avito page parser demo

avito.py

#! /usr/bin/env python3
import csv
import requests
from bs4 import BeautifulSoup

outfile = open('output.csv', 'w')
csvwriter = csv.writer(outfile)
csvwriter.writerow(['name', 'date', 'address', 'price', 'currency', 'photo', 'url'])

session = requests.Session()
p = 0
next_page = 'https://www.avito.ru/pavlovskaya/doma_dachi_kottedzhi'
while next_page:
    p += 1
    print('Requesting page', p)
    resp = session.get(next_page)
    soup = BeautifulSoup(resp.text, features="html5lib")
    resp.close()

    for item in soup.select('div.item.item_table'):
        # photos = item.select('div.item-photo img')
        # photo = '\n'.join('https:' + p.attrs.get('src') for p in photos if p.attrs.get('src'))
        photo = item.select_one('div.item-photo img')
        photo = 'https:' + photo.attrs.get('src') if photo else ''

        csvwriter.writerow([
            item.select_one('span[itemprop=name]').text,
            item.select_one('div[data-absolute-date]').attrs.get('data-absolute-date').strip(),
            item.select_one('p.address').text.strip(),
            item.select_one('span[itemprop=price]').attrs.get('content'),
            item.select_one('span[itemprop=priceCurrency]').attrs.get('content'),
            photo,
            'https://avito.ru' + item.select_one('a[itemprop=url]').attrs.get('href')
        ])

    next_page = soup.select_one('a.pagination-page.js-pagination-next')
    if not next_page:
        break
    next_page = 'https://www.avito.ru' + next_page.attrs.get('href')

outfile.close()