def vecCompare(cs):
client = MG()
db = client.spider_data
collect = db.baiduqa_
data = collect.find()
#设置答案对象
answer = Answer()
#初始化比较值
sim_best = 0
sim_sec = 0
for item in data:
#两个问句的相似度比较
sim_num = vector_similarity(item['pureQstr'], cs)
if sim_num > sim_best:
answer.matchQ1 = item['title']
answer.bestAnswer = item['answer']
sim_best = sim_num
continue
if sim_num > sim_sec:
answer.matchQ2 = item['title']
answer.secAnswer = item['answer']
sim_sec = sim_num
return answer
def Keyword_Compare(cs):
client=MG()
db=client.spider_data
collect=db.baiduqa_
data=collect.find()
collect2=db.baiduQaFormal
data2=collect2.find()
csx=jieba.lcut(cs,cut_all=True)
tmplen=0
best=0
sec=0
bestAns=''
matchQ1=''
secAns=''
matchQ2=''
for item in data:
lx=item['keyword']
ret=[x for x in csx if x in lx ]
tmplen=len(ret)
if tmplen>best:
matchQ1=item['title']
bestAns=item['answer']
best=tmplen
continue
if tmplen>sec:
matchQ2=item['title']
secAns=item['answer']
sec=tmplen
for item in data2:
lx=item['keyword']
ret=[x for x in csx if x in lx ]
tmplen=len(ret)
if tmplen>best:
matchQ1=item['title']
bestAns=item['answer']
best=tmplen
continue
if tmplen>sec:
matchQ2=item['title']
secAns=item['answer']
sec=tmplen
answer=Answer
answer.bestAnswer=bestAns
answer.matchQ1=matchQ1
answer.best=best
answer.secAnswer=secAns
answer.matchQ2=matchQ2
answer.sec=sec
return answer
def build():
client=MG()
db=client.spider_data
collect=db.baiduQaFormal
data=collect.find()
for item in data:
precut=item['title']
print(precut)
cutted=jieba.lcut(precut,cut_all=True)
collect.update({"_id":item["_id"]},{"$set":{"keyword":cutted}})
def __init__(self):
mybot_path = './'
self.mybot = aiml.Kernel()
pathZ = os.path.abspath(os.path.dirname(os.path.dirname(__file__)))
print(pathZ)
#加载机器人对答模板文件
self.mybot.learn(pathZ + '/COMM_robot/std-startup.xml')
self.mybot.learn(pathZ + '/COMM_robot/Common_conversation.aiml')
self.mybot.learn(pathZ + '/COMM_robot/question_analyse.aiml')
#加载预制字典
jieba.load_userdict(pathZ + '/COMM_robot/text_dict.txt')
#mongodb配置
client = MG()
db = client.spider_data
self.collect = db.baidu_baike_3_test
def __init__(self):
'''初始化设置'''
#可修改：定义索引名称
self._index = "law_data"
#可修改，但一般不需要，定义es服务器设置
self.es = ES([{"host": "127.0.0.1", "port": 9200}])
#可修改：定义文档类型
self.doc_type = "line"
#无需修改，链接mongodb
self.MGclient = MG("mongodb://*****:*****@localhost:27017")
#可修改，指定数据库名称
self.db = self.MGclient.spider_data
#可修改,指定collection的名称
self.collect = self.db.LAW
def __init__(self):
'''初始化设置'''
#可修改：定义索引名称
self._index = "news_case"
#可修改，但一般不需要，定义es服务器设置
self.es = ES([{"host": "127.0.0.1", "port": 9200}])
#可修改：定义文档类型
self.doc_type = "case"
#无需修改，链接mongodb
self.MGclient = MG()
#可修改，指定数据库名称
self.db = self.MGclient.spider_data
#可修改,指定collection的名称
self.collect = self.db.tagged_case
def __init__(self):
'''初始化设置'''
#可修改：定义索引名称
self._index = "baike_data_abstract"
#可修改，但一般不需要，定义es服务器设置
self.es = ES([{"host": "localhost", "port": 9200}])
#可修改：定义文档类型
self.doc_type = "knowledge"
#无需修改，链接mongodb
self.MGclient = MG("mongodb://*****:*****@localhost:27017")
#可修改，指定数据库名称
self.db = self.MGclient.spider_data
#可修改,指定collection的名称
self.collect = self.db.baidu_baike_BIG
def __init__(self):
'''初始化设置'''
#可修改：定义索引名称
self._index = "qa_data"
#可修改，但一般不需要，定义es服务器设置
self.es = ES([{"host": "localhost", "port": 9200}])
#可修改：定义文档类型
self.doc_type = "qa"
#无需修改，链接mongodb
self.MGclient = MG("mongodb://*****:*****@localhost:27017")
#可修改，指定数据库名称
self.db = self.MGclient.spider_data
#self.db.authenticate("reader","reader")
#可修改,指定collection的名称
self.collect = self.db.qa_byHand
#导入法条法规 刑法
from pymongo import MongoClient as MG
import re
file = open(
'D:\\Google Download\\#按日期管理的下载\\190404\\法律法规大全\\程序法\\中华人民共和国仲裁法.txt')
line = file.readline()
client = MG()
db = client.spider_data
collect = db.LAW
lawDoc = dict()
lawDoc['name'] = line
lawDoc['content'] = list()
#re规则
bian = re.compile('第.*编!')
zhang = re.compile('第.*章!')
jie = re.compile('第.*节!')
tiaoT = re.compile('第.*?条!')
tiao = re.compile('第.*?条')
fuze = re.compile('附!则')
#根据法条编制规则控制进程
ctrlcount = 0
am_i_in_tiao = 0
#写入进程开始
while line:
print(line)
pureline = line.replace(u'\u3000', '!')
def __init__(self):
self.client = MG()
from pymongo import MongoClient as MG
import re
import datetime
client = MG("mongodb://127.0.0.1:27017")
db = client.NseDb
#db.NseCodesCollection.insert({"_id":"NseCodes","Codes":[]})
NseCodesFile = open("C:\\Users\\Ranjith\\Desktop\\NSE Scripts\\CompleteList.txt")
NseHistoryFile = open("C:\\Users\\Ranjith\\Desktop\\NSE Scripts\\NseHistory.txt")
class InsertNseData :
def __init__(self):
self.InsertData()
def InsertData(self):
for Line in NseHistoryFile.readlines()[:1]:
Code = re.sub("'","",Line.split(':')[0]); print (Code)
CodeLen = len(Code)
History = Line[CodeLen+2:-2]
History = History.split("datetime.date")
print (History)
for Data in History[1:]:
#print (Data)
if "'" in Data:
continue
Date, ClosePrice = Data.split(':')
def __init__(self):
self.client = MG("mongodb://*****:*****@localhost:27017")
