东方财富网爬虫程序

码农NoError

于 2024-07-12 18:08:08 发布

阅读量26

点赞数 1

文章标签：爬虫

本文链接：https://blog.csdn.net/zhangzhaoyuxunlei/article/details/140385946

版权

# 引入模块
import random
from urllib import request
import time
import json

for i in range(1, 283):
    print(f"当前正在爬取第{i}页")
    # 构造页码
    pn = i
    # 构造时间戳
    time_stamp = int(time.time()*1000)
    # 构造网址
    url = f"https://63.push2.eastmoney.com/api/qt/clist/get?cb=jQuery112407270498139752515_1720772400881&pn={pn}&pz=20&po=1&np=1&ut=bd1d9ddb04089700cf9c27f6f7426281&fltt=2&invt=2&dect=1&wbp2u=|0|0|0|web&fid=f3&fs=m:0+t:6,m:0+t:80,m:1+t:2,m:1+t:23,m:0+t:81+s:2048&fields=f1,f2,f3,f4,f5,f6,f7,f8,f9,f10,f12,f13,f14,f15,f16,f17,f18,f20,f21,f23,f24,f25,f22,f11,f62,f128,f136,f115,f152&_={time_stamp}"
    # 将请求结果存入response
    response = request.urlopen(url)
    # 读取数据 解码
    response = response.read().decode()
    # 切片剔除无用数据
    response = response[42:-2]
    # 将字符串转换为字典
    response = json.loads(response)
    # 遍历取值
    for data in response['data']['diff']:
        print(data['f5'],   data['f14'])

    time.sleep(random.randint(1, 3))