Нету класса у блока span

Question

Нету класса у блока span

Рейтинг: 0Ответов: 1Опубликовано: 22.02.2023

из за того что на некоторых отелях нету оценки, выдает ошибку что у блока нету атрибута текст. Как можно обойти это

код:

import requests
import lxml
from bs4 import BeautifulSoup
import csv

def get_data(url):
    headers = {
        'User Agent': 'Mozilla / 5.0(WindowsNT10.0; Win64;x64) AppleWebKit / 537.36(KHTML, likeGecko) Chrome / 110.0.0.0 Safari / 537.36'
    }

    req = requests.get(url=url)

    #with open('index.html', 'w', encoding='utf8') as file:
        #file.write(req.text)

    soup = BeautifulSoup(req.text, 'lxml')

    hotel_cards = soup.find_all('li', class_='item')
    #print(hotel_cards)
    for hotel_url in hotel_cards:
        hotel_url = 'https://101hotels.com' + hotel_url.find('a').get('href')
        #print(hotel_url)

    for title_hotels in hotel_cards:
        title_hotels = title_hotels.find('a').text
        #print(title_hotels)

    for hotel_price_result in hotel_cards:
        hotel_price = hotel_price_result.find('span', class_='price-highlight').text.strip()
        hotel_price2 = hotel_price_result.find('span', class_='currency').text.strip()
        price_with_currency = f'{hotel_price} {hotel_price2}'
        #print(price_with_currency)

    for hotel_rating in hotel_cards:
        hotel_rating = hotel_rating.find('span', {"itemprop": "ratingValue"}).text.strip()
        print(hotel_rating)

def main():
    get_data('https://101hotels.com/main/cities/yuzhno-sakhalinsk')

if __name__ == '__main__':
    main()

python beautiful-soup

Источник: Stack Overflow на русском

Answer 1

▲ 1Принят

Можно исправить следующим образом:

import requests
import lxml
from bs4 import BeautifulSoup
import csv

def get_data(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36'
    }

    req = requests.get(url=url, headers=headers)

    soup = BeautifulSoup(req.text, 'lxml')

    hotel_cards = soup.find_all('li', class_='item')

    hotels = []

    for hotel_card in hotel_cards:
        hotel_url = 'https://101hotels.com' + hotel_card.find('a').get('href')
        title_hotel = hotel_card.find('a').text
        hotel_price_result = hotel_card.find('span', class_='price-highlight')
        hotel_price = hotel_price_result.text.strip() if hotel_price_result else ''
        hotel_price_currency = hotel_card.find('span', class_='currency')
        hotel_price_currency = hotel_price_currency.text.strip() if hotel_price_currency else ''
        hotel_price_with_currency = f'{hotel_price} {hotel_price_currency}'
        hotel_rating_result = hotel_card.find('span', {'itemprop': 'ratingValue'})
        hotel_rating = hotel_rating_result.text.strip() if hotel_rating_result else ''

        hotels.append({
            'url': hotel_url,
            'title': title_hotel,
            'price': hotel_price_with_currency,
            'rating': hotel_rating
        })

    return hotels

def main():
    hotels = get_data('https://101hotels.com/main/cities/yuzhno-sakhalinsk')
    with open('hotels.csv', 'w', encoding='utf8', newline='') as file:
        writer = csv.writer(file)
        writer.writerow(['Title', 'URL', 'Price', 'Rating'])
        for hotel in hotels:
            writer.writerow([hotel['title'], hotel['url'], hotel['price'], hotel['rating']])

if __name__ == '__main__':
    main()

Нету класса у блока span

Ответы