用命令行下载 Youtube 上的视频（zt）

CODE:

#!/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 sys
import optparse
import httplib
import urllib2
import re
import string
import os
import time

# First off, check Python and refuse to run
if sys.hexversion < 0x020400f0:
        sys.exit('Error: Python 2.4 or later needed to run the program')

# 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'<title>YouTube - ([^<]*)</title>', 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 temporal 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 not data is 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

        except (urllib2.URLError, ValueError, httplib.HTTPException, TypeError):
                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, 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 = '2007.01.01'
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_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 not cmdl_opts.outfile is None and cmdl_opts.simulate:
        sys.stderr.write('Warning: video file name given but will not be used.\n')

if not cmdl_opts.outfile is None and cmdl_opts.use_title:
        sys.exit('Error: using the video title conflicts with using a given file name.')

# Verify both or none present
if ((cmdl_opts.username is None and not cmdl_opts.password is None) or
    (not cmdl_opts.username is None and cmdl_opts.password is None)):
        sys.exit('Error: both username and password must be given, or none.')

# 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:
        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 not cmdl_opts.username is None:
        url = const_login_url_str % video_url_id
        post = const_login_post_str % (video_url_id, cmdl_opts.username, cmdl_opts.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:
        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())

        # Abort here if in simulate mode
        if cmdl_opts.simulate:
                sys.exit()

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

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

# Finish
sys.exit()