# coding=utf-8
import requests
# headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3941.4 Safari/537.36"}#模拟浏览器内核
class TiebaSpider:
def __init__ (self,tieba_name):
self.tieba_name = tieba_name
self.url_temp = "http://tieba.baidu.com/f?kw="+tieba_name+"&ie=utf-8&pn={}"
self.headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3941.4 Safari/537.36"}
def get_url_list(self):#1.构造url列表
url_list = []
for i in range(100):
url_list.append(self.url_temp.format(i*2))#爬取页码*2
return url_list
#return [self.url_temp.format(i*2) for i in range(5)]等效前4句
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",encoding="utf-8") as f:
f.write(html_str)
def run(self):
url_list = self.get_url_list()
for url in url_list:
html_str = self.parse_url(url)
page_num = url_list.index(url)+1
self.save_html(html_str,page_num)
if __name__ == '__main__':
tieba_spider = TiebaSpider("lol")
tieba_spider.run()
