Last active
November 30, 2017 09:18
-
-
Save NEJmark/60c55d9b1aed3e380c85 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
股價收盤價抓取練習.py | |
只能抓取近一個月,因為網站提供資料有限 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import urllib.request | |
import lxml.etree as etree | |
import datetime | |
def get_date_close_price(stocknum,date_string,date_format='%Y/%m/%d'): | |
#ex:'2330','2015/8/24','%Y/%m/%d' | |
#dateobj.strftime('%#m')可以 08 => 8 in windows | |
#dateobj.strftime('%-m')可以 08 => 8 in linux? | |
dateobj = datetime.datetime.strptime(date_string,date_format) | |
#print(dateobj) | |
stocknum = str(stocknum) | |
try: | |
data = urllib.request.urlopen('http://www.cnyes.com/twstock/ps_historyprice/'+str(stocknum)+'.htm').read().decode('utf-8',errors='ignores') | |
except Exception as e: | |
#return e.args | |
return 'null' | |
page = etree.HTML(data) | |
#print(page) | |
#print(dateobj.strftime('%Y/%m/%d')) | |
try: | |
return page.xpath('//tr/td[contains(text(),"'+ dateobj.strftime('%Y/%m/%d') +'")]/following-sibling::*')[3].text | |
except Exception as e: | |
#return e.args | |
return 'null' | |
#datetime.datetime.strptime('2015/8/24','%Y/%m/%d') | |
get_date_close_price('2330','2015/09/17') | |
#data = urllib.request.urlopen('http://www.cnyes.com/twstock/ps_historyprice/1101.htm').read().decode('utf-8',errors='ignores') | |
#page = etree.HTML(data) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment