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

Code style improvements (#20)

Browse Source 
* Add sane line length to setup.cfg

* Use Black for quick readability improvements

* Clean up exceptions, docstrings, and comments

Docstrings on dunder functions are redundant and typically ignored
Limit to reasonable line length
General grammar and style corrections
Clarify docstrings and exceptions
Format docstrings per PEP 257 -- Docstring Conventions

* Move archive_url_parser out of Url.save()

It's generally poor form to define a function in a function, as it will
be re-defined each time the function is run.

archive_url_parser does not depend on anything in Url, so it makes sense
to move it out of the class.

* move wayback_timestamp out of class, mark private functions

* DRY in _wayback_timestamp

* Url._url_check should return None

There's no point in returning True if it's never checked and won't ever
be False.
Implicitly returning None or raising an exception is more idiomatic.

* Default parameters should be type-consistant with expected values

* Specify parameters to near

* Use datetime.datetime in _wayback_timestamp

* cleanup __init__.py

* Cleanup formatting in tests

* Fix names in tests

* Revert "Use datetime.datetime in _wayback_timestamp"

This reverts commit 5b30380865.

Introduced unnecessary complexity

* Move _get_response outside of Url

Because Codacy reminded me that I missed it.

* fix imports in tests
This commit is contained in:
AntiCompositeNumber 2020-07-22 00:39:14 -04:00 committed by GitHub
parent a418a4e464
commit be7642c837
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 208 additions and 124 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
setup.cfg
View File

@ -1,3 +1,7 @@
[metadata]
description-file = README.md
license_file = LICENSE
[flake8]
max-line-length = 88
extend-ignore = E203,W503

115
tests/test_1.py
View File

@ -1,30 +1,35 @@
# -*- coding: utf-8 -*-
import sys
sys.path.append("..")
import waybackpy
import pytest
import random
import time
sys.path.append("..")
import waybackpy.wrapper as waybackpy # noqa: E402
if sys.version_info >= (3, 0): # If the python ver >= 3
from urllib.request import Request, urlopen
from urllib.error import URLError
else: # For python2.x
else: # For python2.x
from urllib2 import Request, urlopen, URLError
user_agent = "Mozilla/5.0 (Windows NT 6.2; rv:20.0) Gecko/20121202 Firefox/20.0"
def test_clean_url():
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.clean_url()
test_result = target._clean_url()
assert answer == test_result
def test_url_check():
broken_url = "http://wwwgooglecom/"
with pytest.raises(Exception) as e_info:
with pytest.raises(Exception):
waybackpy.Url(broken_url, user_agent)
def test_save():
# Test for urls that exist and can be archived.
time.sleep(10)
@ -35,89 +40,139 @@ def test_save():
"commons.wikimedia.org",
"www.wiktionary.org",
"www.w3schools.com",
"www.youtube.com"
"www.youtube.com",
]
x = random.randint(0, len(url_list)-1)
x = random.randint(0, len(url_list) - 1)
url1 = url_list[x]
target = waybackpy.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")
target = waybackpy.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",
)
archived_url1 = target.save()
assert url1 in archived_url1
if sys.version_info > (3, 6):
# Test for urls that are incorrect.
with pytest.raises(Exception) as e_info:
with pytest.raises(Exception):
url2 = "ha ha ha ha"
waybackpy.Url(url2, user_agent)
time.sleep(5)
# Test for urls not allowed to archive by robot.txt.
with pytest.raises(Exception) as e_info:
with pytest.raises(Exception):
url3 = "http://www.archive.is/faq.html"
target = waybackpy.Url(url3, "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:25.0) Gecko/20100101 Firefox/25.0")
target = waybackpy.Url(
url3,
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:25.0) "
"Gecko/20100101 Firefox/25.0",
)
target.save()
time.sleep(5)
# Non existent urls, test
with pytest.raises(Exception) as e_info:
url4 = "https://githfgdhshajagjstgeths537agajaajgsagudadhuss8762346887adsiugujsdgahub.us"
target = waybackpy.Url(url3, "Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/533.20.25 (KHTML, like Gecko) Version/5.0.4 Safari/533.20.27")
with pytest.raises(Exception):
url4 = (
"https://githfgdhshajagjstgeths537agajaajgsagudadhuss87623"
"46887adsiugujsdgahub.us"
)
target = waybackpy.Url(
url3,
"Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) "
"AppleWebKit/533.20.25 (KHTML, like Gecko) Version/5.0.4 "
"Safari/533.20.27",
)
target.save()
else:
pass
def test_near():
time.sleep(10)
url = "google.com"
target = waybackpy.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")
target = waybackpy.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",
)
archive_near_year = target.near(year=2010)
assert "2010" in archive_near_year
if sys.version_info > (3, 6):
time.sleep(5)
archive_near_month_year = target.near( year=2015, month=2)
assert ("201502" in archive_near_month_year) or ("201501" in archive_near_month_year) or ("201503" in archive_near_month_year)
target = waybackpy.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")
archive_near_hour_day_month_year = target.near(year=2008, month=5, day=9, hour=15)
assert ("2008050915" in archive_near_hour_day_month_year) or ("2008050914" in archive_near_hour_day_month_year) or ("2008050913" in archive_near_hour_day_month_year)
with pytest.raises(Exception) as e_info:
NeverArchivedUrl = "https://ee_3n.wrihkeipef4edia.org/rwti5r_ki/Nertr6w_rork_rse7c_urity"
archive_near_month_year = target.near(year=2015, month=2)
assert (
("201502" in archive_near_month_year)
or ("201501" in archive_near_month_year)
or ("201503" in archive_near_month_year)
)
target = waybackpy.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",
)
archive_near_hour_day_month_year = target.near(
year=2008, month=5, day=9, hour=15
)
assert (
("2008050915" in archive_near_hour_day_month_year)
or ("2008050914" in archive_near_hour_day_month_year)
or ("2008050913" in archive_near_hour_day_month_year)
)
with pytest.raises(Exception):
NeverArchivedUrl = (
"https://ee_3n.wrihkeipef4edia.org/rwti5r_ki/Nertr6w_rork_rse7c_urity"
)
target = waybackpy.Url(NeverArchivedUrl, user_agent)
target.near(year=2010)
else:
pass
def test_oldest():
url = "github.com/akamhy/waybackpy"
target = waybackpy.Url(url, user_agent)
assert "20200504141153" in target.oldest()
def test_newest():
url = "github.com/akamhy/waybackpy"
target = waybackpy.Url(url, user_agent)
assert url in target.newest()
def test_get():
target = waybackpy.Url("google.com", user_agent)
assert "Welcome to Google" in target.get(target.oldest())
assert "Welcome to Google" in target._get(target.oldest())
def test_wayback_timestamp():
ts = waybackpy.Url("https://www.google.com","UA").wayback_timestamp(year=2020,month=1,day=2,hour=3,minute=4)
ts = waybackpy._wayback_timestamp(
year=2020, month=1, day=2, hour=3, minute=4
)
assert "202001020304" in str(ts)
def test_get_response():
hdr = { 'User-Agent' : 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:78.0) Gecko/20100101 Firefox/78.0'}
req = Request("https://www.google.com", headers=hdr) # nosec
response = waybackpy.Url("https://www.google.com","UA").get_response(req)
hdr = {
"User-Agent": "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:78.0) "
"Gecko/20100101 Firefox/78.0"
}
req = Request("https://www.google.com", headers=hdr) # nosec
response = waybackpy._get_response(req)
assert response.code == 200
def test_total_archives():
if sys.version_info > (3, 6):
target = waybackpy.Url(" https://google.com ", user_agent)
assert target.total_archives() > 500000
else:
pass
target = waybackpy.Url(" https://gaha.e4i3n.m5iai3kip6ied.cima/gahh2718gs/ahkst63t7gad8 ", user_agent)
target = waybackpy.Url(
" https://gaha.e4i3n.m5iai3kip6ied.cima/gahh2718gs/ahkst63t7gad8 ", user_agent
)
assert target.total_archives() == 0

12
waybackpy/__init__.py
View File

@ -28,5 +28,13 @@ Full documentation @ <https://akamhy.github.io/waybackpy/>.
"""
from .wrapper import Url
from .__version__ import __title__, __description__, __url__, __version__
from .__version__ import __author__, __author_email__, __license__, __copyright__
from .__version__ import (
__title__,
__description__,
__url__,
__version__,
__author__,
__author_email__,
__license__,
__copyright__,
)

201
waybackpy/wrapper.py
View File

@ -5,147 +5,164 @@ import sys
import json
from datetime import datetime
from waybackpy.exceptions import WaybackError
from waybackpy.__version__ import __version__
if sys.version_info >= (3, 0): # If the python ver >= 3
from urllib.request import Request, urlopen
from urllib.error import URLError
else: # For python2.x
else: # For python2.x
from urllib2 import Request, urlopen, URLError
default_UA = "waybackpy python package - https://github.com/akamhy/waybackpy"
class Url():
"""waybackpy Url object"""
def _archive_url_parser(header):
"""Parse out the archive from header."""
# Regex1
arch = re.search(
r"rel=\"memento.*?(web\.archive\.org/web/[0-9]{14}/.*?)>", str(header)
)
if arch:
return arch.group(1)
# Regex2
arch = re.search(r"X-Cache-Key:\shttps(.*)[A-Z]{2}", str(header))
if arch:
return arch.group(1)
raise WaybackError(
"No archive URL found in the API response. "
"This version of waybackpy (%s) is likely out of date. Visit "
"https://github.com/akamhy/waybackpy for the latest version "
"of waybackpy.\nHeader:\n%s" % (__version__, str(header))
)
def _wayback_timestamp(**kwargs):
"""Return a formatted timestamp."""
return "".join(
str(kwargs[key]).zfill(2) for key in ["year", "month", "day", "hour", "minute"]
)
def _get_response(req):
"""Get response for the supplied request."""
try:
response = urlopen(req) # nosec
except Exception:
try:
response = urlopen(req) # nosec
except Exception as e:
raise WaybackError(e)
return response
class Url:
"""waybackpy Url object"""
def __init__(self, url, user_agent=default_UA):
self.url = url
self.user_agent = user_agent
self.url_check() # checks url validity on init.
self._url_check() # checks url validity on init.
def __repr__(self):
"""Representation of the object."""
return "waybackpy.Url(url=%s, user_agent=%s)" % (self.url, self.user_agent)
def __str__(self):
"""String representation of the object."""
return "%s" % self.clean_url()
return "%s" % self._clean_url()
def __len__(self):
"""Length of the URL."""
return len(self.clean_url())
return len(self._clean_url())
def url_check(self):
def _url_check(self):
"""Check for common URL problems."""
if "." not in self.url:
raise URLError("'%s' is not a vaild url." % self.url)
return True
raise URLError("'%s' is not a vaild URL." % self.url)
def clean_url(self):
def _clean_url(self):
"""Fix the URL, if possible."""
return str(self.url).strip().replace(" ","_")
def wayback_timestamp(self, **kwargs):
"""Return the formatted the timestamp."""
return (
str(kwargs["year"])
+
str(kwargs["month"]).zfill(2)
+
str(kwargs["day"]).zfill(2)
+
str(kwargs["hour"]).zfill(2)
+
str(kwargs["minute"]).zfill(2)
)
return str(self.url).strip().replace(" ", "_")
def save(self):
"""Create a new archives for an URL on the Wayback Machine."""
request_url = ("https://web.archive.org/save/" + self.clean_url())
hdr = { 'User-Agent' : '%s' % self.user_agent } #nosec
req = Request(request_url, headers=hdr) #nosec
header = self.get_response(req).headers
def archive_url_parser(header):
"""Parse out the archive from header."""
#Regex1
arch = re.search(r"rel=\"memento.*?(web\.archive\.org/web/[0-9]{14}/.*?)>", str(header))
if arch:
return arch.group(1)
#Regex2
arch = re.search(r"X-Cache-Key:\shttps(.*)[A-Z]{2}", str(header))
if arch:
return arch.group(1)
raise WaybackError(
"No archive url found in the API response. Visit https://github.com/akamhy/waybackpy for latest version of waybackpy.\nHeader:\n%s" % str(header)
)
return "https://" + archive_url_parser(header)
def get(self, url=None, user_agent=None, encoding=None):
"""Returns the source code of the supplied URL. Auto detects the encoding if not supplied."""
"""Create a new Wayback Machine archive for this URL."""
request_url = "https://web.archive.org/save/" + self._clean_url()
hdr = {"User-Agent": "%s" % self.user_agent} # nosec
req = Request(request_url, headers=hdr) # nosec
header = _get_response(req).headers
return "https://" + _archive_url_parser(header)
def _get(self, url="", user_agent="", encoding=""):
"""Return the source code of the supplied URL.
If encoding is not supplied, it is auto-detected from the response.
"""
if not url:
url = self.clean_url()
url = self._clean_url()
if not user_agent:
user_agent = self.user_agent
hdr = { 'User-Agent' : '%s' % user_agent }
req = Request(url, headers=hdr) #nosec
response = self.get_response(req)
hdr = {"User-Agent": "%s" % user_agent}
req = Request(url, headers=hdr) # nosec
response = _get_response(req)
if not encoding:
try:
encoding= response.headers['content-type'].split('charset=')[-1]
encoding = response.headers["content-type"].split("charset=")[-1]
except AttributeError:
encoding = "UTF-8"
return response.read().decode(encoding.replace("text/html", "UTF-8", 1))
def get_response(self, req):
"""Get response for the supplied request."""
try:
response = urlopen(req) #nosec
except Exception:
try:
response = urlopen(req) #nosec
except Exception as e:
raise WaybackError(e)
return response
def near(self, year=None, month=None, day=None, hour=None, minute=None):
"""Return the closest Wayback Machine archive to the time supplied.
def near(self, **kwargs):
""" Returns the archived from Wayback Machine for an URL closest to the time supplied.
Supported params are year, month, day, hour and minute.
The non supplied parameters are default to the runtime time.
Supported params are year, month, day, hour and minute.
Any non-supplied parameters default to the current time.
"""
year=kwargs.get("year", datetime.utcnow().strftime('%Y'))
month=kwargs.get("month", datetime.utcnow().strftime('%m'))
day=kwargs.get("day", datetime.utcnow().strftime('%d'))
hour=kwargs.get("hour", datetime.utcnow().strftime('%H'))
minute=kwargs.get("minute", datetime.utcnow().strftime('%M'))
timestamp = self.wayback_timestamp(year=year,month=month,day=day,hour=hour,minute=minute)
request_url = "https://archive.org/wayback/available?url=%s&timestamp=%s" % (self.clean_url(), str(timestamp))
hdr = { 'User-Agent' : '%s' % self.user_agent }
req = Request(request_url, headers=hdr) # nosec
response = self.get_response(req)
now = datetime.utcnow().timetuple()
timestamp = _wayback_timestamp(
year=year if year else now.tm_year,
month=month if month else now.tm_mon,
day=day if day else now.tm_mday,
hour=hour if hour else now.tm_hour,
minute=minute if minute else now.tm_min,
)
request_url = "https://archive.org/wayback/available?url=%s&timestamp=%s" % (
self._clean_url(),
timestamp,
)
hdr = {"User-Agent": "%s" % self.user_agent}
req = Request(request_url, headers=hdr) # nosec
response = _get_response(req)
data = json.loads(response.read().decode("UTF-8"))
if not data["archived_snapshots"]:
raise WaybackError("'%s' is not yet archived. Use wayback.Url(url, user_agent).save() to create a new archive." % self.clean_url())
archive_url = (data["archived_snapshots"]["closest"]["url"])
raise WaybackError(
"'%s' is not yet archived. Use wayback.Url(url, user_agent).save() "
"to create a new archive." % self._clean_url()
)
archive_url = data["archived_snapshots"]["closest"]["url"]
# wayback machine returns http sometimes, idk why? But they support https
archive_url = archive_url.replace("http://web.archive.org/web/","https://web.archive.org/web/",1)
archive_url = archive_url.replace(
"http://web.archive.org/web/", "https://web.archive.org/web/", 1
)
return archive_url
def oldest(self, year=1994):
"""Returns the oldest archive from Wayback Machine for an URL."""
"""Return the oldest Wayback Machine archive for this URL."""
return self.near(year=year)
def newest(self):
"""Returns the newest archive on Wayback Machine for an URL, sometimes you may not get the newest archive because wayback machine DB lag."""
"""Return the newest Wayback Machine archive available for this URL.
Due to Wayback Machine database lag, this may not always be the
most recent archive.
"""
return self.near()
def total_archives(self):
"""Returns the total number of archives on Wayback Machine for an URL."""
hdr = { 'User-Agent' : '%s' % self.user_agent }
request_url = "https://web.archive.org/cdx/search/cdx?url=%s&output=json&fl=statuscode" % self.clean_url()
req = Request(request_url, headers=hdr) # nosec
response = self.get_response(req)
return str(response.read()).count(",") # Most efficient method to count number of archives (yet)
"""Returns the total number of Wayback Machine archives for this URL."""
hdr = {"User-Agent": "%s" % self.user_agent}
request_url = (
"https://web.archive.org/cdx/search/cdx?url=%s&output=json&fl=statuscode"
% self._clean_url()
)
req = Request(request_url, headers=hdr) # nosec
response = _get_response(req)
# Most efficient method to count number of archives (yet)
return str(response.read()).count(",")