airbyte-source-google-search-console 1.5.16.dev202503252224__py3-none-any.whl → 1.5.16.dev202505021903__py3-none-any.whl

{airbyte_source_google_search_console-1.5.16.dev202503252224.dist-info → airbyte_source_google_search_console-1.5.16.dev202505021903.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: airbyte-source-google-search-console
-Version: 1.5.16.dev202503252224
+Version: 1.5.16.dev202505021903
 Summary: Source implementation for Google Search Console.
 License: Elv2
 Author: Airbyte

{airbyte_source_google_search_console-1.5.16.dev202503252224.dist-info → airbyte_source_google_search_console-1.5.16.dev202505021903.dist-info}/RECORD

@@ -17,10 +17,10 @@ source_google_search_console/schemas/search_analytics_site_report_by_site.json,s
 source_google_search_console/schemas/sitemaps.json,sha256=coyPSZCAfzMheybfRp4WPAZCp5JF2KGRF2rWK8oC080,1775
 source_google_search_console/schemas/sites.json,sha256=WNiCRuStPL1YkJiFa8FEbNJmqaERAOf9Yow6ygIumvo,383
 source_google_search_console/service_account_authenticator.py,sha256=gjUxt0xFxj82uviCQNTsA1Jlee__UDhYNjE7bRO1G0U,1227
-source_google_search_console/source.py,sha256=8n10_agSa2rvPvEyBvOfOpmpEardbEhi3H0vlK2A4_g,10002
-source_google_search_console/spec.json,sha256=WYtFvaSqWYGm1Dt2yV9G92U78Q94rh9oarbxJe3H7xo,8470
-source_google_search_console/streams.py,sha256=7C9E8gYpzU4VdQGsrS2AqjQTdMjeQ3mS3iAfvywADek,20436
-airbyte_source_google_search_console-1.5.16.dev202503252224.dist-info/METADATA,sha256=llHA_zmljhs2_GK5_vKBp_TJj7mgizzaB_kFodADb_A,5646
-airbyte_source_google_search_console-1.5.16.dev202503252224.dist-info/WHEEL,sha256=XbeZDeTWKc1w7CSIyre5aMDU_-PohRwTQceYnisIYYY,88
-airbyte_source_google_search_console-1.5.16.dev202503252224.dist-info/entry_points.txt,sha256=DMcgc9bCX-Vt6hm_68pa77qS3eGdeMhg-UdlFc-XKUM,85
-airbyte_source_google_search_console-1.5.16.dev202503252224.dist-info/RECORD,,
+source_google_search_console/source.py,sha256=Dv6es7XWq-eTinrjUI7wAsUU49mOlYsRiXh_OzqNkW4,10204
+source_google_search_console/spec.json,sha256=2fFxbgga6veaSiQyfkoyAtVraSk8FgSGjDyT7T5ctBQ,8764
+source_google_search_console/streams.py,sha256=E2Ib6AU0V5LCmA846_7ekIOmsrV2KX8VONWXMdhB3pc,19917
+airbyte_source_google_search_console-1.5.16.dev202505021903.dist-info/METADATA,sha256=13H2rlconrDe1NF9D_0a8lOgT4N09qaNlLQesbFRMMU,5646
+airbyte_source_google_search_console-1.5.16.dev202505021903.dist-info/WHEEL,sha256=fGIA9gx4Qxk2KDKeNJCbOEwSrmLtjWCwzBz351GyrPQ,88
+airbyte_source_google_search_console-1.5.16.dev202505021903.dist-info/entry_points.txt,sha256=DMcgc9bCX-Vt6hm_68pa77qS3eGdeMhg-UdlFc-XKUM,85
+airbyte_source_google_search_console-1.5.16.dev202505021903.dist-info/RECORD,,

