mirror/archivebox
1
0
Fork 0
mirror of https://github.com/pirate/ArchiveBox.git synced 2025-08-13 01:54:10 +02:00
Code Issues Releases Wiki Activity

tests: Add readability tests

Browse Source
This commit is contained in:
Cristian
2020-08-11 11:15:15 -05:00
parent 8aa7b34de7
commit 2a68af1b94
2 changed files with 36 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
tests/test_extractors.py
View File

@@ -21,3 +21,35 @@ def test_singlefile_works(tmp_path, process, disable_extractors_dict):
archived_item_path = list(tmp_path.glob('archive/**/*'))[0]
output_file = archived_item_path / "singlefile.html"
assert output_file.exists()
def test_readability_works(tmp_path, process, disable_extractors_dict):
disable_extractors_dict.update({"USE_READABILITY": "true"})
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 / "readability" / "content.html"
assert output_file.exists()
def test_readability_works_with_wget(tmp_path, process, disable_extractors_dict):
disable_extractors_dict.update({"USE_READABILITY": "true", "USE_WGET": "true"})
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 / "readability" / "content.html"
assert output_file.exists()
def test_readability_works_with_singlefile(tmp_path, process, disable_extractors_dict):
disable_extractors_dict.update({"USE_READABILITY": "true", "USE_SINGLEFILE": "true"})
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 / "readability" / "content.html"
assert output_file.exists()
def test_readability_works_with_dom(tmp_path, process, disable_extractors_dict):
disable_extractors_dict.update({"USE_READABILITY": "true", "SAVE_DOM": "true"})
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 / "readability" / "content.html"
assert output_file.exists()