hdfs基本操作-python接口

安装hdfs包

　　pip install hdfs

查看hdfs目录

[root@hadoop hadoop]# hdfs dfs -ls -R /
drwxr-xr-x - root supergroup 0 2017-05-18 23:57 /Demo
-rw-r--r-- 1 root supergroup 3494 2017-05-18 23:57 /Demo/hadoop-env.sh
drwxr-xr-x - root supergroup 0 2017-05-18 19:01 /logs
-rw-r--r-- 1 root supergroup 2223 2017-05-18 19:01 /logs/anaconda-ks.cfg
-rw-r--r-- 1 root supergroup 57162 2017-05-18 18:32 /logs/install.log

　　

创建hdfs连接实例

#!/usr/bin/env python
# -*- coding:utf-8 -*-
__Author__ = 'kongZhaGen'

import hdfs
client = hdfs.Client("http://172.10.236.21:50070")

　　

list:返回远程文件夹包含的文件或目录名称，如果路径不存在则抛出错误。

　　hdfs_path:远程文件夹的路径

　　status:同时返回每个文件的状态信息

def list(self, hdfs_path, status=False):
"""Return names of files contained in a remote folder.

:param hdfs_path: Remote path to a directory. If `hdfs_path` doesn't exist
or points to a normal file, an :class:`HdfsError` will be raised.
:param status: Also return each file's corresponding FileStatus_.

"""

　　示例：

print client.list("/",status=False)
结果：
[u'Demo', u'logs']

　　

status:获取hdfs系统上文件或文件夹的状态信息

　　hdfs_path:路径名称

　　strict:

　　　　False:如果远程路径不存在返回None

　　　　True:如果远程路径不存在抛出异常

def status(self, hdfs_path, strict=True):
"""Get FileStatus_ for a file or folder on HDFS.

:param hdfs_path: Remote path.
:param strict: If `False`, return `None` rather than raise an exception if
the path doesn't exist.

.. _FileStatus: FS_
.. _FS: http://hadoop.apache.org/docs/r1.0.4/webhdfs.html#FileStatus 
"""

　　示例：

print client.status(hdfs_path="/Demoo",strict=False)
结果：
None

　　

makedirs:在hdfs上创建目录，可实现递归创建目录

　　hdfs_path:远程目录名称

　　permission:为新创建的目录设置权限

def makedirs(self, hdfs_path, permission=None):
"""Create a remote directory, recursively if necessary.

:param hdfs_path: Remote path. Intermediate directories will be created
appropriately.
:param permission: Octal permission to set on the newly created directory.
These permissions will only be set on directories that do not already
exist.

This function currently has no return value as WebHDFS doesn't return a
meaningful flag.

"""

　　示例：

　　如果想在远程客户端通过脚本给hdfs创建目录，需要修改hdfs-site.xml

　　<property>
　　<name>dfs.permissions</name>
　　<value>false</value>
　　</property>

　　重启hdfs

stop-dfs.sh
start-dfs.sh

　　递归创建目录

client.makedirs("/data/rar/tmp",permission=755)

　　

rename:移动一个文件或文件夹

　　hdfs_src_path:源路径

　　hdfs_dst_path:目标路径，如果路径存在且是个目录，则源目录移动到此目录中。如果路径存在且是个文件，则会抛出异常

def rename(self, hdfs_src_path, hdfs_dst_path):
"""Move a file or folder.

:param hdfs_src_path: Source path.
:param hdfs_dst_path: Destination path. If the path already exists and is
a directory, the source will be moved into it. If the path exists and is
a file, or if a parent destination directory is missing, this method will
raise an :class:`HdfsError`.

"""

　　示例：

client.rename("/SRC_DATA","/dest_data")

　　

delete:从hdfs删除一个文件或目录

　　hdfs_path:hdfs系统上的路径

　　recursive:如果目录非空，True:可递归删除.False:抛出异常。

def delete(self, hdfs_path, recursive=False):
"""Remove a file or directory from HDFS.

:param hdfs_path: HDFS path.
:param recursive: Recursively delete files and directories. By default,
this method will raise an :class:`HdfsError` if trying to delete a
non-empty directory.

This function returns `True` if the deletion was successful and `False` if
no file or directory previously existed at `hdfs_path`.

"""

　　示例：

client.delete("/dest_data",recursive=True)

　　

upload:上传文件或目录到hdfs文件系统，如果目标目录已经存在，则将文件或目录上传到此目录中,否则新建目录。

def upload(self, hdfs_path, local_path, overwrite=False, n_threads=1,
temp_dir=None, chunk_size=2 ** 16, progress=None, cleanup=True, **kwargs):
"""Upload a file or directory to HDFS.

:param hdfs_path: Target HDFS path. If it already exists and is a
directory, files will be uploaded inside.
:param local_path: Local path to file or folder. If a folder, all the files
inside of it will be uploaded (note that this implies that folders empty
of files will not be created remotely).
:param overwrite: Overwrite any existing file or directory.
:param n_threads: Number of threads to use for parallelization. A value of
`0` (or negative) uses as many threads as there are files.
:param temp_dir: Directory under which the files will first be uploaded
when `overwrite=True` and the final remote path already exists. Once the
upload successfully completes, it will be swapped in.
:param chunk_size: Interval in bytes by which the files will be uploaded.
:param progress: Callback function to track progress, called every
`chunk_size` bytes. It will be passed two arguments, the path to the
file being uploaded and the number of bytes transferred so far. On
completion, it will be called once with `-1` as second argument.
:param cleanup: Delete any uploaded files if an error occurs during the
upload.
:param \*\*kwargs: Keyword arguments forwarded to :meth:`write`.

On success, this method returns the remote upload path.

"""

　　示例：

>>> import hdfs
>>> client=hdfs.Client("http://172.10.236.21:50070")
>>> client.upload("/logs","/root/training/jdk-7u75-linux-i586.tar.gz")
'/logs/jdk-7u75-linux-i586.tar.gz'
>>> client.list("/logs")
[u'anaconda-ks.cfg', u'install.log', u'jdk-7u75-linux-i586.tar.gz']

　　

content:获取hdfs系统上文件或目录的概要信息

print client.content("/logs/install.log")
结果：
{u'spaceConsumed': 57162, u'quota': -1, u'spaceQuota': -1, u'length': 57162, u'directoryCount': 0, u'fileCount': 1}

　　

write:在hdfs文件系统上创建文件，可以是字符串，生成器或文件对象

def write(self, hdfs_path, data=None, overwrite=False, permission=None,
blocksize=None, replication=None, buffersize=None, append=False,
encoding=None):
"""Create a file on HDFS.

:param hdfs_path: Path where to create file. The necessary directories will
be created appropriately.
:param data: Contents of file to write. Can be a string, a generator or a
file object. The last two options will allow streaming upload (i.e.
without having to load the entire contents into memory). If `None`, this
method will return a file-like object and should be called using a `with`
block (see below for examples).
:param overwrite: Overwrite any existing file or directory.
:param permission: Octal permission to set on the newly created file.
Leading zeros may be omitted.
:param blocksize: Block size of the file.
:param replication: Number of replications of the file.
:param buffersize: Size of upload buffer.
:param append: Append to a file rather than create a new one.
:param encoding: Encoding used to serialize data written.
"""