Naver API 기본 예제

함수 만들기

import os
import sys
import urllib.request

client_id = "client_id"
client_secret = "client_secret"

encText = urllib.parse.quote("몰스킨")
url = "https://openapi.naver.com/v1/search/shop?query=" + encText # JSON 결과
# url = "https://openapi.naver.com/v1/search/blog.xml?query=" + encText # XML 결과
request = urllib.request.Request(url)
request.add_header("X-Naver-Client-Id",client_id)
request.add_header("X-Naver-Client-Secret",client_secret)
response = urllib.request.urlopen(request)
rescode = response.getcode()

if(rescode==200):
    response_body = response.read()
    print(response_body.decode('utf-8'))
else:
    print("Error Code:" + rescode)

1-1) url 생성 (gen_search_url)

# encText = urllib.parse.quote("몰스킨")
# url = "https://openapi.naver.com/v1/search/shop?query=" + encText 

def gen_search_url(api_node, search_text, start_num, disp_num):
    base = "https://openapi.naver.com/v1/search"
    node = "/" + api_node + ".json"
    param_query = "?query=" + urllib.parse.quote(search_text)
    param_start = "&start=" + str(start_num)
    param_disp = "&display=" + str(disp_num)
    
    return base + node + param_query + param_start + param_disp

1-2) 검색 결과 (get_result_openpage)

import json
import datetime

def get_result_openpage(url):
    request = urllib.request.Request(url)
    request.add_header("X-Naver-Client-Id",client_id)
    request.add_header("X-Naver-Client-Secret",client_secret)
    response = urllib.request.urlopen(request)
    print("[%s] Url Request Success" % datetime.datetime.now())
    return json.loads(response.read().decode("utf-8"))

1-3) 태그 삭제 (delete_tag)

def delete_tag(input_str):
    input_str = input_str.replace("<b>", "")
    input_str = input_str.replace("</b>", "")
    return input_str

1-4) 데이터 추출 (get_fields)

import pandas as pd
def get_fields(json_data):
    title = [delete_tag(each["title"]) for each in json_data["items"]]
    link = [each["link"] for each in json_data["items"]]
    lprice = [each["lprice"] for each in json_data["items"]]
    mall_name = [each["mallName"] for each in json_data["items"]]
    
    result_pd = pd.DataFrame({
        "title":title,
        "link":link,
        "lprice":lprice,
        "mall":mall_name
    }, columns=["title", "lprice", "link", "mall"])
    return result_pd

데이터 모으기 실행

result_mol = []

for n in range(1, 1000, 100):
    url = gen_search_url("shop", "몰스킨", n, 100)
    json_result = get_result_openpage(url)
    pd_result = get_fields(json_result)
    
    result_mol.append(pd_result)
    
result_mol = pd.concat(result_mol)

result_mol.reset_index(drop=True, inplace=True)
result_mol['lprice'] = result_mol['lprice'].astype("float")

엑셀

#!pip install xlsxwriter

writer = pd.ExcelWriter("../data/06_molskin_diary_in_naver_shop.xlsx", engine="xlsxwriter")
result_mol.to_excel(writer, sheet_name="Sheet1")

workbook = writer.book
worksheet = writer.sheets["Sheet1"]
worksheet.set_column("A:A", 4)
worksheet.set_column("B:B", 60)
worksheet.set_column("C:C", 10)
worksheet.set_column("D:D", 10)
worksheet.set_column("E:E", 50)
worksheet.set_column("F:F", 10)

worksheet.conditional_format("C2:C1001", {"type":"3_color_scale"})
writer.save()

시각화

import matplotlib.pyplot as plt
import seaborn as sns
import platform
from matplotlib import font_manager, rc
%matplotlib inline

path = "C:/Windows/Fonts/malgun.ttf"

if platform.system() == "Darwin":
    rc("font", family="Arial Unicode MS")
elif platform.system() == "Windows":
    font_name = font_manager.FontProperties(fname=path).get_name()
    rc("font", family=font_name)
else : 
    print("Unknown system. sorry")

plt.figure(figsize=(15,6))
sns.countplot(
    x=result_mol["mall"],
    data=result_mol,
    palette="RdYlGn",
    order=result_mol["mall"].value_counts().index
)
plt.xticks(rotation=90)
plt.show()