from hdfs.client import Client
class Process_Data_Hdfs():
def __init__(self):
self.client = Client("http://hadoop1:50070")
self.filename = "/user/hdfs/read.txt"
读取hdfs文件内容,将每行存入数组返回
def read_hdfs_file(self):
# with client.read('samples.csv', encoding='utf-8', delimiter='\n') as reader:
# for line in reader:
# pass
lines = []
with self.client.read(self.filename, encoding='utf-8', delimiter='\n') as reader:
for line in reader:
# pass
# print line.strip()
lines.append(line.strip())
return lines