full cdx api support
This commit is contained in:
Akash Mahanty
93
tests/test_cdx.py
Normal file
93
tests/test_cdx.py
Normal file
@ -0,0 +1,93 @@
|
||||
import pytest
|
||||
from waybackpy.cdx import Cdx
|
||||
from waybackpy.exceptions import WaybackError
|
||||
|
||||
|
||||
def test_all_cdx():
|
||||
url = "akamhy.github.io"
|
||||
user_agent = "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, \
|
||||
like Gecko) Chrome/45.0.2454.85 Safari/537.36"
|
||||
cdx = Cdx(
|
||||
url=url,
|
||||
user_agent=user_agent,
|
||||
start_timestamp=2017,
|
||||
end_timestamp=2020,
|
||||
filters=[
|
||||
"statuscode:200",
|
||||
"mimetype:text/html",
|
||||
"timestamp:20201002182319",
|
||||
"original:https://akamhy.github.io/",
|
||||
],
|
||||
gzip=False,
|
||||
collapses=["timestamp:10", "digest"],
|
||||
limit=50,
|
||||
match_type="prefix",
|
||||
)
|
||||
snapshots = cdx.snapshots()
|
||||
for snapshot in snapshots:
|
||||
ans = snapshot.archive_url
|
||||
assert "https://web.archive.org/web/20201002182319/https://akamhy.github.io/" == ans
|
||||
|
||||
url = "akahfjgjkmhy.gihthub.ip"
|
||||
cdx = Cdx(
|
||||
url=url,
|
||||
user_agent=user_agent,
|
||||
start_timestamp=None,
|
||||
end_timestamp=None,
|
||||
filters=[],
|
||||
match_type=None,
|
||||
gzip=True,
|
||||
collapses=[],
|
||||
limit=10,
|
||||
)
|
||||
|
||||
snapshots = cdx.snapshots()
|
||||
print(snapshots)
|
||||
i = 0
|
||||
for _ in snapshots:
|
||||
i += 1
|
||||
assert i == 0
|
||||
|
||||
url = "https://github.com/akamhy/waybackpy/*"
|
||||
cdx = Cdx(url=url, user_agent=user_agent, limit=50)
|
||||
snapshots = cdx.snapshots()
|
||||
|
||||
for snapshot in snapshots:
|
||||
print(snapshot.archive_url)
|
||||
|
||||
url = "https://github.com/akamhy/waybackpy"
|
||||
with pytest.raises(WaybackError):
|
||||
cdx = Cdx(url=url, user_agent=user_agent, limit=50, filters=["ghddhfhj"])
|
||||
snapshots = cdx.snapshots()
|
||||
|
||||
with pytest.raises(WaybackError):
|
||||
cdx = Cdx(url=url, user_agent=user_agent, collapses=["timestamp", "ghdd:hfhj"])
|
||||
snapshots = cdx.snapshots()
|
||||
|
||||
url = "https://github.com"
|
||||
cdx = Cdx(url=url, user_agent=user_agent, limit=50)
|
||||
snapshots = cdx.snapshots()
|
||||
c = 0
|
||||
for snapshot in snapshots:
|
||||
c += 1
|
||||
if c > 100:
|
||||
break
|
||||
|
||||
url = "https://github.com/*"
|
||||
cdx = Cdx(url=url, user_agent=user_agent, collapses=["timestamp"])
|
||||
snapshots = cdx.snapshots()
|
||||
c = 0
|
||||
for snapshot in snapshots:
|
||||
c += 1
|
||||
if c > 30_529: # deafult limit is 10k
|
||||
break
|
||||
|
||||
url = "https://github.com/*"
|
||||
cdx = Cdx(url=url, user_agent=user_agent)
|
||||
c = 0
|
||||
snapshots = cdx.snapshots()
|
||||
|
||||
for snapshot in snapshots:
|
||||
c += 1
|
||||
if c > 100_529:
|
||||
break
|
||||
32
tests/test_snapshot.py
Normal file
32
tests/test_snapshot.py
Normal file
@ -0,0 +1,32 @@
|
||||
import pytest
|
||||
|
||||
from waybackpy.snapshot import CdxSnapshot, datetime
|
||||
|
||||
|
||||
def test_CdxSnapshot():
|
||||
sample_input = "org,archive)/ 20080126045828 http://github.com text/html 200 Q4YULN754FHV2U6Q5JUT6Q2P57WEWNNY 1415"
|
||||
(
|
||||
urlkey,
|
||||
timestamp,
