smokephil/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-12-07 07:15:07 +01:00
Code Issues Projects Releases Packages Wiki Activity

Chore: add headers for wikipedia CI tests (#11253)

Browse source
This commit is contained in:
shamoon 2025-11-01 09:37:49 -07:00 • committed by GitHub
parent 6f52614817
commit cffb9c34f0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 14 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

15
src/paperless_mail/tests/test_parsers_live.py
View file

@ -53,6 +53,15 @@ class TestUrlCanary:
Verify certain URLs are still available so testing is valid still Verify certain URLs are still available so testing is valid still
""" """
# Wikimedia rejects requests without a browser-like User-Agent header and returns 403.
_WIKIMEDIA_HEADERS = {
"User-Agent": (
"Mozilla/5.0 (X11; Linux x86_64) "
"AppleWebKit/537.36 (KHTML, like Gecko) "
"Chrome/123.0.0.0 Safari/537.36"
),
}
def test_online_image_exception_on_not_available(self): def test_online_image_exception_on_not_available(self):
""" """
GIVEN: GIVEN:
@ -70,6 +79,7 @@ class TestUrlCanary:
with pytest.raises(httpx.HTTPStatusError) as exec_info: with pytest.raises(httpx.HTTPStatusError) as exec_info:
resp = httpx.get( resp = httpx.get(
"https://upload.wikimedia.org/wikipedia/en/f/f7/nonexistent.png", "https://upload.wikimedia.org/wikipedia/en/f/f7/nonexistent.png",
headers=self._WIKIMEDIA_HEADERS,
) )
resp.raise_for_status() resp.raise_for_status()
@ -90,7 +100,10 @@ class TestUrlCanary:
""" """
# Now check the URL used in samples/sample.html # Now check the URL used in samples/sample.html
resp = httpx.get("https://upload.wikimedia.org/wikipedia/en/f/f7/RickRoll.png") resp = httpx.get(
"https://upload.wikimedia.org/wikipedia/en/f/f7/RickRoll.png",
headers=self._WIKIMEDIA_HEADERS,
)
resp.raise_for_status() resp.raise_for_status()