Склейка одного слова с каждым элементом списка с помощью .join()

Рейтинг: 1Ответов: 2Опубликовано: 22.02.2023

Нужно склеить с помощью .join() цену и валюту(например 7000 и руб.)

7000 - hotel_price

руб. - hotel_price2

из за того что цен много то он склеивает только последнюю цену, а мне нужно все

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 in hotel_cards:
        hotel_price = hotel_price.find('span', class_='price-highlight').text.strip()
        print(hotel_price)

    for hotel_price2 in hotel_cards:
        hotel_price2 = hotel_price2.find('span', class_='currency').text.strip()
        print(hotel_price2)

        hotel_price_result_str = " ".join()


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

if __name__ == '__main__':
    main()
python
Источник: Stack Overflow на русском

Ответы

▲ 2Принят

Так должно всё сработать:

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)

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

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

    for hotel_url in hotel_cards:
        hotel_url = 'https://101hotels.com' + hotel_url.find('a').get('href')

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

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


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

if __name__ == '__main__':
    main()
▲ 1

Собираем данные:

from bs4 import BeautifulSoup as Soup, Tag
from requests import Session

with Session() as s:
    response = s.get(
        'https://101hotels.com/main/cities/yuzhno-sakhalinsk'
    )

soup = Soup(response.content, 'html.parser')
items = soup.select('li.item')
entries = []

empty_price = Tag(name='price', attrs={})
empty_rating = Tag(name='rating', attrs={})
empty_name = Tag(name='name', attrs={})

for entry in items:
    entries.append(
        dict(
            title=(entry.select_one('.item-content [itemprop="name"]') or empty_name).get_text(strip=True),
            price=int((entry.select_one('.price-value') or empty_price).get('data-price-value') or 0),
            rating=(entry.select_one('.rating-text-description') or empty_rating).get_text(strip=True) or None,
            services=', '.join(item.get('content') for item in entry.select('[itemprop="amenityFeature"] [itemprop="name"]')),
            ad=', '.join(item.get('title') for item in entry.select('.hotel_header-labels__item'))
        )
    )

Сохраняем в excel:

import pandas as pd

pd.DataFrame(entries).to_excel('hotels.xlsx', engine='openpyxl', index=False)

Сохраняем в csv:

import csv

with open('hotels.csv', 'w', encoding='utf-8') as file:
    wrt = csv.DictWriter(
        file,
        fieldnames=entries[0].keys(),
        dialect=csv.unix_dialect
    )

    wrt.writeheader()
    wrt.writerows(
        entries
    )