공공데이터 포털에서 XML과 JSON 데이터 읽어오기

Posted on: 2023년 04월 24일 2023년 04월 24일
Categories: 강의자료, 파이썬

농업기상 조회월별 일 기본 관측데이터(XML) 조회

api_key = '발급받은 api_key 입력'

import requests
import bs4
import pandas as pd
from lxml import html

page_no = 1
page_size = 100
my_url = 'http://apis.data.go.kr/1390802/AgriWeather/WeatherObsrInfo/GnrlWeather/getWeatherYearDayList'
params = {
    'ServiceKey' : api_key ,
    'Page_No' : page_no,
    'Page_Size' : page_size,
    'search_Year' : 2020,
    'obsr_Spot_Code' : '565862A001'
    }

lst_rows = []

for i in range(1, 1000000):
  params['Page_No'] = i

  response = requests.get(my_url, params=params, verify=False) #verify설정 추가
  content = response.text
  xml_obj = bs4.BeautifulSoup(content,'lxml-xml')

  result_Code = int(xml_obj.findAll('result_Code').pop().text)
  if result_Code != 200:
    print('Error')
    break

  #total_Count = int(xml_obj.findAll('total_Count').pop().text)
  rows = xml_obj.findAll('item')
  if len(rows) <= 0: break

  for r in rows:
    dict_row = dict()
    for t in r.contents:
      if t.name is not None:
        dict_row[t.name] = t.text

    lst_rows.append(pd.Series(dict_row))

df = pd.concat(lst_rows, axis=1)
df = df.T
df.to_csv('result.csv')

print(df)

api_key = '발급받은 api_key 입력'

import requests

import bs4

import pandas as pd

from lxml import html

page_no = 1

page_size = 100

my_url = 'http://apis.data.go.kr/1390802/AgriWeather/WeatherObsrInfo/GnrlWeather/getWeatherYearDayList'

params = {

'ServiceKey' : api_key ,

'Page_No' : page_no,

'Page_Size' : page_size,

'search_Year' : 2020,

'obsr_Spot_Code' : '565862A001'

}

lst_rows = []

for i in range(1, 1000000):

params['Page_No'] = i

response = requests.get(my_url, params=params, verify=False) #verify설정 추가

content = response.text

xml_obj = bs4.BeautifulSoup(content,'lxml-xml')

result_Code = int(xml_obj.findAll('result_Code').pop().text)

if result_Code != 200:

print('Error')

break

#total_Count = int(xml_obj.findAll('total_Count').pop().text)

rows = xml_obj.findAll('item')

if len(rows) <= 0: break

for r in rows:

dict_row = dict()

for t in r.contents:

if t.name is not None:

dict_row[t.name] = t.text

lst_rows.append(pd.Series(dict_row))

df = pd.concat(lst_rows, axis=1)

df = df.T

df.to_csv('result.csv')

print(df)

기상청_지상(종관, ASOS) 일자료(JSON) 조회서비스

api_key = ''

import requests
import json
import pandas as pd

lst_rows = []

page_no = 1
page_size = 20
my_url = 'http://apis.data.go.kr/1360000/AsosDalyInfoService/getWthrDataList'
params = {
    'ServiceKey' : api_key ,
    'numOfRows' : page_size,
    'pageNo' : page_no,
    'dataType' : 'JSON',
    'dataCd' : 'ASOS',
    'dateCd' : 'DAY',
    'startDt' : '20100101',
    'endDt' : '20100601',
    'stnIds' : '108'
}

for i in range(1, 1000000):
  params['pageNo'] = i
  response = requests.get(my_url, params=params, verify=False) #verify설정 추가
  html = json.loads(response.text)

  resultCode = html['response']['header']['resultCode']
  if resultCode != '00':
    break

  items = html['response']['body']['items']['item']
  for item in items:
    lst_rows.append(pd.Series(item))

df = pd.concat(lst_rows, axis=1)
df = df.T
df.to_csv('result.csv')
print(df)

api_key = ''

import requests

import json

import pandas as pd

lst_rows = []

page_no = 1

page_size = 20

my_url = 'http://apis.data.go.kr/1360000/AsosDalyInfoService/getWthrDataList'

params = {

'ServiceKey' : api_key ,

'numOfRows' : page_size,

'pageNo' : page_no,

'dataType' : 'JSON',

'dataCd' : 'ASOS',

'dateCd' : 'DAY',

'startDt' : '20100101',

'endDt' : '20100601',

'stnIds' : '108'

}

for i in range(1, 1000000):

params['pageNo'] = i

response = requests.get(my_url, params=params, verify=False) #verify설정 추가

html = json.loads(response.text)

resultCode = html['response']['header']['resultCode']

if resultCode != '00':

break

items = html['response']['body']['items']['item']

for item in items:

lst_rows.append(pd.Series(item))

df = pd.concat(lst_rows, axis=1)

df = df.T

df.to_csv('result.csv')

print(df)

whan0623

516