bellingcat/auto-archiver
1
0
Fork 0
mirror of https://github.com/bellingcat/auto-archiver.git synced 2026-06-13 05:38:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

Various fixes for issues with new architecture (#208)

Browse Source 
* Add formatters to the TOC - fixes #204

* Add 'steps' settings to the example YAML in the docs. Fixes #206

* Improved docs on authentication architecture

* Fix setting modules on the command line - they now override any module settings in the orchestration as opposed to appending

* Fix tests for gsheet-feeder: add a test service_account.json (note: not real keys in there)

* Rename the command line entrypoint to _command_line_run

Also: make it clear that code implementation should not call this
Make sure the command line entry returns (we don't want a generator)

* Fix unit tests to use now code-entry points

* Version bump

* Move iterating of generator up to __main__

* Breakpoint

* two minor fixes

* Fix unit tests + add new '__main__' entry point implementation test

* Skip youtube tests if running on CI. Should still run them locally

* Fix full implementation run on GH actions

* Fix skipif test for GH Actions CI

* Add skipifs for truth - it blocks GH:

---------

Co-authored-by: msramalho <19508417+msramalho@users.noreply.github.com>
This commit is contained in:
Patrick Robertson
2025-02-18 19:10:09 +00:00
committed by GitHub
parent 6d43bc7d4d
commit 3c543a3a6a
18 changed files with 314 additions and 84 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
tests/extractors/test_generic_extractor.py
View File

@@ -9,6 +9,7 @@ import pytest
from auto_archiver.modules.generic_extractor.generic_extractor import GenericExtractor
from .test_extractor_base import TestExtractorBase
CI=os.getenv("GITHUB_ACTIONS", '') == 'true'
class TestGenericExtractor(TestExtractorBase):
"""Tests Generic Extractor
"""
@@ -77,10 +78,11 @@ class TestGenericExtractor(TestExtractorBase):
result = self.extractor.download(item)
assert not result
@pytest.mark.skipif(CI, reason="Currently no way to authenticate when on CI. Youtube (yt-dlp) doesn't support logging in with username/password.")
@pytest.mark.download
def test_youtube_download(self, make_item):
# url https://www.youtube.com/watch?v=5qap5aO4i9A
item = make_item("https://www.youtube.com/watch?v=J---aiyznGQ")
result = self.extractor.download(item)
assert result.get_url() == "https://www.youtube.com/watch?v=J---aiyznGQ"
@@ -114,6 +116,7 @@ class TestGenericExtractor(TestExtractorBase):
result = self.extractor.download(item)
assert result is not False
@pytest.mark.skipif(CI, reason="Truth social blocks GH actions.")
@pytest.mark.download
def test_truthsocial_download_video(self, make_item):
item = make_item("https://truthsocial.com/@DaynaTrueman/posts/110602446619561579")
@@ -121,18 +124,21 @@ class TestGenericExtractor(TestExtractorBase):
assert len(result.media) == 1
assert result is not False
@pytest.mark.skipif(CI, reason="Truth social blocks GH actions.")
@pytest.mark.download
def test_truthsocial_download_no_media(self, make_item):
item = make_item("https://truthsocial.com/@bbcnewa/posts/109598702184774628")
result = self.extractor.download(item)
assert result is not False
@pytest.mark.skipif(CI, reason="Truth social blocks GH actions.")
@pytest.mark.download
def test_truthsocial_download_poll(self, make_item):
item = make_item("https://truthsocial.com/@CNN_US/posts/113724326568555098")
result = self.extractor.download(item)
assert result is not False
@pytest.mark.skipif(CI, reason="Truth social blocks GH actions.")
@pytest.mark.download
def test_truthsocial_download_single_image(self, make_item):
item = make_item("https://truthsocial.com/@mariabartiromo/posts/113861116433335006")
@@ -140,6 +146,7 @@ class TestGenericExtractor(TestExtractorBase):
assert len(result.media) == 1
assert result is not False
@pytest.mark.skipif(CI, reason="Truth social blocks GH actions.")
@pytest.mark.download
def test_truthsocial_download_multiple_images(self, make_item):
item = make_item("https://truthsocial.com/@trrth/posts/113861302149349135")