Python批量下载MOOC课件

今天干了件有点快乐的事情——批量下载MOOC课件
代码搬运，需做以下修改
1.pip install selenium
2.chormedriver下载7.2可
2.修改courseware_url

# coding: utf-8from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.action_chains import ActionChains
from selenium.common.exceptions import *
import requests
from requests.packages.urllib3.exceptions import InsecureRequestWarningrequests.packages.urllib3.disable_warnings(InsecureRequestWarning)
requests.adapters.DEFAULT_RETRIES = 5
import time
import os
import redriver = webdriver.Chrome()
# driver = webdriver.FireFox()
wait = WebDriverWait(driver, 10)def download(url, file_name):headers = {'Host': 'hubble.netease.com','Origin': 'https://www.icourse163.org','Referer': url.split("#")[0],'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.92 Safari/537.36'}if not os.path.exists(file_name) or os.path.getsize(file_name) <= 10:with open(file_name, "wb") as f:r = requests.get(url, headers=headers, verify=False)f.write(r.content)f.close()print("\t下载成功：{}".format(file_name))else:print("\t文件已存在：{}".format(file_name))# 课件地址  存储路径  范围[a, b](第a章到第b章，默认[0, 0]表示全部)
def get_courseware(courseware_url, path, c_range=[0, 0]):t = 0while t < 2:try:driver.get(courseware_url)h3 = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR, "#g-body > div.m-learnhead > div > div > div > a.f-fl > h4")))school_name = re.findall(r'/([a-zA-Z]+)-', courseware_url)[0]title = h3.textpath_1 = os.path.join(path, title + "_" + school_name)if not os.path.exists(path_1):os.makedirs(path_1)path = os.path.join(path_1, "courseware")if not os.path.exists(path):os.makedirs(path)# 总章节数h3_count = len(driver.find_elements_by_css_selector("div > div.m-learnChapterList> div.m-learnChapterNormal > div.titleBox > h3"))if c_range[1] == 0:c_range2 = h3_countelse:c_range2 = c_range[1]for index in range(3 + c_range[0], 3 + c_range2):driver.refresh()h3 = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,"div > div.m-learnChapterList> div.m-learnChapterNormal:nth-child(3) > div.titleBox > h3")))h3.click()h3 = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,"div > div.m-learnChapterList> div.m-learnChapterNormal:nth-child({}) > div.titleBox > h3".format(index))))h3_text = h3.textprint("{}:".format(h3_text), end="\t")patten = re.compile('.*?第(.{1,3})(周|章).*?')match = re.match(patten, h3_text)if match:week = match.group(0)else:week = h3_texth3.click()time.sleep(3)#                 file_count = len(driver.find_elements_by_xpath('//div[@class="f-icon lsicon f-fl "]/span[@class="u-icon-doc"]'))file_count = len(driver.find_elements_by_xpath('//div[@class="sourceList"]/*[@title="文档讲稿"]'))print(file_count)h4_count = len(driver.find_elements_by_css_selector('div.u-learnLesson > h4'))for h4_index in range(1, h4_count + 1):h4 = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR, 'div.u-learnLesson:nth-of-type({}) > h4.j-name'.format(h4_index))))# 标题4h4str = h4.textfile_count = len(driver.find_elements_by_css_selector(f'div.u-learnLesson:nth-of-type({h4_index}) > div.sourceList > div[title^="文档"]'))for f_index in range(1, file_count + 1):title = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,f'div.u-learnLesson:nth-of-type({h4_index}) > div.sourceList > div[title^="文档"]')))titlestr = title.get_attribute("title")title.click()time.sleep(0.2)download_btn = wait.until(EC.element_to_be_clickable((By.PARTIAL_LINK_TEXT, '文档下载')))download_url = download_btn.get_attribute("href")week = week.replace(":", "-").replace("/", " ").replace("\\", " ").replace("课件：", " ").replace("：", " ")titlestr = f'{h4str} {titlestr}'title = titlestr.replace(":", "-").replace("/", " ").replace("\\", " ").replace("课件："," ").replace("：", " ").replace("/", " ")print(week, "   ", title)file_name = path + "\\" + week + " " + "".join(title.split()).replace("：", " ") + "." + \download_url.split(".")[-1].split('&')[0]print(file_name)download(download_url, file_name)driver.back()time.sleep(1)h3 = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,"div > div.m-learnChapterList> div.m-learnChapterNormal:nth-child(3) > div.titleBox > h3")))h3.click()h3 = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,"div > div.m-learnChapterList> div.m-learnChapterNormal:nth-child({}) > div.titleBox > h3".format(index))))h3.click()t = 5except FileNotFoundError:print("FileNotFoundError: [Errno 2] No such file or directory: ")t += 1def main():courseware_url = 'https://www.icourse163.org/learn/XDU-1001638014?tid=1462808447#/learn/content'path = r"D:\大二下\信号与系统\中国大学MOOC"# 课件地址  存储路径  范围[a, b](第a章到第b章，默认[0, 0]表示全部)get_courseware(courseware_url, path, [0, 0])driver.quit()  # 退出浏览器if __name__ == '__main__':main()

