python编程scrapy简单代码实现搜狗图片下载器

https://pic.sogou.com/napi/pc/recommend?key=homeFeedData&category=feed&start=10&len=10
https://pic.sogou.com/napi/pc/recommend?key=homeFeedData&category=feed&start=20&len=10

import scrapy
class SgSpider(scrapy.Spider):
    name = 'sg'
    allowed_domains = ['pic.sogou.com']
    base_url = "https://pic.sogou.com/napi/pc/recommend?key=homeFeedData&category=feed&start={}&len=10"
    start_urls = [base_url.format(0)]
    def parse(self, response):
        json_data = response.json()
        if json_data is not None:
            img_list = json_data["data"]["list"]
            for img in img_list:
                yield {'image_urls': [_["originImage"] for _ in img[0]["picList"]]}
        else:
            return None

yield {'image_urls': [_["originImage"] for _ in img[0]["picList"]]}

# 用户代理设置
USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.54 Safari/537.36'
# Obey robots.txt rules
ROBOTSTXT_OBEY = False
# 下载间隔设置为 3 秒
DOWNLOAD_DELAY = 3
# 默认请求头
DEFAULT_REQUEST_HEADERS = {
    'Accept': 'application/json, text/plain, */*',
    'Accept-Encoding': 'gzip, deflate, br',
    'Accept-Language': 'zh-CN,zh;q=0.9',
    'HOST': 'pic.sogou.com',
}
# 开启 ImagesPipeline 图片保存管道
ITEM_PIPELINES = {
    'scrapy.pipelines.images.ImagesPipeline': 1,
}
# 图片存储文件夹
IMAGES_STORE = "images"

ImagesPipeline requires installing Pillow 4.0.0

class SogouImgPipeline(ImagesPipeline):
    def get_media_requests(self, item, info):
        name = item["name"]
        for index, url in enumerate(item["image_urls"]):
            yield Request(url, meta={'name': name, 'index': index})
    def file_path(self, request, response=None, info=None):
        # 名称
        name = request.meta['name']
        # 索引
        index = request.meta['index']
        filename = u'{0}_{1}.jpg'.format(name, index)
        print(filename)
        return filename

def parse(self, response):
    json_data = response.json()
    if json_data is not None:
        img_list = json_data["data"]["list"]
        for img in img_list:
            yield {
                'name': img[0]['title'],
                'image_urls': [_["originImage"] for _ in img[0]["picList"]],
            }
    else:
        return None