刮刀只得到第一个项目？

Question

我的爬虫只得到下面的第一个列表。如何让它获取列表中的所有地址？这是一个简单的程序，可以提取下面链接中的地址。

# -*- coding: utf-8 -*-
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from scrapy_splash import SplashRequest


class Listings2Spider(CrawlSpider):
    name = 'listings2'
    allowed_domains = ['www.realtor.ca']
    user_agent = "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1"

    script = '''
    function main(splash, args)
        splash.private_mode_enabled = false
        url = args.url
        assert(splash:go(url))
        assert(splash:wait(3))
        return splash:html()
    end
    '''

    def start_requests(self):
        yield SplashRequest(url='https://www.realtor.ca/map#ZoomLevel=13&Center=43.686631%2C-79.339824&LatitudeMax=43.75741&LongitudeMax=-79.25894&LatitudeMin=43.61577&LongitudeMin=-79.42071&view=list&Sort=6-D&PGeoIds=g20_dpz8de7m&GeoName=East%20York%2C%20Toronto%2C%20ON&PropertyTypeGroupID=1&PropertySearchTypeId=1&TransactionTypeId=2&Currency=CAD',
                             headers={'User-Agent': self.user_agent}, callback=self.parse_item, endpoint="execute", args={'lua_source': self.script})

    rules = (
        Rule(LinkExtractor(restrict_xpaths="//div[@class='cardCon']"), callback='parse_item', follow=True, process_request='set_user_agent'),
    )
    def set_user_agent(self, request):
        request.headers['User-Agent'] = self.user_agent
        return request

    def parse_item(self, response):
        yield {
            'Address': response.xpath("//div[@class='listingCardAddress']/text()").get()
        }

Answer 1

似乎应用了速率限制，我可以自动化 api 调用并避免使用浏览器自动化，但网站似乎在几页后阻止了请求。请注意，这样做您每页最多可以获得 100 个结果，这将（当它工作时！）更快，并且您从 json 获得的详细信息比从前端 html 获得的更多。

import requests

s = requests.Session()
home_url = 'https://www.realtor.ca/map#ZoomLevel=13&Center=43.686631%2C-79.339824&LatitudeMax=43.75741&LongitudeMax=-79.25894&LatitudeMin=43.61577&LongitudeMin=-79.42071&view=list&Sort=6-D&PGeoIds=g20_dpz8de7m&GeoName=East%20York%2C%20Toronto%2C%20ON&PropertyTypeGroupID=1&PropertySearchTypeId=1&TransactionTypeId=2&Currency=CAD'
step = s.get(home_url)
print(step)

url = 'https://api2.realtor.ca/Listing.svc/PropertySearch_Post'

headers = {
    'accept':'*/*',
    'accept-encoding':'gzip, deflate, br',
    'content-type':'application/x-www-form-urlencoded; charset=UTF-8',
    'origin':'https://www.realtor.ca',
    'referer':'https://www.realtor.ca/',
    'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.71 Safari/537.36'
    }

output = []
for page in range(1,5):

    payload = {
        'ZoomLevel':'13',
        'LatitudeMax':'43.75741',
        'LongitudeMax':'-79.25894',
        'LatitudeMin':'43.61577',
        'LongitudeMin':'-79.42071',
        'Sort':'6-D',
        'PropertyTypeGroupID':'1',
        'PropertySearchTypeId':'1',
        'TransactionTypeId':'2',
        'Currency':'CAD',
        'RecordsPerPage':'100',
        'ApplicationId':'1',
        'CultureId':'1',
        'Version':'7.0',
        'CurrentPage': str(page)
        }

    post = s.post(url,headers=headers,data=payload).json()
    results = len(post['Results'])
    print(f'Scraping page: {page}, results: {results}')

    for listing in post['Results']:
        print(listing['Id'],listing['Property']['Price'])