Fork of nicovideo-dl(https://osdn.jp/projects/nicovideo-dl/). Made for private using purpose

nicovideo-dl

#!/usr/bin/env python
# -*- coding: utf-8 -*-
#
# Copyright (c) 2009 Keiichiro Nagano
# Copyright (c) 2009 Kimura Youichi
# Copyright (c) 2006-2008 Ricardo Garcia Gonzalez
# Copyright (c) 2008 Ying-Chun Liu (PaulLiu)
#
# 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 sys
import os
import re
import socket
import string
import sys
import time
import urllib2
import cgi
import codecs
import xml.parsers.expat

# Global constants
const_version = '2011.02.08'
const_project_url = 'http://sourceforge.jp/projects/nicovideo-dl'

const_1k = 1024
const_initial_block_size = 10 * const_1k
const_epsilon = 0.0001
const_timeout = 120

const_video_url_str = 'http://www.nicovideo.jp/watch/%s'
const_video_url_re = re.compile(r'^((?:http://)?(?:\w+\.)?(?:nicovideo\.jp/(?:v/|(?:watch(?:\.php)?))?/)?(\w+))')
const_login_url_str = 'https://secure.nicovideo.jp/secure/login?site=niconico'
const_login_post_str = 'current_form=login&mail=%s&password=%s&login_submit=Log+In'
const_url_url_param_re = re.compile(r"url[=](http[^&]*)")
const_video_url_info_str = 'http://www.nicovideo.jp/api/getflv?v=%s&as3=1'
const_video_title_re = re.compile(r'<title>(.*)</title>', re.M | re.I)
const_video_type_re = re.compile(r'^http://.*\.nicovideo\.jp/smile\?(.*?)=.*')

const_comment_getthreadkey_url_str = 'http://flapi.nicovideo.jp/api/getthreadkey?thread=%s'
const_comment_request_str = '<thread thread="%s" version="20061206" res_from="-1000" user_id="%s"%s/>'

# Print error message, followed by standard advice information, and then exit
def error_advice_exit(error_text):
        print('Error: %s.\n' % error_text)
	exit()

# Wrapper to create custom requests with typical headers
def request_create(url, extra_headers, post_data=None):
	retval = urllib2.Request(url)
	if post_data is not None:
		retval.add_data(post_data)
	retval.add_header('User-Agent', 'nicovideo-dl/%s (%s)' % (const_version, const_project_url))
	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')
	if extra_headers is not None:
		for header in extra_headers:
			retval.add_header(header[0], header[1])
	return retval

# Perform a request, process headers and return response
def perform_request(url, headers=None, data=None):
	request = request_create(url, headers, data)
	response = urllib2.urlopen(request)
	return response

# Title string normalization
def title_string_norm(title):
	title_s = unicode(title.decode('utf-8', 'ignore'))
	for title_p in [u'‐ニコニコ動画(SP1)',
			u'‐ニコニコ動画(夏)',
			u'‐ニコニコ動画(秋)', # as of Oct 2008
			u'‐ニコニコ動画(冬)', # as of 5 Dec 2008
			u'‐ニコニコ動画(ββ)', # as of 12 Dec 2008
			u'‐ニコニコ動画(9)', # as of 29 Oct 2009
			u'‐ ニコニコ動画(原宿)', # as of 29 Oct 2010
			]:
		if (title_s.endswith(title_p)):
			title_s = title_s[:title_s.rfind(title_p)]
			break
	title_s = title_s.replace(os.sep, u'%')
	title_s = u'_'.join(title_s.split())
	title_s = title_s.encode('utf-8','ignore')
	return title_s

# 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:
		response = perform_request(url, data=post_data)
		data = response.read()
		if return_data_flag:
			return data, response
		return None

	except (urllib2.URLError, ValueError, httplib.HTTPException, TypeError, socket.error):
		error_advice_exit(step_error)

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

# Generic extract step
def extract_step(step_title, step_error, regexp, data):
	try:
		match = regexp.search(data)
		
		if match is None:
			error_advice_exit(step_error)
		
		extracted_data = match.group(1)
		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 < const_epsilon:
		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):
	dif = now - start
	if current == 0 or dif < const_epsilon:
		return '--:--'
	rate = float(current) / dif
	eta = long((total - current) / rate)
	(eta_mins, eta_secs) = divmod(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):
	dif = now - start
	if bytes == 0 or dif < const_epsilon:
		return 'N/A b'
	return format_bytes(float(bytes) / dif)

# Set socket timeout
socket.setdefaulttimeout(const_timeout)

args = sys.argv
# Get account information if any
video_url_cmdl = args[3]
account_username = args[1]
account_password = args[2]

# Install cookie and proxy handlers
urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler()))
urllib2.install_opener(urllib2.build_opener(urllib2.HTTPCookieProcessor()))

# Log in
if account_username is not None:
	url = const_login_url_str
	post = const_login_post_str % (account_username, account_password)
	download_step(False, 'Logging in', 'unable to log in', url, post)

# Verify video URL format and convert to "standard" format
video_url_mo = const_video_url_re.match(video_url_cmdl)
print video_url_mo
if video_url_mo is None:
        sys.exit('Error: URL does not seem to be a niconico 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

video_extension = '.flv'

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

# Reconvert URL if redirected
if response.geturl() != video_url:
        video_url_id = const_video_url_re.match(response.geturl()).group(2)
        video_url = const_video_url_str % video_url_id

# Extract video title if needed
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_info = const_video_url_info_str % video_url_id
video_info_data, response = download_step(True, 'Retrieving info data', 'unable to retrieve video webpage', video_url_info)
video_url_url_param = cgi.parse_qs(video_info_data)
print(video_url_url_param)
if (video_url_url_param.has_key("url")):
        video_url_url_param=video_url_url_param["url"][0]
else:
        error_advice_exit('cannot extract url parameter')
video_url_real = (video_url_url_param)

# Extract video type and modify video_extension
video_type_mo = const_video_type_re.match(video_url_real)
if (video_type_mo):
        if video_type_mo.group(1) == "s":
                video_extension = ".swf"
        elif video_type_mo.group(1) == "m":
                video_extension = ".mp4"

# Rebuild filename if needed
video_filename = '%s%s' % (video_url_id, video_extension)

# Retrieve video data
try:
        video_data = perform_request(video_url_real)
        
        try:
                video_file = open(video_filename, 'wb')
        except (IOError, OSError):
                sys.exit('Error: unable to open "%s" for writing.' % video_filename)
        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)

                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 amount of data')
        
        video_file.close()

except (urllib2.URLError, ValueError, httplib.HTTPException, TypeError, socket.error):
        error_advice_exit('unable to download video data')

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