|
||||
original,
|
||||
mimetype,
|
||||
statuscode,
|
||||
digest,
|
||||
length,
|
||||
) = sample_input.split(" ")
|
||||
|
||||
snapshot = CdxSnapshot(
|
||||
urlkey, timestamp, original, mimetype, statuscode, digest, length
|
||||
)
|
||||
|
||||
assert urlkey == snapshot.urlkey
|
||||
assert timestamp == snapshot.timestamp
|
||||
assert original == snapshot.original
|
||||
assert mimetype == snapshot.mimetype
|
||||
assert statuscode == snapshot.statuscode
|
||||
assert digest == snapshot.digest
|
||||
assert length == snapshot.length
|
||||
assert datetime.strptime(timestamp, "%Y%m%d%H%M%S") == snapshot.datetime_timestamp
|
||||
archive_url = "https://web.archive.org/web/" + timestamp + "/" + original
|
||||
assert archive_url == snapshot.archive_url
|
||||
assert archive_url == str(snapshot)
|
||||
190
tests/test_utils.py
Normal file
190
tests/test_utils.py
Normal file
@ -0,0 +1,190 @@
|
||||
import pytest
|
||||
import json
|
||||
|
||||
from waybackpy.utils import (
|
||||
_cleaned_url,
|
||||
_url_check,
|
||||
_full_url,
|
||||
URLError,
|
||||
WaybackError,
|
||||
_get_total_pages,
|
||||
_archive_url_parser,
|
||||
_wayback_timestamp,
|
||||
_get_response,
|
||||
_check_match_type,
|
||||
_check_collapses,
|
||||
_check_filters,
|
||||
_ts,
|
||||
)
|
||||
|
||||
|
||||
def test_ts():
|
||||
timestamp = True
|
||||
data = {}
|
||||
assert _ts(timestamp, data)
|
||||
|
||||
data = """
|
||||
{"archived_snapshots": {"closest": {"timestamp": "20210109155628", "available": true, "status": "200", "url": "http://web.archive.org/web/20210109155628/https://www.google.com/"}}, "url": "https://www.google.com/"}
|
||||
"""
|
||||
data = json.loads(data)
|
||||
assert data["archived_snapshots"]["closest"]["timestamp"] == "20210109155628"
|
||||
|
||||
|
||||
def test_check_filters():
|
||||
filters = []
|
||||
_check_filters(filters)
|
||||
|
||||
filters = ["statuscode:200", "timestamp:20215678901234", "original:https://url.com"]
|
||||
_check_filters(filters)
|
||||
|
||||
filters = ["statuscode:2768900", "timestamp:123456789", "original:://url.com"]
|
||||
with pytest.raises(WaybackError):
|
||||
_check_filters(filters)
|
||||
|
||||
with pytest.raises(WaybackError):
|
||||
_check_filters("not-list")
|
||||
|
||||
|
||||
def test_check_collapses():
|
||||
collapses = []
|
||||
_check_collapses(collapses)
|
||||
|
||||
collapses = ["timestamp:10"]
|
||||
_check_collapses(collapses)
|
||||
|
||||
collapses = ["urlkey"]
|
||||
_check_collapses(collapses)
|
||||
|
||||
collapses = "urlkey" # NOT LIST
|
||||
with pytest.raises(WaybackError):
|
||||
_check_collapses(collapses)
|
||||
|
||||
collapses = ["also illegal collapse"]
|
||||
with pytest.raises(WaybackError):
|
||||
_check_collapses(collapses)
|
||||
|
||||
|
||||
def test_check_match_type():
|
||||
assert None == _check_match_type(None, "url")
|
||||
match_type = "exact"
|
||||
url = "test_url"
|
||||
assert None == _check_match_type(match_type, url)
|
||||
|
||||
url = "has * in it"
|
||||
with pytest.raises(WaybackError):
|
||||
_check_match_type("domain", url)
|
||||
|
||||
with pytest.raises(WaybackError):
|
||||
_check_match_type("not a valid type", "url")
|
||||
|
||||
|
||||
def test_cleaned_url():
