make.py

# -*- coding: UTF-8 -*-
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from bs4 import BeautifulSoup
import xlsxwriter
from datetime import datetime


start = datetime.now()
url = 'https://www.xn--kalriaguru-ibb.hu/kaloriatablazat/kaloriatablazat.php'
columns_name = ['left', 'right']

chrome_options = Options()
chrome_options.add_argument("--headless")
driver = webdriver.Chrome(options=chrome_options)
driver.get(url)
driver.find_element_by_xpath('//*[@id="cookieBtn"]').click()
page_soup = BeautifulSoup(driver.page_source, "html.parser")

links = list()
for col in columns_name:
    titles = page_soup("div", {"class": col})[0].contents
    for title in titles:
        if len(title) == 2:
            data = list()
            data.append(title.text)
            data.append("https://www.xn--kalriaguru-ibb.hu"+title.attrs['href'])
            links.append(data)

materials = list()
for link in links:          # teszthez: links[1:2]
    print("Ezeket listázom jelenleg: ", link[0])
    driver.get(link[1])
    page_soup = BeautifulSoup(driver.page_source, "html.parser")
    calorieTable = page_soup("div", {"id": "calorieTable"})[0].contents[0].contents[1].contents
    for content in calorieTable:
        data = list()
        data.append('https://www.xn--kalriaguru-ibb.hu' + content.contents[0].contents[0].attrs['href'])
        for i in range(0, 6):
            data.append(content.contents[i].text)

        driver.get(data[0])
        page_soup = BeautifulSoup(driver.page_source, "html.parser")
        calorieDatas = page_soup("tbody", {"id": "calorieDatas"})
        data.append(calorieDatas[0].contents[17].contents[1].text.split('\xa0')[0])         # rost
        data.append(calorieDatas[0].contents[15].contents[1].text.split('\xa0')[0])         # cukor
        data.insert(5, calorieDatas[0].contents[7].contents[1].text.split('\xa0')[0])       # telített
        data.insert(6, calorieDatas[0].contents[9].contents[1].text.split('\xa0')[0])       # egyszeresen telítettlen
        data.insert(7, calorieDatas[0].contents[11].contents[1].text.split('\xa0')[0])      # többszörösen telítettlen

        materials.append(data)


driver.quit()

workbook = xlsxwriter.Workbook('kalóriatáblázat.xlsx')
worksheet = workbook.add_worksheet()
letterhead = ['Megnevezés', 'Energia', 'Fehérje', 'Zsír', 'Telített', 'Egyszeresen telítettlen',
              'Többszörösen telítettlen', 'Szénhidrát', 'GI', 'Rost', 'Cukor']
worksheet.write_row(0, 0, letterhead)

row = 1
for material in materials:
    worksheet.write_url(row, 0, material[0], string=material[1])
    worksheet.write_row(row, 1, material[2:])
    row += 1

workbook.close()

end = datetime.now()
runtime = end - start
print('Runtime: ', runtime.seconds, 'seconds')