python爬虫四大名著源代码

为了遵守规则3，我将只使用引用中提供的信息来回答您的问题。

以下是一个简单的Python爬虫，用于从四大名著网站获取《红楼梦》的章节内容：

import requests
from bs4 import BeautifulSoup

# 设置请求头
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3'}

# 发送请求
url = 'http://www.xiangcunxiaoshuo.com/hlm/'
response = requests.get(url, headers=headers)

# 解析HTML
soup = BeautifulSoup(response.text, 'html.parser')
chapter_list = soup.find_all('div', class_='book_list')[0].find_all('a')

# 获取所有章节链接
chapter_links = []
for chapter in chapter_list:
    chapter_links.append(chapter['href'])

# 获取每个章节的内容
for link in chapter_links:
    response = requests.get(link, headers=headers)
    soup = BeautifulSoup(response.text, 'html.parser')
    content = soup.find_all('div', class_='book_content')[0].text
    print(content)
    time.sleep(1)  # 防止被封IP