|
||||
test_url = " https://en.wikipedia.org/wiki/Network security "
|
||||
answer = "https://en.wikipedia.org/wiki/Network%20security"
|
||||
assert answer == _cleaned_url(test_url)
|
||||
|
||||
|
||||
def test_url_check():
|
||||
good_url = "https://akamhy.github.io"
|
||||
assert None == _url_check(good_url)
|
||||
|
||||
bad_url = "https://github-com"
|
||||
with pytest.raises(URLError):
|
||||
_url_check(bad_url)
|
||||
|
||||
|
||||
def test_full_url():
|
||||
params = {}
|
||||
endpoint = "https://web.archive.org/cdx/search/cdx"
|
||||
assert endpoint == _full_url(endpoint, params)
|
||||
|
||||
params = {"a": "1"}
|
||||
assert "https://web.archive.org/cdx/search/cdx?a=1" == _full_url(endpoint, params)
|
||||
assert "https://web.archive.org/cdx/search/cdx?a=1" == _full_url(
|
||||
endpoint + "?", params
|
||||
)
|
||||
|
||||
params["b"] = 2
|
||||
assert "https://web.archive.org/cdx/search/cdx?a=1&b=2" == _full_url(
|
||||
endpoint + "?", params
|
||||
)
|
||||
|
||||
params["c"] = "foo bar"
|
||||
assert "https://web.archive.org/cdx/search/cdx?a=1&b=2&c=foo%20bar" == _full_url(
|
||||
endpoint + "?", params
|
||||
)
|
||||
|
||||
|
||||
def test_get_total_pages():
|
||||
user_agent = "Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko"
|
||||
url = "github.com*"
|
||||
assert 212890 <= _get_total_pages(url, user_agent)
|
||||
|
||||
url = "https://zenodo.org/record/4416138"
|
||||
assert 2 >= _get_total_pages(url, user_agent)
|
||||
|
||||
|
||||
def test_archive_url_parser():
|
||||
perfect_header = """
|
||||
{'Server': 'nginx/1.15.8', 'Date': 'Sat, 02 Jan 2021 09:40:25 GMT', 'Content-Type': 'text/html; charset=UTF-8', 'Transfer-Encoding': 'chunked', 'Connection': 'keep-alive', 'X-Archive-Orig-Server': 'nginx', 'X-Archive-Orig-Date': 'Sat, 02 Jan 2021 09:40:09 GMT', 'X-Archive-Orig-Transfer-Encoding': 'chunked', 'X-Archive-Orig-Connection': 'keep-alive', 'X-Archive-Orig-Vary': 'Accept-Encoding', 'X-Archive-Orig-Last-Modified': 'Fri, 01 Jan 2021 12:19:00 GMT', 'X-Archive-Orig-Strict-Transport-Security': 'max-age=31536000, max-age=0;', 'X-Archive-Guessed-Content-Type': 'text/html', 'X-Archive-Guessed-Charset': 'utf-8', 'Memento-Datetime': 'Sat, 02 Jan 2021 09:40:09 GMT', 'Link': '<https://www.scribbr.com/citing-sources/et-al/>; rel="original", <https://web.archive.org/web/timemap/link/https://www.scribbr.com/citing-sources/et-al/>; rel="timemap"; type="application/link-format", <https://web.archive.org/web/https://www.scribbr.com/citing-sources/et-al/>; rel="timegate", <https://web.archive.org/web/20200601082911/https://www.scribbr.com/citing-sources/et-al/>; rel="first memento"; datetime="Mon, 01 Jun 2020 08:29:11 GMT", <https://web.archive.org/web/20201126185327/https://www.scribbr.com/citing-sources/et-al/>; rel="prev memento"; datetime="Thu, 26 Nov 2020 18:53:27 GMT", <https://web.archive.org/web/20210102094009/https://www.scribbr.com/citing-sources/et-al/>; rel="memento"; datetime="Sat, 02 Jan 2021 09:40:09 GMT", <https://web.archive.org/web/20210102094009/https://www.scribbr.com/citing-sources/et-al/>; rel="last memento"; datetime="Sat, 02 Jan 2021 09:40:09 GMT"', 'Content-Security-Policy': "default-src 'self' 'unsafe-eval' 