|
@@ -7,17 +7,16 @@ from hdfs import InsecureClient
|
|
|
client = InsecureClient("http://master-1-1.c-7f31a3eea195cb73.cn-hangzhou.emr.aliyuncs.com:9870", user="spark")
|
|
|
|
|
|
|
|
|
-def read_predict(hdfs_path):
|
|
|
- dir = "/dw/recommend/model/34_ad_predict_data/20241004_351_0927_1003_1000/"
|
|
|
- for file in client.list(dir):
|
|
|
- with client.read(dir + file, encoding="utf-8") as reador:
|
|
|
+def read_predict(hdfs_path: str):
|
|
|
+ for file in client.list(hdfs_path):
|
|
|
+ with client.read(hdfs_path + file, encoding="utf-8") as reador:
|
|
|
with gzip.GzipFile(fileobj=reador, mode="rb") as gz_file:
|
|
|
- content = gz_file.read().decode("utf-8")
|
|
|
- print(f"Content of {file}:\n {content}")
|
|
|
+ content = gz_file.read()
|
|
|
+ print(f"Content of {hdfs_path + file}:\n {content}")
|
|
|
|
|
|
|
|
|
def _main():
|
|
|
- read_predict("")
|
|
|
+ read_predict("/dw/recommend/model/34_ad_predict_data/20241004_351_0927_1003_1000/")
|
|
|
|
|
|
|
|
|
if __name__ == '__main__':
|