
+ _real_extract() methods, as well as the suitable() static method.
+ Probably, they should also be instantiated and added to the main
+ downloader.
+ """
+
+ _ready = False
+ _downloader = None
+
+ def __init__(self, downloader=None):
+ """Constructor. Receives an optional downloader."""
+ self._ready = False
+ self.set_downloader(downloader)
+
+ @staticmethod
+ def suitable(url):
+ """Receives a URL and returns True if suitable for this IE."""
+ return False
+
+ def initialize(self):
+ """Initializes an instance (authentication, etc)."""
+ if not self._ready:
+ self._real_initialize()
+ self._ready = True
+
+ def extract(self, url):
+ """Extracts URL information and returns it in list of dicts."""
+ self.initialize()
+ return self._real_extract(url)
+
+ def set_downloader(self, downloader):
+ """Sets the downloader for this IE."""
+ self._downloader = downloader
+
+ def _real_initialize(self):
+ """Real initialization process. Redefine in subclasses."""
+ pass
+
+ def _real_extract(self, url):
+ """Real extraction process. Redefine in subclasses."""
+ pass
+
+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'
+ _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
+ _NETRC_MACHINE = 'youtube'
+ _available_formats = ['37', '22', '35', '18', '34', '5', '17', '13', None] # listed in order of priority for -b flag
+ _video_extensions = {
+ '13': '3gp',
+ '17': 'mp4',
+ '18': 'mp4',
+ '22': 'mp4',
+ '37': 'mp4',
+ }
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(YoutubeIE._VALID_URL, url) is not None)
+
+ def report_lang(self):
+ """Report attempt to set language."""
+ self._downloader.to_stdout(u'[youtube] Setting language')
+
+ def report_login(self):
+ """Report attempt to log in."""
+ self._downloader.to_stdout(u'[youtube] Logging in')
+
+ def report_age_confirmation(self):
+ """Report attempt to confirm age."""
+ self._downloader.to_stdout(u'[youtube] Confirming age')
+
+ def report_video_info_webpage_download(self, video_id):
+ """Report attempt to download video info webpage."""
+ self._downloader.to_stdout(u'[youtube] %s: Downloading video info webpage' % video_id)
+
+ def report_information_extraction(self, video_id):
+ """Report attempt to extract video information."""
+ self._downloader.to_stdout(u'[youtube] %s: Extracting video information' % video_id)
+
+ def report_unavailable_format(self, video_id, format):
+ """Report extracted video URL."""
+ self._downloader.to_stdout(u'[youtube] %s: Format %s not available' % (video_id, format))
+
+ def report_rtmp_download(self):
+ """Indicate the download will use the RTMP protocol."""
+ self._downloader.to_stdout(u'[youtube] RTMP download detected')
+
+ def _real_initialize(self):
+ if self._downloader is None:
+ return
+
+ username = None
+ password = None
+ downloader_params = self._downloader.params
+
+ # Attempt to use provided username and password or .netrc data
+ if downloader_params.get('username', None) is not None:
+ username = downloader_params['username']
+ password = downloader_params['password']
+ elif downloader_params.get('usenetrc', False):
+ try:
+ info = netrc.netrc().authenticators(self._NETRC_MACHINE)
+ if info is not None:
+ username = info[0]
+ password = info[2]
+ else:
+ raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
+ except (IOError, netrc.NetrcParseError), err:
+ self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))
+ return
+
+ # Set language
+ 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:
+ 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
+ login_form = {
+ 'current_form': 'loginForm',
+ 'next': '/',
+ 'action_login': 'Log In',
+ 'username': username,
+ 'password': password,
+ }
+ request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form), std_headers)
+ try:
+ self.report_login()
+ login_results = urllib2.urlopen(request).read()
+ if re.search(r'(?i)]* name="loginForm"', login_results) is not None:
+ self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password')
+ return
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err))
+ return
+
+ # Confirm age
+ age_form = {
+ 'next_url': '/',
+ 'action_confirm': 'Confirm',
+ }
+ request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form), std_headers)
+ try:
+ self.report_age_confirmation()
+ age_results = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), 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:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+ video_id = mobj.group(2)
+
+ # Downloader parameters
+ best_quality = False
+ all_formats = False
+ format_param = None
+ quality_index = 0
+ if self._downloader is not None:
+ params = self._downloader.params
+ format_param = params.get('format', None)
+ if format_param == '0':
+ format_param = self._available_formats[quality_index]
+ best_quality = True
+ elif format_param == '-1':
+ format_param = self._available_formats[quality_index]
+ all_formats = True
+
+ while True:
+ # Extension
+ video_extension = self._video_extensions.get(format_param, 'flv')
+
+ # Get video info
+ self.report_video_info_webpage_download(video_id)
+ for el_type in ['embedded', 'detailpage', 'vevo']:
+ video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s&el=%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
+ self.report_information_extraction(video_id)
+
+ # "t" param
+ if 'token' not in video_info:
+ # Attempt to see if YouTube has issued an error message
+ if 'reason' not in video_info:
+ self._downloader.trouble(u'ERROR: unable to extract "t" parameter for unknown reason')
+ stream = open('reportme-ydl-%s.dat' % time.time(), 'wb')
+ stream.write(video_info_webpage)
+ stream.close()
+ else:
+ reason = urllib.unquote_plus(video_info['reason'][0])
+ self._downloader.trouble(u'ERROR: YouTube said: %s' % reason.decode('utf-8'))
