使用scrapyImagesPipeline爬取图片资源-创新互联

这篇文章运用简单易懂的例子给大家介绍使用scrapy ImagesPipeline爬取图片资源，内容非常详细，感兴趣的小伙伴们可以参考借鉴，希望对大家能有所帮助。

这是一个使用scrapy的ImagesPipeline爬取下载图片的示例，生成的图片保存在爬虫的full文件夹里。

scrapy startproject DoubanImgs

cd DoubanImgs

scrapy genspider download_douban  douban.com

vim spiders/download_douban.py

# coding=utf-8
from scrapy.spiders import Spider
import re
from scrapy import Request
from ..items import DoubanImgsItem


class download_douban(Spider):
  name = 'download_douban'

  default_headers = {
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
    'Accept-Encoding': 'gzip, deflate, sdch, br',
    'Accept-Language': 'zh-CN,zh;q=0.8,en;q=0.6',
    'Cache-Control': 'max-age=0',
    'Connection': 'keep-alive',
    'Host': 'www.douban.com',
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36',
  }

  def __init__(self, url='1638835355', *args, **kwargs):
    self.allowed_domains = ['douban.com']
    self.start_urls = []
    for i in xrange(23):
      if i == 0:
        page_url = 'http://www.douban.com/photos/album/' + url
      else:
        page_url = 'http://www.douban.com/photos/album/' + url + '/?start=' + str(i*18)
      self.start_urls.append(page_url)
    self.url = url
    # call the father base function

    # super(download_douban, self).__init__(*args, **kwargs)

  def start_requests(self):

    for url in self.start_urls:
      yield Request(url=url, headers=self.default_headers, callback=self.parse)

  def parse(self, response):
    list_imgs = response.xpath('//div[@class="photolst clearfix"]//img/@src').extract()
    if list_imgs:
      item = DoubanImgsItem()
      item['image_urls'] = list_imgs
      yield item