Benjamin_Loison/waybackpy
1
0
Fork 0
Code Issues 1 Pull Requests Packages Projects Releases Wiki Activity

Create separate module for the 3 different APIs also CDX is now CLI supported.

Browse Source
This commit is contained in:
Akash Mahanty
2022-01-02 14:14:45 +05:30
parent a7b805292d
commit 4e68cd5743
25 changed files with 755 additions and 2337 deletions
Download Patch File Download Diff File Expand all files Collapse all files

0
tests/__init__.py
View File

93
tests/test_cdx.py
View File

@@ -1,93 +0,0 @@
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 > 30529: # 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 > 100529:
break

359
tests/test_cli.py
View File

@@ -1,359 +0,0 @@
import sys
import os
import pytest
import random
import string
import argparse
import waybackpy.cli as cli
from waybackpy.wrapper import Url # noqa: E402
from waybackpy.__version__ import __version__
def test_save():
args = argparse.Namespace(
user_agent=None,
url="https://hfjfjfjfyu6r6rfjvj.fjhgjhfjgvjm",
total=False,
version=False,
file=False,
oldest=False,
save=True,
json=False,
archive_url=False,
newest=False,
near=False,
subdomain=False,
known_urls=False,
get=None,
)
reply = cli.args_handler(args)
assert "could happen because either your waybackpy" or "cannot be archived by wayback machine as it is a redirect" in str(reply)
def test_json():
args = argparse.Namespace(
user_agent=None,
url="https://pypi.org/user/akamhy/",
total=False,
version=False,
file=False,
oldest=False,
save=False,
json=True,
archive_url=False,
newest=False,
near=False,
subdomain=False,
known_urls=False,
get=None,
)
reply = cli.args_handler(args)
assert "archived_snapshots" in str(reply)
def test_archive_url():
args = argparse.Namespace(
user_agent=None,
url="https://pypi.org/user/akamhy/",
total=False,
version=False,
file=False,
oldest=False,
save=False,
json=False,
archive_url=True,
newest=False,
near=False,
subdomain=False,
known_urls=False,
get=None,
)
reply = cli.args_handler(args)
assert "https://web.archive.org/web/" in str(reply)
def test_oldest():
args = argparse.Namespace(
user_agent=None,
url="https://pypi.org/user/akamhy/",
total=False,
version=False,
file=False,
oldest=True,
save=False,
json=False,
archive_url=False,
newest=False,
near=False,
subdomain=False,
known_urls=False,
get=None,
)
reply = cli.args_handler(args)
assert "pypi.org/user/akamhy" in str(reply)
uid = "".join(
random.choice(string.ascii_lowercase + string.digits) for _ in range(6)
)
url = "https://pypi.org/yfvjvycyc667r67ed67r" + uid
args = argparse.Namespace(
user_agent=None,
url=url,
total=False,
version=False,
file=False,
oldest=True,
save=False,
json=False,
archive_url=False,
newest=False,
near=False,
subdomain=False,
known_urls=False,
get=None,
)
reply = cli.args_handler(args)
assert "Can not find archive for" in str(reply)
def test_newest():
args = argparse.Namespace(
user_agent="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/600.8.9 \
(KHTML, like Gecko) Version/8.0.8 Safari/600.8.9",
url="https://pypi.org/user/akamhy/",
total=False,
version=False,
file=False,
oldest=False,
save=False,
json=False,
archive_url=False,
newest=True,
near=False,
subdomain=False,
known_urls=False,
get=None,
)
reply = cli.args_handler(args)
assert "pypi.org/user/akamhy" in str(reply)
uid = "".join(
random.choice(string.ascii_lowercase + string.digits) for _ in range(6)
)
url = "https://pypi.org/yfvjvycyc667r67ed67r" + uid
args = argparse.Namespace(
user_agent=None,
url=url,
total=False,
version=False,
file=False,
oldest=False,
save=False,
json=False,
archive_url=False,
newest=True,
near=False,
subdomain=False,
known_urls=False,
get=None,
)
reply = cli.args_handler(args)
assert "Can not find archive for" in str(reply)
def test_total_archives():
args = argparse.Namespace(
user_agent="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/600.8.9 \
(KHTML, like Gecko) Version/8.0.8 Safari/600.8.9",
url="https://pypi.org/user/akamhy/",
total=True,
version=False,
file=False,
oldest=False,
save=False,
json=False,
archive_url=False,
newest=False,
near=False,
subdomain=False,
known_urls=False,
get=None,
)
reply = cli.args_handler(args)
assert isinstance(reply, int)
def test_known_urls():
args = argparse.Namespace(
user_agent="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/600.8.9 \
(KHTML, like Gecko) Version/8.0.8 Safari/600.8.9",
url="https://www.keybr.com",
total=False,
version=False,
file=True,
oldest=False,
save=False,
json=False,
archive_url=False,
newest=False,
near=False,
subdomain=False,
known_urls=True,
get=None,
)
reply = cli.args_handler(args)
assert "keybr" in str(reply)
def test_near():
args = argparse.Namespace(
user_agent="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/600.8.9 \
(KHTML, like Gecko) Version/8.0.8 Safari/600.8.9",
url="https://pypi.org/user/akamhy/",
total=False,
version=False,
file=False,
oldest=False,
save=False,
json=False,
archive_url=False,
newest=False,
near=True,
subdomain=False,
known_urls=False,
get=None,
year=2020,
month=7,
day=15,
hour=1,
minute=1,
)
reply = cli.args_handler(args)
assert "202007" in str(reply)
uid = "".join(
random.choice(string.ascii_lowercase + string.digits) for _ in range(6)
)
url = "https://pypi.org/yfvjvycyc667r67ed67r" + uid
args = argparse.Namespace(
user_agent=None,
url=url,
total=False,
version=False,
file=False,
oldest=False,
save=False,
json=False,
archive_url=False,
newest=False,
near=True,
subdomain=False,
known_urls=False,
get=None,
year=2020,
month=7,
day=15,
hour=1,
minute=1,
)
reply = cli.args_handler(args)
assert "Can not find archive for" in str(reply)
def test_get():
args = argparse.Namespace(
user_agent="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/600.8.9 \
(KHTML, like Gecko) Version/8.0.8 Safari/600.8.9",
url="https://github.com/akamhy",
total=False,
version=False,
file=False,
oldest=False,
save=False,
json=False,
archive_url=False,
newest=False,
near=False,
subdomain=False,
known_urls=False,
get="url",
)
reply = cli.args_handler(args)
assert "waybackpy" in str(reply)
args = argparse.Namespace(
user_agent="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/600.8.9 \
(KHTML, like Gecko) Version/8.0.8 Safari/600.8.9",
url="https://github.com/akamhy/waybackpy",
total=False,
version=False,
file=False,
oldest=False,
save=False,
json=False,
archive_url=False,
newest=False,
near=False,
subdomain=False,
known_urls=False,
get="oldest",
)
reply = cli.args_handler(args)
assert "waybackpy" in str(reply)
args = argparse.Namespace(
user_agent="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/600.8.9 \
(KHTML, like Gecko) Version/8.0.8 Safari/600.8.9",
url="https://akamhy.github.io/waybackpy/",
total=False,
version=False,
file=False,
oldest=False,
save=False,
json=False,
archive_url=False,
newest=False,
near=False,
subdomain=False,
known_urls=False,
get="newest",
)
reply = cli.args_handler(args)
assert "waybackpy" in str(reply)
args = argparse.Namespace(
user_agent="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/600.8.9 \
(KHTML, like Gecko) Version/8.0.8 Safari/600.8.9",
url="https://pypi.org/user/akamhy/",
total=False,
version=False,
file=False,
oldest=False,
save=False,
json=False,
archive_url=False,
newest=False,
near=False,
subdomain=False,
known_urls=False,
get="foobar",
)
reply = cli.args_handler(args)
assert "get the source code of the" in str(reply)
def test_args_handler():
args = argparse.Namespace(version=True)
reply = cli.args_handler(args)
assert ("waybackpy version %s" % (__version__)) == reply
args = argparse.Namespace(url=None, version=False)
reply = cli.args_handler(args)
assert ("waybackpy %s" % (__version__)) in str(reply)
def test_main():
# This also tests the parse_args method in cli.py
cli.main(["temp.py", "--version"])

