update

spark/sources/Sources.py

 import pymysql
 import exception.MyErrorException as ex
+from pyspark import SparkContext
 
 def getMySqlConnect():
     try:
@@ -28,11 +29,21 @@ def getRecordByIdResultT1(id):
         record = cur.fetchone()
     except ex.MyError as e:
         print("executor failed", e.errorinfo)
+        conn.rollback()
     finally:
         cur.close()  # 关闭数据库连接
         conn.close()
     return record
 
+
 def readCsv(spark, path, col):
     df = spark.read.format('csv').option('inferSchema', 'true').load(path).toDF(*col)
     return df
+
+
+def readTxt(spark, path, col, delimiter):
+    rddFile = SparkContext.textFile("1.txt")
+    rddMap = rddFile.map(lambda x: x.split(delimiter))
+    df = spark.createDataFrame(rddMap, col)
+    return df
+

spark/unzip.py

@@ -3,38 +3,69 @@ import sys
 import os
 import shutil
 import zipfile
-import exception.MyErrorException as ex
-pyName = sys.argv[0]   #sys.argv[0] 类似于shell中的$0, 但不是脚本名称，而是脚本的路径
-zipPath = sys.argv[1]    #sys.argv[1] 表示传入的第一个参数
-inputPath = sys.argv[2]    #sys.argv[2] 表示传入的第二个参数
-outputPath = sys.argv[3]
+
+
+# pyName = sys.argv[0]  # sys.argv[0] 类似于shell中的$0, 但不是脚本名称，而是脚本的路径
+# zipPath = sys.argv[1]  # sys.argv[1] 表示传入的第一个参数
+# inputPath = sys.argv[2]  # sys.argv[2] 表示传入的第二个参数
+# outputPath = sys.argv[3]
+#问题:解压的时候要考虑密码吗???
+
 # os.system("hdfs dfs -put /srcPath /dstPath")
 def get_file(srcPath, dstPath):
+
+    if not os.path.exists(srcPath):
+        os.mkdir(srcPath)
+        print("srcPath mkdir success")
+        if not os.path.exists(dstPath):
+            os.mkdir(srcPath)
+            print("dstPath mkdir success")
+    else:
+        res = []
+        for root, dirs, files in os.walk(srcPath, True):
+            for fileName in files:
+                name, suf = os.path.splitext(fileName)
+                if fileName.endswith('.csv'):
+                    shutil.copy(os.path.join(root, fileName), dstPath)
+
+
+
+def unzip_single(srcPath, dstPath):
+    ''' 解压单个文件到目标文件夹。
+    '''
+    zf = zipfile.ZipFile(srcPath)
     try:
-        if not os.path.exists(srcPath):
-            print("srcPath not exist")
-        else:
-            res = []
-            for root, dirs, files in os.walk(srcPath, True):
-                for fileName in files:
-                    name, suf = os.path.splitext(fileName)
-                    if fileName.endswith('.csv'):
-                        shutil.copy(os.path.join(root, fileName), dstPath)
-    except ex.MyError as e:
-        print("失败", e.errorinfo)
-
-def unzip_file(zip_file_name, destination_path):
-    try:
-        archive = zipfile.ZipFile(zip_file_name, mode='r')
-        for file in archive.namelist():
-            archive.extract(file, destination_path)
-    except ex.MyError as e:
-        print("解压失败", e.errorinfo)
-        sys.exit()
+        zf.extractall(path=dstPath)
+    except RuntimeError as e:
+        print(e)
+    zf.close()
+
+
+def unzip_all(source_dir, dest_dir):
+    if not os.path.isdir(source_dir):  # 如果是单一文件
+        unzip_single(source_dir, dest_dir)
+    else:
+        it = os.scandir(source_dir)
+        for entry in it:
+            if entry.is_file() and os.path.splitext(entry.name)[1] == '.zip':
+                unzip_single(entry.path, dest_dir)
+
+# def unzip_file(zip_file_name, destination_path):
+#     archive = zipfile.ZipFile(zip_file_name, mode='r')
+#     for file in archive.namelist():
+#         print(file)
+#         name, suf = os.path.splitext(file)
+#         if file.endswith('.zip'):
+#                 archive.extract(file, destination_path)
+#     print("解压失败")
 
 
 
 if __name__ == '__main__':
+    # if len(sys.argv) == 3:
+    #     source_dir, dest_dir = os.path.abspath(sys.argv[0].strip('"')), sys.argv[1]
     print('解压、复制中...')
-    unzip_file(zipPath, inputPath)
-    get_file(inputPath, outputPath)
+    # unzip_file(zipPath, inputPath)
+    # get_file(inputPath, outputPath)
+    unzip_all("D:\\src", "D:\\dst")
+    get_file("D:\\src", "D:\\dst")