mirrors/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2025-05-13 06:34:25 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

feat: Add options to ease management of node related extractors

Browse source
This commit is contained in:
Cristian 2020-08-18 10:34:28 -05:00
parent 73fad928df
commit cc0fa747ce
4 changed files with 31 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

8
tests/test_extractors.py
View file

@ -53,3 +53,11 @@ def test_readability_works_with_dom(tmp_path, process, disable_extractors_dict):
archived_item_path = list(tmp_path.glob("archive/**/*"))[0]
output_file = archived_item_path / "readability" / "content.html"
assert output_file.exists()
def test_use_node_false_disables_readability_and_singlefile(tmp_path, process, disable_extractors_dict):
disable_extractors_dict.update({"USE_READABILITY": "true", "SAVE_DOM": "true", "USE_SINGLEFILE": "true", "USE_NODE": "false"})
add_process = subprocess.run(['archivebox', 'add', 'http://127.0.0.1:8080/static/example.com.html'],
capture_output=True, env=disable_extractors_dict)
output_str = add_process.stdout.decode("utf-8")
assert "> singlefile" not in output_str
assert "> readability" not in output_str