爬虫-----雪球网的房产信息

import json
import requests
#urllib 的相关操作
url ='https://xueqiu.com/v4/statuses/public_timeline_by_category.json?since_id=-1&max_id={}&count={}&category=111'

def lei (num,max_id = None,count = None):
    #手动设置count
    count = 15
    #判断url 里 的 max _id
    if max_id is None:
        a = url.format(max_id=-1,count=10)
    else:
        a = url.format(max_id,count)

    #爬取市遇到错误,添加头部headers
    headers = {
        # 'Accept' : '*/*',
        # 'Accept-Encoding' : 'gzip, deflate, br',
        # 'Accept-Language' : 'zh-CN,zh;q=0.9',
        # 'Connection' : 'keep-alive',
        'Cookie' : '_ga=GA1.2.196337452.1534315041; _gid=GA1.2.1615699811.1534315041; device_id=16c92affeb2505503c12d5d10895cdbf; aliyungf_tc=AQAAAAe7aEnlqgoAUhVFeemx5vOqGZRe; xq_a_token=584d0cf8d5a5a9809761f2244d8d272bac729ed4; xq_a_token.sig=x0gT9jm6qnwd-ddLu66T3A8KiVA; xq_r_token=98f278457fc4e1e5eb0846e36a7296e642b8138a; xq_r_token.sig=2Uxv_DgYTcCjz7qx4j570JpNHIs; u=691534336127228; Hm_lvt_1db88642e346389874251b5a1eded6e3=1534315043,1534336127; Hm_lpvt_1db88642e346389874251b5a1eded6e3=1534336127; _gat_gtag_UA_16079156_4=1',
        # 'Host' : 'xueqiu.com',
        # 'Referer' : 'https://xueqiu.com/',
        'User-Agent' : 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.84 Safari/537.36',
        # 'X-Requested-With' : 'XMLHttpRequest',
    }
    #设置页码数
    if num<=3:
        num+=1

    response = requests.get(a,headers=headers)

    res_dict = json.loads(response.text)

    list_list = res_dict['list']
    print(list_list)
    for list_item_dict in  list_list:
        data_str = list_item_dict['data']
        s = json.loads(data_str)
        print(s['id'],s['title'],s['description'],s['target'])
        id_str = list_item_dict['id']
        print(id_str)
    # list_list[-1]['id']
    aa =list_list[-1]['id']
    #最后一项的id
    print(aa)
    lei(num,max_id=aa,count=count)
#
if __name__ =='__main__':
    lei(num=1,max_id=-1,count=10)
  • 0
    点赞
  • 1
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值