Python操作HBase之happybase

pip install thrift

pip install happybase

connection = happybase.Connection(host="192.168.0.156",port=9090,timeout=None,autoconnect=True,table_prefix=None,table_prefix_separator=b‘_‘,compat=‘0.98‘, transport=‘buffered‘,protocol=‘binary‘)

# 创建连接，通过参数size来设置连接池中连接的个数
pool = happybase.ConnectionPool(size=3, host=‘10.1.13.111‘, table_prefix=‘myProject‘)
# 获取连接
with pool.connection() as connection:
    print connection.tables()

connection.open()

connection.close()

connection.compact_table(name,major=False)

families = {
    "cf":dict(),
    "df":dict()
}
connection.create_table(name,families)      # 如果连接时，有传递表前缀参数时，真实表名将会是："{}_{}".format(table_prefix,name)

connection.create_table(
    ‘my_table‘,
    {
        ‘cf1‘: dict(max_versions=10),
        ‘cf2‘: dict(max_versions=1, block_cache_enabled=False),
        ‘cf3‘: dict(),  # use defaults
    }
)

connection = happybase.Connection(‘10.1.13.111‘, table_prefix=‘myproject‘)

 connection.delete_table(name,disable=False)

connection.disable_table(name)

connection.enable_table(name)

connection.is_table_enabled(name)

table = connection.table(name,user_prefix=True)     # table为happybase.table.Table类型

table_name_list = connection.tables()

table = happybase.Table(name,connection)

content = table.cells(‘row1‘,‘cf:1‘,5,timestamp=1514861929124,include_timestamp=True)
print content   # [(‘1‘, 1514861925674L)]

table.counter_set(row,column,value=0)

content = table.counter_get(row,column)

content = table.counter_dec(row,column,value=1)

content = table.counter_inc(row,column,value=1)

table.delete(row, columns=None, timestamp=None, wal=True)

info = table.families()
print info

{
    ‘cf‘: {
        ‘max_versions‘: 3,
        ‘bloom_filter_vector_size‘: 0,
        ‘name‘: ‘cf: ‘,
        ‘bloom_filter_type‘: ‘NONE‘,
        ‘bloom_filter_nb_hashes‘: 0,
        ‘time_to_live‘: 2147483647,
        ‘in_memory‘: False,
        ‘block_cache_enabled‘: False,
        ‘compression‘: ‘NONE‘
    },
    ‘cd‘: {
        ‘max_versions‘: 3,
        ‘bloom_filter_vector_size‘: 0,
        ‘name‘: ‘cd: ‘,
        ‘bloom_filter_type‘: ‘NONE‘,
        ‘bloom_filter_nb_hashes‘: 0,
        ‘time_to_live‘: 2147483647,
        ‘in_memory‘: False,
        ‘block_cache_enabled‘: False,
        ‘compression‘: ‘NONE‘
    }
}

# 在row1行,cf:1列插入值1
table.put("row1",{"cf:1":"1"})

# 使用batch一次插入多行数据
bat = table.batch()
bat.put(‘www.test5.com‘, {‘cf1:price‘: 999, ‘cf2:title‘: ‘Hello Python‘, ‘cf2:length‘: 34, ‘cf3:code‘: ‘A43‘})
bat.put(‘www.test6.com‘, {‘cf1:content‘: u‘剃须刀‘, ‘cf1:price‘: 168, ‘cf1:rating‘: ‘97%‘})
bat.put(‘www.test7.com‘, {‘cf3:function‘: ‘print‘})
bat.send()

# 使用with来管理batch
with table.batch() as bat:
    bat.put(‘www.test5.com‘, {‘cf1:price‘: ‘999‘, ‘cf2:title‘: ‘Hello Python‘, ‘cf2:length‘: ‘34‘, ‘cf3:code‘: ‘A43‘})
    bat.put(‘www.test6.com‘, {‘cf1:content‘: u‘剃须刀‘, ‘cf1:price‘: ‘168‘, ‘cf1:rating‘: ‘97%‘})
    bat.put(‘www.test7.com‘, {‘cf3:function‘: ‘print‘})

# 在batch中删除数据
with table.batch() as bat:
    bat.put(‘www.test5.com‘, {‘cf1:price‘: ‘999‘, ‘cf2:title‘: ‘Hello Python‘, ‘cf2:length‘: ‘34‘, ‘cf3:code‘: ‘A43‘})
    bat.put(‘www.test6.com‘, {‘cf1:content‘: u‘剃须刀‘, ‘cf1:price‘: ‘168‘, ‘cf1:rating‘: ‘97%‘})
    bat.put(‘www.test7.com‘, {‘cf3:function‘: ‘print‘})
    bat.delete(‘www.test1.com‘)

# 通过batch_size参数来设置batch的大小
with table.batch(batch_size=10) as bat:
    for i in range(16):
        bat.put(‘www.test{}.com‘.format(i), {‘cf1:price‘: ‘{}‘.format(i)})

info = table.regions()
print info

# [{‘name‘: ‘ddd_ch,,1514948783663.caccaafa3df04cd75737a9effb5615d4.‘, ‘server_name‘: ‘slave3‘, ‘port‘: 16020, ‘end_key‘: ‘‘, ‘version‘: 1, ‘start_key‘: ‘‘, ‘id‘: 1514948783663L}]

info = table.row(row, columns=None, timestamp=None, include_timestamp=False)

# 检索多行数据
rows = table.rows([‘www.test1.com‘, ‘www.test4.com‘])
print rows

# 检索多行数据，返回字典
rows_dict = dict(table.rows([‘www.test1.com‘, ‘www.test4.com‘]))
print rows_dict

# 检索多行数据，返回有序字典
from collection import OrderedDict
rows_ordered_dict = OrderedDict(table.rows([‘www.test1.com‘, ‘www.test4.com‘]))
print rows_ordered_dict

# 通过指定列族来检索数据
row = table.row(‘www.test1.com‘, columns=[‘cf1‘])
print row
# 通过指定列族中的列来检索数据
row = table.row(‘www.test1.com‘, columns=[‘cf1:price‘, ‘cf1:rating‘])
print row
print row[‘cf1:price‘]

# 通过指定时间戳来检索数据，时间戳必须是整数
row = table.row(‘www.test1.com‘, timestamp=1489070666)
print row

# 在返回的数据里面包含时间戳
row = table.row(row=‘www.test1.com‘, columns=[‘cf1:rating‘, ‘cf1:price‘], include_timestamp=True)
print row

# 检索某一个cell所有的版本
cells = table.cells(b‘www.test1.com‘, column=‘cf1:price‘)
print cells

# 通过设置version参数来检索前n个版本
cells = table.cells(b‘www.test1.com‘, column=‘cf1:price‘, versions=3)
print cells

# 删除一整行数据
table.delete(‘www.test4.com‘)
# 删除一个列族的数据
table.delete(‘www.test2.com‘, columns=[‘cf1‘])
# 删除一个列族中几个列的数据
table.delete(‘www.test2.com‘, columns=[‘cf1：name‘, ‘cf1:price‘])

scanner = table.scan(row_start=None, row_stop=None, row_prefix=None, columns=None, filter=None, timestamp=None, include_timestamp=False, batch_size=1000, scan_batching=None, limit=None, sorted_columns=False, reverse=False)

# 全局扫描一个table
for key, value in table.scan():
    print key, value

# 通过row_start参数来设置开始扫描的row key
for key, value in table.scan(row_start=‘www.test2.com‘):
    print key, value

# 通过row_stop参数来设置结束扫描的row key
for key, value in table.scan(row_stop=‘www.test3.com‘):
    print key, value

# 通过row_start和row_stop参数来设置开始和结束扫描的row key
for key, value in table.scan(row_start=‘www.test2.com‘, row_stop=‘www.test3.com‘):
    print key, value

# 通过row_prefix参数来设置需要扫描的row key
for key, value in table.scan(row_prefix=‘www.test‘):
    print key, value

if url_scheme == ‘‘:

if len(url_scheme) <= 1:

url_scheme = urlparse(path).scheme
if url_scheme == ‘‘:

    with open(path) as fh:
        data = fh.read()
elif url_scheme in (‘http‘, ‘https‘):(‘http‘, ‘https‘):
    data = urlopen(path).read()
else:
    raise ThriftParserError(‘ThriftPy does not support generating module ‘
                            ‘with path in protocol \‘{}\‘‘.format(
                                url_scheme))

url_scheme = urlparse(path).scheme
#if url_scheme == ‘‘:
if url_scheme in (‘f‘, ‘‘):
    with open(path) as fh:
        data = fh.read()
elif url_scheme in (‘http‘, ‘https‘):
    data = urlopen(path).read()
else:
    raise ThriftParserError(‘ThriftPy does not support generating module ‘
                            ‘with path in protocol \‘{}\‘‘.format(
                                url_scheme))