爬虫（四）：简单爬取贴吧

#coding=utf-8
import  requests
class TiebaSpider():
    '''
    爬取贴吧
    '''
    def __init__(self,tiebaname):
        self.tiebaname=tiebaname
        self.init_url="https://tieba.baidu.com/f?kw="+tiebaname+"ie=utf-8&pn={}"
        #定义headers,模拟浏览器访问
        self.header={'User-Agent': 'ozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.67 Safari/537.36'}


    def create_urllist(self):
        return [self.init_url.format(i*50) for i in range(100)] #爬取100页


    def get_content(self,url):
        response=requests.get(url,headers=self.header)
        return response.content

    def save_content(self,content,yema):
        file='{}吧第{}页.html'.format(self.tiebaname,yema+1)
        with open(file,'wb') as f:
            f.write(content)

    def run(self):
        #建立url列表
        url_list=self.create_urllist()
        for url in url_list:
            #发送请求,得到数据
            content=self.get_content(url)
            #保存到本地
            yema=url_list.index(url)
            self.save_content(content,yema)

if __name__ == '__main__':
    tieba=TiebaSpider('李毅')
    tieba.run()