import time,random
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
url = 'https://wenku.baidu.com/view/46dcaa1c9a6648d7c1c708a1284ac850ad0204d4.html#'
options = webdriver.ChromeOptions()
options.add_argument("'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36'")
options.add_argument('--headless')
driver = webdriver.Chrome(chrome_options=options)
driver.get(url)
all_text = ''
for page in range(1,25):
driver.find_element_by_xpath('//*[@id="index"]/div[2]/div[1]/div[2]/div[1]/div[1]/div/div[5]/label/input').clear()
driver.find_element_by_xpath('//*[@id="index"]/div[2]/div[1]/div[2]/div[1]/div[1]/div/div[5]/label/input').send_keys(str(page),Keys.ENTER)
time.sleep(1.5+random.random())
page_text = driver.find_elements_by_xpath('//*[@id="pageNo-%d"]/div/div/div/div[4]/div//p'%page)
for i in page_text:
all_text = all_text + i.text
print(all_text)
with open('jiaoan.txt','w') as fp:
fp.write(all_text)
fp.close()
driver.close()
百度文库下载动态加载
最新推荐文章于 2022-08-12 09:48:28 发布