네이버 API

• 가이드 코드 -https://developers.naver.com/docs/serviceapi/search/blog/blog.md#python
• urllib : http 프로토콜에 따라서 서버의 요청/응답을 처리하기 위한 모듈
• urllib.request : 클라이언트의 요청을 처리하는 모듈
• urllib.parse : url 주소에 대한 분석

예제 코드

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

client_id = "ID"
client_secret = "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)

검색 : 책(book)

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

client_id = "ID"
client_secret = "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)

검색 : 카페(cafearticle)

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

client_id = "ID"
client_secret = "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)

몰스킨 검색

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

client_id = "ID"
client_secret = "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()

• encText = urllib.parse.quote("몰스킨")

• url = "https://openapi.naver.com/v1/search/shop?query=" + encText # JSON 결과

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 Success" % 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

(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
    
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    
    
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)

(6) 시각화

import warnings
import matplotlib.pyplot as plt
import seaborn as sns
from matplotlib import rc, font_manager


get_ipython().run_line_magic('matplotlib', 'inline')
plt.rcParams['font.family'] = 'Malgun Gothic'
warnings.simplefilter(action='ignore', category=FutureWarning)

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