东方财富融资融券行业数据

目标：

 

代码：

import  requests
from lxml import etree
from bs4 import  BeautifulSoup
import  re
import  csv
import datetime

today = datetime.date.today().strftime('%Y%m%d')
url = 'http://data.eastmoney.com/gpzy/'

res = requests.get(url)
res.encoding = res.apparent_encoding
soup = BeautifulSoup(res.text,'lxml')
soup = soup.text
# html = etree.HTML(res.text)
# data = soup.text.strip().lstrip('pageCollect("#datatitle .tit");var pagedata={').rstrip(';}').split(':[')
data = re.search(r'hysjlb:\[([\s\S]*?)$',soup).group(1).strip().replace(' ','').replace('T00:00:00','').replace('-','')
location = data.find(']};')
data = data[:location].replace('\r\n','').replace(',{',',,{').split(',,')

date = []
hy = []
amtshareratio_pj = []
gssl = []
amtsharenum = []
bballowance = []
zysz = []

for i in range(len(data)):
    das = eval(data[i])
    date.append(das["tdate"])    #时间
    hy.append(das["hy"])        #行业
    amtshareratio_pj.append(das["amtshareratio_pj"])   #质押比例
    bballowance.append(das["bballowance"])          #质押总股本
    amtsharenum.append(das["amtsharenum"])          #质押总笔数
    gssl.append(das["gssl"])                        #公司家
    zysz.append(das["zysz"])                        #最新质押值


f = open('e:\\shuju\\3.csv', 'w',newline='')    #csv数据存储
writer = csv.writer(f)
writer.writerow(('序号','时间','行业','平均质押比例(%)','公司家数','质押总笔数','质押总股本（万元）','最新质押市值（万元）','采集时间'
))
for i in range(len(hy)):
    writer.writerow((i+1,date[i],hy[i],amtshareratio_pj[i],gssl[i],amtsharenum[i],bballowance[i],zysz[i],today))

结果：