Python + selenium 爬取百度文库Word文本

Posted 2021-01-25 shuai-bi

 1 # -*- coding:utf-8 -*-
 2  
 3 import time
 4 from selenium import webdriver
 5 from selenium.webdriver.chrome.options import Options
 6 from selenium.common.exceptions import NoSuchElementException
 7  
 8 chrome_options = Options()
 9 chrome_options.add_argument(‘--headless‘)
10 chrome_options.add_argument(‘--disable-gpu‘)
11 chrome_options.add_argument("--user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.80 Safari/537.36")
12  
13 driver = webdriver.Chrome(chrome_options=chrome_options)
14 driver.maximize_window()
15  
16 url = input("输入文档链接，搞快点：")
17 driver.get(url)
18  
19 error_str = ""
20  
21 try :
22     page_num = driver.find_element_by_xpath("//span[@class=‘page-count‘]").text
23  
24     find_button = driver.find_element_by_xpath("//div[@class=‘doc-banner-text‘]")
25     driver.execute_script("arguments[0].scrollIntoView();", find_button)
26     button = driver.find_element_by_xpath("//span[@class=‘moreBtn goBtn‘]")
27     button.click()
28  
29     for i in range(1,int(page_num.strip(‘/‘)) + 1) :
30         page = driver.find_element_by_xpath("//div[@data-page-no=‘{}‘]".format(i))
31         driver.execute_script("arguments[0].scrollIntoView();", page)
32         time.sleep(0.3)
33         print(driver.find_elements_by_xpath("//div[@data-page-no=‘{}‘]//div[@class=‘reader-txt-layer‘]".format(i))[-1].text)
34  
35 except NoSuchElementException :
36     if driver.find_element_by_xpath("//div[@class=‘doc-bottom-text‘]").text == "试读已结束，如需继续阅读或下载" :
37         error_str = "
------------------------------------------------------------------

" 38                       "----------百度文库提示试读已结束啦，无法爬取全文，等会再试试吧----------

" 39                       "------------------------------------------------------------------"
40  
41 finally :
42     print(error_str)