| 1 |
#!/usr/bin/env python3 |
| 2 |
# -*- coding: utf-8 -*- |
| 3 |
# |
| 4 |
# Copyright (c) 2009 Keiichiro Nagano |
| 5 |
# Copyright (c) 2009 Kimura Youichi |
| 6 |
# Copyright (c) 2006-2008 Ricardo Garcia Gonzalez |
| 7 |
# Copyright (c) 2008 Ying-Chun Liu (PaulLiu) |
| 8 |
# |
| 9 |
# Permission is hereby granted, free of charge, to any person obtaining a |
| 10 |
# copy of this software and associated documentation files (the "Software"), |
| 11 |
# to deal in the Software without restriction, including without limitation |
| 12 |
# the rights to use, copy, modify, merge, publish, distribute, sublicense, |
| 13 |
# and/or sell copies of the Software, and to permit persons to whom the |
| 14 |
# Software is furnished to do so, subject to the following conditions: |
| 15 |
# |
| 16 |
# The above copyright notice and this permission notice shall be included |
| 17 |
# in all copies or substantial portions of the Software. |
| 18 |
# |
| 19 |
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR |
| 20 |
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, |
| 21 |
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL |
| 22 |
# THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR |
| 23 |
# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, |
| 24 |
# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR |
| 25 |
# OTHER DEALINGS IN THE SOFTWARE. |
| 26 |
# |
| 27 |
# Except as contained in this notice, the name(s) of the above copyright |
| 28 |
# holders shall not be used in advertising or otherwise to promote the |
| 29 |
# sale, use or other dealings in this Software without prior written |
| 30 |
# authorization. |
| 31 |
# |
| 32 |
import getpass |
| 33 |
import http |
| 34 |
import math |
| 35 |
import netrc |
| 36 |
import optparse |
| 37 |
import os |
| 38 |
import re |
| 39 |
import socket |
| 40 |
import string |
| 41 |
import sys |
| 42 |
import time |
| 43 |
import urllib |
| 44 |
import urllib.request |
| 45 |
import cgi |
| 46 |
import codecs |
| 47 |
import xml.parsers.expat |
| 48 |
import html |
| 49 |
import json |
| 50 |
|
| 51 |
# Global constants |
| 52 |
const_version = '2011.02.08' |
| 53 |
const_project_url = 'http://sourceforge.jp/projects/nicovideo-dl' |
| 54 |
|
| 55 |
const_1k = 1024 |
| 56 |
const_initial_block_size = 10 * const_1k |
| 57 |
const_epsilon = 0.0001 |
| 58 |
const_timeout = 120 |
| 59 |
|
| 60 |
const_video_url_str = 'https://www.nicovideo.jp/watch/%s' |
| 61 |
const_video_url_re = re.compile(r'^((?:http[s]?://)?(?:\w+\.)?(?:nicovideo\.jp/(?:v/|(?:watch(?:\.php)?))?/)?(\w+))') |
| 62 |
const_login_url_str = 'https://account.nicovideo.jp/api/v1/login?site=niconico&mail_or_tel=1' |
| 63 |
const_login_post_str = 'current_form=login_form&mail_tel=%s&password=%s&login__submit=Login' |
| 64 |
const_url_url_param_re = re.compile(r"url[=](http[^&]*)") |
| 65 |
const_video_url_info_str = 'https://flapi.nicovideo.jp/api/getflv/%s' |
| 66 |
const_video_title_re = re.compile(r'<title>(.*)</title>', re.M | re.I) |
| 67 |
const_video_type_re = re.compile(r'^http[s]?://.*\.nicovideo\.jp/smile\?(.*?)=.*') |
| 68 |
|
| 69 |
const_comment_getthreadkey_url_str = 'http://flapi.nicovideo.jp/api/getthreadkey?thread=%s' |
| 70 |
const_comment_request_str = '<thread thread="%s" version="20061206" res_from="-1000" user_id="%s"%s/>' |
| 71 |
|
| 72 |
# Print error message, followed by standard advice information, and then exit |
| 73 |
def error_advice_exit(error_text): |
| 74 |
sys.stderr.write('Error: %s.\n' % error_text) |
| 75 |
sys.stderr.write('Try again several times. It may be a temporary problem.\n') |
