def save_to_es(self):
job = ArticleType()
job.url = self['url']
job.url_object_id = self['url_object_id']
job.title = self['title']
job.salary = self['salary']
job.job_city = self['job_city']
job.work_years = self['work_years']
job.degree_need = self['degree_need']
job.job_type = self['job_type']
if self['publish_time']:
job.publish_time = self['publish_time']
job.tags = self['tags']
job.job_advantage = self['job_advantage']
job.job_desc = self['job_desc']
job.job_addr = self['job_addr']
job.company_url = self['company_url']
job.company_name = self['company_name']
job.crawl_time = self['crawl_time']
#job.crawl_update_time = self['crawl_update_time']
job.suggest = gen_suggests(ArticleType._doc_type.index,
((job.title, 10), (job.tags, 7)))
job.save()
redis_cli.incr("lagou_count")
return
def process_item(self, item, spider):
"""
将item转换为es的数据格式
:param item:
:param spider:
:return:
"""
# 初始化一个es的document
article = ArticleType()
# 将该条document的id设置为url_object_id
article.meta.id = item['url_object_id']
article.url = item['url']
article.title = item['title']
article.article_type = item['article_type']
article.data_source = item['data_source']
article.publish_time = item['publish_time']
article.abstract = item['abstract']
if item['tags']:
article.tags = item['tags']
else:
article.tags = '无'
# 热度计算公式
article.hot_score = 8 * item['comment_num'] + 3 * item[
'praise_num'] + 5 * item['collection_num'] + item['read_num']
# 传入的元组需要按权值从大到小排列
article.suggest = self.gen_suggests(ArticleType._doc_type.index,
((article.title, 10),
(article.article_type, 5),
(article.tags, 3)))
# 调用save方法直接存储到es中
article.save()
return item