[Python知识库]python中获取基金数据

完整代码：

from lxml.html import fromstring
from bs4 import BeautifulSoup
import xlwt
import json

with open('rr.html' ,'r' ,encoding='utf-8') as f:
    # Soup = BeautifulSoup(f, 'lxml')
    html = BeautifulSoup(f, 'html.parser')
    html.list=html.find_all('div',class_='box_cont_0 cb')
    # print(html.list)
fund=[]

for item in html.list:
    fundName=item.find('strong',class_='fund_name fl').a.text.strip('')
    fundSum = item.find_all('tr')[1].contents[1].string#获取第二tr标签下的第二个元素
    fundProfit = item.find_all('tr')[1].contents[4].string#获取第二tr标签下的第二个元素
    # print(fundName,fundSum,fundProfit,sep='/')
    # print(len(fundSum))
    fund.append({
        'fundName':fundName,
        'fundSum':fundSum ,
        'fundProfit':fundProfit
    })

with open('.fund.json', 'w', encoding='utf-8')as f:
    json.dump(fund, f, indent=1, ensure_ascii=False)

# 读取json
with open(".fund.json", 'r', encoding='utf-8') as f:
    data = json.load(f)


#创建一个workbook 设置编码
workbook = xlwt.Workbook(encoding='utf-8')
# 创建一个worksheet
worksheet = workbook.add_sheet('Worksheet')
title=["基金名称","总市值","利润"]
for i in range(len(title)):
    worksheet.write(0,i,title)
#写入excel参数对应 行, 列,值
# print(data[i]("fundSum"))
for i in range(len(data)):

    worksheet.write(i+1, 0, label=data[i]['fundName'])#label=data[1]["fundName"])z中的label可以不用
    worksheet.write(i+1, 1, label=data[i]["fundSum"])
    worksheet.write(i+1, 2, label=data[i]["fundProfit"])
    workbook.save('Excel.xls')