需求:爬取三国演义小说所有的章节标题和章节内容;
url = 'https://www.shicimingju.com/book/sanguoyanyi.html'
思路:
- 使用通用爬虫爬取将该页面的源文件
- 解析该源文件,得到章节标题和每个章节对应的详情url地址
- 对该详情url地址进行访问得到章节的内容
from bs4 import BeautifulSoup
import requests
import lxml
import os
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36 Edg/89.0.774.63'
}
url = 'https://www.shicimingju.com/book/sanguoyanyi.html'
# 对首页内容进行爬取
page_text= requests.get(url=url,headers=headers).content
# 解析
# 1.实例化一个BeautifulSoup对象
soup = BeautifulSoup(page_text,'lxml')
# 2.解析 用 select 写一个层级选择器
li_list = soup.select('.book-mulu >ul >li')
fp = open('./sanguo.txt','w',encoding='utf-8')
for li in li_list:
title = li.a.string
detail_url = 'https://www.shicimingju.com' + li.a['href']
# 对详情页发起请求,解析出章节内容
detail_page_text = requests.get(url=detail_url,headers=headers).content
# 解析出详情页中相关的章节内容
detail_soup = BeautifulSoup(detail_page_text,'lxml')
div_tag = detail_soup.find('div',class_='chapter_content')
# 解析到了章节的内容
content = div_tag.text
fp.write(title+':'+content+'\n')
print(title,'爬取成功!!!')