小说抓取实战

把链接改为这个网站的小说第一章节 35中文

import os
path = '.\chromedriver.exe'
from lxml import etree
import re
from selenium import webdriver
import time


driver = webdriver.Chrome(executable_path=path)
driver.get('https://www.swzw.la/xs/288/288812/56975154.html')
driver.maximize_window()
time.sleep(1)
if not os.path.exists('./texts'):
    os.mkdir('./texts')
for i in range(1,50):
    source = driver.page_source
    tree=etree.HTML(source)
    title=tree.xpath('//*[@id="wrapper"]/div[5]/div[2]/div[2]/h1/text()')[0]
    text="".join(tree.xpath('//*[@id="content"]//text()'))
    
    file=open(r'D:/爬虫新学习/Day1/texts/{}.txt'.format(i),'w', encoding='utf-8')
    info=title+"\t"+text+"\n"
    file.write(info)
    file.close()   
    
    driver.find_element_by_xpath('//*[@id="wrapper"]/div[5]/div[2]/div[2]/div/a[4]').click()
    time.sleep(1)