Last active
August 9, 2021 04:08
-
-
Save jyxjjj/35afd58da47eec58ed7f96380c610c73 to your computer and use it in GitHub Desktop.
Tmooc Downloader - To generate TMOOC videos' download links and ffmpeg commands.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#-*- coding: utf-8 -*- | |
from selenium import webdriver | |
from selenium.webdriver.common.action_chains import ActionChains | |
from selenium.webdriver.common.keys import Keys | |
import re | |
import time | |
import os, sys | |
from urllib import parse | |
dir = os.path.abspath(os.path.dirname(os.getcwd())) | |
def ParseCookiestr(cookie_str): | |
cookielist = [] | |
for item in cookie_str.split('; '): | |
cookie={} | |
itemname = item.split('=')[0] | |
itemvalue = item.split('=')[1] | |
cookie['name']= itemname | |
cookie['value']= parse.unquote(itemvalue) | |
cookielist.append(cookie) | |
return cookielist | |
ua = "Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.90 Mobile Safari/537.36" | |
options = webdriver.ChromeOptions() | |
options.add_argument('User-Agent=' + ua) | |
browser = webdriver.Chrome(executable_path="chromedriver.exe", options=options) | |
browser.implicitly_wait(8) | |
browser.get('http://tts.tmooc.cn/video/showVideo?menuId=693540&version=JSDVN201905') | |
# 注意 一定要将访问此域名的cookie放在同级目录的cookie.txt中,再启动。 | |
# 注意 一定要将访问此域名的cookie放在同级目录的cookie.txt中,再启动。 | |
with open('cookie.txt', encoding='utf-8') as cooke: | |
cookies = cooke.read() | |
cookielist = ParseCookiestr(cookies) | |
for i in cookielist: | |
cookie = {} | |
cookie['name'] = i['name'] | |
cookie['value'] = i['value'] | |
browser.delete_cookie(i['name']) | |
browser.add_cookie(cookie) | |
browser.get('http://tts.tmooc.cn/video/showVideo?menuId=690873&version=JSDVN201905') | |
time.sleep(3) | |
chain = ActionChains(browser) | |
for page in range(1,13): | |
elem = browser.find_element_by_xpath('/html/body/div[2]/div/div[3]/div[2]/div/div/div[1]/div[2]/div/p[%s]/a'%page) | |
chain.move_to_element(elem).perform() | |
elem.click() | |
time.sleep(3) | |
url = browser.find_element_by_xpath('/html/body/div[2]/div/div[1]/div/div/div/div/video/source').get_attribute('src') | |
print('ffmpeg -multiple_requests 1 -reconnect_streamed 1 -i "' + url +'" -vcodec h264 W:\\tmooc\\S4\\C1\\D1\\' + '%s'%page + '.mp4') | |
print('\r\n') | |
browser.quit() | |
sys.exit(0) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment