bs4解析爬取三国演义所有章节及内容【★★★】

By yesmore on 2021-07-23
阅读时间 1 分钟
文章共 332
阅读量

复习:Python爬虫介绍

需求:爬取三国演义小说所有的章节标题和章节内容

1
http://www.shicimingju.com/book/sanguoyanyi.html
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
#!/usr/bin/env python 
# -*- coding:utf-8 -*-
import requests
from bs4 import BeautifulSoup

if __name__ == "__main__":
# 对首页的页面数据进行爬取
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'
}
url = 'http://www.shicimingju.com/book/sanguoyanyi.html'
page_text = requests.get(url=url, headers=headers)
page_text.encoding = 'utf-8' # 解决乱码问题
page_text = page_text.text

# 在首页中解析出章节的标题和详情页的url
# 1.实例化BeautifulSoup对象,需要将页面源码数据加载到该对象中
soup = BeautifulSoup(page_text, 'lxml')
# 解析章节标题和详情页的url
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 = 'http://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)
detail_page_text.encoding = 'utf-8' # 解决乱码问题
detail_page_text = detail_page_text.text

# 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+'》\n'+content+'\n')
print(title, '爬取成功!!!')

Tips: Please indicate the source and original author when reprinting or quoting this article.