python操作hdfs

 

复制代码
import contextlib

import pyhdfs


class HdfsUtil(object):
    def __init__(self, hosts='namenode1:9870,namenode2:9870', user_name='hdfs'):
        self.hosts = hosts
        self.user_name = user_name
        self.fs = pyhdfs.HdfsClient(hosts=self.hosts, user_name=self.user_name)

    def listdir(self, dir_name):
        return self.fs.listdir(dir_name)

    def copy_from_local(self, local_file, hdfs_file):
        return self.fs.copy_from_local(local_file, hdfs_file)

    def copy_to_local(self, hdfs_file, local_file):
        return self.fs.copy_to_local(hdfs_file, local_file)

    def delete(self, hdfs_file, recursive=True):
        return self.fs.delete(hdfs_file, recursive=recursive)

    def exists(self, hdfs_file):
        return self.fs.exists(hdfs_file)

    def get_fs(self):
        return self.fs

    def create(self, hdfs_file):
        return self.fs.create(hdfs_file, ''.encode('utf8'))

    def read(self, hdfs_file):
        result = []
        with contextlib.closing(self.fs.open(hdfs_file)) as f:
            line = f.readline()
            while line:
                result.append(str(line, encoding='utf8'))
                line = f.readline()
        return ''.join(result)

    def write(self, hdfs_file, data: bytes):
        if not self.exists(hdfs_file):
            self.create(hdfs_file)
        self.fs.append(hdfs_file, data)
复制代码

 

posted @   Mars.wang  阅读(456)  评论(0编辑  收藏  举报
编辑推荐:
· SQL Server 2025 AI相关能力初探
· Linux系列:如何用 C#调用 C方法造成内存泄露
· AI与.NET技术实操系列(二):开始使用ML.NET
· 记一次.NET内存居高不下排查解决与启示
· 探究高空视频全景AR技术的实现原理
阅读排行:
· 阿里最新开源QwQ-32B,效果媲美deepseek-r1满血版,部署成本又又又降低了!
· SQL Server 2025 AI相关能力初探
· AI编程工具终极对决:字节Trae VS Cursor,谁才是开发者新宠?
· 开源Multi-agent AI智能体框架aevatar.ai,欢迎大家贡献代码
· Manus重磅发布:全球首款通用AI代理技术深度解析与实战指南
点击右上角即可分享
微信分享提示