本文整理汇总了Python中pyes.ES.get_alias方法的典型用法代码示例。如果您正苦于以下问题：Python ES.get_alias方法的具体用法？Python ES.get_alias怎么用？Python ES.get_alias使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类pyes.ES的用法示例。
在下文中一共展示了ES.get_alias方法的2个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: handle
# 需要导入模块: from pyes import ES [as 别名]
# 或者: from pyes.ES import get_alias [as 别名]
def handle(self, *args, **kwargs):
delete_all = kwargs.get('all')
elastic = ES(settings.SEARCH_HOSTS)
indices = []
if delete_all:
indices.extend(elastic.get_indices(True))
indices.extend(elastic.get_closed_indices())
for index in indices:
elastic.delete_index_if_exists(index)
else:
for source_name in args:
indices_aliased = [index for index in elastic.get_alias(source_name) if index == source_name]
elastic.delete_index_if_exists(source_name)
if indices_aliased:
elastic.delete_alias(source_name, indices_aliased)
for index in indices_aliased:
elastic.delete_index_if_exists(index)
if len(indices) and len(args):
elastic.connection.close()
self.stdout.write("Successfully deleted indicies & aliases.\n")
elastic.connection.close()示例2: ProcessSpiderData
# 需要导入模块: from pyes import ES [as 别名]
# 或者: from pyes.ES import get_alias [as 别名]
class ProcessSpiderData(Task):
def run(self, spider_name):
cities = []
backup_source = []
backup_created_date = None
self.elastic = ES(settings.SEARCH_HOSTS, timeout=22.0, bulk_size=1500)
java = JavaInterface()
self.extractor = java.ArticleSentencesExtractor.INSTANCE
self.logger = ProcessSpiderData.get_logger()
spider = Data.objects.get(name=spider_name)
source = spider.source
if spider and len(source):
backup_created_date = spider.created_date
index_new = '%s_%d' % (spider.name, int(time.time()))
# create new index (not connected to alias)
self.elastic.create_index(index_new)
self.elastic.put_mapping('job', {'job':{'properties':mapping}}, index_new)
for item in source:
item = self._process_content(item)
item = self._get_location(item)
if item.has_key('city'):
cities.append(item['city'])
self._create_index(index_new, item)
backup_source.append(item)
# save new index (in bulk)
self.elastic.force_bulk()
# create alias
indices_old = self.elastic.get_alias(spider.name)
self.elastic.set_alias(spider.name, [index_new])
# delete all indices
for index in indices_old:
self.elastic.delete_index_if_exists(index)
# optimize
self.elastic.optimize(index_new, refresh=True)
# save backup (currently processed data)
if len(backup_source) and backup_created_date:
self._process_cities(set(cities), spider_name)
cache.clear()
obj = DataBackup.objects.get_or_create(
name=spider_name,
created_date=backup_created_date
)
obj[0].source = binascii.hexlify(bz2.compress(
JSONEncoder().encode(backup_source)
))
obj[0].save()
# force java & ES garbage collection
self.elastic.connection.close()
del self.extractor
del java
return True
def _process_content(self, item):
if len(item['content']):
item['content'] = self.extractor.getText(jpype.JString(item['content']))
return item
def _get_location(self, item):
if not item.has_key('city'):
return item
try:
geo = geocoders.GeoNames()
places = geo.geocode(item['city'].encode('utf-8'), exactly_one=False)
if places:
place, (lat, lon) = places[0] if isinstance(places, list) else places
if place: item['pin'] = {
'location': { 'lat': lat, 'lon': lon }
}
except: pass
return item
def _create_index(self, index, item):
id = item['id']
del item['id']
try:
self.elastic.get(index, 'job', id)
except ElasticSearchException:
self.elastic.index(
dumps(item, cls=DjangoJSONEncoder),
#.........这里部分代码省略.........