Scrapy 프레임워크를 사용하여 Flickr 이미지 라이브러리 크롤링

import time
import json
import scrapy
from flickr.items import FlickrItem

class FlickrSpider(scrapy.Spider):
    name = 'flickr'
    api_key = 'YOUR_API_KEY'  # 这里填写你自己的API Key
    tags = 'cat,dog'  # 这里将cat和dog作为爬取的关键词，你可以自由定义
    format = 'json'
    nojsoncallback = '1'
    page = '1'
    per_page = '50'

    start_urls = [
        'https://api.flickr.com/services/rest/?method=flickr.photos.search&'
        'api_key={}'
        '&tags={}'
        '&page={}'
        '&per_page={}'
        '&format={}'
        '&nojsoncallback={}'.format(api_key, tags, page, per_page, format, nojsoncallback)
    ]

    def parse(self, response):
        results = json.loads(response.body_as_unicode())
        for photo in results['photos']['photo']:
            item = FlickrItem()
            item['image_title'] = photo['title']
            item['image_url'] = 'https://farm{}.staticflickr.com/{}/{}_{}.jpg'.format(
                photo['farm'], photo['server'], photo['id'], photo['secret'])
            yield item

        if int(self.page) <= results['photos']['pages']:
            self.page = str(int(self.page) + 1)
            next_page_url = 'https://api.flickr.com/services/rest/?method=flickr.photos.search&' 
                            'api_key={}' 
                            '&tags={}' 
                            '&page={}' 
                            '&per_page={}' 
                            '&format={}' 
                            '&nojsoncallback={}'.format(self.api_key, self.tags, self.page, self.per_page, self.format, self.nojsoncallback)
            time.sleep(1)  # 设置延时1秒钟
            yield scrapy.Request(url=next_page_url, callback=self.parse)

ITEM_PIPELINES = {
   'flickr.pipelines.FlickrPipeline': 300,
}

IMAGES_STORE = 'images'

import scrapy
from scrapy.pipelines.images import ImagesPipeline
from scrapy.exceptions import DropItem

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

class FlickrImagesPipeline(ImagesPipeline):
    def get_media_requests(self, item, info):
        for image_url in item['image_url']:
            try:
                yield scrapy.Request(image_url)
            except Exception as e:
                pass

    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

scrapy crawl flickr