استخراج فایلهای ویدئویی از سایت youtube

[مهدی پیشگوی]

سلام من خودم تو کفش بودم 
ابتدا این اسکریپت رو دانلود کنید :

کد: [انتخاب]

#!/usr/bin/env python
#
# Copyright (c) 2006-2007 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
import httplib
import math
import netrc
import optparse
import os
import re
import socket
import string
import sys
import time
import urllib2

# Global constants
const_video_url_str = 'http://www.youtube.com/watch?v=%s'
const_video_url_re = re.compile(r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:v/|(?:watch(?:\.php)?)?\?(?:.+&)?v=))?([0-9A-Za-z_-]+)(?(1)[&/].*)?$')
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'', 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('* Video no longer exists.\n')
sys.stderr.write('* Video requires age confirmation but you did not provide an account.\n')
sys.stderr.write('* You provided the account data, but it is not valid.\n')
sys.stderr.write('* The connection was cut suddenly for some reason.\n')
sys.stderr.write('* YouTube 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

# Conditional print
def cond_print(str):
global cmdl_opts
if not (cmdl_opts.quiet or cmdl_opts.get_url):
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

# Title string minimal transformation
def title_string_touch(title):
return title.replace(os.sep, '%')

# 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

except (urllib2.URLError, ValueError, httplib.HTTPException, TypeError, socket.error):
cond_print('failed.\n')
error_advice_exit(step_error)

except KeyboardInterrupt:
sys.exit('\n')

# 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

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 / 2.0, 1.0)
new_max = max(bytes * 2.0, 1.0)
dif = after - before
if dif < 0.0001:
return int(new_max)
rate = bytes / dif
if rate > new_max:
return int(new_max)
if rate < new_min:
return int(new_min)
return int(rate)

# Get optimum 1k exponent to represent a number of bytes
def optimum_k_exp(num_bytes):
global const_1k
if num_bytes == 0:
return 0
return long(math.log(num_bytes, const_1k))

# Get optimum representation of number of bytes
def format_bytes(num_bytes):
global const_1k
try:
exp = optimum_k_exp(num_bytes)
suffix = 'bkMGTPEZY'[exp]
if exp == 0:
return '%s%s' % (num_bytes, suffix)
converted = float(num_bytes) / float(const_1k**exp)
return '%.2f%s' % (converted, suffix)
except IndexError:
sys.exit('Error: internal error formatting number of bytes.')

# Calculate ETA and return it in string format as MM:SS
def calc_eta(start, now, total, current):
if current == 0:
return '--:--'
rate = float(current) / (now - start)
eta = long((total - current) / rate)
eta_mins = eta / 60
eta_secs = eta % 60
if eta_mins > 99:
return '--:--'
return '%02d:%02d' % (eta_mins, eta_secs)

# Calculate speed and return it in string format
def calc_speed(start, now, bytes):
if bytes == 0:
return 'N/A b'
return format_bytes(float(bytes) / (now - start))

# Create the command line options parser and parse command line
cmdl_usage = 'usage: %prog [options] video_url'
cmdl_version = '2007.06.22'
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('-l', '--literal', action='store_true', dest='use_literal', help='use literal title in file name')
cmdl_parser.add_option('-n', '--netrc', action='store_true', dest='use_netrc', help='use .netrc authentication data')
cmdl_parser.add_option('-g', '--get-url', action='store_true', dest='get_url', help='print final video URL only')
cmdl_parser.add_option('-2', '--title-too', action='store_true', dest='get_title', help='used with -g, print title too')
(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(2)
video_url = const_video_url_str % video_url_id

# Check conflicting options
if cmdl_opts.outfile is not None and (cmdl_opts.simulate or cmdl_opts.get_url):
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 or cmdl_opts.use_literal):
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.')

if cmdl_opts.use_title and cmdl_opts.use_literal:
sys.exit('Error: cannot use title and literal title at the same time.')

if cmdl_opts.quiet and cmdl_opts.get_url:
sys.exit('Error: cannot be quiet and print final URL at the same time.')