| 76 |
sys.stderr.write('Other typical problems:\n\n') |
| 77 |
sys.stderr.write('* Video no longer exists.\n') |
| 78 |
sys.stderr.write('* You provided the account data, but it is not valid.\n') |
| 79 |
sys.stderr.write('* The connection was cut suddenly for some reason.\n') |
| 80 |
sys.stderr.write('* Your account is free and perhaps only usable at 02:00 to 19:00 (+0900).\n') |
| 81 |
sys.stderr.write('* Niconico changed their system, and the program no longer works.\n') |
| 82 |
sys.stderr.write('\nTry to confirm you are able to view the video using a web browser.\n') |
| 83 |
sys.stderr.write('Use the same video URL and account information, if needed, with this program.\n') |
| 84 |
sys.stderr.write('When using a proxy, make sure http_proxy has http://host:port format.\n') |
| 85 |
sys.stderr.write('Try again several times and contact me if the problem persists.\n') |
| 86 |
sys.exit('\n') |
| 87 |
|
| 88 |
# Wrapper to create custom requests with typical headers |
| 89 |
def request_create(url, extra_headers, post_data=None): |
| 90 |
retval = urllib.request.Request(url) |
| 91 |
if post_data is not None: |
| 92 |
retval.data = post_data |
| 93 |
retval.add_header('User-Agent', 'nicovideo-dl/%s (%s)' % (const_version, const_project_url)) |
| 94 |
retval.add_header('Accept-Charset', 'ISO-8859-1,utf-8;q=0.7,*;q=0.7') |
| 95 |
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') |
| 96 |
retval.add_header('Accept-Language', 'en-us,en;q=0.5') |
| 97 |
if extra_headers is not None: |
| 98 |
for header in extra_headers: |
| 99 |
retval.add_header(header[0], header[1]) |
| 100 |
return retval |
| 101 |
|
| 102 |
# Perform a request, process headers and return response |
| 103 |
def perform_request(url, headers=None, data=None): |
| 104 |
request = request_create(url, headers, data) |
| 105 |
response = urllib.request.urlopen(request) |
| 106 |
return response |
| 107 |
|
| 108 |
# Conditional print |
| 109 |
def cond_print(str): |
| 110 |
global cmdl_opts |
| 111 |
if not (cmdl_opts.quiet or cmdl_opts.get_url): |
| 112 |
sys.stdout.write(str) |
| 113 |
sys.stdout.flush() |
| 114 |
|
| 115 |
# Title string normalization |
| 116 |
def title_string_norm(title): |
| 117 |
title_s = title |
| 118 |
for title_p in ['���������������������(SP1)', |
| 119 |
'���������������������(���)', |
| 120 |
'���������������������(���)', # as of Oct 2008 |
| 121 |
'���������������������(���)', # as of 5 Dec 2008 |
| 122 |
'���������������������(����)', # as of 12 Dec 2008 |
| 123 |
'���������������������(9)', # as of 29 Oct 2009 |
| 124 |
'��� ������������������(������)', # as of 29 Oct 2010 |
| 125 |
]: |
| 126 |
if (title_s.endswith(title_p)): |
| 127 |
title_s = title_s[:title_s.rfind(title_p)] |
| 128 |
break |
| 129 |
title_s = title_s.replace(os.sep, '%') |
| 130 |
title_s = '_'.join(title_s.split()) |
| 131 |
return title_s |
| 132 |
|
| 133 |
# Title string minimal transformation |
| 134 |
def title_string_touch(title): |
| 135 |
return title.replace(os.sep, '%') |
| 136 |
|
| 137 |
# Generic download step |
| 138 |
def download_step(return_data_flag, step_title, step_error, url, post_data=None): |
| 139 |
try: |
| 140 |
cond_print('%s... ' % step_title) |
| 141 |
response = perform_request(url, data=post_data) |
| 142 |
data = response.read().decode(response.headers.get_content_charset()) |
| 143 |
cond_print('done.\n') |
| 144 |
if return_data_flag: |
| 145 |
return data, response |
| 146 |
return None |
| 147 |
|
| 148 |
# except (urllib.error.URLError, ValueError, http.client.HTTPException, TypeError, socket.error): |
| 149 |
