Skip to content

Scrapy, a fast high-level web crawling & scraping framework for Python.

Fix FileFeedStorage handling of Windows paths without file:// scheme (#6897)

Thalison Fernandes0d86fb69dcfb
diff --git a/scrapy/extensions/feedexport.py b/scrapy/extensions/feedexport.py
index d9e9ea775..f7bf50a5c 100644
--- a/scrapy/extensions/feedexport.py
+++ b/scrapy/extensions/feedexport.py
@@ -185,7 +185,7 @@ class StdoutFeedStorage:
@implementer(IFeedStorage)
class FileFeedStorage:
def __init__(self, uri: str, *, feed_options: dict[str, Any] | None = None):
- self.path: str = file_uri_to_path(uri)
+ self.path: str = file_uri_to_path(uri) if uri.startswith("file://") else uri
feed_options = feed_options or {}
self.write_mode: OpenBinaryMode = (
"wb" if feed_options.get("overwrite", False) else "ab"
diff --git a/tests/test_feedexport.py b/tests/test_feedexport.py
index f8f3eb22a..7073d5a35 100644
--- a/tests/test_feedexport.py
+++ b/tests/test_feedexport.py
@@ -155,6 +155,11 @@ class TestFileFeedStorage:
finally:
path.unlink()
+ def test_preserves_windows_path_without_file_scheme(self):
+ path = r"C:\Users\user\Desktop\test.txt"
+ storage = FileFeedStorage(path)
+ assert storage.path == path
+
class TestFTPFeedStorage(unittest.TestCase):
def get_test_spider(self, settings=None):