百度贴吧爬虫获取网页

"""
  贴吧
"""

import requests
import re
from  urllib import parse
import time
import random


class BaiduSpider:
    def __init__(self):
        self.url = 'http://tieba.baidu.com/f?kw={}&pn={}'
        self.headers = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/13.0.782.41 Safari/535.1 QQBrowser/6.9.11079.201'}
    def get_html(self,url):
        html = requests.get(url=url,headers=self.headers).content.decode('utf-8')
        return html
    def parse_html(self):
        pass
    def save_html(self,filename,html):
        with open(filename,'w') as f:
            f.write(html)
    def run(self):
        name = input('请输入贴吧名')
        # page = int(input("请输入页码"))
        start = int(input('开始页'))
        end = int(input('结束页'))
        params = parse.quote(name)
        for page in range(start,end+1):
            pn = (page - 1) *50
            url = self.url.format(params,pn)
            html = self.get_html(url)
            filename = '{}第{}页.html'.format(name,page)
            self.save_html(filename,html)
            print('完成')
            time.sleep(random.randint(1,8))


if __name__ == '__main__':
    spider = BaiduSpider()
    spider.run()