问Scrapy图像下载

EN

import scrapy
import re
import os
import urlparse
from scrapy.spiders import CrawlSpider, Rule
from scrapy.linkextractors import LinkExtractor
from scrapy.loader.processors import Join, MapCompose, TakeFirst
from scrapy.pipelines.images import ImagesPipeline
from production.items import ProductionItem, ListResidentialItem

class productionSpider(scrapy.Spider):
    name = "production"
    allowed_domains = ["someurl.com"]
    start_urls = [
        "someurl.com"
]

def parse(self, response):
    for sel in response.xpath('//html/body'):
        item = ProductionItem()
        img_url = sel.xpath('//a[@data-tealium-id="detail_nav_showphotos"]/@href').extract()[0]
        yield scrapy.Request(urlparse.urljoin(response.url, img_url),callback=self.parseBasicListingInfo,  meta={'item': item})

def parseBasicListingInfo(item, response):
    item = response.request.meta['item']
    item = ListResidentialItem()
    try:
        image_urls = map(unicode.strip,response.xpath('//a[@itemprop="contentUrl"]/@data-href').extract())
        item['image_urls'] = [ x for x in image_urls]
    except IndexError:
        item['image_urls'] = ''

    return item

from scrapy.settings.default_settings import ITEM_PIPELINES
from scrapy.pipelines.images import ImagesPipeline

BOT_NAME = 'production'

SPIDER_MODULES = ['production.spiders']
NEWSPIDER_MODULE = 'production.spiders'
DEFAULT_ITEM_CLASS = 'production.items'

ROBOTSTXT_OBEY = True
DEPTH_PRIORITY = 1
IMAGE_STORE = '/images'

CONCURRENT_REQUESTS = 250

DOWNLOAD_DELAY = 2

ITEM_PIPELINES = {
    'scrapy.contrib.pipeline.images.ImagesPipeline': 300,
}

# -*- coding: utf-8 -*-
import scrapy

class ProductionItem(scrapy.Item):
    img_url = scrapy.Field()

# ScrapingList Residential & Yield Estate for sale
class ListResidentialItem(scrapy.Item):
    image_urls = scrapy.Field()
    images = scrapy.Field()

    pass