Python Scrapy图片爬取原理及代码实例

class ImgSpider(scrapy.Spider):
  name = 'img'
  # allowed_domains = ['www.xxx.com']
  start_urls = ['http://www.521609.com/daxuemeinv/']
  url = 'http://www.521609.com/daxuemeinv/list8%d.html'
  pageNum = 1
  def parse(self, response):
    li_list = response.xpath('//*[@id="content"]/div[2]/div[2]/ul/li')
    for li in li_list:
      img_src = 'http://www.521609.com'+li.xpath('./a[1]/img/@src').extract_first()
      item = ImgproItem()
      item['src'] = img_src

      yield item

from scrapy.pipelines.images import ImagesPipeline
import scrapy

class ImgproPipeline(ImagesPipeline):

  #对某一个媒体资源进行请求发送
  #item就是接收到的spider提交过来的item
  def get_media_requests(self, item, info):
    yield scrapy.Request(item['src'])

  #制定媒体数据存储的名称
  def file_path(self, request, response=None, info=None):
    name = request.url.split('/')[-1]
    print('正在下载：',name)
    return name

  #将item传递给下一个即将给执行的管道类
  def item_completed(self, results, item, info):
    return item