40
tests/test_snapshot.py
View File

@@ -1,40 +0,0 @@
import pytest
from waybackpy.snapshot import CdxSnapshot, datetime
def test_CdxSnapshot():
sample_input = "org,archive)/ 20080126045828 http://github.com text/html 200 Q4YULN754FHV2U6Q5JUT6Q2P57WEWNNY 1415"
prop_values = sample_input.split(" ")
properties = {}
(
properties["urlkey"],
properties["timestamp"],
properties["original"],
properties["mimetype"],
properties["statuscode"],
properties["digest"],
properties["length"],
) = prop_values
snapshot = CdxSnapshot(properties)
assert properties["urlkey"] == snapshot.urlkey
assert properties["timestamp"] == snapshot.timestamp
assert properties["original"] == snapshot.original
assert properties["mimetype"] == snapshot.mimetype
assert properties["statuscode"] == snapshot.statuscode
assert properties["digest"] == snapshot.digest
assert properties["length"] == snapshot.length
assert (
datetime.strptime(properties["timestamp"], "%Y%m%d%H%M%S")
== snapshot.datetime_timestamp
)
archive_url = (
"https://web.archive.org/web/"
+ properties["timestamp"]
+ "/"
+ properties["original"]
)
assert archive_url == snapshot.archive_url
assert sample_input == str(snapshot)

186
tests/test_utils.py
View File

@@ -1,186 +0,0 @@
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,
_timestamp_manager,
)
def test_timestamp_manager():
timestamp = True
data = {}
assert _timestamp_manager(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)
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 _check_match_type(None, "url") is None
match_type = "exact"
url = "test_url"
assert _check_match_type(match_type, url) is None
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 _url_check(good_url) is None
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

28
tests/test_wrapper.py
View File

@@ -1,28 +0,0 @@
import pytest
from waybackpy.wrapper import Url
user_agent = "Mozilla/5.0 (Windows NT 6.2; rv:20.0) Gecko/20121202 Firefox/20.0"
def test_url_check():
"""No API Use"""
broken_url = "http://wwwgooglecom/"
with pytest.raises(Exception):
Url(broken_url, user_agent)
def test_near():
with pytest.raises(Exception):
NeverArchivedUrl = (
"https://ee_3n.wrihkeipef4edia.org/rwti5r_ki/Nertr6w_rork_rse7c_urity"
)
target = Url(NeverArchivedUrl, user_agent)
target.near(year=2010)
def test_json():
url = "github.com/akamhy/waybackpy"
target = Url(url, user_agent)
assert "archived_snapshots" in str(target.JSON)