# 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.')

if cmdl_opts.get_url is None and cmdl_opts.get_title is not None:
sys.exit('Error: getting title requires getting URL.')

# 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 or cmdl_opts.get_url):
try:
disk_test = open(video_filename, 'wb')
disk_test.close()

except (OSError, IOError):
sys.exit('Error: unable to open %s for writing.' % video_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)

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)

# Retrieve video webpage
video_webpage = download_step(True, 'Retrieving video webpage', 'unable to retrieve video webpage', video_url)

# Extract video title if needed
if cmdl_opts.use_title or cmdl_opts.use_literal or cmdl_opts.get_title:
video_title = extract_step('Extracting video title', 'unable to extract video title', const_video_title_re, video_webpage)

# 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

# Retrieve video data
try:
video_data = perform_request(video_url_real)
cond_print('Video data found at %s\n' % video_data.geturl())

if cmdl_opts.get_title:
print video_title

if cmdl_opts.get_url:
print video_data.geturl()

if cmdl_opts.simulate or cmdl_opts.get_url:
sys.exit()

video_file = open(video_filename, 'wb')
try:
video_len = long(video_data.info()['Content-length'])
video_len_str = format_bytes(video_len)
except KeyError:
video_len = None
video_len_str = 'N/A'

byte_counter = 0
block_size = const_initial_block_size
start_time = time.time()
while True:
if video_len is not None:
percent = float(byte_counter) / float(video_len) * 100.0
percent_str = '%.1f' % percent
eta_str = calc_eta(start_time, time.time(), video_len, byte_counter)
else:
percent_str = '---.-'
eta_str = '--:--'
counter = format_bytes(byte_counter)
speed_str = calc_speed(start_time, time.time(), byte_counter)
cond_print('\rRetrieving video data: %5s%% (%8s of %s) at %8s/s ETA %s ' % (percent_str, counter, video_len_str, speed_str, eta_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)

if video_len is not None and byte_counter != video_len:
error_advice_exit('server did not send the expected ammount of data')

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 or cmdl_opts.use_literal:
try:
if cmdl_opts.use_title:
prefix = title_string_norm(video_title)
else:
prefix = title_string_touch(video_title)
final_filename = '%s-%s.flv' % (prefix, video_url_id)
os.rename(video_filename, final_filename)
cond_print('Video file renamed to %s\n' % final_filename)

except OSError:
sys.stderr.write('Warning: unable to rename file.\n')

except KeyboardInterrupt:
sys.exit('\n')

# Finish
sys.exit()
بعدش از این اسکریپت که به زبان پایتون نوشته شده به همراه آدرس فایل تصویری استفاده کنین . اینو بگم که خودم تست نکردم
به مثالهای زیر دقت کنین :

کد: [انتخاب]

youtube-dl -o filename.flv "Entire path to youtube clip(ex:- http://www.youtube.com/watch?v=foobar ) where foobar would be actual code of the clip"
یا این مثال :

کد: [انتخاب]

youtube-dl -u username -p password "Entire path to youtube clip(ex:- http://www.youtube.com/watch?v=foobar ) where foobar would be actual code of the clip" -o filename.flv


[sorena]

ممنون مهدی جان ولی راه‌های ساده‌تری هم هست.
یکی استفاده از اکستنشن‌های فایرفاکس هست. کافیه در قسمت add on های فایرفاکس youtube رو جستجو کنید. بعضی از اکستنشن ها قابلیت امکان دانلود هر گونه فیلمی رو از هر سایتی رو دارند.
دومی استفاده از یک سری سایت های خاص هستند که امکان دانلود فیلم های youtube رو میدن.

کد: [انتخاب]

http://javimoya.com/blog/youtube_en.php
http://keepvid.com
http://www.youtubex.com/
http://www.viloader.net/


[مهدی پیشگوی]

تو علم کامپیوتر برای هیچ کاری یک راه وجود نداره .
ولی لذتش تو برنامه نویسی و اسکریپت نویسی هستش نه استفاده ( نظر شخصی من اینه )

[Mehdi]

و مثل همیشه میتونید از

کد: [انتخاب]

sudo apt-get install youtube-dl
هم استفاده کنید