LG전자 식단 스크래핑 코드

hourhome-menu-scraping

import requests
import time
import pprint
from bs4 import BeautifulSoup


def download_html(bid):
    url = f"https://appmobile.ourhome.co.kr/front/menu/todayMenuSelectList.do?mi=R030010&busiplcd={bid}"
    headers = {
        "Cookie": "user_id=95hGdlCULG8/s5IJcB6YXA==;"
    }
    return requests.get(url, headers=headers).text

def parsing_menu_table(html):
    oneday_data = [[] for x in range(4)]

    # load HTML
    soup = BeautifulSoup(html, 'html5lib')

    # 0:아침 / 1:점심 / 2:저녁 / 3:야식
    for i in range (0, 4):
        meal_data = []
        selector = f"#menu{i+1}_c > .textShadowBox"
        htmls_of_each_catering_companies = soup.select(selector)
        for html in htmls_of_each_catering_companies:
            catering_data= {}
            # catering company
            selector = ".menuTitle"
            name_of_catering_company = html.select(selector)[0].text
            catering_data[name_of_catering_company] = [];
            # main menu
            selector = ".menuTitle2"
            main_menu = html.select(selector)
            if len(main_menu) == 0:
                main_dish = "-"
            else:
                main_dish = main_menu[0].text.strip()
            catering_data[name_of_catering_company].append(main_dish)
            # side menu
            selector = ".sub"
            side_menu = html.select(selector)
            if len(side_menu) > 0 :
                catering_data[name_of_catering_company].append(
                        "/".join([x.text for x in side_menu]))
            meal_data.append(catering_data)

        if len(meal_data) > 0:
            oneday_data[i] = meal_data

    return oneday_data



bids = ["FA0GA", "FA116", "FA117", "FA126", "FA12B", "FA12V", "FA13A", "FAG92",
        "FAG97", "FAH71", "FAM62", "FAM80", "FAM97", "FAN08", "FAP51", "FAP52",
        "FAP53", "FAQ84"]

for bid in bids[:3]:
    html = download_html(bid)
    result = parsing_menu_table(html)
    pprint.pprint(result)
    print("-" * 20)
    time.sleep(1)