import pandas as pd
from elasticsearch import Elasticsearch as Es
def es_index_adapt(index_prefix, doc_type, rw=None):
"""get the adapted index name
"""
assert rw in [None, 'read', 'write']
index = '-'.join((index_prefix, doc_type))
if rw:
index = '-'.join((index, rw))
return index
def get_es(es_hosts_config=None):
init_args = {
# 'hosts':settings.ES_HOSTS,
# no sniffing
'sniff_on_start': False,
'sniff_on_connection_fail': False,
}
ES_V2_HOSTS = [
{
'host': '172.16.31.17',
'port': 9000,
}, {
'host': '172.16.31.11',
'port': 9000,
}, {
'host': '172.16.31.13',
'port': 9000,
}
]
new_hosts = ES_V2_HOSTS
new_es = Es(hosts=new_hosts, **init_args)
return new_es
def es_query(doc, body, offset, size, es=None):
if es is None:
es = get_es()
index = es_index_adapt(
index_prefix='gm-dbmw',
doc_type=doc,
rw='read'
)
res = es.search(
index=index,
doc_type=doc,
timeout='10s',
body=body,
from_=offset,
size=size)
number = res["hits"]["total"]
return number
# total = res["hits"]["hits"]
# print(total)
# r = []
# for i in total:
# r.append(i['_source']['id'])
# return r
def answer():
tags = ["下颌角切除术", "M唇", "瘦身", "抽脂", "隆胸", "丰乳房", "孕睫术", "眶隔脂肪释放术", "小腿神经阻断术", '瘦脸针',
'水光针',
'光子嫩肤',
'热玛吉',
'瘦腿针',
'超声刀',
'面部吸脂',
'瘦肩针',
'皮秒',
'果酸焕肤',
'热拉提',
'微针',
'牙齿矫正',
'超皮秒',
'点阵激光',
'植发',
'小气泡',
'双眼皮修复',
'自体脂肪隆胸',
'鼻翼缩小',
'假体隆胸',
'玻尿酸丰下巴',
'埋线双眼皮',
'纹眉',
'颧骨内推',
'拉皮',
'玻尿酸隆鼻',
'女性私密紧致',
'嗨体',
'溶脂针瘦脸',
'黄金微针',
'磨骨',
'肋骨鼻',
'洗牙',
'植发际线',
'光纤溶脂',
'点痣',
'下颌角切除',
'切开双眼皮',
'腰腹吸脂',
'激光祛斑',
'白瓷娃娃',
'大腿吸脂',
'假体下巴',
'除皱针注射',
'溶解酶',
'吸脂瘦手臂',
'微针祛痘坑',
'厚唇改薄',
'玻尿酸',
'大分子玻尿酸',
'耳软骨',
'鼻中隔软骨',
'肋软骨',
'硅胶',
'膨体',
'假体',
'自体真皮',
'自体脂肪',
'自体软骨',
'自体血清',
'溶解酶',
'嗨体',
'胶原蛋白',
'双美胶原蛋白',
'黄金',
'药物',
'生长因子',
'肉毒素',
'埋线提升',
'悦升线',
'蛋白线',
'水杨酸',
'果酸',
'杏仁酸',
'奥美定',
'干细胞',
'纳米树脂',
'黑脸娃娃',
'眼睑下至',
'童颜针',
'微笑唇',
'减肥',
'瘦身',
'隆鼻',
'V脸',
'祛斑',
'祛痣',
'祛黑头',
'祛疤',
'祛痘',
'溶脂',
'吸脂',
'嘟嘟唇',
'丰唇',
'丰下巴',
'丰胸',
'皮秒',
'蜂巢皮秒',
'超皮秒',
'深蓝射频',
'美瞳',
'提眉',
'纹眉',
'孕睫',
'瓷贴面',
'全瓷牙',
'美容冠',
'黄金微雕',
'微雕',
'削骨',
'截骨',
'脂肪胶',
'prp',
'轮廓针',
'水光针',
'婴儿针',
'三文鱼针',
'少女针',
'素颜针',
'瘦脸针',
'熊猫针',
'瘦腿针',
'小气泡',
'正颌',
'一针降颧骨',
'脱毛',
'近视',
'面部提升',
'嫩肤',
'镭射净肤',
'红蓝光',
'二氧化碳点阵',
'狐臭',
'清洁',
'补水',
'内窥镜',
'热立塑',
'威塑',
'优立塑',
'酷塑',
'调Q激光',
'DPL',
'染料激光',
'体检',
'产后',
'正骨术',
'隔空溶脂',
'pst',
'唇裂',
'塑身',
'微晶瓷',
'ICL晶体植入',
'全飞秒',
'半飞秒',
'根管治疗',
'抗衰',
'紧致',
'飞梭雷射',
'三点双眼皮',
'颊脂垫',
'嫩红',
'眶隔脂肪释放',
'针清',
'美白',
'冷光美白',
'美白仓',
'小腿神经阻断',
'正畸',
'变性',
'干细胞疗法',
'月光脱毛',
'火凤凰溶脂',
'微拉美',
'剥落点阵',
'非剥落点阵']
total_list = []
query_operator = "and"
query_type = "cross_fields"
for i in tags:
tmp = [i]
query = i
star3_q = {
"query": {"filtered": {
"filter": {
"bool": {
"must": [{
"multi_match": {
"fields": ["title^1", "desc^1", "answer^1"],
"operator": query_operator,
"type": query_type,
"query": query
}
}, {
"term": {
"is_online": True
}
}, {"term": {
"content_level": 3
}
}]
}
}
}
}
}
tmp.append(es_query('answer', star3_q, 0, 1))
star4_q = {
"query": {
"filtered": {
"filter": {
"bool": {
"must": [{
"multi_match": {
"fields": ["title^1", "desc^1", "answer^1"],
"operator": query_operator,
"type": query_type,
"query": query
}
}, {
"term": {
"is_online": True
}
}, {"term": {
"content_level": 4
}
}]
}
}
}
}
}
tmp.append(es_query('answer', star4_q, 0, 1))
star5_q = {
"query": {
"filtered": {
"filter": {
"bool": {
"must": [{
"multi_match": {
"fields": ["title^1", "desc^1", "answer^1"],
"operator": query_operator,
"type": query_type,
"query": query
}
}, {
"term": {
"is_online": True
}
}, {"term": {
"content_level": 5
}
}]
}
}
}
}
}
tmp.append(es_query('answer', star5_q, 0, 1))
video_star3_q = {
"query": {
"filtered": {
"filter": {
"bool": {
"must": [{
"multi_match": {
"fields": ["title^1", "desc^1", "answer^1"],
"operator": query_operator,
"type": query_type,
"query": query
}
}, {
"term": {
"is_online": True
}
}, {
"term": {
"content_type": 1
}
}, {"term": {
"content_level": 3
}
}]
}
}
}
}
}
tmp.append(es_query('answer', video_star3_q, 0, 1))
video_star4_q = {
"query": {
"filtered": {
"filter": {
"bool": {
"must": [{
"multi_match": {
"fields": ["title^1", "desc^1", "answer^1"],
"operator": query_operator,
"type": query_type,
"query": query
}
}, {
"term": {
"is_online": True
}
}, {
"term": {
"content_type": 1
}
}, {"term": {
"content_level": 4
}
}]
}
}
}
}
}
tmp.append(es_query('answer', video_star4_q, 0, 1))
video_star5_q = {
"query": {
"filtered": {
"filter": {
"bool": {
"must": [{
"multi_match": {
"fields": ["title^1", "desc^1", "answer^1"],
"operator": query_operator,
"type": query_type,
"query": query
}
}, {
"term": {
"is_online": True
}
}, {
"term": {
"content_type": 1
}
}, {"term": {
"content_level": 5
}
}]
}
}
}
}
}
tmp.append(es_query('answer', video_star5_q, 0, 1))
total_list.append(tmp)
# print(i)
# print(tmp)
df = pd.DataFrame(total_list)
df = df.rename(columns={0: "tag", 1: "star_3", 2: "star_4", 3: "star_5",
4: "video_star_3", 5: "video_star_4", 6: "video_star_5"})
df.to_csv("/home/gmuser/tag_answer.csv", index=False, encoding="utf_8_sig")
def question():
tags = ["下颌角切除术", "M唇", "瘦身", "抽脂", "隆胸", "丰乳房", "孕睫术", "眶隔脂肪释放术", "小腿神经阻断术", '瘦脸针',
'水光针',
'光子嫩肤',
'热玛吉',
'瘦腿针',
'超声刀',
'面部吸脂',
'瘦肩针',
'皮秒',
'果酸焕肤',
'热拉提',
'微针',
'牙齿矫正',
'超皮秒',
'点阵激光',
'植发',
'小气泡',
'双眼皮修复',
'自体脂肪隆胸',
'鼻翼缩小',
'假体隆胸',
'玻尿酸丰下巴',
'埋线双眼皮',
'纹眉',
'颧骨内推',
'拉皮',
'玻尿酸隆鼻',
'女性私密紧致',
'嗨体',
'溶脂针瘦脸',
'黄金微针',
'磨骨',
'肋骨鼻',
'洗牙',
'植发际线',
'光纤溶脂',
'点痣',
'下颌角切除',
'切开双眼皮',
'腰腹吸脂',
'激光祛斑',
'白瓷娃娃',
'大腿吸脂',
'假体下巴',
'除皱针注射',
'溶解酶',
'吸脂瘦手臂',
'微针祛痘坑',
'厚唇改薄',
'玻尿酸',
'大分子玻尿酸',
'耳软骨',
'鼻中隔软骨',
'肋软骨',
'硅胶',
'膨体',
'假体',
'自体真皮',
'自体脂肪',
'自体软骨',
'自体血清',
'溶解酶',
'嗨体',
'胶原蛋白',
'双美胶原蛋白',
'黄金',
'药物',
'生长因子',
'肉毒素',
'埋线提升',
'悦升线',
'蛋白线',
'水杨酸',
'果酸',
'杏仁酸',
'奥美定',
'干细胞',
'纳米树脂',
'黑脸娃娃',
'眼睑下至',
'童颜针',
'微笑唇',
'减肥',
'瘦身',
'隆鼻',
'V脸',
'祛斑',
'祛痣',
'祛黑头',
'祛疤',
'祛痘',
'溶脂',
'吸脂',
'嘟嘟唇',
'丰唇',
'丰下巴',
'丰胸',
'皮秒',
'蜂巢皮秒',
'超皮秒',
'深蓝射频',
'美瞳',
'提眉',
'纹眉',
'孕睫',
'瓷贴面',
'全瓷牙',
'美容冠',
'黄金微雕',
'微雕',
'削骨',
'截骨',
'脂肪胶',
'prp',
'轮廓针',
'水光针',
'婴儿针',
'三文鱼针',
'少女针',
'素颜针',
'瘦脸针',
'熊猫针',
'瘦腿针',
'小气泡',
'正颌',
'一针降颧骨',
'脱毛',
'近视',
'面部提升',
'嫩肤',
'镭射净肤',
'红蓝光',
'二氧化碳点阵',
'狐臭',
'清洁',
'补水',
'内窥镜',
'热立塑',
'威塑',
'优立塑',
'酷塑',
'调Q激光',
'DPL',
'染料激光',
'体检',
'产后',
'正骨术',
'隔空溶脂',
'pst',
'唇裂',
'塑身',
'微晶瓷',
'ICL晶体植入',
'全飞秒',
'半飞秒',
'根管治疗',
'抗衰',
'紧致',
'飞梭雷射',
'三点双眼皮',
'颊脂垫',
'嫩红',
'眶隔脂肪释放',
'针清',
'美白',
'冷光美白',
'美白仓',
'小腿神经阻断',
'正畸',
'变性',
'干细胞疗法',
'月光脱毛',
'火凤凰溶脂',
'微拉美',
'剥落点阵',
'非剥落点阵']
total_list = []
query_operator = "and"
query_type = "cross_fields"
category = 'question'
for i in tags:
tmp = [i]
query = i
q = {
"query": {"filtered": {
"filter": {
"bool": {
"must": [{
"multi_match": {
"fields": ["title^1", "content^1", "tags^1"],
"operator": query_operator,
"type": query_type,
"query": query
}
}, {
"term": {
"is_online": True
}
}]
}
}
}
}
}
tmp.append(es_query(category, q, 0, 1))
video_q = {
"query": {
"filtered": {
"filter": {
"bool": {
"must": [{
"multi_match": {
"fields": ["title^1", "content^1", "tags^1"],
"operator": query_operator,
"type": query_type,
"query": query
}
}, {
"term": {
"is_online": True
}
}, {
"term": {
"content_type": 1
}
}]
}
}
}
}
}
tmp.append(es_query(category, video_q, 0, 1))
total_list.append(tmp)
# print(i)
# print(tmp)
df = pd.DataFrame(total_list)
df = df.rename(columns={0: "tag", 1: "number", 2: "video_number"})
df.to_csv("/home/gmuser/tag_question.csv", index=False, encoding="utf_8_sig")
def topic():
tags = ["下颌角切除术", "M唇", "瘦身", "抽脂", "隆胸", "丰乳房", "孕睫术", "眶隔脂肪释放术", "小腿神经阻断术", '瘦脸针',
'水光针',
'光子嫩肤',
'热玛吉',
'瘦腿针',
'超声刀',
'面部吸脂',
'瘦肩针',
'皮秒',
'果酸焕肤',
'热拉提',
'微针',
'牙齿矫正',
'超皮秒',
'点阵激光',
'植发',
'小气泡',
'双眼皮修复',
'自体脂肪隆胸',
'鼻翼缩小',
'假体隆胸',
'玻尿酸丰下巴',
'埋线双眼皮',
'纹眉',
'颧骨内推',
'拉皮',
'玻尿酸隆鼻',
'女性私密紧致',
'嗨体',
'溶脂针瘦脸',
'黄金微针',
'磨骨',
'肋骨鼻',
'洗牙',
'植发际线',
'光纤溶脂',
'点痣',
'下颌角切除',
'切开双眼皮',
'腰腹吸脂',
'激光祛斑',
'白瓷娃娃',
'大腿吸脂',
'假体下巴',
'除皱针注射',
'溶解酶',
'吸脂瘦手臂',
'微针祛痘坑',
'厚唇改薄',
'玻尿酸',
'大分子玻尿酸',
'耳软骨',
'鼻中隔软骨',
'肋软骨',
'硅胶',
'膨体',
'假体',
'自体真皮',
'自体脂肪',
'自体软骨',
'自体血清',
'溶解酶',
'嗨体',
'胶原蛋白',
'双美胶原蛋白',
'黄金',
'药物',
'生长因子',
'肉毒素',
'埋线提升',
'悦升线',
'蛋白线',
'水杨酸',
'果酸',
'杏仁酸',
'奥美定',
'干细胞',
'纳米树脂',
'黑脸娃娃',
'眼睑下至',
'童颜针',
'微笑唇',
'减肥',
'瘦身',
'隆鼻',
'V脸',
'祛斑',
'祛痣',
'祛黑头',
'祛疤',
'祛痘',
'溶脂',
'吸脂',
'嘟嘟唇',
'丰唇',
'丰下巴',
'丰胸',
'皮秒',
'蜂巢皮秒',
'超皮秒',
'深蓝射频',
'美瞳',
'提眉',
'纹眉',
'孕睫',
'瓷贴面',
'全瓷牙',
'美容冠',
'黄金微雕',
'微雕',
'削骨',
'截骨',
'脂肪胶',
'prp',
'轮廓针',
'水光针',
'婴儿针',
'三文鱼针',
'少女针',
'素颜针',
'瘦脸针',
'熊猫针',
'瘦腿针',
'小气泡',
'正颌',
'一针降颧骨',
'脱毛',
'近视',
'面部提升',
'嫩肤',
'镭射净肤',
'红蓝光',
'二氧化碳点阵',
'狐臭',
'清洁',
'补水',
'内窥镜',
'热立塑',
'威塑',
'优立塑',
'酷塑',
'调Q激光',
'DPL',
'染料激光',
'体检',
'产后',
'正骨术',
'隔空溶脂',
'pst',
'唇裂',
'塑身',
'微晶瓷',
'ICL晶体植入',
'全飞秒',
'半飞秒',
'根管治疗',
'抗衰',
'紧致',
'飞梭雷射',
'三点双眼皮',
'颊脂垫',
'嫩红',
'眶隔脂肪释放',
'针清',
'美白',
'冷光美白',
'美白仓',
'小腿神经阻断',
'正畸',
'变性',
'干细胞疗法',
'月光脱毛',
'火凤凰溶脂',
'微拉美',
'剥落点阵',
'非剥落点阵']
total_list = []
query_operator = "and"
query_type = "cross_fields"
category = 'tractate'
for i in tags:
tmp = [i]
query = i
star3_q = {
"query": {"filtered": {
"filter": {
"bool": {
"must": [{
"multi_match": {
"fields": ["content^1", "author^1", "tractate_tag_name^1",
"tractate_tag_name_content^1"],
"operator": query_operator,
"type": query_type,
"query": query
}
}, {
"term": {
"is_online": True
}
}, {"term": {
"content_level": 3
}
},
{
"term": {
"status": "3"
}
}]
}
}
}
}
}
tmp.append(es_query(category, star3_q, 0, 1))
star4_q = {
"query": {"filtered": {
"filter": {
"bool": {
"must": [{
"multi_match": {
"fields": ["content^1", "author^1", "tractate_tag_name^1",
"tractate_tag_name_content^1"],
"operator": query_operator,
"type": query_type,
"query": query
}
}, {
"term": {
"is_online": True
}
}, {"term": {
"content_level": 4
}
},
{
"term": {
"status": "3"
}
}]
}
}
}
}
}
tmp.append(es_query(category, star4_q, 0, 1))
star5_q = {
"query": {"filtered": {
"filter": {
"bool": {
"must": [{
"multi_match": {
"fields": ["content^1", "author^1", "tractate_tag_name^1",
"tractate_tag_name_content^1"],
"operator": query_operator,
