[제로베이스] 7주차_EDA 09

해오름·2023년 3월 15일

[zb]

목록 보기

15/18

📌3/14 영상 강의 Naver API , 팀 스터디

Naver API

1. 네이버 API 사용 등록

네이버 개발자 센터
https://developers.naver.com/apps/#/wizard/register?auth=true
Application
- 어플리케이션 등록
- 어플리케이션 이름 ds_study
- 사용 API
  - 검색
  - 데이터랩(검색어트렌드)
  - 데이터랩(쇼핑인사이트)
  -환경추가
  - WEB 설정
  - http://localhost
- Client ID: y6KOl0hqAheZ2YCUYuxr
- Client Secret: K4XOKgPETW
- https://developers.naver.com/apps/#/myapps/y6KOl0hqAheZ2YCUYuxr/overview

2. 네이버 검색 API 사용하기

https://developers.naver.com/docs/serviceapi/search/blog/blog.md#python # 개발 가이드

ulrlib : http 프로토콜에 따라서 서버의 요청/응답을 처리하기 위한 모듈
urllib.request : 클라리언트의 요청을 처리하는 모듈
urllib.parse : url 주소에 대한 분석

검색하기

블로그(blog), 책(book), 영화(movie), 카페(cafearticle), 쇼핑(shop), 백과사전(encyc)
원하는 검색 종류로 url 부분 수정한다

import os
import sys
import urllib.request

client_id = "나의 client_id"
client_secret = "나의 client_secret"

encText = urllib.parse.quote("머신러닝") #검색할 단어
url = "https://openapi.naver.com/v1/search/blog?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)

글자로 읽을 경우, decode utf-8 설정
print(response_body.decode("utf-8"))

3. 상품 검색

몰스킨

(1) gen_search_url()

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
    
gen_search_url("shop", "Test", 10, 3)

(2) 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()) # %포메팅
    return json.loads(response.read().decode("utf-8"))
    
url= gen_search_url("shop", "몰스킨", 1, 5)
one_result = get_result_openpage(url) # json 값은 dic 형태로 담겨있다

(3) get_fields()

import pandas as pd

def get_fields(json_data):
    title = [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  
    
get_fields(one_result)

(4) delete_tag()

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

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  
get_fields(one_result)

(5) actMain()

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)

(6) to_excel()

!pip install xlsxwriter # 만약 설치 안되면 코랩에서 설치하자

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()

ls"../data/06_molskin_diary_in_naver_shop.xlsx"

(7) 시각화

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