我需要抓取一个带有“加载更多按钮”的网站。这是我用 Python 编写的爬虫代码:

import scrapy
import json
import requests
import re
from parsel import Selector
from scrapy.selector import Selector 
from scrapy.http import HtmlResponse

headers = {
'origin': 'https://www.tayara.tn',
'accept-encoding': 'gzip, deflate, br',
'accept-language': 'en-US,en;q=0.9',
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36',
'content-type': 'application/json',
'accept': '*/*',
'referer': 'https://www.tayara.tn/sc/immobilier/bureaux-et-plateaux',
'authority': 'www.tayara.tn',
'dnt': '1',
}
data = '{"query":"query ListingsPage($page: Page, $filter: SearchFilter, $sortBy: SortOrder) {\\n  listings: searchAds(page: $page, filter: $filter, sortBy: $sortBy) {\\n    items {\\n      uuid\\n      title\\n      price\\n      currency\\n      thumbnail\\n      createdAt\\n      category {\\n        id\\n        name\\n        engName\\n        __typename\\n      }\\n      user {\\n        uuid\\n        displayName\\n        avatar(width: 96, height: 96) {\\n          url\\n          __typename\\n        }\\n        __typename\\n      }\\n      __typename\\n    }\\n    trackingInfo {\\n      transactionId\\n      listName\\n      recommenderId\\n      experimentId\\n      variantId\\n      __typename\\n    }\\n    totalCount\\n    pageInfo {\\n      startCursor\\n      hasPreviousPage\\n      endCursor\\n      hasNextPage\\n      __typename\\n    }\\n    __typename\\n  }\\n}\\n","variables":{"page":{"count":36,"offset":"cDEwbg==.MjAxOC0xMi0wMlQxMzo1MDoxMlo=.MzY="},"filter":{"queryString":null,"category":"140","regionId":null,"attributeFilters":[]},"sortBy":"CREATED_DESC"},"operationName":"ListingsPage"}'

class Tun(scrapy.Spider):

name="tayaracommercial"
start_urls = [
    'https://www.tayara.tn/sc/immobilier/bureaux-et-plateaux'
    ]

def parse(self, response):        
    yield Request('https://www.tayara.tn/graphql', method='post', headers=headers, body=data, self.parse_item)


def parse_item(self, response):

    source = 'Tayara'        
    reference = response.url.split('//')[1].split('/')[3]
    titre = response.xpath('//h1[@data-name="adview_title"]/text()').extract()   

    yield{'Source':source, 'Reference':reference, 'Titre':titre}

这是我的小试炼。我知道那是假的。你能纠正我吗？

最佳答案

您可以使用以下示例抓取数据:

# Importing the dependencies
# This is needed to create a lxml object that uses the css selector
 from lxml.etree import fromstring
  
# The requests library
import requests
  
class WholeFoodsScraper:
  
  API_url = 'http://www.wholefoodsmarket.com/views/ajax'
    scraped_stores = []

    def get_stores_info(self, page):
     
        # This is the only data required by the api 
        # To send back the stores info
        data = {
        'view_name': 'store_locations_by_state',
        'view_display_id': 'state',
        'page': page
        }
        # Making the post request
        response = requests.post(self.API_url, data=data)

        # The data that we are looking is in the second
        # Element of the response and has the key 'data', 
        # so that is what's returned
        return response.json()[1]['data']

https://stackoverflow.com/questions/54171736/