__NEXT_DATA__ TO JSON

jaehoon sim·2023년 1월 3일

code

import requests
from bs4 import BeautifulSoup
import json

url = 'https://ridibooks.com/category/bestsellers/6050'

req_header_dict = {
    # 요청헤더 : 브라우저정보
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.99 Safari/537.36'
}
res = requests.get(url, headers=req_header_dict)

html = res.text

soup = BeautifulSoup(html, 'html.parser')

next_data = soup.select('#__NEXT_DATA__')

book_list = []
for i in next_data:
    a = i.text
    book_list.append(json.loads(a))


with open('ridi.json', 'w', encoding='utf-8') as file:
    json.dump(book_list, file, ensure_ascii=False, indent="\t")
profile
Nomadcoder이고싶은

0개의 댓글