'unsafe-inline' data: blob: archive.org web.archive.org analytics.archive.org pragma.archivelab.org", 'X-Archive-Src': 'spn2-20210102092956-wwwb-spn20.us.archive.org-8001.warc.gz', 'Server-Timing': 'captures_list;dur=112.646325, exclusion.robots;dur=0.172010, exclusion.robots.policy;dur=0.158205, RedisCDXSource;dur=2.205932, esindex;dur=0.014647, LoadShardBlock;dur=82.205012, PetaboxLoader3.datanode;dur=70.750239, CDXLines.iter;dur=24.306278, load_resource;dur=26.520179', 'X-App-Server': 'wwwb-app200', 'X-ts': '200', 'X-location': 'All', 'X-Cache-Key': 'httpsweb.archive.org/web/20210102094009/https://www.scribbr.com/citing-sources/et-al/IN', 'X-RL': '0', 'X-Page-Cache': 'MISS', 'X-Archive-Screenname': '0', 'Content-Encoding': 'gzip'}
|
||||
"""
|
||||
|
||||
archive = _archive_url_parser(
|
||||
perfect_header, "https://www.scribbr.com/citing-sources/et-al/"
|
||||
)
|
||||
assert "web.archive.org/web/20210102094009" in archive
|
||||
|
||||
header = """
|
||||
vhgvkjv
|
||||
Content-Location: /web/20201126185327/https://www.scribbr.com/citing-sources/et-al
|
||||
ghvjkbjmmcmhj
|
||||
"""
|
||||
archive = _archive_url_parser(
|
||||
header, "https://www.scribbr.com/citing-sources/et-al/"
|
||||
)
|
||||
assert "20201126185327" in archive
|
||||
|
||||
header = """
|
||||
hfjkfjfcjhmghmvjm
|
||||
X-Cache-Key: https://web.archive.org/web/20171128185327/https://www.scribbr.com/citing-sources/et-al/US
|
||||
yfu,u,gikgkikik
|
||||
"""
|
||||
archive = _archive_url_parser(
|
||||
header, "https://www.scribbr.com/citing-sources/et-al/"
|
||||
)
|
||||
assert "20171128185327" in archive
|
||||
|
||||
# The below header should result in Exception
|
||||
no_archive_header = """
|
||||
{'Server': 'nginx/1.15.8', 'Date': 'Sat, 02 Jan 2021 09:42:45 GMT', 'Content-Type': 'text/html; charset=utf-8', 'Transfer-Encoding': 'chunked', 'Connection': 'keep-alive', 'Cache-Control': 'no-cache', 'X-App-Server': 'wwwb-app52', 'X-ts': '523', 'X-RL': '0', 'X-Page-Cache': 'MISS', 'X-Archive-Screenname': '0'}
|
||||
"""
|
||||
|
||||
with pytest.raises(WaybackError):
|
||||
_archive_url_parser(
|
||||
no_archive_header, "https://www.scribbr.com/citing-sources/et-al/"
|
||||
)
|
||||
|
||||
|
||||
def test_wayback_timestamp():
|
||||
ts = _wayback_timestamp(year=2020, month=1, day=2, hour=3, minute=4)
|
||||
assert "202001020304" in str(ts)
|
||||
|
||||
|
||||
def test_get_response():
|
||||
endpoint = "https://www.google.com"
|
||||
user_agent = (
|
||||
"Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:78.0) Gecko/20100101 Firefox/78.0"
|
||||
)
|
||||
headers = {"User-Agent": "%s" % user_agent}
|
||||
response = _get_response(endpoint, params=None, headers=headers)
|
||||
assert response.status_code == 200
|
||||
|
||||
endpoint = "http/wwhfhfvhvjhmom"
|
||||
with pytest.raises(WaybackError):
|
||||
_get_response(endpoint, params=None, headers=headers)
|
||||
|
||||
endpoint = "https://akamhy.github.io"
|
||||
url, response = _get_response(
|
||||
endpoint, params=None, headers=headers, return_full_url=True
|
||||
)
|
||||
assert endpoint == url
|
||||
@ -4,85 +4,17 @@ import random
|
||||
import requests
|
||||
from datetime import datetime
|
||||
|
||||
sys.path.append("..")
|
||||
|
||||
import waybackpy.wrapper as waybackpy # noqa: E402
|
||||
from waybackpy.wrapper import Url, Cdx
|
||||
|
||||
|
||||
user_agent = "Mozilla/5.0 (Windows NT 6.2; rv:20.0) Gecko/20121202 Firefox/20.0"
|
||||
|
||||
|
||||
def test_cleaned_url():
|
||||
"""No API use"""
|
||||
test_url = " https://en.wikipedia.org/wiki/Network security "
|
||||
answer = "https://en.wikipedia.org/wiki/Network_security"
|
||||
target = waybackpy.Url(test_url, user_agent)
|
||||
test_result = target._cleaned_url()
|
||||
assert answer == test_result
|
||||
|
||||
|
||||
def test_ts():
|
||||
a = waybackpy.Url("https://google.com", user_agent)
|
||||
ts = a._timestamp
|
||||
assert str(datetime.utcnow().year) in str(ts)
|
||||
|
||||
|
||||
def test_dunders():
|
||||
"""No API use"""
|
||||
url = "https://en.wikipedia.org/wiki/Network_security"
|
||||
user_agent = "UA"
|
||||
target = waybackpy.Url(url, user_agent)
|
||||
assert "waybackpy.Url(url=%s, user_agent=%s)" % (url, user_agent) == repr(target)
|
||||
assert "en.wikipedia.org" in str(target)
|
||||
|
||||
|
||||
def test_url_check():
|
||||
"""No API Use"""
|
||||
broken_url = "http://wwwgooglecom/"
|
||||
with pytest.raises(Exception):
|
||||
waybackpy.Url(broken_url, user_agent)
|
||||
|
||||
|
||||
def test_archive_url_parser():
|
||||
"""No API Use"""
|
||||
perfect_header = """
|
||||
{'Server': 'nginx/1.15.8', 'Date': 'Sat, 02 Jan 2021 09:40:25 GMT', 'Content-Type': 'text/html; charset=UTF-8', 'Transfer-Encoding': 'chunked', 'Connection': 'keep-alive', 'X-Archive-Orig-Server': 'nginx', 'X-Archive-Orig-Date': 'Sat, 02 Jan 2021 09:40:09 GMT', 'X-Archive-Orig-Transfer-Encoding': 'chunked', 'X-Archive-Orig-Connection': 'keep-alive', 'X-Archive-Orig-Vary': 'Accept-Encoding', 'X-Archive-Orig-Last-Modified': 'Fri, 01 Jan 2021 12:19:00 GMT', 'X-Archive-Orig-Strict-Transport-Security': 'max-age=31536000, max-age=0;', 'X-Archive-Guessed-Content-Type': 'text/html', 'X-Archive-Guessed-Charset': 'utf-8', 'Memento-Datetime': 'Sat, 02 Jan 2021 09:40:09 GMT', 'Link': '<https://www.scribbr.com/citing-sources/et-al/>; rel="original", <https://web.archive.org/web/timemap/link/https://www.scribbr.com/citing-sources/et-al/>; rel="timemap"; type="application/link-format", <https://web.archive.org/web/https://www.scribbr.com/citing-sources/et-al/>; rel="timegate", <https://web.archive.org/web/20200601082911/https://www.scribbr.com/citing-sources/et-al/>; rel="first memento"; datetime="Mon, 01 Jun 2020 08:29:11 GMT", <https://web.archive.org/web/20201126185327/https://www.scribbr.com/citing-sources/et-al/>; rel="prev memento"; datetime="Thu, 26 Nov 2020 18:53:27 GMT", <https://web.archive.org/web/20210102094009/https://www.scribbr.com/citing-sources/et-al/>; rel="memento"; datetime="Sat, 02 Jan 2021 09:40:09 GMT", <https://web.archive.org/web/20210102094009/https://www.scribbr.com/citing-sources/et-al/>; rel="last memento"; datetime="Sat, 02 Jan 2021 09:40:09 GMT"', 