#coding=utf-8
import requests as r
import json
import threading
import time
#發(fā)送數(shù)據(jù)到目的url des_url，data_dict 參數(shù)為去掉version鍵值后的一條字典數(shù)據(jù)
def send_data(des_url,data_dict):
 data={"add":{ "doc":data_dict}}
 headers = {"Content-Type": "application/json"}
 params = {"boost":1.0,"overwrite":"true","&commitWithin":1000,"commit":"true"}
 url = "%s/update?wt=json"%(des_url)
 re = r.post(url,json = data,params=params,headers=headers)
 if re.status_code != 200:
  print("導(dǎo)入出錯(cuò)",data)

#獲取數(shù)據(jù)，調(diào)用send_data 發(fā)送數(shù)據(jù)到目的url
def get_data(des_url,src_url):
  #定義起始行
 start = 0
 #先獲取到總的數(shù)據(jù)條數(shù)
 se_data=r.get("%s/select?q=*:*&rows=0&start=%s"%(src_url,start)).text
 se_dict = json.loads(se_data)
 numFound = int(se_dict["response"]["numFound"])
 #while循環(huán)，1000條數(shù)據(jù)為一個(gè)循環(huán)
 while start < numFound:
  #定義存放多線程的列表
  th_li = []
    #獲取1000條數(shù)據(jù)
  se_data=r.get("%s/select?q=*:*&rows=1000&start=%s"%(src_url,start)).text
    #把獲取的數(shù)據(jù)轉(zhuǎn)換成字典
  se_dict = json.loads(se_data)
    #獲取數(shù)據(jù)里的docs數(shù)據(jù)
  s_data = (se_dict["response"]["docs"])

  #循環(huán)得到的數(shù)據(jù)，刪除 version鍵值，并使用多線程調(diào)用send_data 方法發(fā)送數(shù)據(jù)
  for i in s_data:
   del i["_version_"]
   th = threading.Thread(target=send_data,args=(des_url,i))
   th_li.append(th)

  for t in th_li:
   t.start()
   t.join()

  start += 1000
  print(start)

if __name__ == "__main__":
 #源數(shù)據(jù)，查詢數(shù)據(jù)的collection地址
 src_url = "http://ip:port/solr/src_connection"
 #導(dǎo)入數(shù)據(jù)導(dǎo)目的collection 的地址
 des_url = "http://ip:port/solr/des_connection"
 start_time = time.time()
 get_data(des_url,src_url)
 end_time = time.time()
 print("耗時(shí)：",end_time-start_time,"秒")

file = open("solr.json","a+")
for i in s_data:
del i["version"]
file.write(str(i)+"\n")
file.close()

#控制web界面刪除數(shù)據(jù)
<delete><query>:</query></delete>
<commit/>