# cond_print('failed.\n') |
| 150 |
# error_advice_exit(step_error) |
| 151 |
|
| 152 |
except KeyboardInterrupt: |
| 153 |
sys.exit('\n') |
| 154 |
|
| 155 |
# Generic extract step |
| 156 |
def extract_step(step_title, step_error, regexp, data): |
| 157 |
try: |
| 158 |
cond_print('%s... ' % step_title) |
| 159 |
match = regexp.search(data) |
| 160 |
|
| 161 |
if match is None: |
| 162 |
cond_print('failed.\n') |
| 163 |
error_advice_exit(step_error) |
| 164 |
|
| 165 |
extracted_data = match.group(1) |
| 166 |
cond_print('done.\n') |
| 167 |
return extracted_data |
| 168 |
|
| 169 |
except KeyboardInterrupt: |
| 170 |
sys.exit('\n') |
| 171 |
|
| 172 |
# Calculate new block size based on previous block size |
| 173 |
def new_block_size(before, after, bytes): |
| 174 |
new_min = max(bytes / 2.0, 1.0) |
| 175 |
new_max = max(bytes * 2.0, 1.0) |
| 176 |
dif = after - before |
| 177 |
if dif < const_epsilon: |
| 178 |
return int(new_max) |
| 179 |
rate = bytes / dif |
| 180 |
if rate > new_max: |
| 181 |
return int(new_max) |
| 182 |
if rate < new_min: |
| 183 |
return int(new_min) |
| 184 |
return int(rate) |
| 185 |
|
| 186 |
# Get optimum 1k exponent to represent a number of bytes |
| 187 |
def optimum_k_exp(num_bytes): |
| 188 |
global const_1k |
| 189 |
if num_bytes == 0: |
| 190 |
return 0 |
| 191 |
return int(math.log(num_bytes, const_1k)) |
| 192 |
|
| 193 |
# Get optimum representation of number of bytes |
| 194 |
def format_bytes(num_bytes): |
| 195 |
global const_1k |
| 196 |
try: |
| 197 |
exp = optimum_k_exp(num_bytes) |
| 198 |
suffix = 'bkMGTPEZY'[exp] |
| 199 |
if exp == 0: |
| 200 |
return '%s%s' % (num_bytes, suffix) |
| 201 |
converted = float(num_bytes) / float(const_1k**exp) |
| 202 |
return '%.2f%s' % (converted, suffix) |
| 203 |
except IndexError: |
| 204 |
sys.exit('Error: internal error formatting number of bytes.') |
| 205 |
|
| 206 |
# Calculate ETA and return it in string format as MM:SS |
| 207 |
def calc_eta(start, now, total, current): |
| 208 |
dif = now - start |
| 209 |
if current == 0 or dif < const_epsilon: |
| 210 |
return '--:--' |
| 211 |
rate = float(current) / dif |
| 212 |
eta = int((total - current) / rate) |
| 213 |
(eta_mins, eta_secs) = divmod(eta, 60) |
| 214 |
if eta_mins > 99: |
| 215 |
return '--:--' |
| 216 |
return '%02d:%02d' % (eta_mins, eta_secs) |
| 217 |
|
| 218 |
# Calculate speed and return it in string format |
| 219 |
def calc_speed(start, now, bytes): |
| 220 |
dif = now - start |
| 221 |
if bytes == 0 or dif < const_epsilon: |
| 222 |
return 'N/A b' |
| 223 |
return format_bytes(float(bytes) / dif) |
| 224 |
|
| 225 |
# Download comment and save to the file |
| 226 |
def download_comment(cmdl_opts, video_url, video_filename, video_url_id, video_info_data): |
| 227 |
def extract_param(param, key): |
| 228 |
if key in param: |
| 229 |
return param[key][0] |
| 230 |
else: |
| 231 |
error_advice_exit('cannot extract %s parameter' % key) |
| 232 |
|
| 233 |
def post(name, url, post_data=None): |
| 234 |
data, res = download_step(True, 'Retrieving %s' % name, 'unable to get %s' % name, url, post_data=post_data) |
| 235 |
return data |
| 236 |
|
| 237 |
def get_thread_info(): |
| 238 |
url = const_comment_getthreadkey_url_str % video_url_id |
| 239 |
data = post('thread key', url) |
| 240 |
info = cgi.parse_qs(data) |
| 241 |
return extract_param(info, "threadkey"), extract_param(info, "force_184") |
| 242 |
|
| 243 |
def make_request(thread_id, user_id): |
| 244 |
options = '' |
| 245 |
|
| 246 |
if video_url_id.isdigit(): |
| 247 |
options = ' threadkey="%s" force_184="%s"' % get_thread_info() |
