def _get_tags(self, article_info):
'''
获取tags
:return:
'''
tmp_tags = list_duplicate_remove(
[str(item.get('name', '')) for item in article_info.get('noteInfo', {}).get('relatedTags', [])])
# self.my_lg.info(str(tmp_tags))
# list先转str, 去掉敏感字眼, 再转list, 并去除''元素, 得到最后list
tmp_tags = delete_list_null_str(self.wash_sensitive_info('|'.join(tmp_tags)).split('|'))
tags = [{ # tags可以为空list!
'keyword': item,
} for item in tmp_tags]
return tags
async def _get_article(self, data, taobao_short_url):
'''
得到该文章的需求信息
:param data:
:return:
'''
try:
nick_name = data.get('data', {}).get('models', {}).get('account', {}).get('name', '')
assert nick_name != '', '获取到的nick_name为空值!'
head_url = await self._get_head_url(data=data)
# 推荐人的简介或者个性签名
tmp_profile = data.get('data', {}).get('models', {}).get('account', {}).get('accountDesc', '')
profile = tmp_profile if tmp_profile is not None else ''
title = self._wash_sensitive_info(data.get('data', {}).get('models', {}).get('content', {}).get('title', ''))
# self.my_lg.info(title)
assert title != '', '获取到的title为空值!请检查!'
# 达人的评论，可用于荐好首页的文字信息
comment_content = self._wash_sensitive_info(data.get('data', {}).get('models', {}).get('content', {}).get('summary', ''))
'''微淘抓包的接口: 图片，商品依次对应'''
tmp_goods_list = data.get('data', {}).get('models', {}).get('content', {}).get('drawerList', [])
assert tmp_goods_list != [], '获取到的goods_id_list为空list! 请检查! 可能该文章推荐商品为空[]!'
share_img_url_list = [{'img_url': 'https:' + item.get('itemImages', [])[0].get('picUrl', '')} for item in tmp_goods_list]
goods_id_list = [{'goods_id': item.get('itemId', '')} for item in tmp_goods_list]
# 由于微淘的图片跟商品信息一一对应，so直接存一个字段, 清除重复的推荐商品(list去重，并保持原来的顺序)
share_goods_base_info = list_duplicate_remove([{
'img_url': 'https:' + item.get('itemImages', [])[0].get('picUrl', ''),
'goods_id': item.get('itemId', ''),
} for item in tmp_goods_list])
# div_body
div_body = self._wash_sensitive_info(await self._get_div_body(rich_text=data.get('data', {}).get('models', {}).get('content', {}).get('richText', [])))
# print(div_body)
# 待抓取的商品地址, 统一格式为淘宝的，如果是tmall地址, 浏览器会重定向到天猫
goods_url_list = [{'goods_url': 'https://item.taobao.com/item.htm?id=' + item.get('goods_id', '')} for item in goods_id_list]
_ = (await self._get_target_url_and_content_id_and_csid(taobao_short_url))
gather_url = _[0]
share_id = _[1] # 即content_id
create_time = get_shanghai_time()
site_id = 2 # 淘宝微淘
# tags 额外的文章地址
tags = await self._get_tags(data=data)
# pprint(tags)
except Exception as e:
self.my_lg.error('出错短链接地址:{0}'.format(taobao_short_url))
self.my_lg.exception(e)
return {}
article = WellRecommendArticle()
article['nick_name'] = nick_name
article['head_url'] = head_url
article['profile'] = profile
article['share_id'] = share_id
article['title'] = title
article['comment_content'] = comment_content
article['share_img_url_list'] = share_img_url_list
article['goods_id_list'] = goods_id_list
article['div_body'] = div_body
article['gather_url'] = gather_url
article['create_time'] = create_time
article['site_id'] = site_id
article['goods_url_list'] = goods_url_list
article['tags'] = tags
article['share_goods_base_info'] = share_goods_base_info
return article