Update setup.py

* fix code Complexity

* Update wrapper.py

* codefactor badge

.travis.yml

@@ -0,0 +1,14 @@
+language: python
+python:
+  - "2.7"
+  - "3.6"
+  - "3.8"
+os: linux
+dist: xenial
+cache: pip
+install:
+  - pip install pytest
+before_script:
+    cd tests
+script:
+  - pytest test_1.py

README.md

@@ -1,7 +1,14 @@
 # waybackpy
+[![Build Status](https://travis-ci.org/akamhy/waybackpy.svg?branch=master)](https://travis-ci.org/akamhy/waybackpy)
+[![Downloads](https://img.shields.io/pypi/dm/waybackpy.svg)](https://pypistats.org/packages/waybackpy)
+[![Release](https://img.shields.io/github/v/release/akamhy/waybackpy.svg)](https://github.com/akamhy/waybackpy/releases)
 [![Codacy Badge](https://api.codacy.com/project/badge/Grade/255459cede9341e39436ec8866d3fb65)](https://www.codacy.com/manual/akamhy/waybackpy?utm_source=github.com&utm_medium=referral&utm_content=akamhy/waybackpy&utm_campaign=Badge_Grade)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://github.com/akamhy/waybackpy/blob/master/LICENSE)
+[![Maintainability](https://api.codeclimate.com/v1/badges/942f13d8177a56c1c906/maintainability)](https://codeclimate.com/github/akamhy/waybackpy/maintainability)
+[![CodeFactor](https://www.codefactor.io/repository/github/akamhy/waybackpy/badge)](https://www.codefactor.io/repository/github/akamhy/waybackpy)
 [![made-with-python](https://img.shields.io/badge/Made%20with-Python-1f425f.svg)](https://www.python.org/)
+![pypi](https://img.shields.io/pypi/v/waybackpy.svg)
+![PyPI - Python Version](https://img.shields.io/pypi/pyversions/waybackpy?style=flat-square)
 [![Maintenance](https://img.shields.io/badge/Maintained%3F-yes-green.svg)](https://github.com/akamhy/waybackpy/graphs/commit-activity)
 
 
@@ -15,20 +22,22 @@ Table of contents
 =================
 <!--ts-->
 
-* [Installation](#installation)
+* [Installation](https://github.com/akamhy/waybackpy#installation)
 
-* [Usage](#usage)
-  * [Saving an url using save()](#capturing-aka-saving-an-url-using-save)
-  * [Receiving the oldest archive for an URL Using oldest()](#receiving-the-oldest-archive-for-an-url-using-oldest)
-  * [Receiving the recent most/newest archive for an URL using newest()](#receiving-the-newest-archive-for-an-url-using-newest)
-  * [Receiving archive close to a specified year, month, day, hour, and minute using near()](#receiving-archive-close-to-a-specified-year-month-day-hour-and-minute-using-near)
-  * [Get the content of webpage using get()](#get-the-content-of-webpage-using-get)
+* [Usage](https://github.com/akamhy/waybackpy#usage)
+  * [Saving an url using save()](https://github.com/akamhy/waybackpy#capturing-aka-saving-an-url-using-save)
+  * [Receiving the oldest archive for an URL Using oldest()](https://github.com/akamhy/waybackpy#receiving-the-oldest-archive-for-an-url-using-oldest)
+  * [Receiving the recent most/newest archive for an URL using newest()](https://github.com/akamhy/waybackpy#receiving-the-newest-archive-for-an-url-using-newest)
+  * [Receiving archive close to a specified year, month, day, hour, and minute using near()](https://github.com/akamhy/waybackpy#receiving-archive-close-to-a-specified-year-month-day-hour-and-minute-using-near)
+  * [Get the content of webpage using get()](https://github.com/akamhy/waybackpy#get-the-content-of-webpage-using-get)
+  * [Count total archives for an URL using total_archives()](https://github.com/akamhy/waybackpy#count-total-archives-for-an-url-using-total_archives)
 
-* [Tests](#tests)
 
