Python翻页爬取股票数据

 

# encoding:utf-8
import requests
import csv

headers = {
    'cookie':'device_id=02a63e162n=0035d9dae1eded6e3=1666944669347886',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/107.0.0.0 Safari/537.36'
    }


#循环翻页功能
for ye in range(1,5):
    url = 'https://stock.xueqiu.com/v5/stock/screener/quote/list.json?page=%d&size=30&order=desc&orderby=percent&order_by=percent&market=CN&type=sh_sz' %ye
    print('\033[1;33m%s\033[0m' % (("开始爬取第%s页数据" %ye).center(166, '-')))
    print(url)

    #################################################################################################################################
    print('\033[1;33m%s\033[0m' %("分割线".center(166,'-')))
    #################################################################################################################################

    response = requests.get(url=url, headers=headers)
    print(response)
    html_data = response.json()
    print(html_data)
    data_list = html_data['data']['list']
    print(data_list)

    #################################################################################################################################
    print('\033[1;33m%s\033[0m' %("分割线".center(166,'-')))
    #################################################################################################################################

    for i in data_list:
      dit = {}
      dit['股票代码'] = i['symbol']
      dit['股票名字'] = i['name']
      dit['当前价'] = i['current']
      dit['涨跌额'] = i['chg']
      dit['涨跌幅/%'] = i['percent']
      dit['年初至今/%'] = i['current_year_percent']
      dit['成交量'] = i['volume']
      dit['成交额'] = i['amount']
      dit['换手率/%'] = i['turnover_rate']
      dit['市盈率TTM'] = i['pe_ttm']
      dit['股息率/%'] = i['dividend_yield']
      dit['市值'] = i['market_capital']
      print(dit)


      #保存数据
      # f = open('股票数据.csv', mode='a', encoding='utf-8-sig', newline='')
      # csv_writer = csv.DictWriter(f, fieldnames=['股票代码', '股票名字', '当前价', '涨跌额', '涨跌幅/%', '年初至今/%',
      #                                            '成交量', '成交额', '换手率/%', '市盈率TTM', '股息率/%', '市值'])
      # csv_writer.writeheader()
      # csv_writer.writerow(dit)
      # f.close()

 

 

 

 

 

 

 

 

 

# encoding:utf-8

# encoding:utf-8
import requests
import csv
import time

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/107.0.0.0 Safari/537.36'
    }

cookies = {
  'Cookie': 'device_id=02a6jaWQiOiJkOW9347886'
 }

for ye in range(1,3):

    date = round(time.time() * 1000)

    params = {
        'page': '{}'.format(ye),
        'size': '30',
        'order': 'desc',
        'order_by': 'amount',
        'exchange': 'CN',
        'market': 'CN',
        'type': 'sha',
        '_': '{}'.format(date),
    }


    url = 'https://stock.xueqiu.com/v5/stock/screener/quote/list.json'
    print('\033[1;33m%s\033[0m' % (("开始爬取第%s页数据" %ye).center(166, '-')))
    print(url)

    #################################################################################################################################
    print('\033[1;33m%s\033[0m' %("分割线".center(166,'-')))
    #################################################################################################################################

    response = requests.get(url=url, params=params, headers=headers, cookies=cookies)
    print(response)
    html_data = response.json()
    print(html_data)
    data_list = html_data['data']['list']
    print(data_list)

    #################################################################################################################################
    print('\033[1;33m%s\033[0m' %("分割线".center(166,'-')))
    #################################################################################################################################

    for i in data_list:
      dit = {}
      dit['股票代码'] = i['symbol']
      dit['股票名字'] = i['name']
      dit['当前价'] = i['current']
      dit['涨跌额'] = i['chg']
      dit['涨跌幅/%'] = i['percent']
      dit['年初至今/%'] = i['current_year_percent']
      dit['成交量'] = i['volume']
      dit['成交额'] = i['amount']
      dit['换手率/%'] = i['turnover_rate']
      dit['市盈率TTM'] = i['pe_ttm']
      dit['股息率/%'] = i['dividend_yield']
      dit['市值'] = i['market_capital']
      print(dit)


      #保存数据
      # f = open('股票数据.csv', mode='a', encoding='utf-8-sig', newline='')
      # csv_writer = csv.DictWriter(f, fieldnames=['股票代码', '股票名字', '当前价', '涨跌额', '涨跌幅/%', '年初至今/%',
      #                                            '成交量', '成交额', '换手率/%', '市盈率TTM', '股息率/%', '市值'])
      # csv_writer.writeheader()
      # csv_writer.writerow(dit)
      # f.close()

 

 

 

 

 

 

# encoding:utf-8

import requests
import json
for ye in range(1, 3):
    print('\033[1;33m%s\033[0m' % (("开始爬取第%s页数据" % ye).center(166, '-')))
    url = "http://48.push2.eastmoney.com/api/qt/clist/get?cb=jQuery112402508937289440778_1658838703304&pn=%s&pz=20&po=1&np=1&ut=bd1d9ddb04089700cf9c27f6f7426281&fltt=2&invt=2&wbp2u=|0|0|0|web&fid=f3&fs=m:0+t:6,m:0+t:80,m:1+t:2,m:1+t:23,m:0+t:81+s:2048&fields=f1,f2,f3,f4,f5,f6,f7,f8,f9,f10,f12,f13,f14,f15,f16,f17,f18,f20,f21,f23,f24,f25,f22,f11,f62,f128,f136,f115,f152&_=1658838703305" % str(
        ye)
    print(url)
    res = requests.get(url)
    print("状态码:",res)

    result = res.text.split("jQuery112402508937289440778_1658838703304")[1].split("(")[1].split(");")[0]
    print("分割后的数据: ",result,'\n')

    result_json = json.loads(result)
    print("转换为字典后的数据: ",result_json,'\n')

    stock_data = result_json['data']['diff']
    print("股票数据: ",stock_data)

    for data in stock_data:
        print(data)
        #print(data["f14"])