'Content-Security-Policy': "default-src 'self' 'unsafe-eval' 'unsafe-inline' data: blob: archive.org web.archive.org analytics.archive.org pragma.archivelab.org", 'X-Archive-Src': 'spn2-20210102092956-wwwb-spn20.us.archive.org-8001.warc.gz', 'Server-Timing': 'captures_list;dur=112.646325, exclusion.robots;dur=0.172010, exclusion.robots.policy;dur=0.158205, RedisCDXSource;dur=2.205932, esindex;dur=0.014647, LoadShardBlock;dur=82.205012, PetaboxLoader3.datanode;dur=70.750239, CDXLines.iter;dur=24.306278, load_resource;dur=26.520179', 'X-App-Server': 'wwwb-app200', 'X-ts': '200', 'X-location': 'All', 'X-Cache-Key': 'httpsweb.archive.org/web/20210102094009/https://www.scribbr.com/citing-sources/et-al/IN', 'X-RL': '0', 'X-Page-Cache': 'MISS', 'X-Archive-Screenname': '0', 'Content-Encoding': 'gzip'}
|
||||
"""
|
||||
|
||||
archive = waybackpy._archive_url_parser(
|
||||
perfect_header, "https://www.scribbr.com/citing-sources/et-al/"
|
||||
)
|
||||
assert "web.archive.org/web/20210102094009" in archive
|
||||
|
||||
header = """
|
||||
vhgvkjv
|
||||
Content-Location: /web/20201126185327/https://www.scribbr.com/citing-sources/et-al
|
||||
ghvjkbjmmcmhj
|
||||
"""
|
||||
archive = waybackpy._archive_url_parser(
|
||||
header, "https://www.scribbr.com/citing-sources/et-al/"
|
||||
)
|
||||
assert "20201126185327" in archive
|
||||
|
||||
header = """
|
||||
hfjkfjfcjhmghmvjm
|
||||
X-Cache-Key: https://web.archive.org/web/20171128185327/https://www.scribbr.com/citing-sources/et-al/US
|
||||
yfu,u,gikgkikik
|
||||
"""
|
||||
archive = waybackpy._archive_url_parser(
|
||||
header, "https://www.scribbr.com/citing-sources/et-al/"
|
||||
)
|
||||
assert "20171128185327" in archive
|
||||
|
||||
# The below header should result in Exception
|
||||
no_archive_header = """
|
||||
{'Server': 'nginx/1.15.8', 'Date': 'Sat, 02 Jan 2021 09:42:45 GMT', 'Content-Type': 'text/html; charset=utf-8', 'Transfer-Encoding': 'chunked', 'Connection': 'keep-alive', 'Cache-Control': 'no-cache', 'X-App-Server': 'wwwb-app52', 'X-ts': '523', 'X-RL': '0', 'X-Page-Cache': 'MISS', 'X-Archive-Screenname': '0'}
|
||||
"""
|
||||
|
||||
with pytest.raises(Exception):
|
||||
waybackpy._archive_url_parser(
|
||||
no_archive_header, "https://www.scribbr.com/citing-sources/et-al/"
|
||||
)
|
||||
Url(broken_url, user_agent)
|
||||
|
||||
|
||||
def test_save():
|
||||
@ -90,15 +22,14 @@ def test_save():
|
||||
|
||||
url_list = [
|
||||
"en.wikipedia.org",
|
||||
"www.wikidata.org",
|
||||
"commons.wikimedia.org",
|
||||
"akamhy.github.io",
|
||||
"www.wiktionary.org",
|
||||
"www.w3schools.com",
|
||||
"www.ibm.com",
|
||||
"youtube.com",
|
||||
]
|
||||
x = random.randint(0, len(url_list) - 1)
|
||||
url1 = url_list[x]
|
||||
target = waybackpy.Url(
|
||||
target = Url(
|
||||
url1,
|
||||
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.36 "
|
||||
"(KHTML, like Gecko) Chrome/36.0.1944.0 Safari/537.36",
|
||||
@ -109,11 +40,11 @@ def test_save():