| 248 |
|
| 249 |
return const_comment_request_str % (thread_id, user_id, options) |
| 250 |
|
| 251 |
def parse_comment_xml(comment_xml): |
| 252 |
comments = [] |
| 253 |
|
| 254 |
def start(name, attrs): |
| 255 |
if name == 'chat': |
| 256 |
comments.append([int(attrs['vpos']), None]) |
| 257 |
|
| 258 |
def text(data): |
| 259 |
comments[-1][1] = data |
| 260 |
|
| 261 |
parser = xml.parsers.expat.ParserCreate() |
| 262 |
parser.StartElementHandler = start |
| 263 |
parser.CharacterDataHandler = text |
| 264 |
parser.Parse(comment_xml) |
| 265 |
|
| 266 |
comments.sort() |
| 267 |
|
| 268 |
return comments |
| 269 |
|
| 270 |
def write_comments(comments, f): |
| 271 |
f.write('comments for %s on %s\n' % (video_url, time.asctime())) |
| 272 |
|
| 273 |
if all(vpos < 600000 for vpos, comment in comments): |
| 274 |
timestamp = '%02d:%02d ' |
| 275 |
else: |
| 276 |
timestamp = '%03d:%02d ' |
| 277 |
|
| 278 |
for vpos, comment in comments: |
| 279 |
f.write(timestamp % divmod(vpos / 100, 60)) |
| 280 |
f.write(comment) |
| 281 |
f.write('\n') |
| 282 |
|
| 283 |
info = cgi.parse_qs(video_info_data) |
| 284 |
thread_id = extract_param(info, "thread_id") |
| 285 |
user_id = extract_param(info, "user_id") |
| 286 |
msg_url = extract_param(info, "ms") |
| 287 |
|
| 288 |
request_xml = make_request(thread_id, user_id) |
| 289 |
comment_xml = post('comment', msg_url, post_data=request_xml) |
| 290 |
|
| 291 |
outfile = cmdl_opts.comment_outfile |
| 292 |
|
| 293 |
if outfile is None: |
| 294 |
if cmdl_opts.comment_in_xml: |
| 295 |
outfile = '%s.xml' % video_filename |
| 296 |
else: |
| 297 |
outfile = '%s.txt' % video_filename |
| 298 |
|
| 299 |
try: |
| 300 |
f = codecs.open(outfile, 'w', 'utf-8') |
| 301 |
except (IOError, OSError): |
| 302 |
sys.exit('Error: unable to open "%s" for writing.' % outfile) |
| 303 |
|
| 304 |
if cmdl_opts.comment_in_xml: |
| 305 |
f.write(comment_xml.decode('utf-8')) |
| 306 |
else: |
| 307 |
write_comments(parse_comment_xml(comment_xml), f) |
| 308 |
|
| 309 |
f.close() |
| 310 |
|
| 311 |
cond_print('comment saved to %s\n' % outfile) |
| 312 |
|
| 313 |
# Create the command line options parser and parse command line |
| 314 |
cmdl_usage = 'usage: %prog [options] video_url' |
| 315 |
cmdl_version = const_version |
| 316 |
cmdl_parser = optparse.OptionParser(usage=cmdl_usage, version=cmdl_version, conflict_handler='resolve') |
| 317 |
cmdl_parser.add_option('-h', '--help', action='help', help='print this help text and exit') |
| 318 |
cmdl_parser.add_option('-v', '--version', action='version', help='print program version and exit') |
| 319 |
cmdl_parser.add_option('-u', '--username', dest='username', metavar='USERNAME', help='account username') |
| 320 |
cmdl_parser.add_option('-p', '--password', dest='password', metavar='PASSWORD', help='account password') |
| 321 |
cmdl_parser.add_option('-o', '--output', dest='outfile', metavar='FILE', help='output video file name') |
| 322 |
cmdl_parser.add_option('-q', '--quiet', action='store_true', dest='quiet', help='activates quiet mode') |
| 323 |
cmdl_parser.add_option('-s', '--simulate', action='store_true', dest='simulate', help='do not download video') |
| 324 |
cmdl_parser.add_option('-t', '--title', action='store_true', dest='use_title', help='use title in file name') |
| 325 |
cmdl_parser.add_option('-l', '--literal', action='store_true', dest='use_literal', help='use literal title in file name') |
| 326 |
cmdl_parser.add_option('-n', '--netrc', action='store_true', dest='use_netrc', help='use .netrc authentication data') |
