基本信息

---

下载

   友情提示：（无需注册或充值，赞助后即可获取资源下载链接）

---

     嘿，亲！知识可是无价之宝呢，但咱这精心整理的资料也耗费了不少心血呀。小小地破费一下，绝对物超所值哦！如有下载和支付问题，请联系我们QQ(微信同号)：813200300

本次赞助数额为： 2 元　

支付宝支付

微信支付

   源码介绍

---

mport requests from lxml import etree class Tieba(object): def __init__(self,name): self.url = "https://tieba.baidu.com/f?ie=utf-8&kw={}".format(name) self.headers1 = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36 Edg/89.0.774.57"} #        self.headers = {"User-Agent":"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; en) Opera 9.50"}   def get_data(self,url):
        response = requests.get(url,headers=self.headers1) with open("./temp.html","wb") as f:
            f.write(response.content) return response.content def parse_data(self,data): # 创建element对象  data = data.decode().replace("<!--","").replace("-->","")
        html = etree.HTML(data)
        el_list = html.xpath('//li[@class=" j_thread_list clearfix thread_item_box"]/div/div[2]/div[1]/div[1]/a') # print(len(el_list))  data_list = [] for el in el_list:
            temp ={}
            temp['title'] = el.xpath("./text()")[0]
            temp['link'] = 'http://tieba.baidu.com'  el.xpath("./@href")[0]
            data_list.append(temp) # 获取下一页url 找翻页url尽量不要使用索引  try: #next_url = 'https:'   html.xpath('//a[@class="next pagination-item"]/@href')  next_url = 'https:'  html.xpath('//a[contains(text(),"下一页>")]/@href')[0] except:
                next_url = None  return data_list,next_url def save_data(self,data_list): for data in data_list: print(data) def run(self): # url  # headers  next_url = self.url while True: # 发送请求，获取响应  data = self.get_data(next_url) # 从响应获取数据（数据和翻页用的url）  data_list,next_url = self.parse_data(data) self.save_data(data_list) #  print(next_url,"----------------------------------")  # 判断是否终结  if next_url == None: break  if __name__ == '__main__':
    tieba = Tieba("传智播客")
    tieba.run()