def __sort_item(self, key):
item = self.items.pop(key)
item['media_urls'].sort(key=lambda url: int(re.findall(r'qd_index=(\d+)&', url)[0]))
item['info'].pop('index', None)
item['info'].pop('count', None)
item['info'].pop('player', None)
return item
# class MultimediaCrawlerMiddleware(object):
# @classmethod
# def from_crawler(cls, crawler):
# # This method is used by Scrapy to create your spiders.
# s = cls()
# crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
# return s
#
# def process_spider_input(self, response, spider):
# # Called for each response that goes through the spider
# # middleware and into the spider.
#
# # Should return None or raise an exception.
# return None
#
# def process_spider_output(self, response, result, spider):
# # Called with the results returned from the Spider, after
# # it has processed the response.
# # Must return an iterable of Request, dict or Item objects.
# for i in result:
# yield i
#
# def process_spider_exception(self, response, exception, spider):
# # Called when a spider or process_spider_input() method
# # (from other spider middleware) raises an exception.
#
# # Should return either None or an iterable of Response, dict
# # or Item objects.
# pass
#
# def process_start_requests(self, start_requests, spider):
# # Called with the start requests of the spider, and works
# # similarly to the process_spider_output() method, except
# # that it doesn’t have a response associated.
#
# # Must return only requests (not items).
# for r in start_requests:
# yield r
#
# def spider_opened(self, spider):
# spider.logger.info('Spider opened: %s' % spider.name)
评论列表
文章目录
