# -*- coding: utf-8 -*- from selenium import webdriver import requests,re,pprint,time url=‘https://www.sbiquge.com/5_5374/‘ browser = webdriver.Chrome(‘C:\Program Files (x86)\Google\Chrome\Application\chromedriver.exe‘) response= requests.get(url) html= response.text result = re.findall(‘\w\shref\s="/5_5374/(\d+)‘,html,re.S) esult = re.findall(‘\w\shref\s="/5_5374/\d+\.html">(.*?)</a>‘,html,re.S) print(result) #print(esult) n=0 while n<10000: try: browser.get(url+"{}.html".format(result [n])) time.sleep(0.1) n=n+1 cont=browser.find_element_by_xpath(‘// *[ @ id = "book"] / div[2] / h1‘) con=browser.find_element_by_class_name(‘showtxt‘) print(cont.text) print(con.text) novel_name = ‘诛仙.txt‘ with open(novel_name,‘a‘,encoding=‘utf-8‘)as f: f.write(‘\n\n‘+cont.text+‘\n\n\t‘+con.text+n) except Exception as e: print(e) print(result[n]+"这章加载太慢了====================================================================================!") pass browser.close()
原文:https://www.cnblogs.com/fqqwz/p/11632495.html