【爬虫系列】bs4+requests 爬取三国演绎文本

import requests
from bs4 import BeautifulSoup
#需求：爬取三国演义小说所有的章节标题和章节内容http://www.shicimingju.com/book/sanguoyanyi.html

if __name__ == '__main__':
    # 对首页的页面数据进行爬取
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.71 Safari/537.36'
    }
    url = 'http://www.shicimingju.com/book/sanguoyanyi.html'
    response = requests.get(url=url,headers=headers)
    response.encoding = response.apparent_encoding #设置编码为utf-8
    print(response.encoding)
    # Html1 = page_text.encode('iso-8859-1').decode('gbk')
    # 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(response.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_res = requests.get(url=detail_url,headers=headers)
        detail_page_res.encoding = detail_page_res.apparent_encoding #防止乱码
        detail_page_text = detail_page_res.text
        #解析出详情页中相关的章节内容
        detail_soup = BeautifulSoup(detail_page_text,'lxml')
        div_tg = detail_soup.find('div',class_='chapter_content')
        #解析到了章节的内容
        content = div_tg.text
        fp.write(title + ':' + content + '\n\n')
        print(title,'爬取成功！！！')

 

 

 

encoding是从http中的header中的charset字段中提取的编码方式，若header中没有charset字段则默认为ISO-8859-1编码模式，则无法解析中文，这是乱码的原因

apparent_encoding会从网页的内容中分析网页编码的方式，所以apparent_encoding比encoding更加准确。当网页出现乱码时可以把apparent_encoding的编码格式赋值给encoding。