溫馨提示×

溫馨提示×

您好，登錄后才能下訂單哦！

密碼登錄×
登錄注冊×
其他方式登錄
點擊 登錄注冊 即表示同意《億速云用戶服務條款》

對python 操作solr索引數(shù)據(jù)的實例詳解

發(fā)布時間：2020-09-22 21:41:30 來源：腳本之家 閱讀：208 作者：shaomine 欄目：開發(fā)技術

測試代碼1：

def test(self):
  data = {"add": {"doc": {"id": "100001", "*字段名*": u"我是一個大好人"}}}
  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

測試代碼2：

實際數(shù)據(jù)：

對python 操作solr索引數(shù)據(jù)的實例詳解

def Index_Data_FromCSV(self, csvfile):
  '''
   從CSV文件中讀取數(shù)據(jù)，并索引到solr中
   :param csvfile: csv文件，包括完整路徑
   :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: # 第一行是標題
    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客戶端代碼
 def pysolr_Index_Data_FromCSV(self, csvfile,url='http://127.0.0.1:8983/solr/mycore/'):
  '''
   從CSV文件中讀取數(shù)據(jù)，并索引到solr中
   :param csvfile: csv文件，包括完整路徑
   :return:
   '''
  list = CSVOP.ReadCSV(csvfile)
  index = 0
  listdocs = []
  for item in list:
   if index > 0: # 第一行是標題
    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

查詢代碼： 

def search_data(self,message='視頻'):
  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客戶端
  def search_data(self,where='視頻',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:視頻',**dict)
  # result = solr.search('title:視頻')
  # 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 '

'

輸出結(jié)果：

{
 "responseHeader":{
 "status":0,
 "QTime":0,
 "params":{
  "q":"title:\"\\視頻\"",
  "indent":"true",
  "wt":"json"}},
 "response":{"numFound":123,"start":0,"docs":[
  {
  "source":"中彩網(wǎng)",
  "link":"http://www.zhcw.com/video/kaijiangshipin-3D/11981126.shtml",
  "keyword":"視頻",
  "title":"福彩3D開獎 視頻 -中彩 視頻",
  "id":"2f0a9d21-3771-4efa-a0cc-e0484cc97993",
  "_version_":1584214368617234432},
  {
  "source":"新浪視頻",
  "link":"http://video.sina.com.cn/news/spj/topvideoes20170707/?opsubject_id=top1",
  "keyword":"視頻",
  "title":"今日熱門 視頻 匯總20170707",
  "id":"c8aae0af-01e9-491f-b999-24b97004a4ba",
  "_version_":1584214367507841024},
  {
  "source":"網(wǎng)易新聞",
  "link":"http://news.163.com/17/0707/13/COOCNUIE00018AOR.html",
  "keyword":"視頻",
  "title":"網(wǎng)傳＂蘭桂坊附近不雅 視頻 ＂ 警方：傳播 視頻 將追責",
  "id":"353de48d-ede7-481b-89d3-bc20ab4b3884",
  "_version_":1584214367821365248},
  {
  "source":"鳳凰視頻",
  "link":"http://v.ifeng.com/video_7480871.shtml",
  "keyword":"視頻",
  "title":"創(chuàng)想動畫片：花粉過敏癥的痛誰懂-鳳凰 視頻 -最具媒體品質(zhì)的綜合 視頻 ...",
  "id":"dc5f19c4-180f-4004-a0db-4499d875a60f",
  "_version_":1584214366819975168},
  {
  "source":"鳳凰視頻",
  "link":"http://v.ifeng.com/video_7805858.shtml",
  "keyword":"視頻",
  "title":"節(jié)氣說：小暑時節(jié)就該這樣養(yǎng)生-鳳凰 視頻 -最具媒體品質(zhì)的綜合 視頻 門...",
  "id":"5e9eb7a7-48b8-4e41-9514-7712ae619d9a",
  "_version_":1584214367516229632},
  {
  "source":"鳳凰視頻",
  "link":"http://v.ifeng.com/video_7483506.shtml",
  "keyword":"視頻",
  "title":"聽導演講《神奇女俠》的故事 -鳳凰 視頻 -最具媒體品質(zhì)的綜合 視頻 門戶-...",
  "id":"6b1482f1-c0c9-479f-bef7-7de324fb9372",
  "_version_":1584214367647301632},
  {
  "source":"汽車雜志",
  "link":"http://www.jiemian.com/article/1445267.html",
  "keyword":"視頻",
  "title":"【視頻】歐寶最近找了一堆穿睡衣的辣媽拍了一段超牛的視頻",
  "id":"1d327555-a6f3-4513-9a21-43d59418ab82",
  "_version_":1584214368157958144},
  {
  "source":"味覺大師",
  "link":"http://www.jiemian.com/article/1453545.html",
  "keyword":"視頻",
  "title":"【視頻】大董沒有肉的肉味燒茄子",
  "id":"7d777870-93cb-4c18-a32b-734af8f133f1",
  "_version_":1584213891451191296},
  {
  "source":"新浪汽車",
  "link":"http://auto.sina.com.cn/video/zz/2017-07-07/detail-ifyhwehx5311889.shtml",
  "keyword":"視頻",
  "title":"視頻 ：兩大神車pk！高爾夫思域怎么選？",
  "id":"3a50b303-6b54-4da3-aee1-a61c678c752d",
  "_version_":1584213892090822656},
  {
  "source":"味覺大師",
  "link":"http://www.jiemian.com/article/1453545.html",
  "keyword":"視頻",
  "title":"【視頻】大董沒有肉的肉味燒茄子",
  "id":"01da8e11-77bc-4c31-ba3a-ba668e846d9d",
  "_version_":1584214366191878144}]
 }}

完整代碼：

#-*- 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"我是一個大好人"}}}
  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/'):
  '''
   從CSV文件中讀取數(shù)據(jù)，并索引到solr中
   :param csvfile: csv文件，包括完整路徑
   :return:
   '''
  list = CSVOP.ReadCSV(csvfile)
  index = 0
  listdocs = []
  for item in list:
   if index > 0: # 第一行是標題
    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):
  '''
   從CSV文件中讀取數(shù)據(jù)，并索引到solr中
   :param csvfile: csv文件，包括完整路徑
   :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: # 第一行是標題
    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='視頻',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:視頻',**dict)
  # result = solr.search('title:視頻')
  # 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/'):
  '''
  刪除索引
  :param where: 刪除的條件
  :param url: url
  :return:
  '''
  solr = pysolr.Solr(url, timeout=10)
  # solr.delete(id=where) #id='id1':刪除id為“id1”的索引
  result = solr.delete(q=where) #q='*:*'刪除所有索引
  print result


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

以上這篇對python 操作solr索引數(shù)據(jù)的實例詳解就是小編分享給大家的全部內(nèi)容了，希望能給大家一個參考，也希望大家多多支持億速云。

向AI問一下細節(jié)

免責聲明：本站發(fā)布的內(nèi)容（圖片、視頻和文字）以原創(chuàng)、轉(zhuǎn)載和分享為主，文章觀點不代表本網(wǎng)站立場，如果涉及侵權(quán)請聯(lián)系站長郵箱：is@yisu.com進行舉報，并提供相關證據(jù)，一經(jīng)查實，將立刻刪除涉嫌侵權(quán)內(nèi)容。

AI
助
手