-* [Dependency](#dependency)
+* [Tests](https://github.com/akamhy/waybackpy#tests)
 
-* [License](#license)
+* [Dependency](https://github.com/akamhy/waybackpy#dependency)
+
+* [License](https://github.com/akamhy/waybackpy#license)
 
 <!--te-->
 
@@ -138,10 +147,30 @@ print(webpage)
 ```
 > This should print the source code for <https://example.com/>.
 
+#### Count total archives for an URL using total_archives()
+
+```diff
++ waybackpy.total_archives(url, UA=user_agent)
+```
+> url is mandatory. UA is not, but highly recommended.
+
+```python
+from waybackpy import total_archives
+# retriving the webpage from any url including the archived urls. Don't need to import other libraies :)
+# Default user-agent (UA) is "waybackpy python package", if not specified in the call.
+# supported argumnets are url and UA
+count = total_archives("https://en.wikipedia.org/wiki/Python (programming language)", UA="User-Agent")
+print(count)
+```
+> This should print an integer (int), which is the number of total archives on archive.org
+
+## Tests
+* [Here](https://github.com/akamhy/waybackpy/tree/master/tests)
+
 ## Dependency
-* None, just python standard libraries. Both python 2 and 3 are supported :)
+* None, just python standard libraries (json, urllib and datetime). Both python 2 and 3 are supported :)
 
 
 ## License
 
-[MIT License](LICENSE)
+[MIT License](https://github.com/akamhy/waybackpy/blob/master/LICENSE)

_config.yml

@@ -0,0 +1 @@
+theme: jekyll-theme-cayman

index.rst

@@ -0,0 +1,232 @@
+waybackpy
+=========
+
+|Build Status| |Downloads| |Release| |Codacy Badge| |License: MIT|
+|Maintainability| |CodeFactor| |made-with-python| |pypi| |PyPI - Python
+Version| |Maintenance|
+
+.. |Build Status| image:: https://travis-ci.org/akamhy/waybackpy.svg?branch=master
+   :target: https://travis-ci.org/akamhy/waybackpy
+.. |Downloads| image:: https://img.shields.io/pypi/dm/waybackpy.svg
+   :target: https://pypistats.org/packages/waybackpy
+.. |Release| image:: https://img.shields.io/github/v/release/akamhy/waybackpy.svg
+   :target: https://github.com/akamhy/waybackpy/releases
+.. |Codacy Badge| image:: https://api.codacy.com/project/badge/Grade/255459cede9341e39436ec8866d3fb65
+   :target: https://www.codacy.com/manual/akamhy/waybackpy?utm_source=github.com&utm_medium=referral&utm_content=akamhy/waybackpy&utm_campaign=Badge_Grade
+.. |License: MIT| image:: https://img.shields.io/badge/License-MIT-yellow.svg
+   :target: https://github.com/akamhy/waybackpy/blob/master/LICENSE
+.. |Maintainability| image:: https://api.codeclimate.com/v1/badges/942f13d8177a56c1c906/maintainability
+   :target: https://codeclimate.com/github/akamhy/waybackpy/maintainability
+.. |CodeFactor| image:: https://www.codefactor.io/repository/github/akamhy/waybackpy/badge
+   :target: https://www.codefactor.io/repository/github/akamhy/waybackpy
+.. |made-with-python| image:: https://img.shields.io/badge/Made%20with-Python-1f425f.svg
+   :target: https://www.python.org/
+.. |pypi| image:: https://img.shields.io/pypi/v/waybackpy.svg
+.. |PyPI - Python Version| image:: https://img.shields.io/pypi/pyversions/waybackpy?style=flat-square
+.. |Maintenance| image:: https://img.shields.io/badge/Maintained%3F-yes-green.svg
+   :target: https://github.com/akamhy/waybackpy/graphs/commit-activity
+   
+|Internet Archive| |Wayback Machine|
+
+The waybackpy is a python wrapper for `Internet Archive`_\ ’s `Wayback
+Machine`_.
+
+.. _Internet Archive: https://en.wikipedia.org/wiki/Internet_Archive
+.. _Wayback Machine: https://en.wikipedia.org/wiki/Wayback_Machine
+
+.. |Internet Archive| image:: https://upload.wikimedia.org/wikipedia/commons/thumb/8/84/Internet_Archive_logo_and_wordmark.svg/84px-Internet_Archive_logo_and_wordmark.svg.png
