对python 操作solr索引数据的实例详解
作者:shaomine 发布时间:2023-11-02 16:18:19
标签:python,solr
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:
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)
来源:https://www.cnblogs.com/shaosks/p/7845576.html
0
投稿
猜你喜欢
- 各位大哥: 在javascript中如何取整?比如: var
- 一、Excel环境配置 服务器端的环境配置从参考资料上看,微软系列的配置应该都行,即:1.Win9x+PWS+Office2.Wi
- 记得以前的Windows任务定时是可以正常使用的,今天试了下,发现不能正常使用了,任务计划总是挂起。接下来记录下Python爬虫定时任务的几
- 制作自己的训练集下图是我们数据的存放格式,在data目录下有验证集与测试集分别对应iris_test, iris_train 为了向伟大的M
- 如何用ASP建立Index Server查询对象并为其参数赋值?我们有两个方法可以做到这一点。一个方法是利用Index Server que
- 传统行业里,缺做互联网资深的人;互联网行业里,缺玩传统业务资深的人。于是会造成很多问题,比如两边难沟通,在传统行业者心目中,网络营销e-Ma
- 1 、创建一个django项目使用django-admin.py startproject MyDjangoSite 参考这里2、建立视图f
- 在Google Reader上看到网友分享的一个链接,真的发现自己已经out了。上面的这张图,是纯CSS实现的,没有背景图、没有Javasc
- 内连接(inner join)。 外连接: 全连接(full join)、左连接(left join)、右连接(right join)。 交
- 该脚本是为了结合之前的编写的脚本,来实现数据的比对模块,实现数据的自动化!由于数据格式是定死的,该代码只做参考,有什么问题可以私信我!CSV
- Serilog是.net下的新兴的日志框架,本文这里简单的介绍一下它的用法。首先安装Nuget包:Install-Package Seril
- 本文实例讲述了PHP使用自定义key实现对数据加密解密的方法。分享给大家供大家参考,具体如下:客户端和服务端通信时,有个场景很常见,通过一个
- 分页浏览功能是常见的Web应用功能,对于MySQL数据库来说可以很轻松的使用limit语句实现分页,而对于SQL Server数据库来说,常
- 问:怎样才能指定MySQL只监听某个特定地址?答:比较常见的办法是,在my.cnf之mysqld节,添加bind-address=127.0
- 创建多个交易各个客户进行的交易在系统中排队;矿工从这个队列中获取交易并将其添加到块中.然后他们将挖掘区块,获胜的矿工将有权将区块添加到区块链
- 在 MySQL下,在进行中文模糊检索时,经常会返回一些与之不相关的记录,如查找 "%a%" 时,返回的可能有中文字符,却
- 在学习 Python 类的时候,会碰见类中有 __init__() 这样一个函数,其实它就是 Python 的构造方法。构造方法类似于类似
- 使用MySQL的命令终端时,如果输入SQL有误,将有beep声。若要关闭该功能,根据mysql --help,使用mysql --no-be
- 安装模块下面需要用模块,先安装一下:pip install numpy pip install opencv-python==4.5.5.6
- 本人曾经用过的备份方式有:mysqldump、mysqlhotcopy、BACKUP TABLE 、SELECT INTO OUTFILE,