Issue
I just began to learn Python and Scrapy.
My first project is to crawl information on a website containing web security information. But when I run that using cmd, it says that
crawled 0 pages (at 0 pages/min) scraped 0 items (at 0 items/min)
and nothing seems to come out. I'd be grateful if someone kind could solve my problem.
Following is my spider file:
Items:
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
Spider:
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
Solution
You need to always check logs first:
2018-09-09 09:19:21 [scrapy.spidermiddlewares.offsite] DEBUG: Filtered offsite request to 'www.zonaprop.com.ar': https://www.zonaprop.com.ar/propiedades/galpon-de-337-m2-7-79-x-43-30-m-a-metros-de-av-43096244.html>
Also you have an error in your first Rule (the correct class name is "pagination-action-next "). Also don't forget to fix your XPath errors (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
Answered By - gangabass
0 comments:
Post a Comment
Note: Only a member of this blog may post a comment.