| 327 |
cmdl_parser.add_option('-g', '--get-url', action='store_true', dest='get_url', help='print final video URL only') |
| 328 |
cmdl_parser.add_option('-2', '--title-too', action='store_true', dest='get_title', help='used with -g, print title too') |
| 329 |
cmdl_parser.add_option('-c', '--get-comment', action='store_true', dest='get_comment', help='download comment') |
| 330 |
cmdl_parser.add_option('-x', '--raw-comment', action='store_true', dest='comment_in_xml', help='save comment in raw xml') |
| 331 |
cmdl_parser.add_option('--comment-output', dest='comment_outfile', metavar='FILE', help='output comment file name') |
| 332 |
(cmdl_opts, cmdl_args) = cmdl_parser.parse_args() |
| 333 |
|
| 334 |
# Set socket timeout |
| 335 |
socket.setdefaulttimeout(const_timeout) |
| 336 |
|
| 337 |
# Get video URL |
| 338 |
if len(cmdl_args) == 0: |
| 339 |
cmdl_parser.print_help() |
| 340 |
sys.exit('\n') |
| 341 |
|
| 342 |
# Check conflicting options |
| 343 |
if cmdl_opts.outfile is not None and (cmdl_opts.simulate or cmdl_opts.get_url): |
| 344 |
sys.stderr.write('Warning: video file name given but will not be used.\n') |
| 345 |
|
| 346 |
if cmdl_opts.outfile is not None and (cmdl_opts.use_title or cmdl_opts.use_literal): |
| 347 |
sys.exit('Error: using the video title conflicts with using a given file name.') |
| 348 |
|
| 349 |
if cmdl_opts.use_title and cmdl_opts.use_literal: |
| 350 |
sys.exit('Error: cannot use title and literal title at the same time.') |
| 351 |
|
| 352 |
if cmdl_opts.quiet and cmdl_opts.get_url: |
| 353 |
sys.exit('Error: cannot be quiet and print final URL at the same time.') |
| 354 |
|
| 355 |
# Incorrect option formatting |
| 356 |
if cmdl_opts.username is None and cmdl_opts.password is not None: |
| 357 |
sys.exit('Error: password give but username is missing.') |
| 358 |
|
| 359 |
if cmdl_opts.use_netrc and (cmdl_opts.username is not None or cmdl_opts.password is not None): |
| 360 |
sys.exit('Error: cannot use netrc and username/password at the same time.') |
| 361 |
|
| 362 |
if cmdl_opts.get_url is None and cmdl_opts.get_title is not None: |
| 363 |
sys.exit('Error: getting title requires getting URL.') |
| 364 |
|
| 365 |
# Get account information if any |
| 366 |
account_username = None |
| 367 |
account_password = None |
| 368 |
|
| 369 |
if cmdl_opts.use_netrc: |
| 370 |
try: |
| 371 |
info = netrc.netrc().authenticators('nicovideo') |
| 372 |
if info is None: |
| 373 |
sys.exit('Error: no authenticators for machine nicovideo.') |
| 374 |
netrc_username = info[0] |
| 375 |
netrc_password = info[2] |
| 376 |
except IOError: |
| 377 |
sys.exit('Error: unable to read .netrc file.') |
| 378 |
except netrc.NetrcParseError: |
| 379 |
sys.exit('Error: unable to parse .netrc file.') |
| 380 |
|
| 381 |
if cmdl_opts.password is not None: |
| 382 |
account_username = cmdl_opts.username |
| 383 |
account_password = cmdl_opts.password |
| 384 |
else: |
| 385 |
if cmdl_opts.username is not None and cmdl_opts.use_netrc: |
| 386 |
if cmdl_opts.username != netrc_username: |
| 387 |
sys.exit('Error: conflicting username from .netrc and command line options.') |
| 388 |
account_username = cmdl_opts.username |
| 389 |
account_password = netrc_password |
| 390 |
elif cmdl_opts.username is not None: |
| 391 |
account_username = cmdl_opts.username |
| 392 |
account_password = getpass.getpass('Type Niconico password and press return: ') |
| 393 |
elif cmdl_opts.use_netrc: |
| 394 |
if len(netrc_username) == 0: |
| 395 |
sys.exit('Error: empty username in .netrc file.') |
| 396 |
account_username = netrc_username |
