Question

我刚刚开始学习Python和Scrapy。

我的第一个项目是在包含Web安全信息的网站上爬网信息。但是当我使用cmd运行该命令时，它会说

抓取0页（以0页/分钟）抓取0条（以0条/分钟）

，似乎什么都没出来。如果有人能解决我的问题，我将不胜感激。

以下是我的蜘蛛文件：

项目：

import scrapy


class ReporteinmobiliarioItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    titulo = scrapy.Field()
    precioAlquiler = scrapy.Field()
    ubicacion = scrapy.Field()
    descripcion = scrapy.Field()
    superficieTotal = scrapy.Field()
    superficieCubierta = scrapy.Field()
    antiguedad = scrapy.Field()
    pass

蜘蛛：

import scrapy
from scrapy.spider import CrawlSpider, Rule
from scrapy.linkextractors import LinkExtractor
from scrapy.exceptions import CloseSpider
from reporteInmobiliario.items import ReporteinmobiliarioItem

class reporteInmobiliario(CrawlSpider):
    name = 'reporteInmobiliario'
    allowed_domains = ['zonaprop.com.ar/']
    item_count = 0
    start_urls = ['https://www.zonaprop.com.ar/terrenos-alquiler-capital-federal.html']

    rules = {
        # Para cada item
        Rule(LinkExtractor(allow = (), restrict_xpaths = ('//li[@class="pagination-action-next"]/a'))),
        Rule(LinkExtractor(allow = (), restrict_xpaths = ('//h4[@class="aviso-data-title"]')),
                           callback = 'parse_item', follow = False)
            }


def parse_item(self,response):
    rp_item = ReporteinmobiliarioItem()

    rp_item['titulo']= response.xpath('//div[@class="card-title"]/text()').extract()
    rp_item['precioAlquiler'] = response.xpath('normalize-space(//*[@id="layout-content"]/div[1]/div[1]/div[2]/div[2]/div[1]/div[2]/p/strong)').extract()
    rp_item['ubicacion'] = response.xpath('normalize-space(//*[@id="map"]/div[1]/div/ul/li)').extract()
    rp_item['descripcion'] = response.xpath('normalize-space(//*[@id="id-descipcion-aviso"]').extract()
    rp_item['superficieTotal'] = response.xpath('//*[@id="layout-content"]/div[1]/div[1]/div[2]/div[1]/div[4]/div[1]/div[1]/div/ul/li[4]/span)').extract()
    rp_item['superficieCubierta'] = response.xpath('normalize-space(//*[@id="layout-content"]/div[1]/div[1]/div[2]/div[1]/div[4]/div[1]/div[1]/div/ul/li[5]/span)').extract()
    rp_item['antiguedad'] = response.xpath('normalize-space(//*[@id="layout-content"]/div[1]/div[1]/div[2]/div[1]/div[4]/div[1]/div[1]/div/ul/li[6]/span)').extract()

    self.item_count += 1
    if self.item_count > 5:
        raise CloseSpider('item_exceeded')
    yield rp_item

Answer 1

您需要始终先检查日志：

2018-09-09 09:19:21 [scrapy.spidermiddlewares.offsite]调试：已过滤向'www.zonaprop.com.ar'的异地请求：https://www.zonaprop.com.ar/propiedades/galpon-de-337-m2-7-79-x-43-30-ma-metros-de -av-43096244.html>

您的第一条规则也有错误（正确的类名称为“ pagination-action-next”）。另外，不要忘记修复您的XPath错误（parse_item）！

class reporteInmobiliario(CrawlSpider):
    name = 'reporteInmobiliario'
    allowed_domains = ['zonaprop.com.ar']
    item_count = 0
    start_urls = ['https://www.zonaprop.com.ar/terrenos-alquiler-capital-federal.html']

    rules = {
        # Para cada item
        Rule(LinkExtractor(allow = (), restrict_xpaths = ('//li[contains(@class, "pagination-action-next")]/a'))),
        Rule(LinkExtractor(allow = (), restrict_xpaths = ('//h4[@class="aviso-data-title"]')),
                           callback = 'parse_item')
            }


    def parse_item(self,response):
        rp_item = ReporteinmobiliarioItem()

        rp_item['titulo']= response.xpath('//div[@class="card-title"]/text()').extract()
        rp_item['precioAlquiler'] = response.xpath('normalize-space(//*[@id="layout-content"]/div[1]/div[1]/div[2]/div[2]/div[1]/div[2]/p/strong)').extract()
        rp_item['ubicacion'] = response.xpath('normalize-space(//*[@id="map"]/div[1]/div/ul/li)').extract()
        rp_item['descripcion'] = response.xpath('normalize-space(//*[@id="id-descipcion-aviso"]').extract()
        rp_item['superficieTotal'] = response.xpath('//*[@id="layout-content"]/div[1]/div[1]/div[2]/div[1]/div[4]/div[1]/div[1]/div/ul/li[4]/span)').extract()
        rp_item['superficieCubierta'] = response.xpath('normalize-space(//*[@id="layout-content"]/div[1]/div[1]/div[2]/div[1]/div[4]/div[1]/div[1]/div/ul/li[5]/span)').extract()
        rp_item['antiguedad'] = response.xpath('normalize-space(//*[@id="layout-content"]/div[1]/div[1]/div[2]/div[1]/div[4]/div[1]/div[1]/div/ul/li[6]/span)').extract()

        self.item_count += 1
        if self.item_count > 5:
            raise CloseSpider('item_exceeded')
        yield rp_item

抓取0页抓取0条

1 个答案: