def save_to_es(self):
article = ArticleType()
article.title = self['title']
article.create_date = self['create_date']
article.content = remove_tags(self['content'])
article.front_image_url = self['front_image_url']
if 'front_image_path' in self:
article.front_image_path = self['front_image_path']
try:
article.praise_number = self["praise_number"]
except:
print("items出错")
article.praise_number = 99999
article.comment_nums = self['comment_nums']
article.content = self['content']
article.tags = self['tags']
article.fav_nums = self['fav_nums']
article.url = self['url']
article.meta.id = self['url_object_id']
article.suggest = gen_suggests(ArticleType._doc_type.index,((article.title,10),(article.tags,7))) #分词
article.save()
return
def save_to_es(self):
article = ArticleType()
article.title = self['title']
article.create_date = self["create_date"]
article.content = (self["content"])
if "front_image_url" in self:
article.front_image_url = self["front_image_url"]
if "front_image_path" in self:
article.front_image_path = self["front_image_path"]
article.praise_nums = self["praise_nums"]
article.fav_nums = self["fav_nums"]
article.comment_nums = self["comment_nums"]
article.url = self["url"]
article.tags = self["tags"]
article.id = self["url_object_id"]
# 生成搜索建议词
article.suggest = gen_suggests(ArticleType._doc_type.index,
((article.title, 10),
(article.tags, 7)))
article.save()
# 数据加1操作
redis_cli.incr("cnblogs_count")
return
def save_to_es(self):
article = ArticleType()
article.title = self['title']
article.create_date = self["create_date"]
article.content = remove_tags(self["content"])
article.front_image_url = self["front_image_url"]
if "front_image_path" in self:
article.front_image_path = self["front_image_path"]
if "praise_nums" in self:
article.praise_nums = self["praise_nums"]
else:
article.praise_nums = 0
article.fav_nums = self["fav_nums"]
article.comment_nums = self["comment_nums"]
article.url = self["url"]
article.tags = self["tags"]
article.meta.id = self["url_object_id"]
article.suggest = gen_suggests(ArticleType._doc_type.index,
((article.title, 10),
(article.tags, 7)))
article.save()
redis_cli.incr("jobbole_count")
return
def save_to_es(self):
article = ArticleType()
article.title = self['title']
article.create_date = self["create_date"]
article.content = remove_tags(self["content"])
article.front_image_url = self["front_image_url"]
if "front_image_path" in self:
article.front_image_path = self["front_image_path"]
article.praise_nums = self["praise_nums"]
article.fav_nums = self["fav_nums"]
article.comment_nums = self["comment_nums"]
article.url = self["url"]
article.tags = self["tags"]
article.meta.id = self["url_object_id"]
article.save()
return
def save_to_es(self):
article = ArticleType()
article.title = self['title']
article.create_date = self["create_date"]
article.content = remove_tags(self["contents"])
article.front_img_url = self["front_img_url"]
if "front_img_path" in self:
article.front_img_path = self["front_img_path"]
article.store = self["store"]
article.zan = self["zan"]
article.comments = self["comments"]
article.url = self["url"]
article.tags = self["tags"]
article.url_md5= self["url_md5"]
article.suggest = gen_suggests(ArticleType._doc_type.index, ((article.title,10), (article.tags, 7)))
article.save()
return
def save_to_es(self):
article = ArticleType()
article.title = self['title']
article.create_date = self['create_date']
article.content = self['content']
article.url = self['url']
article.tags = self['tags']
article.fav_nums = self['fav_nums']
article.praise_nums = self['praise_nums']
article.comment_nums = self['comment_nums']
article.suggest = gen_suggests(ArticleType._doc_type.index,
((article.title, 10),
(article.tags, 7)))
article.save()
return
def process_item(self, item, spider):
#将item转换为es的数据
article = ArticleType()
article.title = item['title']
article.create_date = item["create_date"]
article.content = remove_tags(item["content"])
article.front_image_url = item["front_image_url"]
