bs4解析02

爬取《三国演义》小说所有的章节标题和章节内容

from bs4 import BeautifulSoup
import requests
# 对首页的页面数据进行爬取
url = 'http://sanguo.5000yan.com/'
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.107'
                 ' Safari/537.36 Edg/92.0.902.62'
}
page_text = requests.get(url=url,headers=headers).text
# 在首页中解析出章节的标题和详情页的url
# 实例化BeautifulSoup对象，需要将首页源码数据加载到该对象中
soup = BeautifulSoup(page_text,'lxml')
# 解析章节标题和详情页的URL
li_list = soup.select('.sidamingzhu-list-mulu>ul>li')
fp = open('./sgyy.txt','w',encoding='utf-8')
for li in li_list:
    title = li.a.string
    detail_url = 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_='grap')
    # 解析到了章节的内容
    content = div_tag.text
    fp.write(title+':' + content + '\n')
    print(title,'爬取成功！！！')