spider.py

import scrapy

from io import BytesIO
from PIL import Image, ImageOps
from scrapy.pipelines.images import ImagesPipeline


class ArticleItem(scrapy.Item):
    image_urls = scrapy.Field()
    images = scrapy.Field()


class ArticleImagesPipeline(ImagesPipeline):

    def convert_image(self, image, size=None):
        if image.format == 'PNG' and image.mode == 'RGBA':
            background = Image.new('RGBA', image.size, (255, 255, 255))
            background.paste(image, image)
            image = background.convert('RGB')
        elif image.mode != 'RGB':
            image = image.convert('RGB')

        if size:
            # Use ImageOps.fit instead of image.thumbnail so that we get an
            # image with the exact dimensions given by `size`.
            image = ImageOps.fit(image, size, Image.ANTIALIAS)

        buf = BytesIO()
        image.save(buf, 'JPEG')
        return image, buf


class ArticleSpider(scrapy.Spider):
    name = 'article'
    custom_settings = {
        'ITEM_PIPELINES': {
            'spider.ArticleImagesPipeline': 100,
        },
        'IMAGES_STORE': 'articles',
        'IMAGES_THUMBS': {
            'small': (290, 150),
            'medium': (610, 320),
        },
        'AUTOTHROTTLE_ENABLED': True,
    }

    def start_requests(self):
        yield scrapy.Request(u'http://www.latimes.com/travel/la-trb-ellis-island-video-20160621-premiumvideo.html')

    def parse(self, response):
        yield ArticleItem(image_urls=['http://www.trbimg.com/img-57699896/turbine/la-trb-ellis-island-video-20160621'])