#coding=utf-8
import requests
class TiebaSpider:
def __init__ (self,tieba_name):
self.tieba_name = tieba_name
self.url_temp = "https://tieba.baidu.com/f?kw="+tieba_name+"&ie=utf-8&pn={}"
self.headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36"}
def get_url_list(self):#构造url列表
# url_list = []
# for i in range(1000):
# url_list.append(self.url_temp.format(i*50))
# return url_list
return [self.url_temp.format(i*50) for i in range(1000)]
def parse_url(self,url):#发送请求获取响应
print(url)
response = requests.get(url,headers=self.headers)
return response.content.decode()
def save_html(self,html_str,page_num):#保存 html字符串
file_path = "{}-第{}页.html".format(self.tieba_name,page_num)
with open(file_path,"w",encodin