class DoubanImgsItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    image_urls = Field()
    images = Field()
    image_paths = Field()

# Configure item pipelines
# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html

# ImagePipeline的自定義實現(xiàn)類
ITEM_PIPELINES = {
    "douban_imgs.pipelines.DoubanImgDownloadPipeline": 300,
}
#設置圖片下載路徑
IMAGES_STORE = "D:doubanimgs"
# 過期天數(shù)
IMAGES_EXPIRES = 90  #90天內抓取的都不會被重抓

# 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 = [
            "http://www.douban.com/photos/album/%s/" % (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("http://div[@class="photolst clearfix"]//img/@src").extract()
        if list_imgs:
            item = DoubanImgsItem()
            item["image_urls"] = list_imgs
            yield item

# -*- coding: utf-8 -*-

# Define your item pipelines here
#
# Don"t forget to add your pipeline to the ITEM_PIPELINES setting
# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
from scrapy.pipelines.images import ImagesPipeline
from scrapy.exceptions import DropItem
from scrapy import Request
from scrapy import log


class DoubanImgsPipeline(object):
    def process_item(self, item, spider):
        return item


class DoubanImgDownloadPipeline(ImagesPipeline):
    default_headers = {
        "accept": "image/webp,image/*,*/*;q=0.8",
        "accept-encoding": "gzip, deflate, sdch, br",
        "accept-language": "zh-CN,zh;q=0.8,en;q=0.6",
        "cookie": "bid=yQdC/AzTaCw",
        "referer": "https://www.douban.com/photos/photo/2370443040/",
        "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 get_media_requests(self, item, info):
        for image_url in item["image_urls"]:
            self.default_headers["referer"] = image_url
            yield Request(image_url, headers=self.default_headers)

    def item_completed(self, results, item, info):
        image_paths = [x["path"] for ok, x in results if ok]
        if not image_paths:
            raise DropItem("Item contains no images")
        item["image_paths"] = image_paths
        return item

在自定義ImagePipeline代碼中，作為重要的是要重載get_media_requests(self, item, info)和item_completed(self, results, item, info)這兩個函數(shù)。

get_media_requests(self,item, info)：

ImagePipeline根據(jù)image_urls中指定的url進行爬取，可以通過get_media_requests為每個url生成一個Request。如：

for image_url in item["image_urls"]:
            self.default_headers["referer"] = image_url
            yield Request(image_url, headers=self.default_headers)

item_completed(self, results, item, info)：

圖片下載完畢后，處理結果會以二元組的方式返回給item_completed()函數(shù)。這個二元組定義如下：

(success, image_info_or_failure)

其中，第一個元素表示圖片是否下載成功；第二個元素是一個字典。如：

 def item_completed(self, results, item, info):
        image_paths = [x["path"] for ok, x in results if ok]
        if not image_paths:
            raise DropItem("Item contains no images")
        item["image_paths"] = image_paths
        return item

運行結果如下：

下載成功以后，你就會在剛才設置的保存圖片的路徑里看到下載完成的圖片：IMAGES_STORE = "D:doubanimgs"

默認情況下，使用ImagePipeline組件下載圖片的時候，圖片名稱是以圖片URL的SHA1值進行保存的。

如：
圖片URL:http://www.example.com/image.jpg
SHA1結果：3afec3b4765f8f0a07b78f98c07b83f013567a0a
則圖片名稱：3afec3b4765f8f0a07b78f98c07b83f013567a0a.jpg

如果想進行更改，請參考：使用scrapy框架的ImagesPipeline下載圖片如何保持原文件名呢？