forks/archivebox
1
0
Fork 0
Code Releases Activity

Added more asserts

Browse source
This commit is contained in:
Angel Rey 2020-09-14 16:35:45 -05:00 committed by Cristian Vargas
parent dc160daba8
commit ee6caca3ca
2 changed files with 19 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
tests/mock_server/server.py
View file

@ -2,7 +2,7 @@ from os.path import abspath
from os import getcwd from os import getcwd
from pathlib import Path from pathlib import Path
from bottle import route, run, static_file from bottle import route, run, static_file, response
@route("/") @route("/")
def index(): def index():
@ -21,5 +21,14 @@ def static_no_content_type(filename):
response.set_header("Content-Type", "") response.set_header("Content-Type", "")
return response return response
@route("/static/headers/<filename>")
def static_path_with_headers(filename):
template_path = abspath(getcwd()) / Path("tests/mock_server/templates")
response = static_file(filename, root=template_path)
response.add_header("Content-Language", "en")
response.add_header("Content-Script-Type", "text/javascript")
response.add_header("Content-Style-Type", "text/css")
return response
def start(): def start():
run(host='localhost', port=8080) run(host='localhost', port=8080)

11
tests/test_extractors.py
View file

@ -1,4 +1,5 @@
from .fixtures import * from .fixtures import *
import json as pyjson
from archivebox.extractors import ignore_methods, get_default_archive_methods, should_save_title from archivebox.extractors import ignore_methods, get_default_archive_methods, should_save_title
def test_wget_broken_pipe(tmp_path, process, disable_extractors_dict): def test_wget_broken_pipe(tmp_path, process, disable_extractors_dict):
@ -71,8 +72,14 @@ def test_use_node_false_disables_readability_and_singlefile(tmp_path, process, d
assert "> readability" not in output_str assert "> readability" not in output_str
def test_headers(tmp_path, process, disable_extractors_dict): 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'], add_process = subprocess.run(['archivebox', 'add', 'http://127.0.0.1:8080/static/headers/example.com.html'],
capture_output=True, env=disable_extractors_dict) capture_output=True, env=disable_extractors_dict)
archived_item_path = list(tmp_path.glob("archive/**/*"))[0] archived_item_path = list(tmp_path.glob("archive/**/*"))[0]
output_file = archived_item_path / "headers.json" output_file = archived_item_path / "headers.json"
assert output_file.exists() assert output_file.exists()
headers_file = archived_item_path / 'headers.json'
with open(headers_file) as f:
headers = pyjson.load(f)
assert headers['Content-Language'] == 'en'
assert headers['Content-Script-Type'] == 'text/javascript'
assert headers['Content-Style-Type'] == 'text/css'