Scrape data with scrapy

Question

I am going to scrape the Pararius.nl as a practice with scrapy but when I start crawling it returns the fairlane protection, how can I pass it? Do I need any tools? please help with one example

def parse(self, response):
    url = 'https://www.pararius.nl/{deal_type}/nederland/p-{page}/'

        for deal_type in ['huurwoningen', 'koopwoningen']:
            for i in range(1, 2):
                yield scrapy.Request(url.format(deal_type=deal_type, page=i), callback=self.parse_pages,cookies=self.cookies,
                                     headers=self.h, method='GET', cb_kwargs={'deal_type': deal_type})
    
    
    def parse_pages(self, response, deal_type):
        print(response.url)
        return

Answer 1

I was able to paginate and collect data from the page without any issues. as I see in your URL you using p- but as I see on the website it should be page-

here is code I've using for it:

def parse(self, response):
    url = 'https://www.pararius.nl/{deal_type}/nederland/page-{page}/'
    # 'koopwoningen'
    for deal_type in ['huurwoningen']:
        for i in range(1, 2):
            yield scrapy.Request(
                url.format(deal_type=deal_type, page=i),
                callback=self.parse_pages,
                method='GET',
            )

def parse_pages(self, response):
    for row in response.css('li.search-list__item'):
        href = row.css('a.listing-search-item__link--depiction::attr(href)').get()
        if href:
            yield {
                'seacrh_url': response.url,
                'url': 'https://pararius.nl' + href,
                'title': row.xpath(
                    './/div[contains(@class, "listing-search-item__sub-title\'")]/text()').get().strip()
            }

    page = response.meta.get('page', 2)
    if 'page-' in response.url:
        next_url = re.sub(r'page-\d+', f'page-{page}', response.url)
    else:
        next_url = response.url.strip('/') + f'/page-{page}'
    page += 1
    if page < 10:
        yield scrapy.Request(
            next_url,
            callback=self.parse_pages,
            method='GET',
            meta={'page': page}
        )

additional settings I've used:

USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36'
ROBOTSTXT_OBEY = False

and this is example of result I've received:

{"seacrh_url": "https://www.pararius.nl/huurwoningen/nederland/page-2", "url": "https://pararius.nl/studio-te-huur/breda/60de7cf7/vredenburchstraat", "title": "4811 RD Breda (Boeimeer)"},
{"seacrh_url": "https://www.pararius.nl/huurwoningen/nederland/page-2", "url": "https://pararius.nl/appartement-te-huur/eindhoven/7035fc54/aalsterweg", "title": "5615 CH Eindhoven (Looiakkers)"},
{"seacrh_url": "https://www.pararius.nl/huurwoningen/nederland/page-2", "url": "https://pararius.nl/appartement-te-huur/rotterdam/a5eba2a3/herman-gorterstraat", "title": "3061 SM Rotterdam (Kralingen West)"},

for zah.nl additional lib is required pip install undetected-chromedriver

you can use the following:

import re
import time

import scrapy

import undetected_chromedriver as UC


class ZahSpider(scrapy.Spider):
    name = 'zah'
    allowed_domains = ['www.zah.nl']
    start_urls = ['https://www.zah.nl/te-koop/?page=1']

    headers = {
        'authority': 'www.zah.nl',
        'accept':     'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
        'accept-language': 'uk-UA,uk;q=0.9,en-US;q=0.8,en;q=0.7',
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36',
    }

    def start_requests(self):
        options = uc.ChromeOptions()
        driver = uc.Chrome(options=options)
        driver.maximize_window()
        driver.get('https://www.zah.nl/te-koop/?page=1')
        time.sleep(5)

        cookies_list = driver.get_cookies()
        self.cookies_dict = {}
        for cookie in cookies_list:
            self.cookies_dict[cookie['name']] = cookie['value']
        driver.quit()

        yield scrapy.Request(
            url='https://www.zah.nl/te-koop/?page=1',
            cookies=self.cookies_dict,
            headers=self.headers,
            callback=self.parse
        )

    def parse(self, response):
        for row in response.css('div.result'):
            yield {
                'title': row.css('a > h2::text').get(),
                'url': row.css('a::attr(href)').get()
            }

        page = response.meta.get('page', 2)
        if page < 5:
            next_url = re.sub(r'page=\d+', f'page={page}', response.url)
            page += 1
           yield scrapy.Request(
                url=next_url,
                cookies=self.cookies_dict,
                headers=self.headers,
                meta={'page': page},
               callback=self.parse
            )