原文提供了从选股宝API获取数据的代码,本文在原代码基础上对数据进行处理,有需要的可在此基础上增加其他数据内容的处理。因为格式问题,引用的时候要稍微调整下。
collector.py代码:
import urllib.request
import http.cookiejar
import time
import datetime
class Collector(object):
def init(self):
self.cookies = http.cookiejar.CookieJar()
self.handler=urllib.request.HTTPCookieProcessor(self.cookies)
self.opener = urllib.request.build_opener(self.handler)
def requestURL(self,url):retryCount = 200while retryCount>0: retryCount = retryCount-1try: response = self.opener.open(url)return response.read()except Exception as e: print(url,e,datetime.datetime.now()) time.sleep(0.7)continue
xuangubao.py代码:
import datetime
import json
import pandas as pd
from collector import Collector
from jqdatasdk import *
auth('*', '*')
class Xuangubao(Collector):
def init(self):
Collector.init(self)
pass
def get_limitup_info(self):# trade_date = self.get_recent_tradingday()#trade_date = '2019-03-1'trade_date = datetime.datetime.now()print(trade_date)#url = 'https://flash-api.xuangubao.cn/api/pool/detail?pool_name=limit_up'url = 'https://flash-api.xuangubao.cn/api/pool/detail?pool_name=limit_up'content = self.requestURL(url) content = json.loads(content)#print(content)if content["code"] != 20000:print(content)return None# content 就是数据了,是个listcontent = content["data"]# 把数据放到dataframe中df_result = pd.DataFrame(content) stock_code = [] stock_name = [] stock_reason = [] plate_name = [] plate_reason = [] turnover_ratio = [] volume_bias_ratio = []for i in range(0,len(list(df_result['stock_chi_name']))): stock_code.append(df_result.iloc[i]['surge_reason']['symbol'][:6]) stock_name.append(df_result.iloc[i]['stock_chi_name']) stock_reason.append(df_result.iloc[i]['surge_reason']['stock_reason']) plate_name.append(df_result.iloc[i]['surge_reason']['related_plates'][0]['plate_name']) try: plate_reason.append(df_result.iloc[i]['surge_reason']['related_plates'][0]['plate_reason']) except: plate_reason.append('NA') pass turnover_ratio.append(df_result.iloc[i]['turnover_ratio']) volume_bias_ratio.append(df_result.iloc[i]['volume_bias_ratio'])print (stock_code)print(stock_name)print(stock_reason) df1 = pd.DataFrame(stock_code, columns=['股票代码']) df1['股票名称'] = pd.Series(stock_name, index=df1.index) df1['涨停原因'] = pd.Series(stock_reason, index=df1.index) df1['板块'] = pd.Series(plate_name, index=df1.index) df1['板块原因'] = pd.Series(plate_reason, index=df1.index) df1['换手率'] = pd.Series(turnover_ratio, index=df1.index) df1['volume_bias_ratio'] = pd.Series(volume_bias_ratio, index=df1.index)#df1=df1[df1['板块']!='ST股']#过滤STdf1 = df1[df1['板块'] != 'ST股']#过滤创业板,可以根据情况取消df2 = df1[(df1['股票代码']) < '300000'] df3 = df1[(df1['股票代码']) > '400000'] df1 = pd.concat([df2, df3])for i in range(0, len(list(df1['股票代码']))):#print("df1:")for j in range(0, len(list(df_result['stock_chi_name']))):if df1['股票名称'].iloc[i]==df_result['stock_chi_name'].iloc[j]: df1['股票代码'].iloc[i] = df_result['symbol'].iloc[j]# 注意文件中的时间类型都是时间戳,可以格式化为字符串df_result['first_break_limit_down'] = df_result['first_break_limit_down'].apply( lambda x: datetime.datetime.utcfromtimestamp(x).strftime("%Y-%m-%d %H:%M:%S")) df_result['first_break_limit_up'] = df_result['first_break_limit_up'].apply( lambda x: datetime.datetime.utcfromtimestamp(x).strftime("%Y-%m-%d %H:%M:%S")) df_result['first_limit_down'] = df_result['first_limit_down'].apply( lambda x: datetime.datetime.utcfromtimestamp(x).strftime("%Y-%m-%d %H:%M:%S")) df_result['first_limit_up'] = df_result['first_limit_up'].apply( lambda x: datetime.datetime.utcfromtimestamp(x).strftime("%Y-%m-%d %H:%M:%S")) df_result['last_break_limit_down'] = df_result['last_break_limit_down'].apply( lambda x: datetime.datetime.utcfromtimestamp(x).strftime("%Y-%m-%d %H:%M:%S")) df_result['last_break_limit_up'] = df_result['last_break_limit_up'].apply( lambda x: datetime.datetime.utcfromtimestamp(x).strftime("%Y-%m-%d %H:%M:%S")) df_result['last_limit_down'] = df_result['last_limit_down'].apply( lambda x: datetime.datetime.utcfromtimestamp(x).strftime("%Y-%m-%d %H:%M:%S")) df_result['last_limit_up'] = df_result['last_limit_up'].apply( lambda x: datetime.datetime.utcfromtimestamp(x).strftime("%Y-%m-%d %H:%M:%S")) df_result['listed_date'] = df_result['listed_date'].apply( lambda x: datetime.datetime.utcfromtimestamp(x).strftime("%Y-%m-%d %H:%M:%S")) df_result['new_stock_break_limit_up'] = df_result['new_stock_break_limit_up'].apply( lambda x: datetime.datetime.utcfromtimestamp(x).strftime("%Y-%m-%d %H:%M:%S"))# 保存文件或者存数据库,之后就可以在本地进行统计分析了df_result.to_csv("F:\limit_up.csv", encoding="gbk", index=False) df1.to_csv("F:\chulihou.csv", encoding="gbk", index=False)print("all done")
if name == "main":
cc = Xuangubao()
cc.get_limitup_info()
本社区仅针对特定人员开放
查看需注册登录并通过风险意识测评
5秒后跳转登录页面...
移动端课程