def process_spider_output(self, response, result, spider):
for i in result:
if isinstance(i, scrapy.Item) and (i['info'].get('player', '') == 'iqiyi'):
key = i['url']
if key not in self.items.keys():
self.items[key] = copy.deepcopy(i)
else:
self.items[key]['media_urls'].append(i['media_urls'][0])
if i['info']['count'] == len(self.items[key]['media_urls']):
yield self.__sort_item(key)
else:
yield i
评论列表
文章目录