欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页

使用bs4爬取小说

程序员文章站 2022-05-02 20:43:48
...

使用bs4爬取小说

#需求:爬取三国演义小说所有的章节和章节内容
import  requests
from bs4 import  BeautifulSoup
if __name__=="__main__":
    #对首页的页面数据解析爬取
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.163 Safari/537.36'
    }
    url = 'https://www.shicimingju.com/book/sanguoyanyi.html'
    response = requests.get(url=url,headers=headers)
    response.encoding = response.apparent_encoding
    page_text = response.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,需要将页面源码对象加载到该对象中
    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 = 'https://www.shicimingju.com'+li.a['href']
        #对详情页发起请求,解析出章节内容
        #解决乱码使用response = requests.get(url=url,headers=headers)
        #          response.encoding = response.apparent_encoding
        #response.apparent_encoding他是一个备用编码方式,他会根据内容自动匹配给你个合适的编码方式
        detail_response = requests.get(url=detail_url, headers=headers)
        detail_response.encoding = detail_response.apparent_encoding
        detail_page_text = detail_response.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+":"+content+'\n')
        print(title,'爬取成功。。。')