+.. |Wayback Machine| image:: https://upload.wikimedia.org/wikipedia/commons/thumb/0/01/Wayback_Machine_logo_2010.svg/284px-Wayback_Machine_logo_2010.svg.png
+
+Installation
+------------
+
+Using `pip`_:
+
+**pip install waybackpy**
+
+.. _pip: https://en.wikipedia.org/wiki/Pip_(package_manager)
+
+Usage
+-----
+
+Archiving aka Saving an url Using save()
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. code:: diff
+
+   + waybackpy.save(url, UA=user_agent)
+
+..
+
+   url is mandatory. UA is not, but highly recommended.
+
+.. code:: python
+
+   import waybackpy
+   # Capturing a new archive on Wayback machine.
+   # Default user-agent (UA) is "waybackpy python package", if not specified in the call.
+   archived_url = waybackpy.save("https://github.com/akamhy/waybackpy", UA = "Any-User-Agent")
+   print(archived_url)
+
+This should print something similar to the following archived URL:
+
+https://web.archive.org/web/20200504141153/https://github.com/akamhy/waybackpy
+
+Receiving the oldest archive for an URL Using oldest()
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. code:: diff
+
+   + waybackpy.oldest(url, UA=user_agent)
+
+..
+
+   url is mandatory. UA is not, but highly recommended.
+
+.. code:: python
+
+   import waybackpy
+   # retrieving the oldest archive on Wayback machine.
+   # Default user-agent (UA) is "waybackpy python package", if not specified in the call.
+   oldest_archive = waybackpy.oldest("https://www.google.com/", UA = "Any-User-Agent")
+   print(oldest_archive)
+
+This returns the oldest available archive for https://google.com.
+
+http://web.archive.org/web/19981111184551/http://google.com:80/
+
+Receiving the newest archive for an URL using newest()
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. code:: diff
+
+   + waybackpy.newest(url, UA=user_agent)
+
+..
+
+   url is mandatory. UA is not, but highly recommended.
+
+.. code:: python
+
+   import waybackpy
+   # retrieving the newest archive on Wayback machine.
+   # Default user-agent (UA) is "waybackpy python package", if not specified in the call.
+   newest_archive = waybackpy.newest("https://www.microsoft.com/en-us", UA = "Any-User-Agent")
+   print(newest_archive)
+
+This returns the newest available archive for
+https://www.microsoft.com/en-us, something just like this:
+
+http://web.archive.org/web/20200429033402/https://www.microsoft.com/en-us/
+
+Receiving archive close to a specified year, month, day, hour, and minute using near()
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. code:: diff
+
+   + waybackpy.near(url, year=2020, month=1, day=1, hour=1, minute=1, UA=user_agent)
+
+..
+
+   url is mandotory. year,month,day,hour and minute are optional
+   arguments. UA is not mandotory, but higly recomended.
+
+.. code:: python
+
+   import waybackpy
+   # retriving the the closest archive from a specified year.
+   # Default user-agent (UA) is "waybackpy python package", if not specified in the call.
+   # supported argumnets are year,month,day,hour and minute
+   archive_near_year = waybackpy.near("https://www.facebook.com/", year=2010, UA ="Any-User-Agent")
+   print(archive_near_year)
+
+returns :
+http://web.archive.org/web/20100504071154/http://www.facebook.com/
+
+``waybackpy.near("https://www.facebook.com/", year=2010, month=1, UA ="Any-User-Agent")``
+returns:
+http://web.archive.org/web/20101111173430/http://www.facebook.com//
+
+``waybackpy.near("https://www.oracle.com/index.html", year=2019, month=1, day=5, UA ="Any-User-Agent")``
+returns:
+http://web.archive.org/web/20190105054437/https://www.oracle.com/index.html
+> Please note that if you only specify the year, the current month and
+day are default arguments for month and day respectively. Do not expect
+just putting the year parameter would return the archive closer to
+January but the current month you are using the package. If you are
+using it in July 2018 and let’s say you use
+``waybackpy.near("https://www.facebook.com/", year=2011, UA ="Any-User-Agent")``
+then you would be returned the nearest archive to July 2011 and not
+January 2011. You need to specify the month “1” for January.
+
+   Do not pad (don’t use zeros in the month, year, day, minute, and hour
+   arguments). e.g. For January, set month = 1 and not month = 01.
+
+Get the content of webpage using get()
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. code:: diff
+
+   + waybackpy.get(url, encoding="UTF-8", UA=user_agent)
+
+..
+
+   url is mandatory. UA is not, but highly recommended. encoding is
+   detected automatically, don’t specify unless necessary.
+
+.. code:: python
+
+   from waybackpy import get
+   # retriving the webpage from any url including the archived urls. Don't need to import other libraies :)
+   # Default user-agent (UA) is "waybackpy python package", if not specified in the call.
+   # supported argumnets are url, encoding and UA
+   webpage = get("https://example.com/", UA="User-Agent")
+   print(webpage)
+
+..
+
+   This should print the source code for https://example.com/.
+
+Count total archives for an URL using total_archives()
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. code:: diff
+
+   + waybackpy.total_archives(url, UA=user_agent)
+
+..
+
+   url is mandatory. UA is not, but highly recommended.
+
+.. code:: python
+
+   from waybackpy import total_archives
+   # retriving the webpage from any url including the archived urls. Don't need to import other libraies :)
+   # Default user-agent (UA) is "waybackpy python package", if not specified in the call.
+   # supported argumnets are url and UA
+   count = total_archives("https://en.wikipedia.org/wiki/Python (programming language)", UA="User-Agent")
+   print(count)
+
+..
+
+   This should print an integer (int), which is the number of total
+   archives on archive.org
+
+Tests
+-----
+
+-  `Here`_
+
+Dependency
+----------
+
+-  None, just python standard libraries (json, urllib and datetime).
+   Both python 2 and 3 are supported :)
+
+License
+-------
+
+`MIT License`_
+
+.. _Here: https://github.com/akamhy/waybackpy/tree/master/tests
+.. _MIT License: https://github.com/akamhy/waybackpy/blob/master/LICENSE

setup.cfg

@@ -1,2 +1,3 @@
 [metadata]
 description-file = README.md
+license_file = LICENSE

setup.py

@@ -4,29 +4,46 @@ from setuptools import setup
 with open(os.path.join(os.path.dirname(__file__), 'README.md')) as f:
     long_description = f.read()
 
+about = {}
+with open(os.path.join(os.path.dirname(__file__), 'waybackpy', '__version__.py')) as f:
+    exec(f.read(), about)
+    
 setup(
-    name = 'waybackpy',
+    name = about['__title__'],
     packages = ['waybackpy'],
-    version = 'v1.2',
-    description = 'A python wrapper for Internet Archives Wayback Machine',
+    version = about['__version__'],
+    description = about['__description__'],
     long_description=long_description,
     long_description_content_type='text/markdown',
-    license='MIT',
-    author = 'akamhy',
-    author_email = 'akash3pro@gmail.com',
-    url = 'https://github.com/akamhy/waybackpy',
-    download_url = 'https://github.com/akamhy/waybackpy/archive/v1.2.tar.gz',
+    license= about['__license__'],
+    author = about['__author__'],
+    author_email = about['__author_email__'],
+    url = about['__url__'],
+    download_url = 'https://github.com/akamhy/waybackpy/archive/v1.5.tar.gz',
     keywords = ['wayback', 'archive', 'archive website', 'wayback machine', 'Internet Archive'],
     install_requires=[],
-    python_requires='>=3.6',
