今天干了件有點快樂的事情——批量下載MOOC課件
代碼搬運，需做以下修改
1.pip install selenium
2.chormedriver下載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下載成功：{}".format(file_name))else:print("\t文件已存在：{}".format(file_name))# 課件地址 存儲路徑 范圍[a, b](第a章到第b章，默認[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)# 總章節數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="文檔講稿"]'))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))))# 標題4h4str = h4.textfile_count = len(driver.find_elements_by_css_selector(f'div.u-learnLesson:nth-of-type({h4_index}) > div.sourceList > div[title^="文檔"]'))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^="文檔"]')))titlestr = title.get_attribute("title")title.click()time.sleep(0.2)download_btn = wait.until(EC.element_to_be_clickable((By.PARTIAL_LINK_TEXT, '文檔下載')))download_url = download_btn.get_attribute("href")week = week.replace(":", "-").replace("/", " ").replace("\\", " ").replace("課件：", " ").replace("：", " ")titlestr = f'{h4str} {titlestr}'title = titlestr.replace(":", "-").replace("/", " ").replace("\\", " ").replace("課件："," ").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\信號與系統\中國大學MOOC"# 課件地址 存儲路徑 范圍[a, b](第a章到第b章，默認[0, 0]表示全部)get_courseware(courseware_url, path, [0, 0])driver.quit() # 退出瀏覽器if __name__ == '__main__':main()

question：
1.每節只能下一個課件，應該有多少下多少
2.命名格式調一下更好，放假了來改進

總結

以上是生活随笔為你收集整理的Python批量下载MOOC课件的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。