Hi there. Currently I am building a web scraper which is running not very fast. Could I manage somehow my spider to use other CPU cores or multiple same spiders to run in parallel?
砖砌体
# -*- coding: utf-8 -*-
import scrapy
import csv
from scrapy import FormRequest
from scrapy import Request
from scrapy.loader import ItemLoader
from bricomarche.items import Product
from datetime import date
from scrapy.loader.processors import TakeFirst
CATEGORIES = ['http://www.bricomarche.com/l/nos-produits/bricolage/outillage-et-equipement-de-l-atelier/outillage-electroportatif/perceuse-sans-fil-visseuse-accessoire-87.html?limit=90&p=1&solr_is_local=1', 'http://www.bricomarche.com/l/nos-produits/bricolage/outillage-et-equipement-de-l-atelier/outillage-electroportatif/perceuse-perforateur-et-marteau-piqueur-88.html?limit=90&p=1&solr_is_local=1', 'http://www.bricomarche.com/l/nos-produits/bricolage/outillage-et-equipement-de-l-atelier/outillage-electroportatif/meuleuse-rainureuse-accessoire-85.html?limit=90&p=1&solr_is_local=1']
class BricoMarcheSpider(scrapy.Spider):
name = 'brico_marche'
def start_requests(self):
# full path
with open('file.csv') as csvfile:
reader = csv.DictReader(csvfile)
for i, row in enumerate(reader):
magasin_id = row['Id']
if row['Id'][0] == '0':
magasin_id = row['Id'][1:]
formdata = {'city' : row['City'], 'market' : row['Brand'], 'idPdv' : magasin_id}
yield FormRequest(url='http://www.bricomarche.com/bma_popin/Geolocalisation/choisirMagasin', formdata=formdata, dont_filter=True, callback=self.parse, meta={'cookiejar': i})
def parse(self, response):
for url in CATEGORIES:
yield Request(url=url, dont_filter=True, callback=self.parse_category, meta={'cookiejar': response.meta['cookiejar']})
def parse_category(self, response):
pos = response.xpath('//div[@class="store-details"]/p/strong/text()').extract_first()
if pos:
for url in response.xpath('//a[@class="view-product"]/@href').extract():
yield Request(url=url, dont_filter=True, callback=self.parse_product, meta={'cookiejar': response.meta['cookiejar'], 'pos' : pos.strip()})
next_page = response.xpath('//a[@title="Suivant"]/@href').extract_first()
if next_page is not None:
yield Request(url=next_page, callback=self.parse_category, dont_filter=True, meta={'cookiejar':response.meta['cookiejar'], 'pos' : pos.strip()})
def parse_product(self, response):
l = ItemLoader(item=Product(), response=response)
l.default_output_processor = TakeFirst()
l.add_value('id_source', 'BRMRCH_FR')
l.add_value('extract_date', str(date.today()))
l.add_value('pos_name', response.meta['pos'])
l.add_xpath('brand_seller', '//td[@itemprop="brand"]/text()')
l.add_xpath('price_vat', '//span[contains(@class,"new-price")]/text()')
categories = response.xpath('//li[@itemprop="itemListElement"]//span[@itemprop="name"]/text()').extract()
# setting categories and family
# check with category which has fewer categories to verify values
try:
l.add_value('prod_name', categories[-1])
l.add_value('prod_family', categories[-2])
l.add_value('prod_category1', categories[0])
l.add_value('prod_category2', categories[1])
l.add_value('prod_category3', categories[2])
l.add_value('prod_category4', categories[3])
except:
pass
l.add_xpath('sku_seller', '//div[@class="content-fiche-produit"]/ul/li/p/text()')
# Réserver en magasin
existing_stock = response.xpath('//script[contains(text(),"STOCK_PDV")]').extract()
# Produit disponible en magasin text
product_available =response.xpath('//span[@class="product_avaliable"]').extract()
if existing_stock:
l.add_value('inventory', existing_stock)
l.add_value('available_yn', '1')
if product_available:
l.add_value('available_yn', '1')
l.add_value('inventory', response.xpath('//div[@class="bg-white"]/p/text()').extract_first())
else:
l.add_value('available_yn', '0')
l.add_xpath('available_pos_status', '//div[@class="fiche-items"]/div/p/text()')
l.add_xpath('available_pos_date', '//div[@class="fiche-items"]/div/p/text()')
return l.load_item()
Basically this is my spider. In
file.csv
there are approximately 450 lines. If I have to scrape 100 products my requests are ~ 450 x 100 = 45 000GET
requests. ThePOST
requests are used for cookies. Every item is added to my database. In mysettings.py
I useDOWNLOAD_DELAY=00.5
and the other parameters are by default. When I tried withAutoThrottle
on it triples the time. Some information for what I tested:
AutoThrottle
-82分钟,用于1000个产品AutoThrottle
-73.5分钟,用于1000个产品AutoThrottle
的并发请求-对于1000个产品,22.4分钟
最好的方法是使用scrapyd。在
文档中关于Distributed crawls的大部分建议也可以应用于在一台机器上运行,除非您将在同一个scrapyd服务器上多次运行spider。在
相关问题 更多 >
编程相关推荐