对python 操作solr索引数据的实例详解


Posted in Python onDecember 07, 2018

测试代码1:

def test(self):
  data = {"add": {"doc": {"id": "100001", "*字段名*": u"我是一个大好人"}}}
  params = {"boost": 1.0, "overwrite": "true", "commitWithin": 1000}
  url = 'http://127.0.0.1:8983/solr/mycore/update?wt=json'
  headers = {"Content-Type": "application/json"}
  r = requests.post(url, json=data, params=params, headers=headers)
  print r.text


 def Index_data(self):
  solr = pysolr.Solr('http://127.0.0.1:8983/solr/mycore/', timeout=10)

  # How you'd index data.
  result = solr.add([
   {
    "id": "doc_1",
    "title": "A test document",
   },
   {
    "id": "doc_2",
    "title": "The Banana: Tasty or Dangerous?",
   },
  ])
  print result

测试代码2:

实际数据:

对python 操作solr索引数据的实例详解

def Index_Data_FromCSV(self, csvfile):
  '''
   从CSV文件中读取数据,并索引到solr中
   :param csvfile: csv文件,包括完整路径
   :return:
   '''
  list = CSVOP.ReadCSV(csvfile)
  index = 0
  doc = {}
  params = {"boost": 1.0, "overwrite": "true", "commitWithin": 1000}
  url = 'http://127.0.0.1:8983/solr/mycore/update?wt=json'
  headers = {"Content-Type": "application/json"}
  for item in list:
   if index > 0: # 第一行是标题
    try:
     doc['title'] = item[0].decode('GB2312')
     doc['link'] = item[1]
     # doc['date'] = item[2]
     doc['source'] = item[3].decode('GB2312')
     doc['keyword'] = item[4].decode('GB2312')
     data = {"add": {"doc": doc}}
     r = requests.post(url, json=data, params=params, headers=headers)
     print r.text
    except Exception,e:
     print e.message

   print index
   index += 1

#pysolr客户端代码
 def pysolr_Index_Data_FromCSV(self, csvfile,url='http://127.0.0.1:8983/solr/mycore/'):
  '''
   从CSV文件中读取数据,并索引到solr中
   :param csvfile: csv文件,包括完整路径
   :return:
   '''
  list = CSVOP.ReadCSV(csvfile)
  index = 0
  listdocs = []
  for item in list:
   if index > 0: # 第一行是标题
    doc = {}
    try:
     doc['title'] = item[0].decode('GB2312')
     doc['link'] = item[1]
     # doc['date'] = item[2]
     doc['source'] = item[3].decode('GB2312')
     doc['keyword'] = item[4].decode('GB2312')
     listdocs.append(doc)
    except Exception,e:
     print e.message
   index += 1
  solr = pysolr.Solr(url, timeout=10)
  result = solr.add(listdocs)
  print result

查询代码:

def search_data(self,message='视频'):
  url = 'http://127.0.0.1:8983/solr/mycore/select?q=title:"\%s"&wt=json&indent=true' % message
  r = requests.get(url, verify=False)
  print r.text
  r = r.json()['response']['numFound']
  print message + ":" + str(r)
  
  #pysolr客户端
  def search_data(self,where='视频',url='http://127.0.0.1:8983/solr/mycore/'):
  solr = pysolr.Solr(url, timeout=10)
  dict = {'start':10,'rows': 30,'fl':'title,keyword,source,link'}
  result = solr.search('title:视频',**dict)
  # result = solr.search('title:视频')
  # print result.raw_response['response']['numFound']

  for item in result:
   print 'keyword: %s'% item['keyword']
   print 'title: %s'% item['title']
   print 'source: %s'% item['source']
   print 'link: %s'% item['link']
   print '

'

输出结果:

{
 "responseHeader":{
 "status":0,
 "QTime":0,
 "params":{
  "q":"title:\"\\视频\"",
  "indent":"true",
  "wt":"json"}},
 "response":{"numFound":123,"start":0,"docs":[
  {
  "source":"中彩网",
  "link":"http://www.zhcw.com/video/kaijiangshipin-3D/11981126.shtml",
  "keyword":"视频",
  "title":"福彩3D开奖 视频 -中彩 视频",
  "id":"2f0a9d21-3771-4efa-a0cc-e0484cc97993",
  "_version_":1584214368617234432},
  {
  "source":"新浪视频",
  "link":"http://video.sina.com.cn/news/spj/topvideoes20170707/?opsubject_id=top1",
  "keyword":"视频",
  "title":"今日热门 视频 汇总20170707",
  "id":"c8aae0af-01e9-491f-b999-24b97004a4ba",
  "_version_":1584214367507841024},
  {
  "source":"网易新闻",
  "link":"http://news.163.com/17/0707/13/COOCNUIE00018AOR.html",
  "keyword":"视频",
  "title":"网传"兰桂坊附近不雅 视频 " 警方:传播 视频 将追责",
  "id":"353de48d-ede7-481b-89d3-bc20ab4b3884",
  "_version_":1584214367821365248},
  {
  "source":"凤凰视频",
  "link":"http://v.ifeng.com/video_7480871.shtml",
  "keyword":"视频",
  "title":"创想动画片:花粉过敏症的痛谁懂-凤凰 视频 -最具媒体品质的综合 视频 ...",
  "id":"dc5f19c4-180f-4004-a0db-4499d875a60f",
  "_version_":1584214366819975168},
  {
  "source":"凤凰视频",
  "link":"http://v.ifeng.com/video_7805858.shtml",
  "keyword":"视频",
  "title":"节气说:小暑时节就该这样养生-凤凰 视频 -最具媒体品质的综合 视频 门...",
  "id":"5e9eb7a7-48b8-4e41-9514-7712ae619d9a",
  "_version_":1584214367516229632},
  {
  "source":"凤凰视频",
  "link":"http://v.ifeng.com/video_7483506.shtml",
  "keyword":"视频",
  "title":"听导演讲《神奇女侠》的故事 -凤凰 视频 -最具媒体品质的综合 视频 门户-...",
  "id":"6b1482f1-c0c9-479f-bef7-7de324fb9372",
  "_version_":1584214367647301632},
  {
  "source":"汽车杂志",
  "link":"http://www.jiemian.com/article/1445267.html",
  "keyword":"视频",
  "title":"【视频】欧宝最近找了一堆穿睡衣的辣妈拍了一段超牛的视频",
  "id":"1d327555-a6f3-4513-9a21-43d59418ab82",
  "_version_":1584214368157958144},
  {
  "source":"味觉大师",
  "link":"http://www.jiemian.com/article/1453545.html",
  "keyword":"视频",
  "title":"【视频】大董没有肉的肉味烧茄子",
  "id":"7d777870-93cb-4c18-a32b-734af8f133f1",
  "_version_":1584213891451191296},
  {
  "source":"新浪汽车",
  "link":"http://auto.sina.com.cn/video/zz/2017-07-07/detail-ifyhwehx5311889.shtml",
  "keyword":"视频",
  "title":"视频 :两大神车pk!高尔夫思域怎么选?",
  "id":"3a50b303-6b54-4da3-aee1-a61c678c752d",
  "_version_":1584213892090822656},
  {
  "source":"味觉大师",
  "link":"http://www.jiemian.com/article/1453545.html",
  "keyword":"视频",
  "title":"【视频】大董没有肉的肉味烧茄子",
  "id":"01da8e11-77bc-4c31-ba3a-ba668e846d9d",
  "_version_":1584214366191878144}]
 }}

完整代码:

#-*- coding: UTF-8 -*-
import csv
import os
import codecs


def ReadCSV(filename):
 if os.path.exists(filename):
  with open(filename, 'r') as f:
   reader = csv.reader(f)
   list = []
   for item in reader:
    list.append(item)
   return list

#################################################
#coding=utf-8
import json
import requests

import os
import time
from os import walk
import CSVOP
from datetime import datetime
import pysolr
import math

class SolrClientObj:

 def test(self):
  data = {"add": {"doc": {"id": "100001", "*字段名*": u"我是一个大好人"}}}
  params = {"boost": 1.0, "overwrite": "true", "commitWithin": 1000}
  url = 'http://127.0.0.1:8983/solr/mycore/update?wt=json'
  headers = {"Content-Type": "application/json"}
  r = requests.post(url, json=data, params=params, headers=headers)
  print r.text

 def pysolr_Index_Data_FromCSV(self, csvfile,url='http://127.0.0.1:8983/solr/mycore/'):
  '''
   从CSV文件中读取数据,并索引到solr中
   :param csvfile: csv文件,包括完整路径
   :return:
   '''
  list = CSVOP.ReadCSV(csvfile)
  index = 0
  listdocs = []
  for item in list:
   if index > 0: # 第一行是标题
    doc = {}
    try:
     doc['title'] = item[0].decode('GB2312')
     doc['link'] = item[1]
     # doc['date'] = item[2]
     doc['source'] = item[3].decode('GB2312')
     doc['keyword'] = item[4].decode('GB2312')
     listdocs.append(doc)
    except Exception,e:
     print e.message
   index += 1
  solr = pysolr.Solr(url, timeout=10)
  result = solr.add(listdocs)
  print result

 def Index_Data_FromCSV(self, csvfile):
  '''
   从CSV文件中读取数据,并索引到solr中
   :param csvfile: csv文件,包括完整路径
   :return:
   '''
  list = CSVOP.ReadCSV(csvfile)
  index = 0
  doc = {}
  params = {"boost": 1.0, "overwrite": "true", "commitWithin": 1000}
  url = 'http://127.0.0.1:8983/solr/mycore/update?wt=json'
  headers = {"Content-Type": "application/json"}
  for item in list:
   if index > 0: # 第一行是标题
    try:
     doc['title'] = item[0].decode('GB2312')
     doc['link'] = item[1]
     # doc['date'] = item[2]
     doc['source'] = item[3].decode('GB2312')
     doc['keyword'] = item[4].decode('GB2312')
     data = {"add": {"doc": doc}}
     r = requests.post(url, json=data, params=params, headers=headers)
     print r.text
    except Exception,e:
     print e.message

   print index
   index += 1

 def Index_data(self):
  solr = pysolr.Solr('http://127.0.0.1:8983/solr/mycore/', timeout=10)

  # How you'd index data.
  result = solr.add([
   {
    "id": "doc_1",
    "title": "A test document",
   },
   {
    "id": "doc_2",
    "title": "The Banana: Tasty or Dangerous?",
   },
  ])
  print result

 def search_data(self,where='视频',url='http://127.0.0.1:8983/solr/mycore/'):
  solr = pysolr.Solr(url, timeout=10)
  dict = {'start':10,'rows': 30,'fl':'title,keyword,source,link'}
  result = solr.search('title:视频',**dict)
  # result = solr.search('title:视频')
  # print result.raw_response['response']['numFound']

  for item in result:
   print 'keyword: %s'% item['keyword']
   print 'title: %s'% item['title']
   print 'source: %s'% item['source']
   print 'link: %s'% item['link']
   print '    '

 def delete_index_data(self,where,url='http://127.0.0.1:8983/solr/mycore/'):
  '''
  删除索引
  :param where: 删除的条件
  :param url: url
  :return:
  '''
  solr = pysolr.Solr(url, timeout=10)
  # solr.delete(id=where) #id='id1':删除id为“id1”的索引
  result = solr.delete(q=where) #q='*:*'删除所有索引
  print result


obj = SolrClientObj()
# obj.delete_index_data('*:*') #删除所有索引
# obj.Index_data()
# obj.search_data()
# obj.delete_index_data('doc_1')
obj.search_data('视频')
# csvfile = 'D:/work/Solr/other/exportExcels/2017-07-07_info.csv'
# obj.pysolr_Index_Data_FromCSV(csvfile)

以上这篇对python 操作solr索引数据的实例详解就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持三水点靠木。

Python 相关文章推荐
python使用xmlrpc实例讲解
Dec 17 Python
python2.7安装图文教程
Mar 13 Python
Jupyter安装nbextensions,启动提示没有nbextensions库
Apr 23 Python
利用Pandas 创建空的DataFrame方法
Apr 08 Python
python 实现在txt指定行追加文本的方法
Apr 29 Python
python re模块的高级用法详解
Jun 06 Python
pip install urllib2不能安装的解决方法
Jun 12 Python
python函数声明和调用定义及原理详解
Dec 02 Python
对Tensorflow中tensorboard日志的生成与显示详解
Feb 04 Python
Django中Q查询及Q()对象 F查询及F()对象用法
Jul 09 Python
python实现三次密码验证的示例
Apr 29 Python
Python中的np.argmin()和np.argmax()函数用法
Jun 02 Python
python用post访问restful服务接口的方法
Dec 07 #Python
python3 实现验证码图片切割的方法
Dec 07 #Python
python 用opencv调用训练好的模型进行识别的方法
Dec 07 #Python
Python cv2 图像自适应灰度直方图均衡化处理方法
Dec 07 #Python
浅析python3字符串格式化format()函数的简单用法
Dec 07 #Python
Python实现的批量修改文件后缀名操作示例
Dec 07 #Python
Python实现随机创建电话号码的方法示例
Dec 07 #Python
You might like
Zend Framework动作控制器用法示例
2016/12/09 PHP
php中分页及SqlHelper类用法实例
2017/01/12 PHP
php使用 readfile() 函数设置文件大小大小的方法
2017/08/11 PHP
Laravel创建数据库表结构的例子
2019/10/09 PHP
js下通过prototype扩展实现indexOf的代码
2010/12/08 Javascript
js中top、clientTop、scrollTop、offsetTop的区别 文字详细说明版
2011/01/08 Javascript
jQuery帮助之筛选查找 children([expr])
2011/01/31 Javascript
编写js扩展方法判断一个数组中是否包含某个元素
2013/11/08 Javascript
javascript中动态加载js文件多种解决办法总结
2013/11/15 Javascript
jQuery实现下拉框左右选择的简单实例
2014/02/22 Javascript
使用jQuery仿苹果官网焦点图特效
2014/12/23 Javascript
jQuery插件Skippr实现焦点图幻灯片特效
2015/04/12 Javascript
javaScript中push函数用法实例分析
2015/06/08 Javascript
JavaScript实现为input与textarea自定义hover,focus效果的方法
2015/08/21 Javascript
全面理解闭包机制
2016/07/11 Javascript
什么是JavaScript注入攻击?
2016/09/14 Javascript
NodeJS处理Express中异步错误
2017/03/26 NodeJs
Webpack打包css后z-index被重新计算的解决方法
2017/06/18 Javascript
Angular2 组件间通过@Input @Output通讯示例
2017/08/24 Javascript
webpack将js打包后的map文件详解
2018/02/22 Javascript
Vue.js自定义事件的表单输入组件方法
2018/03/08 Javascript
微信小程序CSS3动画下拉菜单效果
2018/11/04 Javascript
在JavaScript中如何访问暂未存在的嵌套对象
2019/06/18 Javascript
vue 实现LED数字时钟效果(开箱即用)
2019/12/08 Javascript
JQuery复选框全选效果如何实现
2020/05/08 jQuery
Python列表生成器的循环技巧分享
2015/03/06 Python
python生成随机mac地址的方法
2015/03/16 Python
每天迁移MySQL历史数据到历史库Python脚本
2018/04/13 Python
Python贪心算法实例小结
2018/04/22 Python
详解用TensorFlow实现逻辑回归算法
2018/05/02 Python
Python异常的检测和处理方法
2018/10/26 Python
python 求10个数的平均数实例
2019/12/16 Python
英国蛋糕装饰用品一站式商店:Craft Company
2019/03/18 全球购物
J2EE面试题大全
2016/08/06 面试题
信息管理专业学生自荐信格式
2013/09/22 职场文书
开展读书活动总结
2014/06/30 职场文书