bs4实战之三国演义数据爬取

# 需求：爬取三国演义小说中的章节标题与章节内容http://www.shicimingju.com/book/sanguoyanyi.html
import requests
from bs4 import BeautifulSoup
if __name__ == "__main__":
    # 对首页数据进行爬取
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
    }   # UA伪装
    url = 'http://www.shicimingju.com/book/sanguoyanyi.html'
    page_text = requests.get(url=url,headers=headers).text

    # 在首页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')
    # 在首页解析出章节的标题和详情页的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 #todo
        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).text
        # 解析出详情页中的相关内容
        detail_soup = BeautifulSoup(detail_page_text,'lxml')
        div_tag = detail_soup.find('div',class_= 'chapter_content')
        # 解析到了章节内容
        content = div_tag.text()
        fp.write(title +':'+ content+'\n')
        print(title,"爬取成功")