if "front_image_path" in item:
article.front_image_path = item["front_image_path"]
article.praise_nums = item["praise_nums"]
article.fav_nums = item["fav_nums"]
article.comment_nums = item["comment_nums"]
article.url = item["url"]
article.tags = item["tags"]
article.meta.id = item["url_object_id"]
article.suggest = gen_suggests(ArticleType._doc_type.index,
((article.title, 10),
(article.tags, 7)))
article.save()
return item
def save_to_es(self):
# 将jobbole文章item转换为es的数据
article = ArticleType()
article.title = self['title']
article.create_date = self['create_date']
article.content = remove_tags(self['content'])
article.front_image_url = self['front_image_url']
if "front_image_path" in self:
article.front_image_path = self['front_image_path']
article.comments_nums = self['comments_nums']
article.praise_nums = self['praise_nums']
article.fav_nums = self['fav_nums']
article.url = self['url']
article.tags = self['tags']
article.meta.id = self['url_object_id']
article.suggest = gen_suggests(ArticleType._doc_type.index,
((article.title, 10),
(article.tags, 7)))
article.save()
def process_item(self, item, spider):
article = ArticleType()
article.title = item["title"]
article.create_date = item["create_date"]
article.content = remove_tags(item["content"]).strip().replace(
"\r\n", "").replace("\t", "")
article.front_image_url = item["front_image_url"]
# article.front_image_path = item["front_image_path"]
article.praise_nums = item["praise_nums"]
article.comment_nums = item["comment_nums"]
article.fav_nums = item["fav_nums"]
article.url = item["url"]
article.tags = item["tags"]
article.id = item["url_object_id"]
title_suggest = self.gen_suggests(article.title, article.tags)
article.title_suggest = title_suggest
article.save()
redis_cli.incr("jobbole_count")
return item
def save_to_es(self):
# 将item转换为es的数据
article = ArticleType()
article.title = self['title']
article.create_date = self['create_date']
article.content = remove_tags(self['content'])
article.front_image_url = self['front_image_url']
if "front_image_path" in self:
article.front_image_path = self['front_image_path']
article.praise_nums = self['praise_nums']
article.fav_nums = self['fav_nums']
article.comment_nums = self['comment_nums']
article.url = self['url']
article.tags = self['tags']
article.meta.id = self['url_object_id']
# article.suggest = [{"input":[],"weight":2}]
article.suggest = gen_suggests(ArticleType._index._name,
((article.title, 10),
(article.tags, 7)))
article.save()
return
def save_to_es(self):
article = ArticleType()
article.title = self['title']
article.create_date = self['create_date']
article.content = remove_tags(self['content'])
article.front_image_url = self['front_image_url']
if 'front_image_path' in self:
article.front_image_path = self['front_image_path']
article.praise_nums = self['praise_nums']
article.fav_nums = self['fav_nums']
article.comment_nums = self['comment_nums']
article.url = self['url']
article.tags = self['tags']
article.meta.id = self['url_object_id']
article.suggest = gen_suggests(ArticleType._doc_type.index, ((article.title, 10), (article.tags, 7)))
article.save()
redis_cli.incr("jobbole_count")
return
def save_to_es(self):
article = ArticleType()
article.title = self['title']
article.create_date = self["create_date"]
article.content = remove_tags(self["content"])
article.front_image_url = self["front_image_url"]
if "front_image_path" in self: #front_image_path可能不存在
article.front_image_path = self["front_image_path"]
article.praise_nums = self["praise_nums"]
article.fav_nums = self["fav_nums"]
article.comment_nums = self["comment_nums"]
article.url = self["url"]
article.tags = self["tags"]
article.meta.id = self["url_object_id"] # 用 url_object_id 作为es的id
# article.suggest = [{"input":[]},{"weight":2}] # input 可以用es的GET _analyze来获取
article.suggest = gen_suggests(ArticleType._doc_type.index,
((article.title, 10),
(article.tags, 7))) # 设置搜索建议的值
# #gen_suggests(index, info_tuple)
article.save()
return
