HSI_hist_data/sharehold.py

#
# https://programmer.ink/think/5d872dc23f36a.html
# 
from  lxml import etree
import requests
import csv
import os

def get_shareholdings(stkcode, tdate, lang='c'):

    headers={"User-Agent":"Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.112 Safari/537.36"}
    
    url= "https://www.hkexnews.hk/sdw/search/searchsdw%s.aspx" % ('_c' if lang == 'c' else '')
    print(url)
    shs_hold_date = '%s/%s/%s' % (tdate[0:4], tdate[4:6], tdate[6:8])
    datatime = {'__EVENTTARGET': 'btnSearch',
                '__EVENTARGUMENT':'',
                '__VIEWSTATE': '/wEPDwULLTIwNTMyMzMwMThkZHNjXATvSlyVIlPSDhuziMEZMG94',
                '__VIEWSTATEGENERATOR': '3B50BBBD',
                'today': tdate,
                'sortBy': 'shareholding',
                'sortDirection': 'desc',
                'alertMsg':'',
                'txtShareholdingDate': shs_hold_date,
                'txtStockCode': stkcode,
                'txtStockName': '',
                'txtParticipantID':'',
                'txtParticipantName':''
                }
    repensoe=requests.post(url,headers=headers,data=datatime)
    text=repensoe.text
    html1 = etree.HTML(text)
    div = html1.xpath("//div[@id='pnlResultNormal']//tbody%s" % ('/tr' if lang != 'en' else ''))
    data = []
    print("--" * 2)
    valuetime = html1.xpath("//input[@id='txtShareholdingDate']/@value")
    print(valuetime[0]+"Data available")
    filename = 'shshold-%s-%s%s.csv' % (stkcode, tdate, ('_c' if lang != 'en' else ''))
    
    for tb in div:
        try:
            participant_id = tb.xpath("./td[1]/div/text()")[1]
        except IndexError:
            participant_id = ''
        participant_name = tb.xpath("./td[2]/div/text()")[1]
        print (participant_name)
        participant_address = tb.xpath("./td[3]/div/text()")[1]
        right = tb.xpath("./td[4]/div/text()")[1]
        percent = tb.xpath("./td[5]/div/text()")[1]
        datadic = {"date": valuetime[0], "Participant number": participant_id, "Central System Participant Name": participant_name, "address": participant_address, "Shareholding": right,"Proportion": percent}
        data.append(datadic)
        
        


    csvhead = ["date", "Participant number", "Central System Participant Name", "address", "Shareholding","Proportion"]
    with open(filename, 'w', newline='') as fp:
        write = csv.DictWriter(fp, csvhead)
        write.writeheader()
        write.writerows(data)
    


if __name__ == '__main__':
    os.getcwd()
    os.chdir("./holding")    
    get_shareholdings('01810', '20210204')