对python 操作solr索引数据的实例详解

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 '