[제로베이스 데이터 취업 스쿨 15기] 6주차 (EDA: 6. Naver API)

김지환·2023년 6월 10일

python

6주차: 6/5/2023 - 6/11/2023

User Registration

Naver Developer Center
Application
- Registration
- Application name: ds_study
- API
- Search
- Data Lab (Search word trend)
- Data Lab (Shopping insight)
  - Environment
  - WEB
  - http://localhost
- Client ID: **
- Client ****
- https://developers.naver.com/apps/#/myapps/2PZEuGo6Bvy18P1q4cBf/overview

Naver Search API

https://developers.naver.com/docs/serviceapi/search/blog/blog.md#python
urllib: module to manage the request/response of the server based on the http protocol
urllib.request: module to manage the request of the client
urllib.parse: analyzes the url address

Search: blogs

# 네이버 검색 API 예제 - 블로그 검색
import os
import sys
import urllib.request

client_id = "Insert ID"
client_secret = "Insert Secret"

encText = urllib.parse.quote("파이썬")
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)

response, response.getcode(), response.code, response.status

# Decode with utf-8 to read characters
print(response_body.decode("utf-8"))

Search: books

# 네이버 검색 API 예제 - 책 검색
import os
import sys
import urllib.request

client_id = "Insert ID"
client_secret = "Insert Secret"

encText = urllib.parse.quote("파이썬")
url = "https://openapi.naver.com/v1/search/book?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)

Search: cafes

# 네이버 검색 API 예제 - 카페 검색
import os
import sys
import urllib.request

client_id = "Insert ID"
client_secret = "Insert Secret"

encText = urllib.parse.quote("파이썬")
url = "https://openapi.naver.com/v1/search/cafearticle?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)

Search: shopping

# 네이버 검색 API 예제 - 쇼핑 검색
import os
import sys
import urllib.request

client_id = "Insert ID"
client_secret = "Insert Secret"

encText = urllib.parse.quote("파이썬")
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)

Search: encyclopedia

# 네이버 검색 API 예제 - 블로그 검색
import os
import sys
import urllib.request

client_id = "Insert ID"
client_secret = "Insert Secret"

encText = urllib.parse.quote("파이썬")
url = "https://openapi.naver.com/v1/search/encyc?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)

Search Product

import os
import sys
import urllib.request

client_id = "Insert ID"
client_secret = "Insert 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) 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_onpage()

import json
import datetime

def get_result_onpage(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 Successful" % datetime.datetime.now())
    return json.loads(response.read().decode("utf-8"))

url = gen_search_url("shop", "몰스킨", 1, 5)
one_result = get_result_onpage(url)

one_result
one_result["items"][0]["title"]
one_result["items"][0]["link"]
one_result["items"][0]["lprice"]
one_result["items"][0]["mallName"]

(3) 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

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

url = gen_search_url("shop", "몰스킨", 1, 5)
json_result = get_result_onpage(url)
pd_result = get_fields(json_result)

pd_result

(5) actMain()

result_mol = []

for n in range(1, 1000, 100):
    url = gen_search_url("shop", "몰스킨", n, 100)
    json_result = get_result_onpage(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.info()

result_mol["lprice"] = result_mol["lprice"].astype("float")
result_mol.info()

(6) to_excel()

!pip install xlsxwriter

writer = pd.ExcelWriter("../data/06_molskine_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.close()

(7) Visualization

!pip install koreanize-matplotlib
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline

import koreanize_matplotlib

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()