question：
1.每节只能下一个课件，应该有多少下多少
2.命名格式调一下更好，放假了来改进

Python批量下载MOOC课件相关推荐

python调用默认播放器_用Python批量下载MOOC资源
简介这是我编写的一个Python脚本,用来批量下载一门MOOC的资源,包括视频.PDF和课程目录. 你是否也曾上MOOC学习过?有没有和我一样遇到这些情况:在线看MOOC视频消耗流量好多,或者浏览器 ...
python下载网页里面所有的图片-Python批量下载网页图片详细教程
很多朋友在网上查找批量下载图片的方法~发觉挺凌乱的,无从下手.这里绿茶小编就来跟大家分享下使用Python批量下载图片方法. 目标:爬取某个网站上n多页的链接,每个链接有n多张图片,每一页对应一个文件 ...
群里又会python的吗_自从会了Python在群里斗图就没输过，Python批量下载表情包！...
原标题:自从会了Python在群里斗图就没输过,Python批量下载表情包! 导语最近图慌,于是随便写了个表情包批量下载的脚本,没什么技术含量,纯娱乐性质. 让我们愉快地开始吧~ 开发工具 Pyth ...
python批量下载b站_python 批量下载bilibili视频的gui程序
运行效果: 完整代码: # !/usr/bin/python # -*- coding:utf-8 -*- # time: 2019/07/02--08:12 __author__ = 'Henry' ...
Python 批量下载SIGMOD,VLDB的论文 Mac OS
这里写自定义目录标题 Python 批量下载SIGMOD,VLDB的论文 Mac OS 实现 0.要爬取的网站 1.下载单篇论文 2.获得所有论文的链接完整代码 Python 批量下载SIGMOD, ...
教你怎么使用python批量下载图片
教你怎么使用python批量下载图片文章目录教你怎么使用python批量下载图片前言一.运行环境 1. win10 2. python==3.7.2 二.需要用到的参数 1. download ...
python批量下载模库网图片
这里写自定义目录标题 python批量下载模库网图片步骤: 代码 python批量下载模库网图片步骤: 获取页数获取列表页获取图片链接和名字相关字典创建存放图片的文件夹下载图片代码 im ...
python怎么批量下载年报_使用Python批量下载Wind数据库中的PDF报告
原标题:使用Python批量下载Wind数据库中的PDF报告背景最近小编出于工作需要,准备在Wind金融数据终端批量下载上市公司2019年第一季度业绩预告.通过相关的条件检索,发现其相关数据有近百 ...
使用Python批量下载哨兵一号（sentinel-1）的精密轨道数据（precise orbit data）
使用Python批量下载哨兵一号(sentinel-1)的精密轨道数据 1. 安装Python及data_downloader包 2. 下载精密轨道数据与辅助数据 1. 安装Python及data_d ...
用Python批量下载DACC的MODIS数据
本人初次尝试用Python批量下载DACC的MODIS数据,记下步骤,提醒自己,数据还在下载,成功是否未知,等待结果中...... 若有大佬发现步骤有不对之处,望指出,不胜感激. 1.下载Python ...

Python批量下载MOOC课件

Python批量下载MOOC课件相关推荐

最新文章

热门文章