# import the python subprocess module import subprocess  def run_cmd(args_list):         """         run linux commands         """         # import subprocess         print('Running system command: {0}'.format(' '.join(args_list)))         proc = subprocess.Popen(args_list, stdout=subprocess.PIPE, stderr=subprocess.PIPE)         s_output, s_err = proc.communicate()         s_return =  proc.returncode         return s_return, s_output, s_err  

ls：返回文件或目录的信息

如果是文件，则按照如下格式返回文件信息：
文件名 <副本数> 文件大小 修改日期 修改时间 权限 用户ID 组ID
如果是目录，则返回它直接子文件的一个列表，就像在Unix中一样。目录返回列表的信息如下：
目录名 \<dir> 修改日期 修改时间 权限 用户ID 组ID
示例：
hadoop fs -ls /user/hadoop/file1 /user/hadoop/file2 hdfs://host:port/user/hadoop/dir1 /nonexistentfile
返回值：
成功返回0，失败返回-1。

# Run Hadoop ls command in Python (ret, out, err)= run_cmd(['hdfs', 'dfs', '-ls', 'hdfs_file_path']) lines = out.split('\n') 

get：下载文件到本地

# Run Hadoop get command in Python (ret, out, err)= run_cmd(['hdfs', 'dfs', '-get', 'hdfs_file_path', 'local_path']) 

put：从本地文件系统中复制单个或多个源路径到目标文件系统。也支持从标准输入中读取输入写入目标文件系统。

# Run Hadoop put command in Python (ret, out, err)= run_cmd(['hdfs', 'dfs', '-put', 'local_file', 'hdfs_file_path']) 

copyFromLocal：限定从hdfs复制到本地

# Run Hadoop copyFromLocal command in Python (ret, out, err)= run_cmd(['hdfs', 'dfs', '-copyFromLocal', 'local_file', 'hdfs_file_path']) 

copyToLocal：限定从本地复制到hdfs

# Run Hadoop copyToLocal command in Python (ret, out, err)= run_cmd(['hdfs', 'dfs', '-copyToLocal', 'hdfs_file_path', 'local_file']) 

rm：删除hdfs上的文件，只删除非空目录和文件

# hdfs的常规命令 # hdfs dfs -rm -skipTrash /path/to/file/you/want/to/remove/permanently  # Run Hadoop remove file command in Python (ret, out, err)= run_cmd(['hdfs', 'dfs', '-rm', 'hdfs_file_path']) (ret, out, err)= run_cmd(['hdfs', 'dfs', '-rm', '-skipTrash', 'hdfs_file_path']) 

rm -r：递归删除hdfs上的文件，会删除目录

# hdfs的常规命令 # rm -r # HDFS Command to remove the entire directory and all of its content from HDFS. # Usage: hdfs dfs -rm -r <path>      (ret, out, err)= run_cmd(['hdfs', 'dfs', '-rm', '-r', 'hdfs_file_path']) (ret, out, err)= run_cmd(['hdfs', 'dfs', '-rm', '-r', '-skipTrash', 'hdfs_file_path']) 

test + 参数：检查文件是否存在

Check if a file exist in HDFS Usage: hadoop fs -test -[defsz] URI   Options:   -d: f the path is a directory, return 0. -e: if the path exists, return 0. -f: if the path is a file, return 0. -s: if the path is not empty, return 0. -z: if the file is zero length, return 0. Example:   hadoop fs -test -e filename   hdfs_file_path = '/tmpo' cmd = ['hdfs', 'dfs', '-test', '-e', hdfs_file_path] ret, out, err = run_cmd(cmd) print(ret, out, err) if ret:     print('file does not exist') 

本文翻译自 Interacting-with-Hadoop-HDFS-using-Python-codes
其他参考文档：
hadoop shell指南
hdfs工具 snakebite