python爬虫爬取深交所数据

python爬虫爬取深交所数据

话不多说，直接上代码：

import requests
from bs4 import BeautifulSoup
import xlwt

headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.150 Safari/537.36 Edg/88.0.705.63'}

def Get_data(url):
	jsondata = requests.get(url,headers=headers).json()
	data1 = jsondata[0]
	list_col = data1['metadata']
	cols = list_col['cols']
	data2 = data1['data']
	COLS = []
	ROW1 = []
	ROW2 = []
	ROW3 = []
	ROW4 = []
	col1 = cols['lbmc']
	col2 = cols['zqsl']
	col3 = cols['zgb']
	col4 = cols['sjzz']
	col5 = cols['cjje']
	COLS.append(col1)
	COLS.append(col2.replace('<br>','/'))
	COLS.append(col3.replace('<br>','/'))
	COLS.append(col4.replace('<br>','/'))
	COLS.append(col5.replace('<br>','/'))
	row1 = data2[0]
	row11 = row1['lbmc']
	row12 = row1['zqsl']
	row13 = row1['zgb']
	row14 = row1['sjzz']
	row15 = row1['cjje']
	ROW1.append(row11)
	ROW1.append(row12)
	ROW1.append(row13)
	ROW1.append(row14)
	ROW1.append(row15)
	row2 = data2[1]
	row21 = row2['lbmc']
	row22 = row2['zqsl']
	row23 = row2['zgb']
	row24 = row2['sjzz']
	row25 = row2['cjje']
	ROW2.append(row21[-3:])
	ROW2.append(row22)
	ROW2.append(row23)
	ROW2.append(row24)
	ROW2.append(row25)
	row3 = data2[2]
	row31 = row3['lbmc']
	row32 = row3['zqsl']
	row33 = row3['zgb']
	row34 = row3['sjzz']
	row35 = row3['cjje']
	ROW3.append(row31[-3:])
	ROW3.append(row32)
	ROW3.append(row33)
	ROW3.append(row34)
	ROW3.append(row35)
	row4 = data2[3]
	row41 = row4['lbmc']
	row42 = row4['zqsl']
	row43 = row4['zgb']
	row44 = row4['sjzz']
	row45 = row4['cjje']
	ROW4.append(row41[-5:])
	ROW4.append(row42)
	ROW4.append(row43)
	ROW4.append(row44)
	ROW4.append(row45)
	print('*'*101)
	print('{0}      {1}       {2}       {3}        {4}'.format(col1,col2.replace('<br>','/'),col3.replace('<br>','/'),col4.replace('<br>','/'),col5.replace('<br>','/')))
	print('{0}          {1}                   {2}           {3}             {4}'.format(row11,row12,row13,row14,row15))
	print('{0}           {1}                   {2}           {3}             {4}'.format(row21[-3:],row22,row23,row24,row25))
	print('{0}           {1}                   {2}            {3}              {4}'.format(row31[-3:],row32,row33,row34,row35))
	print('{0}      {1}                       {2}               {3}                  {4}'.format(row41[-5:],row42,row43,row44,row45))
	print('*'*101)
	book = xlwt.Workbook(encoding='utf-8',style_compression=0)
	sheet = book.add_sheet('深交所基金市场概况',cell_overwrite_ok=True)
	for Col in range(len(COLS)):
		sheet.write(0,Col,COLS[Col])
	for Row1 in range(len(ROW1)):
		sheet.write(1,Row1,ROW1[Row1])
	for Row2 in range(len(ROW2)):
		sheet.write(2,Row2,ROW2[Row2])
	for Row3 in range(len(ROW3)):
		sheet.write(3,Row3,ROW3[Row3])
	for Row4 in range(len(ROW4)):
		sheet.write(4,Row4,ROW4[Row4])
	book.save("C:/Users/DELL/Desktop/深交所基金市场概况.xls")

if __name__ == '__main__':
	url = 'http://fund.szse.cn/api/report/ShowReport/data?SHOWTYPE=JSON&CATALOGID=lf_fund_scgk&loading=first&random=0.9140249439976937'
	Get_data(url)

运行结果：