按照渠道跑数据

local/meigou.py

@@ -280,36 +280,36 @@ if __name__ == '__main__':
         .set("spark.driver.maxResultSize", "8g").set("spark.sql.avro.compression.codec", "snappy")
 
     spark = SparkSession.builder.config(conf=sparkConf).enableHiveSupport().getOrCreate()
-    # for os in ["ios","android"]:
-    #     all_list = []
-    #     for i in range(1,3):
-    #         date_str = (datetime.date.today() - datetime.timedelta(days=i)).strftime("%Y%m%d")
-    #         tmp_list = [date_str]
-    #         tmp_list.extend(os_all_click(i,os))
-    #         tmp_list.extend(os_cpc_click(i,os))
-    #         all_list.append(tmp_list)
-    #     df = pd.DataFrame(all_list)
-    #     df = df.rename(columns={0: "date",1: "search", 2: "xiangguan",3:"home",4:"service_home",
-    #                             5: "all_clcik",
-    #                             6: "cpc_search", 7: "cpc_xiangguan",8:"cpc_home",9:"cpc_service_home",
-    #                             10:"cpc_all"})
-    #     df.to_csv('/home/gmuser/cpc_{}.csv'.format(os), index=False)
-
-    all_list = []
-    for i in range(1, 4):
-        date_str = (datetime.date.today() - datetime.timedelta(days=i)).strftime("%Y%m%d")
-        tmp_list = [date_str]
-        tmp_list.extend(all_click(i))
-        tmp_list.extend(cpc_click(i))
-        all_list.append(tmp_list)
-
-    df = pd.DataFrame(all_list)
-
-    df = df.rename(columns={0: "date",1: "search", 2: "xiangguan",3:"home",4:"service_home",
-                            5: "all_clcik",
-                            6: "cpc_search", 7: "cpc_xiangguan",8:"cpc_home",9:"cpc_service_home",
-                            10:"cpc_all"})
-    df.to_csv('/home/gmuser/cpc_1011.csv', index=False)
+    for os in ["ios","android"]:
+        all_list = []
+        for i in range(1,21):
+            date_str = (datetime.date.today() - datetime.timedelta(days=i)).strftime("%Y%m%d")
+            tmp_list = [date_str]
+            tmp_list.extend(os_all_click(i,os))
+            tmp_list.extend(os_cpc_click(i,os))
+            all_list.append(tmp_list)
+        df = pd.DataFrame(all_list)
+        df = df.rename(columns={0: "date",1: "search", 2: "xiangguan",3:"home",4:"service_home",
+                                5: "all_clcik",
+                                6: "cpc_search", 7: "cpc_xiangguan",8:"cpc_home",9:"cpc_service_home",
+                                10:"cpc_all"})
+        df.to_csv('/home/gmuser/cpc_{}.csv'.format(os), index=False)
+
+    # all_list = []
+    # for i in range(1, 4):
+    #     date_str = (datetime.date.today() - datetime.timedelta(days=i)).strftime("%Y%m%d")
+    #     tmp_list = [date_str]
+    #     tmp_list.extend(all_click(i))
+    #     tmp_list.extend(cpc_click(i))
+    #     all_list.append(tmp_list)
+    #
+    # df = pd.DataFrame(all_list)
+    #
+    # df = df.rename(columns={0: "date",1: "search", 2: "xiangguan",3:"home",4:"service_home",
+    #                         5: "all_clcik",
+    #                         6: "cpc_search", 7: "cpc_xiangguan",8:"cpc_home",9:"cpc_service_home",
+    #                         10:"cpc_all"})
+    # df.to_csv('/home/gmuser/cpc_1011.csv', index=False)
 
     spark.stop()