| 397 |
account_password = netrc_password |
| 398 |
elif account_username is None: |
| 399 |
account_username = input("Type Niconico E-mail account: ") |
| 400 |
account_password = getpass.getpass('Type Niconico password and press return: ') |
| 401 |
|
| 402 |
# Install cookie and proxy handlers |
| 403 |
urllib.request.install_opener(urllib.request.build_opener(urllib.request.ProxyHandler())) |
| 404 |
urllib.request.install_opener(urllib.request.build_opener(urllib.request.HTTPCookieProcessor())) |
| 405 |
|
| 406 |
# Log in |
| 407 |
if account_username is not None: |
| 408 |
url = const_login_url_str |
| 409 |
post = const_login_post_str % (account_username, account_password) |
| 410 |
download_step(False, 'Logging in', 'unable to log in', url, post.encode("utf-8")) |
| 411 |
|
| 412 |
for video_url_cmdl in cmdl_args: |
| 413 |
# Verify video URL format and convert to "standard" format |
| 414 |
video_url_mo = const_video_url_re.match(video_url_cmdl) |
| 415 |
if video_url_mo is None: |
| 416 |
sys.exit('Error: URL does not seem to be a niconico video URL. If it is, report a bug.') |
| 417 |
video_url_id = video_url_mo.group(2) |
| 418 |
video_url = const_video_url_str % video_url_id |
| 419 |
|
| 420 |
video_extension = '.flv' |
| 421 |
|
| 422 |
# Retrieve video webpage |
| 423 |
video_webpage, response = download_step(True, 'Retrieving video webpage', 'unable to retrieve video webpage', video_url) |
| 424 |
|
| 425 |
# Reconvert URL if redirected |
| 426 |
if response.geturl() != video_url: |
| 427 |
video_url_id = const_video_url_re.match(response.geturl()).group(2) |
| 428 |
video_url = const_video_url_str % video_url_id |
| 429 |
|
| 430 |
# Extract video title if needed |
| 431 |
if cmdl_opts.use_title or cmdl_opts.use_literal or cmdl_opts.get_title: |
| 432 |
video_title = extract_step('Extracting video title', 'unable to extract video title', const_video_title_re, video_webpage) |
| 433 |
|
| 434 |
# Extract needed video URL parameters |
| 435 |
video_url_info = const_video_url_info_str % video_url_id |
| 436 |
video_info_data, response = download_step(True, 'Retrieving info data', 'unable to retrieve video webpage', video_url_info) |
| 437 |
|
| 438 |
cond_print('Extracting URL "url" parameter... ') |
| 439 |
video_url_url_param = urllib.parse.parse_qs(video_info_data) |
| 440 |
if ('url' in video_url_url_param): |
| 441 |
video_url_url_param=video_url_url_param['url'][0] |
| 442 |
else: |
| 443 |
error_advice_exit('cannot extract url parameter') |
| 444 |
cond_print('done.\n') |
| 445 |
video_url_real = video_url_url_param |
| 446 |
|
| 447 |
video_url_info = const_video_url_str % video_url_id |
| 448 |
video_info_data, response = download_step(True, 'Retrieving info data', 'unable to retrieve video webpage', video_url_info) |
| 449 |
data_api_data_re = re.compile(r'.*data-api-data=["]([^"]*)["].*', re.M | re.I | re.MULTILINE) |
| 450 |
data_api_data_match = data_api_data_re.search(video_info_data) |
| 451 |
if (not (data_api_data_match is None)): |
| 452 |
video_url_url_param = json.loads(html.unescape(data_api_data_match.group(1))) |
| 453 |
if ('video' in video_url_url_param and 'smileInfo' in video_url_url_param['video'] and 'url' in video_url_url_param['video']['smileInfo']): |
| 454 |
video_url_real = video_url_url_param['video']['smileInfo']['url'] |
| 455 |
|
| 456 |
# Extract video type and modify video_extension |
| 457 |
video_type_mo = const_video_type_re.match(video_url_real) |
| 458 |
if (video_type_mo): |
| 459 |
if video_type_mo.group(1) == "s": |
| 460 |
video_extension = ".swf" |
| 461 |
