Mirrors/ArchiveBox
2
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox synced 2024-11-22 04:03:06 +00:00
Code Issues Projects Releases Packages Wiki Activity

Added test headers extractor

Browse source
This commit is contained in:
Angel Rey 2020-09-11 14:18:36 -05:00 committed by Cristian Vargas
parent 852e3c9cff
commit 1cce786d6d
1 changed files with 8 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
tests/test_extractors.py
View file

@ -68,4 +68,11 @@ def test_use_node_false_disables_readability_and_singlefile(tmp_path, process, d
capture_output=True, env=disable_extractors_dict) capture_output=True, env=disable_extractors_dict)
output_str = add_process.stdout.decode("utf-8") output_str = add_process.stdout.decode("utf-8")
assert "> singlefile" not in output_str assert "> singlefile" not in output_str
assert "> readability" not in output_str assert "> readability" not in output_str
def test_headers(tmp_path, process, disable_extractors_dict):
add_process = subprocess.run(['archivebox', 'add', 'http://127.0.0.1:8080/static/example.com.html'],
capture_output=True, env=disable_extractors_dict)
archived_item_path = list(tmp_path.glob("archive/**/*"))[0]
output_file = archived_item_path / "headers.json"
assert output_file.exists()