get_hafh_hostels.py

import requests
from bs4 import BeautifulSoup
import lxml.html
import time
import csv


def parse(url):
    response = requests.get(url)
    if response.status_code == 200:
        html = lxml.html.fromstring(response.content)
        name = html.xpath(
            "/html/body/div/div[1]/div/main/div[2]/section[1]/div/div[1]/h1")[0].text

        description = html.xpath(
            "/html/body/div/div[1]/div/main/div[2]/section[2]/p/span[2]/text()")[0]
        address = html.xpath(
            "/html/body/div/div[1]/div/main/div[2]/section[5]/div/div[3]/text()")[0]

        return [name, description, address, url]


num = 210
url = "https://hafh.com/properties/"

hostel_list = csv.writer(open('hostel_list.csv', 'w'))

hostel_list.writerow(["name", "description", "address", "url"])

for i in range(num):
    print(f"Checking {i} of {num}")
    time.sleep(10)
    row=parse(url + str(i + 1))

    if (row):
        hostel_list.writerow(row)