Scrapy爬取美女图片续集 (原创)

jiandanSpider.py(和之前没有变化):
#coding:utf-8
#需要安装pillow模块
import scrapy
from jiandan.items import JiandanItem

from scrapy.crawler import CrawlerProcess

class jiandanSpider(scrapy.Spider):
    name = ‘jiandan‘
    allowed_domains = []
    start_urls = ["http://jandan.net/ooxx"]



    def parse(self, response):
        item = JiandanItem()
        item[‘image_urls‘] = response.xpath(‘//img//@src‘).extract()#提取图片链接
        # print ‘image_urls‘,item[‘image_urls‘]
        yield item
        new_url= response.xpath(‘//a[@class="previous-comment-page"]//@href‘).extract_first()#翻页
        # print ‘new_url‘,new_url
        if new_url:
            yield scrapy.Request(new_url,callback=self.parse)

items.py(增加了一个字段，请看之前对Images Pipeline的描述) :
# -*- coding: utf-8 -*-

# Define here the models for your scraped items
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/items.html

import scrapy

class JiandanItem(scrapy.Item):
    # define the fields for your item here like:
    image_urls = scrapy.Field()#图片的链接
    images = scrapy.Field()

pipelines.py(改变最大,看注释):

# -*- 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
import os
import urllib
import scrapy
from scrapy.exceptions import DropItem
from scrapy.pipelines.images import ImagesPipeline

from jiandan import settings

class JiandanPipeline(ImagesPipeline):#继承ImagesPipeline这个类，实现这个功能

    def get_media_requests(self, item, info):#重写ImagesPipeline   get_media_requests方法
        ‘‘‘
        :param item:
        :param info:
        :return:
        在工作流程中可以看到，
        管道会得到文件的URL并从项目中下载。
        为了这么做，你需要重写 get_media_requests() 方法，
        并对各个图片URL返回一个Request:
        ‘‘‘
        for image_url in item[‘image_urls‘]:
            yield scrapy.Request(image_url)


    def item_completed(self, results, item, info):
        ‘‘‘

        :param results:
        :param item:
        :param info:
        :return:
        当一个单独项目中的所有图片请求完成时（要么完成下载，要么因为某种原因下载失败），
         item_completed() 方法将被调用。
        ‘‘‘
        image_paths = [x[‘path‘] for ok, x in results if ok]
        if not image_paths:
            raise DropItem("Item contains no images")
        return item

settings.py(主要是对缩略图的设置):
# -*- coding: utf-8 -*-

# Scrapy settings for jiandan project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     http://doc.scrapy.org/en/latest/topics/settings.html
#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html

BOT_NAME = ‘jiandan‘

SPIDER_MODULES = [‘jiandan.spiders‘]
NEWSPIDER_MODULE = ‘jiandan.spiders‘


ITEM_PIPELINES = {
   ‘jiandan.pipelines.JiandanPipeline‘: 1,

}
# ITEM_PIPELINES = {‘jiandan.pipelines.ImagesPipeline‘: 1}
IMAGES_STORE=‘E:\\jiandan2‘
DOWNLOAD_DELAY = 0.25
IMAGES_THUMBS = {#缩略图的尺寸，设置这个值就会产生缩略图
    ‘small‘: (50, 50),
    ‘big‘: (200, 200),
}