scrapeje/BozzaScrapeJE.py

import requests
from bs4 import BeautifulSoup
import cloudscraper

nome=[]
desc=[]
npezzi=[]
prezzo=[]
n=0

#scrape html
# scraper = cloudscraper.create_scraper(browser={'browser': 'firefox','platform': 'windows','mobile': False})
# page = scraper.get("https://www.justeat.it/restaurants-saporedialeppo/menu").content
# with open('aleppo.html', 'wb') as f:
#     f.write(page)

with open('aleppo.html', 'rb') as f:
    page = f.read()

soup = BeautifulSoup(page, "html.parser")
menu = soup.find(attrs={"data-test-id": "menu-item"})

#Stampa nome ristorante
print("\nRISTORANTE:",soup.title.text)

# alla riga 870 dell html c'è "allergenPhoneNumber":"3389529446"

for menu in soup.find_all(attrs={"data-test-id": "menu-item"}):
    att=menu
    #riempie la lista "nome" 
    for att in menu.find(attrs={"data-test-id": "menu-item-name"}):
        if att != " ":
            nome.append(att.lstrip().splitlines()[0])

    #riempie la lista "desc" 
    att=menu.find("p", class_="c-menuItems-description")
    if att != None:
        for att in menu.find("p", class_="c-menuItems-description"):
            desc.append(att.lstrip().splitlines()[0])
    else:
        desc.append(None)

    #riempie la lista "prezzo" 
    for att in menu.find("p", class_="c-menuItems-price notranslate"):
        prezzo.append(att.lstrip().splitlines()[0])

    #riempie la lista "npezzi" 
    att=menu.find_all(attrs={"data-test-id": "menu-item-description"})
    if att != None:
        if menu.text.find("pezzo") > 0 or menu.text.find("pezzi") > 0:
            npezzi.append(menu.text.splitlines()[7].lstrip())
        else:
            npezzi.append(None)
    continue

#stampa liste
for x in range(len(nome)):
     print("\n")
     print(nome[x])
     print(desc[x])
     print(npezzi[x])
     print(prezzo[x])

#stampa lunghezza liste
print("\nlista nomi:",len(nome))
print("lista desc:",len(desc))
print("lista npezzi:",len(npezzi))
print("lista prezzi:",len(prezzo))