elif video_type_mo.group(1) == "m": |
| 462 |
video_extension = ".mp4" |
| 463 |
|
| 464 |
# Get output file name |
| 465 |
if cmdl_opts.outfile is None: |
| 466 |
video_filename = '%s%s' % (video_url_id, video_extension) |
| 467 |
else: |
| 468 |
video_filename = cmdl_opts.outfile |
| 469 |
|
| 470 |
# Rebuild filename if needed |
| 471 |
if cmdl_opts.use_title or cmdl_opts.use_literal: |
| 472 |
if cmdl_opts.use_title: |
| 473 |
prefix = title_string_norm(video_title) |
| 474 |
else: |
| 475 |
prefix = title_string_touch(video_title) |
| 476 |
video_filename = '%s-%s%s' % (prefix, video_url_id, video_extension) |
| 477 |
|
| 478 |
# Check name |
| 479 |
if not video_filename.lower().endswith(video_extension): |
| 480 |
sys.stderr.write('Warning: video file name does not end in %s\n' % video_extension) |
| 481 |
|
| 482 |
# Download and save comment |
| 483 |
if cmdl_opts.get_comment: |
| 484 |
download_comment(cmdl_opts, video_url, video_filename, video_url_id, video_info_data) |
| 485 |
|
| 486 |
# Retrieve video data |
| 487 |
try: |
| 488 |
cond_print('Requesting video file... ') |
| 489 |
video_data = perform_request(video_url_real) |
| 490 |
cond_print('done.\n') |
| 491 |
cond_print('Video data found at %s\n' % video_data.geturl()) |
| 492 |
|
| 493 |
if cmdl_opts.get_title: |
| 494 |
print (video_title) |
| 495 |
|
| 496 |
if cmdl_opts.get_url: |
| 497 |
print (video_data.geturl()) |
| 498 |
|
| 499 |
if cmdl_opts.simulate or cmdl_opts.get_url: |
| 500 |
continue |
| 501 |
|
| 502 |
try: |
| 503 |
video_file = open(video_filename, 'wb') |
| 504 |
except (IOError, OSError): |
| 505 |
sys.exit('Error: unable to open "%s" for writing.' % video_filename) |
| 506 |
try: |
| 507 |
video_len = int(video_data.info()['Content-length']) |
| 508 |
video_len_str = format_bytes(video_len) |
| 509 |
except KeyError: |
| 510 |
video_len = None |
| 511 |
video_len_str = 'N/A' |
| 512 |
|
| 513 |
byte_counter = 0 |
| 514 |
block_size = const_initial_block_size |
| 515 |
start_time = time.time() |
| 516 |
while True: |
| 517 |
if video_len is not None: |
| 518 |
percent = float(byte_counter) / float(video_len) * 100.0 |
| 519 |
percent_str = '%.1f' % percent |
| 520 |
eta_str = calc_eta(start_time, time.time(), video_len, byte_counter) |
| 521 |
else: |
| 522 |
percent_str = '---.-' |
| 523 |
eta_str = '--:--' |
| 524 |
counter = format_bytes(byte_counter) |
| 525 |
speed_str = calc_speed(start_time, time.time(), byte_counter) |
| 526 |
cond_print('\rRetrieving video data: %5s%% (%8s of %s) at %8s/s ETA %s ' % (percent_str, counter, video_len_str, speed_str, eta_str)) |
| 527 |
|
| 528 |
before = time.time() |
| 529 |
video_block = video_data.read(block_size) |
| 530 |
after = time.time() |
| 531 |
dl_bytes = len(video_block) |
| 532 |
if dl_bytes == 0: |
| 533 |
break |
| 534 |
byte_counter += dl_bytes |
| 535 |
video_file.write(video_block) |
| 536 |
block_size = new_block_size(before, after, dl_bytes) |
| 537 |
|
| 538 |
if video_len is not None and byte_counter != video_len: |
| 539 |
error_advice_exit('server did not send the expected amount of data') |
| 540 |
|
| 541 |
video_file.close() |
| 542 |
cond_print('done.\n') |
| 543 |
cond_print('Video data saved to %s\n' % video_filename) |
| 544 |
|
| 545 |
except (urllib.request.URLError, ValueError, http.client.HTTPException, TypeError, socket.error): |
| 546 |
cond_print('failed.\n') |
| 547 |
error_advice_exit('unable to download video data') |
| 548 |
|
| 549 |
except KeyboardInterrupt: |
| 550 |
sys.exit('\n') |
| 551 |
# Finish |
| 552 |
sys.exit() |
Parent Directory
Revision Log