对python 操作solr索引数据的实例详解

程序员文章站 2022-07-11 13:46:22

测试代码1： def test(self): data = {"add": {"doc": {"id": "100001", "*字段名*": u"我是一个...

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":"*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。

上一篇： JS访问对象两种方式区别解析

下一篇：一个网站定位多少个关键词最合适

对python 操作solr索引数据的实例详解

对Python+opencv将图片生成视频的实例详解

对python3 Serial 串口助手的接收读取数据方法详解

对Python 检查文件名是否规范的实例详解

对Python生成汉字字库文字,以及转换为文字图片的实例详解

对python3.4 字符串转16进制的实例详解

对python读取CT医学图像的实例详解

对Python中TKinter模块中的Label组件实例详解

对Python多线程读写文件加锁的实例详解

对python:循环定义多个变量的实例详解

对python中if语句的真假判断实例详解