def test_check_success_and_available():
target_url = "www.whitehouse.gov/issues/immigration/"
resptext = FIXTURES_DIR.joinpath("check/available-true.json").read_text()
expected_snap_url = "http://web.archive.org/web/20200903230055/https://www.whitehouse.gov/issues/immigration/"
responses.add(
"GET", wb.url_for_availability(target_url), body=resptext,
)
answer, meta = wb.check_availability(target_url)
assert answer == expected_snap_url
assert meta.snapshot_url == expected_snap_url
assert meta.target_url == target_url
assert meta.is_success() is True
assert meta.was_new_snapshot_created() is False
assert meta.created_at.strftime("%Y-%m-%d %H:%M:%S%z") == "2020-09-01 14:30:55+0000"
data = meta.to_dict()
assert data["request_meta"]["target_url"] == target_url
assert (
data["server_payload"]["url"] == target_url
) # TODO: not sure if this is guranteed, if target_url ends up being redirected??
ac = data["server_payload"]["archived_snapshots"]["closest"]
assert ac["available"] is True
assert ac["status"] == "200"
assert ac["url"] == answer
def test_check_not_available():
"""by default, returns just the available_url"""
target_url = "http://danwin.com/is/poop"
datatext = FIXTURES_DIR.joinpath("check/available-false.json").read_text()
data = jsonlib.loads(datatext)
responses.add("GET",
wb.url_for_availability(target_url),
body=datatext,
status=200)
result = runner.invoke(checkcli, [target_url])
assert result.output == "\n"
def test_check():
"""by default, returns just the available_url"""
target_url = "www.whitehouse.gov/issues/immigration/"
datatext = FIXTURES_DIR.joinpath("check/available-true.json").read_text()
data = jsonlib.loads(datatext)
responses.add("GET",
wb.url_for_availability(target_url),
body=datatext,
status=200)
result = runner.invoke(checkcli, [target_url])
assert result.output == data["archived_snapshots"]["closest"]["url"] + "\n"
assert result.exit_code == 0
def test_check_not_available_w_json():
"""by default, returns just the available_url"""
target_url = "http://danwin.com/is/poop"
datatext = FIXTURES_DIR.joinpath("check/available-false.json").read_text()
data = jsonlib.loads(datatext)
responses.add("GET",
wb.url_for_availability(target_url),
body=datatext,
status=200)
result = runner.invoke(checkcli, [target_url, "-j"])
jd = jsonlib.loads(result.output)
assert jd["request_meta"]["target_url"] == target_url
assert not jd["snapshot_url"]
assert jd["server_payload"]["archived_snapshots"] == {}
def test_check_w_json():
"""by default, returns just the available_url"""
target_url = "www.whitehouse.gov/issues/immigration/"
datatext = FIXTURES_DIR.joinpath("check/available-true.json").read_text()
data = jsonlib.loads(datatext)
responses.add("GET",
wb.url_for_availability(target_url),
body=datatext,
status=200)
result = runner.invoke(checkcli, [target_url, "-j"])
jd = jsonlib.loads(result.output)
assert jd["request_meta"]["target_url"] == target_url
ad = jd["server_payload"]["archived_snapshots"]["closest"]
assert jd["snapshot_url"] == ad["url"]
assert ad["available"] is True
def test_check_success_but_not_available():
target_url = "http://danwin.com/is/poop"
resptext = FIXTURES_DIR.joinpath("check/available-false.json").read_text()
responses.add(
"GET", wb.url_for_availability(target_url), body=resptext,
)
answer, meta = wb.check_availability(target_url)
assert answer is None
assert meta.snapshot_url is None
assert meta.request_meta["target_url"] == target_url
# TODO: not sure if this is guaranteed, if target_url ends up being redirected??
assert meta.server_payload["url"] == target_url
assert meta.server_payload["archived_snapshots"] == {}
def test_save_unless_within_hours():
target_url = "http://example.com/foo"
payload = {
"url": "http://example.com/foo",
"archived_snapshots": {
"closest": {
"available": True,
"status": "200",
"timestamp": "20151120111111",
"url": "http://web.archive.org/web/20151118111111/http://example.com/foo",
}
},
}
responses.add(
"GET", wb.url_for_availability(target_url), body=jsonlib.dumps(payload),
)
answer, meta = wb.snapshot(target_url, within_hours=24)
assert answer == meta.snapshot_url
assert meta.request_meta["within_hours"] == 24
assert meta.was_new_snapshot_created() is False
assert meta.server_payload == payload # brittle as hell!
def test_snapshot_too_many_for_period():
srcdir = FIXTURES_DIR.joinpath("job-save-too-many-today")
submit_resptext = srcdir.joinpath("submit-response.html").read_text()
target_url = "https://nytimes.com/"
responses.add(
"POST",
wb.url_for_savepage(target_url),
body=submit_resptext,
status=200,
match=[
responses.urlencoded_params_matcher(
{"url": target_url, "capture_all": "on"}
)
],
)
# mock request for availability URL
responses.add(
"GET",
wb.url_for_availability(target_url),
body=srcdir.joinpath("check-availability.json").read_text(),
)
answer, meta = wb.snapshot(target_url)
assert answer == meta.snapshot_url
assert meta.subcommand == "snapshot"
assert meta.was_new_snapshot_created() == False
assert (
meta.too_many_during_period()
== """This URL has been already captured 10 times today. Please email us at "*****@*****.**" if you would like to discuss this more."""
)
# import pdb; pdb.set_trace()
# server payload is the payload returned by availability API response
assert meta.server_payload["archived_snapshots"]["closest"]["available"] is True