Make the output archive name variable based on the spider

scrapy_webarchive/extensions.py

@@ -104,8 +104,8 @@ def response_received(self, response: Response, request: Request, spider: Spider
         self.writer.write_request(request, concurrent_to=record)
         self.stats.inc_value("wacz/exporter/request_written", spider=spider)
 
-    def spider_closed(self) -> None:
-        WaczFileCreator(warc_fname=self.writer.warc_fname, store=self.store).create()
+    def spider_closed(self, spider: Spider) -> None:
+        WaczFileCreator(store=self.store, warc_fname=self.writer.warc_fname, collection_name=spider.name).create()
 
 
 def get_archive_uri_template_variables() -> dict:

scrapy_webarchive/wacz.py

@@ -21,10 +21,11 @@ class WARCReader(BaseWARCReader):
 class WaczFileCreator:
     """Handles creating WACZ archives"""
 
-    def __init__(self, store, warc_fname: str, cdxj_fname: str = "index.cdxj") -> None:
+    def __init__(self, store, warc_fname: str, collection_name: str, cdxj_fname: str = "index.cdxj") -> None:
         self.store = store
         self.warc_fname = warc_fname
         self.cdxj_fname = cdxj_fname
+        self.collection_name = collection_name
 
     def create(self) -> None:
         """Create the WACZ file from the WARC and CDXJ index and save it in the configured store"""
@@ -68,7 +69,7 @@ def cleanup_files(self, *files: str) -> None:
     def get_wacz_fname(self) -> str:
         """Generate WACZ filename based on the WARC filename"""
 
-        return f"archive-{get_current_timestamp()}.wacz"
+        return f"{self.collection_name}-{get_current_timestamp()}.wacz"
 
 
 class WaczFile:

tests/test_wacz.py

@@ -8,39 +8,45 @@
 
 
 class TestWaczFileCreator:
+    warc_fname = "example-20241007000000-00000-test.warc"
+    cdxj_fname = "index.cdxj"
+    collection_name = "example"
+
     @pytest.fixture
     def wacz_file_creator(self):
         """Fixture to initialize the WaczFileCreator with a mocked store"""
 
-        store = Mock()
-        warc_fname = "/scrapy-webarchive/quotes-20241007000000-00000-test.warc"
-        cdxj_fname = "/scrapy-webarchive/index.cdxj"
-        return WaczFileCreator(store=store, warc_fname=warc_fname, cdxj_fname=cdxj_fname)
+        return WaczFileCreator(
+            store=Mock(),
+            warc_fname=self.warc_fname,
+            collection_name=self.collection_name,
+            cdxj_fname=self.cdxj_fname,
+        )
 
     @freeze_time("2024-10-04 08:27:11")
     def test_create_wacz(self, fs, wacz_file_creator):
         # Setup the fake filesystem
-        fs.create_file("/scrapy-webarchive/index.cdxj", contents="")
-        fs.create_file("/scrapy-webarchive/quotes-20241007000000-00000-test.warc", contents="")
+        fs.create_file(self.cdxj_fname, contents="")
+        fs.create_file(self.warc_fname, contents="")
 
         wacz_file_creator.create()
 
         # Ensure the files are removed after creation
-        assert not fs.exists("/scrapy-webarchive/index.cdxj")
-        assert not fs.exists("/scrapy-webarchive/quotes-20241007000000-00000-test.warc")
+        assert not fs.exists(self.cdxj_fname)
+        assert not fs.exists(self.warc_fname)
 
         # Verify the WACZ file was persisted in the store
         wacz_fname = wacz_file_creator.get_wacz_fname()
         wacz_file_creator.store.persist_file.assert_called_once()
 
         # Assert that the correct WACZ filename was used
-        assert wacz_fname == "archive-20241004082711.wacz"
+        assert wacz_fname == f"{self.collection_name}-20241004082711.wacz"
 
         # Retrieve the zip buffer from the call args
         call_args = wacz_file_creator.store.persist_file.call_args
         zip_buffer = call_args[0][1]
 
         # Verify that the WACZ zip content is correct
         zip_file = zipfile.ZipFile(zip_buffer)
-        assert "indexes/index.cdxj" in zip_file.namelist()
-        assert "archive/quotes-20241007000000-00000-test.warc" in zip_file.namelist()
+        assert f"indexes/{self.cdxj_fname}" in zip_file.namelist()
+        assert f"archive/{self.warc_fname}" in zip_file.namelist()