{airbyte_source_google_search_console-1.5.16.dev202503252224.dist-info → airbyte_source_google_search_console-1.5.16.dev202505021903.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 2.1.1
+Generator: poetry-core 2.1.2
 Root-Is-Purelib: true
 Tag: py3-none-any

source_google_search_console/source.py

@@ -49,6 +49,7 @@ custom_reports_schema = {
         "properties": {
             "name": {"type": "string", "minLength": 1},
             "dimensions": {"type": "array", "items": {"type": "string", "minLength": 1}},
+            "aggregation_type": {"type": "string", "enum": ["auto", "by_page", "by_property"], "default": "auto"},
         },
         "required": ["name", "dimensions"],
     },
@@ -195,7 +196,9 @@ class SourceGoogleSearchConsole(AbstractSource):
 
     def get_custom_reports(self, config: Mapping[str, Any], stream_config: Mapping[str, Any]) -> List[Optional[Stream]]:
         return [
-            type(report["name"], (SearchAnalyticsByCustomDimensions,), {})(dimensions=report["dimensions"], **stream_config)
+            type(report["name"], (SearchAnalyticsByCustomDimensions,), {})(
+                dimensions=report["dimensions"], aggregation_type=report.get("aggregation_type", "auto"), **stream_config
+            )
             for report in config.get("custom_reports_array", [])
         ]
 

source_google_search_console/spec.json

@@ -144,6 +144,13 @@
               },
               "default": ["date"],
               "minItems": 0
+            },
+            "aggregation_type": {
+              "title": "Aggregation Type",
+              "description": "The type of aggregation to apply to the report.",
+              "type": "string",
+              "enum": ["auto", "by_page", "by_property"],
+              "default": "auto"
             }
           },
           "required": ["name", "dimensions"]

source_google_search_console/streams.py

@@ -390,19 +390,12 @@ class SearchByKeyword(SearchAnalytics):
             keywords_records = search_appearance_stream.read_records(
                 sync_mode=SyncMode.full_refresh, stream_state=stream_state, stream_slice=stream_slice
             )
-            # Safely extract keywords, handling cases where "searchAppearance" might be missing
-            keywords = {record["searchAppearance"] for record in keywords_records if "searchAppearance" in record}
-
-            if keywords:
-                # If keywords exist, yield a slice for each keyword with filters
-                for keyword in keywords:
-                    filters = {"dimension": "searchAppearance", "operator": "equals", "expression": keyword}
-                    # Create a copy to avoid modifying the original stream_slice
-                    stream_slice_with_filter = stream_slice.copy()
-                    stream_slice_with_filter["dimensionFilterGroups"] = [{"groupType": "and", "filters": [filters]}]
-                    yield stream_slice_with_filter
-            else:
-                # If no keywords are found, yield the base slice without filters
+            keywords = {record["searchAppearance"] for record in keywords_records}
+
+            for keyword in keywords:
+                filters = {"dimension": "searchAppearance", "operator": "equals", "expression": keyword}
+                stream_slice["dimensionFilterGroups"] = [{"groupType": "and", "filters": filters}]
+
                 yield stream_slice
 
     def request_body_json(
@@ -412,8 +405,7 @@ class SearchByKeyword(SearchAnalytics):
         next_page_token: Mapping[str, Any] = None,
     ) -> Optional[Union[Dict[str, Any], str]]:
         data = super().request_body_json(stream_state, stream_slice, next_page_token)
-        if "dimensionFilterGroups" in stream_slice:
-            data["dimensionFilterGroups"] = stream_slice["dimensionFilterGroups"]
+        data["dimensionFilterGroups"] = stream_slice["dimensionFilterGroups"]
         return data
 
 
@@ -466,9 +458,10 @@ class SearchAnalyticsByCustomDimensions(SearchAnalytics):
 
     primary_key = None
 
-    def __init__(self, dimensions: List[str], *args, **kwargs):
+    def __init__(self, dimensions: List[str], aggregation_type: str, *args, **kwargs):
         super(SearchAnalyticsByCustomDimensions, self).__init__(*args, **kwargs)
         self.dimensions = dimensions + [dimension for dimension in self.DEFAULT_DIMENSIONS if dimension not in dimensions]
+        self.aggregation_type = QueryAggregationType[aggregation_type]
         # Assign the dimensions as PK for the custom report stream.
         # Site URL and Search Type are included in the API call thus affect the resulting data.
         # `site_url` is a required URL param for making API calls;