python爬取股票信息—简略版（沪股）

简单写了个爬虫爬取东方财富网的股票信息，运用pandas将数据存储在excel表中。

# -*- codeing = utf-8 -*-
# @Time : 2021/3/2 18:10
# @Author : 老七疯狂吸氧
# @file indew.py
# @Software:PyCharm
import re
import requests
import pandas as pd
import json
import time
t = time.strftime('%Y%m%d', time.localtime(time.time()))
id=600000
urls=' '
for i in range(0,200):
  id+=1
  url='http://push2.eastmoney.com/api/qt/stock/get?ut=fa5fd1943c7b386f172d6893dbfba10b&fltt=2&fields=f59,f169,f170,f161,f163,f171,f126,f168,f164,f78,f162,f43,f46,f44,f45,f60,f47,f48,f49,f84,f116,f55,f92,f71,f50,f167,f117,f85,f84,f58,f57,f86,f172,f108,f118,f107,f164,f177&invt=2&secid=1.'+str(id)+'&cb=jQuery1124011428787362161041_1614607938714&_=1614607938729'
  html=requests.get(url).text
  print('完成',i)
  urls+=html
findlink43=re.compile(r'"f43":(.*?),')
dmoney=re.findall(findlink43,urls)
findlink44=re.compile(r'"f44":(.*?),')
hmoney=re.findall(findlink44,urls)
findlink45=re.compile(r'"f45":(.*?),')
smoney=re.findall(findlink45,urls)
findlink47=re.compile(r'"f47":(.*?),')
allh=re.findall(findlink47,urls)
findlink48=re.compile(r'"f48":(.*?),')
amoney=re.findall(findlink48,urls)
findlink58=re.compile(r'"f58":(.*?),')
name=re.findall(findlink58,urls)
findlink57=re.compile(r'"f57":(.*?),')
num=re.findall(findlink57,urls)
df = pd.DataFrame({'名称': name, '实时股价': dmoney,'日最高股价':hmoney,'日最低股价':smoney,'交易量':allh,'交易金额':amoney,'股票编号':num})
df = df.set_index("名称")
df.to_excel('D:/股票信息'+t+'.xlsx')