金融界網站 股票數據爬蟲案例

#!/usr/bin/env python 
# -*- coding: utf-8 -*-
# @Time    : 11/22/2019 4:05 PM
# @Author  : DeltaT
# @File    : 股票爬蟲2.py

"""
該爬蟲爬取了 金融界網站的股票數據.
在不使用selenium的情況下, 解決網頁異步加載數據的問題.
"""

import requests
import json

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36'
}

url = 'http://zjhqquery.jrj.com.cn/bzj.do?vname=sflow&c=name,code,sname,scode,pl,zjin,inratio,zlin,zlratio,j2,' \
      'zdratio,j1,xdratio&sort=zlin&page=1&order=desc&size=20&_dc=1574409865601'
response = requests.get(url, headers=headers)
json_str = response.content.decode('gbk')
json_str = json_str.replace('var sflow=', '')
index = json_str.find('HqData')
# print(index)
data = json_str[index:]
data = data.replace('HqData:', '')
data = data.replace('}', '')
data = json.loads(data)
for d in data:
    print(d)