爬虫学习-爬取小说

import requests

from bs4 import BeautifulSoup

# 发送请求，获得响应
def get_page(url):
    header={
        'User-agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36'
    }
    cont=requests.get(url,headers=header)  #发送请求
    html=cont.content  #获取网页内容
    title=BeautifulSoup(html).title.text.split('(')[0]  #根据网页获取书名
    filename=title+'.txt'  #建立书单
    tag = BeautifulSoup(html).find_all('dd', {'class': 'col-md-3'}) #获取章节名
    with open(filename,'w+',encoding="utf-8") as file:
        file.write(title+'\n\n')
        for link in tag:
            title=link.string
            file.write(title+'\n\n')
            link=link.find('a')['href']
            link=requests.get(url+link)
            html2=link.content
            cont=BeautifulSoup(html2).find(id='htmlContent')
            content=cont.text
            file.write(content+'\n\n')


if __name__ == '__main__':
    # 1.获取url地址
    page=input('请输入对应的网页：')#填写一个对应的数字即可
    url='http://www.7kankan.la/book/'+page+'/'
    get_page(url)