다음(Daum)사이트 일별 환율 정보 웹 크롤링 - 주피터

import requests
import pandas as pd

① 웹 서비스 분석(개발자도구 ): URL

country="JPY"
page=1
perPage=10
url = f"https://finance.daum.net/api/exchanges/FRX.KRW{country}/days?symbolCode=FRX.KRW{country}&terms=days&page={page}&perPage={perPage}"

② request(url,params,headers) > response(json) : JSON(str) 

 

403 에러가 날 경우 user-agent,referer,cookie 확인하기

따라서, 이 때는 user-agent,referer를 넣으면 해결된다.

#headers를 추가안 할 시 오류가 생성됨
headers={
    "user-agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.0.0 Safari/537.36",
    "referer":f"https://finance.daum.net/exchanges/FRX.KRW{country}"
}

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

③ JSON(str) > list, dict > DataFrame 

data = response.json()["data"]
df = pd.DataFrame(data)[["date","basePrice"]]
df

④ 함수로 만들기

def exchange(country,page,perPage):
    url = f"https://finance.daum.net/api/exchanges/FRX.KRW{country}/days?symbolCode=FRX.KRW{country}&terms=days&page={page}&perPage={perPage}"
    headers={
        "user-agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.0.0 Safari/537.36",
        "referer":f"https://finance.daum.net/exchanges/FRX.KRW{country}"
    }
    response = requests.get(url,headers=headers)
    data = response.json()["data"]
    return pd.DataFrame(data)[["date","basePrice"]]

df = exchange("JPY",1,50)
df