python获取涨停板历史数据

获取A股每天的涨停板数据，起始日期和截止日期都可以自定义。
这个数据可以用来后续的大数据分析，比如统计每天涨停板的数目和大盘指数的相关性，涨停打开次数与当日人气的强弱的关系。
 

Screenshot_from_2018-04-23_20-31-13.png
点击查看大图

python代码（pyhton2版本，另外最下面有python3版本的代码实现）：
# -*- coding=utf-8 -*-

import datetime



__author__ = 'Rocky'

'''

http://30daydo.com

Contact: weigesysu@qq.com

'''

# 每天的涨跌停

import urllib2, re, time, xlrd, xlwt, sys, os

import setting

import pandas as pd

import tushare as ts

from setting import LLogger

reload(sys)

sys.setdefaultencoding('gbk')



logger = LLogger('zdt.log')

class GetZDT:

    def __init__(self,current):

        self.user_agent = "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Ubuntu Chromium/64.0.3282.167 Chrome/64.0.3282.167 Safari/537.36"

        # self.today = time.strftime("%Y%m%d")

        self.today=current

        self.path = os.path.join(os.path.dirname(__file__), 'data')

        self.zdt_url = 'http://home.flashdata2.jrj.com.cn/limitStatistic/ztForce/' + self.today + ".js"

        self.zrzt_url = 'http://hqdata.jrj.com.cn/zrztjrbx/limitup.js'



        self.host = "home.flashdata2.jrj.com.cn"

        self.reference = "http://stock.jrj.com.cn/tzzs/z ... ot%3B



        self.header_zdt = {"User-Agent": self.user_agent,

                           "Host": self.host,

                           "Referer": self.reference}



        self.zdt_indexx = [u'代码', u'名称', u'最新价格', u'涨跌幅', u'封成比', u'封流比', u'封单金额', u'最后一次涨停时间', u'第一次涨停时间', u'打开次数',

                           u'振幅',

                           u'涨停强度']



        self.zrzt_indexx = [u'序号', u'代码', u'名称', u'昨日涨停时间', u'最新价格', u'今日涨幅', u'最大涨幅', u'最大跌幅', u'是否连板', u'连续涨停次数',

                            u'昨日涨停强度', u'今日涨停强度', u'是否停牌', u'昨天的日期', u'昨日涨停价', u'今日开盘价格', u'今日开盘涨幅']

        self.header_zrzt = {"User-Agent": self.user_agent,

                            "Host": "hqdata.jrj.com.cn",

                            "Referer": "http://stock.jrj.com.cn/tzzs/zrztjrbx.shtml"

                            }



    def getdata(self, url, headers, retry=5):

        req = urllib2.Request(url=url, headers=headers)

        for i in range(retry):

            try:

                resp = urllib2.urlopen(req,timeout=20)

                content = resp.read()

                md_check = re.findall('summary|lasttradedate',content)

                if content and len(md_check)>0:

                    return content

                else:

                    time.sleep(60)

                    logger.log('failed to get content, retry: {}'.format(i))

                    continue

            except Exception, e:

                logger.log(e)

                time.sleep(60)

                continue

        return None



    def convert_json(self, content):

        p = re.compile(r'"Data":(.*)};', re.S)

        if len(content)<=0:

            logger.log('Content\'s length is 0')

            exit(0)

        result = p.findall(content)

        if result:

            try:

            # print result

                t1 = result[0]

                t2 = list(eval(t1))

                return t2

            except Exception,e:

                logger.log(e)

                return None

        else:

            return None





    def save_to_dataframe(self, data, indexx, choice, post_fix):

        engine = setting.get_engine('db_zdt')

        if not data:

            exit()

        data_len = len(data)

        if choice == 1:

            for i in range(data_len):

                data[choice] = data[choice].decode('gbk')



        df = pd.DataFrame(data, columns=indexx)



        filename = os.path.join(self.path, self.today + "_" + post_fix + ".xls")

        if choice == 1:

            df[u'今天的日期']=self.today

            df.to_excel(filename, encoding='gbk')

            try:

                df.to_sql(self.today + post_fix, engine, if_exists='fail')

            except Exception,e:

                logger.log(e)





    def storedata(self):

        zdt_content = self.getdata(self.zdt_url, headers=self.header_zdt)

        logger.log('zdt Content'+zdt_content)

        zdt_js = self.convert_json(zdt_content)

        self.save_to_dataframe(zdt_js, self.zdt_indexx, 1, 'zdt')

        time.sleep(5)



if __name__ == '__main__':

    date_list = [datetime.datetime.strftime(i,'%Y%m%d') for i in list(pd.date_range('20170401','20171231'))]

    for today in date_list:



        if not ts.is_holiday(datetime.datetime.strptime(today,'%Y%m%d').strftime('%Y-%m-%d')):

            print today

            obj = GetZDT(today)

            obj.storedata()

        else:

            logger.log('Holiday')

 
python3代码：
# -*- coding=utf-8 -*-

__author__ = 'Rocky'

'''

http://30daydo.com

Contact: weigesysu@qq.com

'''

