네이버 금융에서 일별 종가를 읽어오는 클래스 (http://estenpark.tistory.com/353 참고 - 이걸 그대로 클래스로 구현함)

stock_cralwer.py

## http://estenpark.tistory.com/353 참고 (거의 그대로 가져옴)

import urllib
import time
import sys
from urllib import urlopen
from bs4 import BeautifulSoup

class NaverStockCrawler(object):
    """네이버 금융에서 일별 종가를 읽어오는 클래스"""
    def __init__(self, stock_item):
        self.stock_item = stock_item
        self.url = 'http://finance.naver.com/item/sise_day.nhn?code='+ stock_item
        self.items = OrderedDict()
    
    def get(self, days=40):
        url = 'http://finance.naver.com/item/sise_day.nhn?code='+ self.stock_item
        html = urlopen(self.url) 
        source = BeautifulSoup(html.read(), "html.parser")

        maxPage=source.find_all("table", align="center")
        mp = maxPage[0].find_all("td", class_="pgRR")
        mpNum = int(mp[0].a.get('href')[-3:])
        pages = days//10 if days%10==0 else days//10 + 1

        for page in range(1, pages+1):
            sys.stdout.write("\r* crawling page " + str(page) + "...")
            sys.stdout.flush()
            page_url = self.url +'&page='+ str(page)
            html = urlopen(page_url)
            source = BeautifulSoup(html.read(), "html.parser")
            srlists=source.find_all("tr")
            isCheckNone = None
            if((page % 1) == 0):
                time.sleep(1.40)

            for i in range(1,len(srlists)-1):
                if(srlists[i].span != isCheckNone):
                    date = srlists[i].find_all("td",align="center")[0].text
                    price = srlists[i].find_all("td",class_="num")[0].text
                    self.items[date] = float(price.replace(",", ""))