"type": query_type,
"query": query
}
}, {
"term": {
"is_online": True
}
}, {"term": {
"content_level": 5
}
},
{
"term": {
"status": "3"
}
}]
}
}
}
}
}
tmp.append(es_query(category, star5_q, 0, 1))
video_star3_q = {
"query": {"filtered": {
"filter": {
"bool": {
"must": [{
"multi_match": {
"fields": ["content^1", "author^1", "tractate_tag_name^1",
"tractate_tag_name_content^1"],
"operator": query_operator,
"type": query_type,
"query": query
}
}, {
"term": {
"is_online": True
}
}, {"term": {
"content_level": 3
}
},
{
"term": {
"status": "3"
}
}, {"term": {"is_video": True}}]
}
}
}
}
}
tmp.append(es_query(category, video_star3_q, 0, 1))
video_star4_q = {
"query": {"filtered": {
"filter": {
"bool": {
"must": [{
"multi_match": {
"fields": ["content^1", "author^1", "tractate_tag_name^1",
"tractate_tag_name_content^1"],
"operator": query_operator,
"type": query_type,
"query": query
}
}, {
"term": {
"is_online": True
}
}, {"term": {
"content_level": 4
}
},
{
"term": {
"status": "3"
}
}, {"term": {"is_video": True}}]
}
}
}
}
}
tmp.append(es_query(category, video_star4_q, 0, 1))
video_star5_q = {
"query": {"filtered": {
"filter": {
"bool": {
"must": [{
"multi_match": {
"fields": ["content^1", "author^1", "tractate_tag_name^1",
"tractate_tag_name_content^1"],
"operator": query_operator,
"type": query_type,
"query": query
}
}, {
"term": {
"is_online": True
}
}, {"term": {
"content_level": 5
}
},
{
"term": {
"status": "3"
}
}, {"term": {"is_video": True}}]
}
}
}
}
}
tmp.append(es_query(category, video_star5_q, 0, 1))
total_list.append(tmp)
df = pd.DataFrame(total_list)
df = df.rename(columns={0: "tag", 1: "star_3", 2: "star_4", 3: "star_5",
4: "video_star_3", 5: "video_star_4", 6: "video_star_5"})
df.to_csv("/home/gmuser/tag_topic.csv", index=False, encoding="utf_8_sig")
def test_topic():
query_operator = "and"
query_type = "cross_fields"
category = 'tractate'
query = "眶隔脂肪释放术"
star3_q = {
"query": {"filtered": {
"filter": {
"bool": {
"must": [{
"multi_match": {
"fields": ["content^1", "author^1", "tractate_tag_name^1",
"tractate_tag_name_content^1"],
"operator": query_operator,
"type": query_type,
"query": query
}
}, {
"term": {
"is_online": True
}
}, {"term": {
"content_level": 3
}
},
{
"term": {
"status": "3"
}
}]
}
}
}
},"_source":{"include":"id"}
}
print(es_query(category, star3_q, 0, 10))
if __name__ == "__main__":
topic()
print("topic ok")
question()
print("ques ok")
answer()
print("answer ok")