# 每天的涨跌停

import re

import time

import xlrd

import xlwt

import sys

import os

import setting

from setting import is_holiday, DATA_PATH

import pandas as pd

import tushare as ts

from setting import llogger

import requests

from send_mail import sender_139

import datetime

# reload(sys)

# sys.setdefaultencoding('gbk')



logger = llogger(__file__)





class GetZDT:

    def __init__(self):

        self.user_agent = "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Ubuntu Chromium/64.0.3282.167 Chrome/64.0.3282.167 Safari/537.36"

        self.today = time.strftime("%Y%m%d")

        self.path = DATA_PATH

        self.zdt_url = 'http://home.flashdata2.jrj.com.cn/limitStatistic/ztForce/' + \

            self.today + ".js"

        self.zrzt_url = 'http://hqdata.jrj.com.cn/zrztjrbx/limitup.js'



        self.host = "home.flashdata2.jrj.com.cn"

        self.reference = "http://stock.jrj.com.cn/tzzs/z ... ot%3B



        self.header_zdt = {"User-Agent": self.user_agent,

                           "Host": self.host,

                           "Referer": self.reference}



        self.zdt_indexx = [u'代码', u'名称', u'最新价格', u'涨跌幅', u'封成比', u'封流比', u'封单金额', u'最后一次涨停时间', u'第一次涨停时间', u'打开次数',

                           u'振幅',

                           u'涨停强度']



        self.zrzt_indexx = [u'序号', u'代码', u'名称', u'昨日涨停时间', u'最新价格', u'今日涨幅', u'最大涨幅', u'最大跌幅', u'是否连板', u'连续涨停次数',

                            u'昨日涨停强度', u'今日涨停强度', u'是否停牌', u'昨天的日期', u'昨日涨停价', u'今日开盘价格', u'今日开盘涨幅']

        self.header_zrzt = {"User-Agent": self.user_agent,

                            "Host": "hqdata.jrj.com.cn",

                            "Referer": "http://stock.jrj.com.cn/tzzs/zrztjrbx.shtml"

                            }



    def getdata(self, url, headers, retry=5):

        for i in range(retry):

            try:

                resp = requests.get(url=url, headers=headers)

                content = resp.text

                md_check = re.findall('summary|lasttradedate', content)

                if content and len(md_check) > 0:

                    return content

                else:

                    time.sleep(60)

                    logger.info('failed to get content, retry: {}'.format(i))

                    continue

            except Exception as e:

                logger.info(e)

                time.sleep(60)

                continue

        return None



    def convert_json(self, content):

        p = re.compile(r'"Data":(.*)};', re.S)

        if len(content) <= 0:

            logger.info('Content\'s length is 0')

            exit(0)

        result = p.findall(content)

        if result:

            try:

                # print(result)

                t1 = result[0]

                t2 = list(eval(t1))

                return t2

            except Exception as e:

                logger.info(e)

                return None

        else:

            return None



    # 2016-12-27 to do this

    def save_excel(self, date, data):

        # data is list type

        w = xlwt.Workbook(encoding='gbk')

        ws = w.add_sheet(date)

        excel_filename = date + ".xls"

        # sheet=open_workbook(excel_filenme)

        # table=wb.sheets()[0]

        xf = 0

        ctype = 1

        rows = len(data)

        point_x = 1

        point_y = 0

        ws.write(0, 0, u'代码')

        ws.write(0, 1, u'名称')

        ws.write(0, 2, u'最新价格')

        ws.write(0, 3, u'涨跌幅')

        ws.write(0, 4, u'封成比')

        ws.write(0, 5, u'封流比')

        ws.write(0, 6, u'封单金额')

        ws.write(0, 7, u'第一次涨停时间')

        ws.write(0, 8, u'最后一次涨停时间')

        ws.write(0, 9, u'打开次数')

        ws.write(0, 10, u'振幅')

        ws.write(0, 11, u'涨停强度')

        print("Rows:%d" % rows)

        for row in data:

            rows = len(data)

            cols = len(row)

            point_y = 0

            for col in row:

                # print(col)

                # table.put_cell(row,col,)

                # print(col)

                ws.write(point_x, point_y, col)

                # print("[%d,%d]" % (point_x, point_y))

                point_y = point_y + 1



            point_x = point_x + 1



        w.save(excel_filename)



    def save_to_dataframe(self, data, indexx, choice, post_fix):

        engine = setting.get_engine('db_zdt')

        if not data:

            exit()

        data_len = len(data)

        if choice == 1:

            for i in range(data_len):

                data[i][choice] = data[i][choice]



        df = pd.DataFrame(data, columns=indexx)



        filename = os.path.join(

            self.path, self.today + "_" + post_fix + ".xls")



        # 今日涨停

        if choice == 1:

            df['今天的日期'] = self.today

            df.to_excel(filename, encoding='gbk')

            try:

                df.to_sql(self.today + post_fix, engine, if_exists='fail')

            except Exception as e:

                logger.info(e)