+ return
+ token = urllib.unquote_plus(video_info['token'][0])
+ video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&eurl=&el=detailpage&ps=default&gl=US&hl=en' % (video_id, token)
+ if format_param is not None:
+ video_real_url = '%s&fmt=%s' % (video_real_url, format_param)
+
+ # Check possible RTMP download
+ if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
+ self.report_rtmp_download()
+ video_real_url = video_info['conn'][0]
+
+ # uploader
+ 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
+ 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'_')
+
+ 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'),
+ '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')),
+ })
+
+ if all_formats:
+ if quality_index == len(self._available_formats) - 1:
+ # None left to get
+ return
+ else:
+ quality_index += 1
+ format_param = self._available_formats[quality_index]
+ if format_param == None:
+ return
+ continue
+
+ return
+
+ except UnavailableFormatError, err:
+ if best_quality or all_formats:
+ if quality_index == len(self._available_formats) - 1:
+ # I don't ever expect this to happen
+ if not all_formats:
+ self._downloader.trouble(u'ERROR: no known formats available for video')
+ return
+ else:
+ self.report_unavailable_format(video_id, format_param)
+ quality_index += 1
+ format_param = self._available_formats[quality_index]
+ if format_param == None:
+ return
+ continue
+ else:
+ self._downloader.trouble('ERROR: format not available for video')
+ return
+
+
+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):
+ InfoExtractor.__init__(self, downloader)
+ self._youtube_ie = youtube_ie
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(MetacafeIE._VALID_URL, url) is not None)
+
+ def report_disclaimer(self):
+ """Report disclaimer retrieval."""
+ self._downloader.to_stdout(u'[metacafe] Retrieving disclaimer')
+
+ def report_age_confirmation(self):
+ """Report attempt to confirm age."""
+ self._downloader.to_stdout(u'[metacafe] Confirming age')
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_stdout(u'[metacafe] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_stdout(u'[metacafe] %s: Extracting information' % video_id)
+
+ def _real_initialize(self):
+ # Retrieve disclaimer
+ request = urllib2.Request(self._DISCLAIMER, None, std_headers)
+ try:
+ self.report_disclaimer()
+ disclaimer = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % str(err))
+ return
+
+ # Confirm age
+ disclaimer_form = {
+ 'filters': '0',
+ 'submit': "Continue - I'm over 18",
+ }
+ 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:
+ 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:
+ 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:
+ self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1))
+ return
+
+ 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)
+ 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
+
+ # Extract URL, uploader and title from webpage
+ self.report_extraction(video_id)
+ mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract media URL')
+ return
+ mediaURL = urllib.unquote(mobj.group(1))
+
+ #mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
+ #if mobj is None:
+ # self._downloader.trouble(u'ERROR: unable to extract gdaKey')
+ # return
+ #gdaKey = mobj.group(1)
+ #
+ #video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
+
+ video_url = mediaURL
+
+ mobj = re.search(r'(?im)(.*) - Video', 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)
-# Finish
-sys.exit()
+ mobj = re.search(r'(?ms)By:\s*(.+?)<', webpage)
+ if mobj is None:
+ 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'),
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ 'format': u'NA',
+ })
+ except UnavailableFormatError:
+ self._downloader.trouble(u'ERROR: format not available for video')
+
+
+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):
+ InfoExtractor.__init__(self, downloader)
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(GoogleIE._VALID_URL, url) is not None)
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_stdout(u'[video.google] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_stdout(u'[video.google] %s: Extracting information' % video_id)
+
+ 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
+
+ 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'(.*)', 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)
+
+ try:
+ # Process video information
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url.decode('utf-8'),
+ 'uploader': u'NA',
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ 'format': u'NA',
+ })
+ except UnavailableFormatError:
+ self._downloader.trouble(u'ERROR: format not available for 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_stdout(u'[photobucket] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_stdout(u'[photobucket] %s: Extracting information' % video_id)
+
+ 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
+
+ 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'', 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'(.*) video by (.*) - Photobucket', 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,
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ 'format': u'NA',
+ })
+ except UnavailableFormatError:
+ self._downloader.trouble(u'ERROR: format not available for 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_stdout(u'[video.yahoo] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_stdout(u'[video.yahoo] %s: Extracting information' % video_id)
+
+ 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
+
+ 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)
+
+ # 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'', 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'