bs4 爬取某网站三国演义标题及内容

from bs4 import BeautifulSoup
import requests

if __name__ == '__main__':
    url = "https://www.shicimingju.com/book/sanguoyanyi.html"
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/"
                      "85.0.4183.83 Safari/537.36"
    }

    page_text = requests.get(url=url, headers=headers).text

    soup = BeautifulSoup(page_text, "lxml")
    li_list = soup.select(".book-mulu > ul > li")
    fp = open("./三国演义.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).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")
        # 解析到章节内容
        content = div_tag.text
        fp.write(title + ":" + content + "\n")
        print(title, "Over")