From 32e790979e2f37c3615b52e0ed858603abd429a5 Mon Sep 17 00:00:00 2001 From: Cristian Date: Tue, 7 Jul 2020 10:07:44 -0500 Subject: [PATCH] feat: Enable depth=1 functionality --- archivebox/cli/archivebox_add.py | 16 ++++++++-------- tests/test_args.py | 9 ++++++++- 2 files changed, 16 insertions(+), 9 deletions(-) diff --git a/archivebox/cli/archivebox_add.py b/archivebox/cli/archivebox_add.py index 5bbccb19..65335679 100644 --- a/archivebox/cli/archivebox_add.py +++ b/archivebox/cli/archivebox_add.py @@ -61,14 +61,14 @@ def main(args: Optional[List[str]]=None, stdin: Optional[IO]=None, pwd: Optional index_only=command.index_only, out_dir=pwd or OUTPUT_DIR, ) - #if command.depth == 1: - # add( - # import_str=None, - # import_path=command.import_path, - # update_all=command.update_all, - # index_only=command.index_only, - # out_dir=pwd or OUTPUT_DIR, - # ) + if command.depth == 1: + add( + import_str=None, + import_path=command.import_path, + update_all=command.update_all, + index_only=command.index_only, + out_dir=pwd or OUTPUT_DIR, + ) if __name__ == '__main__': diff --git a/tests/test_args.py b/tests/test_args.py index 59d43fee..e0c6020e 100644 --- a/tests/test_args.py +++ b/tests/test_args.py @@ -12,4 +12,11 @@ def test_depth_flag_0_crawls_only_the_arg_page(tmp_path, process): archived_item_path = list(tmp_path.glob('archive/**/*'))[0] with open(archived_item_path / "index.json", "r") as f: output_json = json.load(f) - assert output_json["base_url"] == "example.com" \ No newline at end of file + assert output_json["base_url"] == "example.com" + +def test_depth_flag_1_crawls_the_page_AND_links(tmp_path, process): + arg_process = subprocess.run(["archivebox", "add", "https://example.com", "--depth=1"], capture_output=True) + with open(tmp_path / "index.json", "r") as f: + archive_file = f.read() + assert "https://example.com" in archive_file + assert "https://www.iana.org/domains/example" in archive_file \ No newline at end of file