|
||||
# Test for urls that are incorrect.
|
||||
with pytest.raises(Exception):
|
||||
url2 = "ha ha ha ha"
|
||||
waybackpy.Url(url2, user_agent)
|
||||
Url(url2, user_agent)
|
||||
url3 = "http://www.archive.is/faq.html"
|
||||
|
||||
with pytest.raises(Exception):
|
||||
target = waybackpy.Url(
|
||||
target = Url(
|
||||
url3,
|
||||
"Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) "
|
||||
"AppleWebKit/533.20.25 (KHTML, like Gecko) Version/5.0.4 "
|
||||
@ -124,7 +55,7 @@ def test_save():
|
||||
|
||||
def test_near():
|
||||
url = "google.com"
|
||||
target = waybackpy.Url(
|
||||
target = Url(
|
||||
url,
|
||||
"Mozilla/5.0 (Windows; U; Windows NT 6.0; de-DE) AppleWebKit/533.20.25 "
|
||||
"(KHTML, like Gecko) Version/5.0.3 Safari/533.19.4",
|
||||
@ -139,7 +70,7 @@ def test_near():
|
||||
or ("2015-03" in archive_near_month_year)
|
||||
)
|
||||
|
||||
target = waybackpy.Url(
|
||||
target = Url(
|
||||
"www.python.org",
|
||||
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 "
|
||||
"(KHTML, like Gecko) Chrome/42.0.2311.135 Safari/537.36 Edge/12.246",
|
||||
@ -157,13 +88,13 @@ def test_near():
|
||||
NeverArchivedUrl = (
|
||||
"https://ee_3n.wrihkeipef4edia.org/rwti5r_ki/Nertr6w_rork_rse7c_urity"
|
||||
)
|
||||
target = waybackpy.Url(NeverArchivedUrl, user_agent)
|
||||
target = Url(NeverArchivedUrl, user_agent)
|
||||
target.near(year=2010)
|
||||
|
||||
|
||||
def test_oldest():
|
||||
url = "github.com/akamhy/waybackpy"
|
||||
target = waybackpy.Url(url, user_agent)
|
||||
target = Url(url, user_agent)
|
||||
o = target.oldest()
|
||||
assert "20200504141153" in str(o)
|
||||
assert "2020-05-04" in str(o._timestamp)
|
||||
@ -171,50 +102,35 @@ def test_oldest():
|
||||
|
||||
def test_json():
|
||||
url = "github.com/akamhy/waybackpy"
|
||||
target = waybackpy.Url(url, user_agent)
|
||||
target = Url(url, user_agent)
|
||||
assert "archived_snapshots" in str(target.JSON)
|
||||
|
||||
|
||||
def test_archive_url():
|
||||
url = "github.com/akamhy/waybackpy"
|
||||
target = waybackpy.Url(url, user_agent)
|
||||
target = Url(url, user_agent)
|
||||
assert "github.com/akamhy" in str(target.archive_url)
|
||||
|
||||
|
||||
def test_newest():
|
||||
url = "github.com/akamhy/waybackpy"
|
||||
target = waybackpy.Url(url, user_agent)
|
||||
target = Url(url, user_agent)
|
||||
assert url in str(target.newest())
|
||||
|
||||
|
||||
def test_get():
|
||||
target = waybackpy.Url("google.com", user_agent)
|
||||
target = Url("google.com", user_agent)
|
||||
assert "Welcome to Google" in target.get(target.oldest())
|
||||
|
||||
|
||||
def test_wayback_timestamp():
|
||||
ts = waybackpy._wayback_timestamp(year=2020, month=1, day=2, hour=3, minute=4)
|
||||
assert "202001020304" in str(ts)
|
||||
|
||||
|
||||
def test_get_response():
|
||||
endpoint = "https://www.google.com"
|
||||
user_agent = (
|
||||
"Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:78.0) Gecko/20100101 Firefox/78.0"
|
||||
)
|
||||
headers = {"User-Agent": "%s" % user_agent}
|
||||
response = waybackpy._get_response(endpoint, params=None, headers=headers)
|
||||
assert response.status_code == 200
|
||||
|
||||
|
||||
def test_total_archives():
|
||||
user_agent = (
|
||||
"Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:78.0) Gecko/20100101 Firefox/78.0"
|
||||
)
|
||||
target = waybackpy.Url(" https://outlook.com ", user_agent)
|
||||
target = Url(" https://outlook.com ", user_agent)
|
||||
assert target.total_archives() > 80000
|
||||
|
||||
target = waybackpy.Url(
|
||||
target = Url(
|
||||
" https://gaha.e4i3n.m5iai3kip6ied.cima/gahh2718gs/ahkst63t7gad8 ", user_agent
|
||||
)
|
||||
assert target.total_archives() == 0
|
||||
@ -222,8 +138,8 @@ def test_total_archives():
|
||||
|
||||
def test_known_urls():
|
||||
|
||||
target = waybackpy.Url("akamhy.github.io", user_agent)
|
||||
target = Url("akamhy.github.io", user_agent)
|
||||
assert len(target.known_urls(alive=True, subdomain=False)) > 2
|
||||
|
||||
target = waybackpy.Url("akamhy.github.io", user_agent)
|
||||
target = Url("akamhy.github.io", user_agent)
|
||||
assert len(target.known_urls()) > 3
|
||||
|
||||
Reference in New Issue
Block a user