        # 昨日涨停

        if choice == 2:

            df = df.set_index(u'序号')

            df[u'最大涨幅'] = df[u'最大涨幅'].map(lambda x: round(x * 100, 3))

            df[u'最大跌幅'] = df[u'最大跌幅'].map(lambda x: round(x * 100, 3))

            df[u'今日开盘涨幅'] = df[u'今日开盘涨幅'].map(lambda x: round(x * 100, 3))

            df[u'昨日涨停强度'] = df[u'昨日涨停强度'].map(lambda x: round(x, 0))

            df[u'今日涨停强度'] = df[u'今日涨停强度'].map(lambda x: round(x, 0))

            try:

                df.to_sql(self.today + post_fix, engine, if_exists='fail')

            except Exception as e:

                logger.info(e)



            avg = round(df['今日涨幅'].mean(), 2)

            current = datetime.datetime.now().strftime('%Y-%m-%d')

            title = '昨天涨停个股今天{}\n的平均涨幅{}\n'.format(current, avg)

            try:

                sender_139(title, title)

            except Exception as e:

                print(e)



    # 昨日涨停今日的状态，今日涨停



    def storedata(self):

        zdt_content = self.getdata(self.zdt_url, headers=self.header_zdt)

        logger.info('zdt Content' + zdt_content)

        zdt_js = self.convert_json(zdt_content)

        self.save_to_dataframe(zdt_js, self.zdt_indexx, 1, 'zdt')

        time.sleep(0.5)

        zrzt_content = self.getdata(self.zrzt_url, headers=self.header_zrzt)

        logger.info('zrzt Content' + zdt_content)



        zrzt_js = self.convert_json(zrzt_content)

        self.save_to_dataframe(zrzt_js, self.zrzt_indexx, 2, 'zrzt')





if __name__ == '__main__':

    # today='2018-04-16'

    # 填补以前的数据

    # x=pd.date_range('20170101','20180312')

    # date_list = [datetime.datetime.strftime(i,'%Y%m%d') for i in list(pd.date_range('20170401','20171231'))



    if is_holiday():

        logger.info('Holiday')

        exit()

    logger.info("start")

    obj = GetZDT()

    obj.storedata()

 
原创。
转载请注明出处。
http://30daydo.com/article/295
 [/i][/i][/code] 
欢迎关注公众号：可转债量化分析
 
0
分享 2018-04-23

18 个评论

cgbin

cgbin

兄好，提示找不到模块了/

import setting
import pandas as pd
import tushare as ts
2018-07-01 13:26
李魔佛

李魔佛 回复 cgbin

setting是自己写的一个模块,只是保存了一些配置信息.
2018-07-02 09:38
fenghuting

fenghuting

你这个数据是写入mongodb的吗? setting里定义了数据库信息?
2018-09-21 14:31
李魔佛

李魔佛 回复 fenghuting

对。----------
2018-09-22 22:51
龙晓静

龙晓静

您好，这个程序怎么样才能够运行啊?在我电脑上运行不了。 写程序的小白。
2018-11-14 17:23
李魔佛

李魔佛 回复 龙晓静

贴出错误来看看？
2018-11-14 18:17
龙晓静

龙晓静

哥哥：您有联系方式吗？或者我的微信是15701332990.我觉得这个模型很好。
2018-11-14 19:21
龙晓静

龙晓静

File "I:/python/zhangtingban.py", line 29
self.reference = "http://stock.jrj.com.cn/tzzs/z ... ot%3B
^
SyntaxError: EOL while scanning string literal
2018-11-14 19:24
sxinfo

sxinfo

错误提示：
except Exception, e:
invalid syntax
2019-02-01 16:50
李魔佛

李魔佛 回复 sxinfo

python2的代码，你要换成py2
2019-02-01 18:10
sxinfo

sxinfo

哦，能改成PY3的吗？
2019-02-01 19:43
sxinfo

sxinfo

哦，那个改了。最后的 [/i][/i]又报 invalid syntax错误了
2019-02-01 19:47
李魔佛

李魔佛 回复 sxinfo

可以，后面可以改一下
2019-02-02 08:55
李魔佛

李魔佛 回复 sxinfo

那个是编辑器显示的问题，现在应该好了
2019-02-02 08:55
张易无忌

张易无忌

楼主你好 谢谢分享 请问这个项目能放到git上吗？ 因为缺少setting文件 没法复现
2019-05-02 21:07
李魔佛

李魔佛 回复 张易无忌

setting文件不是必须的，你可以把setting用的包注释了也可以运行的。
2019-05-05 09:00
serene233

serene233

你好，我想问一下，我把代码里用到setting的都注释掉了，然后跑起来程序没有输出，请问是什么情况呢，谢谢！
2019-05-25 00:10
李魔佛

李魔佛 回复 serene233

那是因为周末不会执行。。
2019-05-26 00:13

要回复文章请先登录或注册

Copyright © 2024