+    python_requires= ">=2.7",
     classifiers=[
         'Development Status :: 5 - Production/Stable',
-        'Intended Audience :: Developers',  
+        'Intended Audience :: Developers',
+        'Natural Language :: English',
         'Topic :: Software Development :: Build Tools',
         'License :: OSI Approved :: MIT License',
-        'Programming Language :: Python :: 3',      
+        'Programming Language :: Python',
+        'Programming Language :: Python :: 2',
+        'Programming Language :: Python :: 2.7',
+        'Programming Language :: Python :: 3',
+        'Programming Language :: Python :: 3.2',
+        'Programming Language :: Python :: 3.3',
         'Programming Language :: Python :: 3.4',
         'Programming Language :: Python :: 3.5',
         'Programming Language :: Python :: 3.6',
+        'Programming Language :: Python :: 3.7',
+        'Programming Language :: Python :: 3.8',
+        'Programming Language :: Python :: Implementation :: CPython',
         ],
+    project_urls={
+        'Documentation': 'https://waybackpy.readthedocs.io',
+        'Source': 'https://github.com/akamhy/waybackpy',
+    },
 )

tests/test_1.py

@@ -0,0 +1,98 @@
+import sys
+sys.path.append("..")
+import waybackpy
+import pytest
+
+
+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"
+    test_result = waybackpy.clean_url(test_url)
+    assert answer == test_result
+
+def test_url_check():
+    InvalidUrl = "http://wwwgooglecom/"
+    with pytest.raises(Exception) as e_info:
+        waybackpy.url_check(InvalidUrl)
+
+def test_save():
+    # Test for urls that exist and can be archived.
+    url1="https://github.com/akamhy/waybackpy"
+    archived_url1 = waybackpy.save(url1, UA=user_agent)
+    assert url1 in archived_url1
+    
+    # Test for urls that are incorrect.
+    with pytest.raises(Exception) as e_info:
+        url2 = "ha ha ha ha"
+        waybackpy.save(url2, UA=user_agent)
+
+    # Test for urls not allowed to archive by robot.txt.
+    with pytest.raises(Exception) as e_info:
+        url3 = "http://www.archive.is/faq.html"
+        waybackpy.save(url3, UA=user_agent)
+    
+    # Non existent urls, test
+    with pytest.raises(Exception) as e_info:
+        url4 = "https://githfgdhshajagjstgeths537agajaajgsagudadhuss8762346887adsiugujsdgahub.us"
+        archived_url4 = waybackpy.save(url4, UA=user_agent)
+
+def test_near():
+    url = "google.com"
+    archive_near_year = waybackpy.near(url, year=2010, UA=user_agent)
+    assert "2010" in archive_near_year
+
+    archive_near_month_year = waybackpy.near(url, year=2015, month=2, UA=user_agent)
+    assert ("201502" in archive_near_month_year) or ("201501" in archive_near_month_year) or ("201503" in archive_near_month_year)
+
+    archive_near_day_month_year = waybackpy.near(url, year=2006, month=11, day=15, UA=user_agent)
+    assert ("20061114" in archive_near_day_month_year) or ("20061115" in archive_near_day_month_year) or ("2006116" in archive_near_day_month_year)
+
+    archive_near_hour_day_month_year = waybackpy.near("www.python.org", year=2008, month=5, day=9, hour=15, UA=user_agent)
+    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"
+        waybackpy.near(NeverArchivedUrl, year=2010, UA=user_agent)
+
+def test_oldest():
+    url = "github.com/akamhy/waybackpy"
+    archive_oldest = waybackpy.oldest(url, UA=user_agent)
+    assert "20200504141153" in archive_oldest
+
+def test_newest():
+    url = "github.com/akamhy/waybackpy"
+    archive_newest = waybackpy.newest(url, UA=user_agent)
+    assert url in archive_newest
+
+def test_get():
+    oldest_google_archive = waybackpy.oldest("google.com", UA=user_agent)
+    oldest_google_page_text =  waybackpy.get(oldest_google_archive, UA=user_agent)
+    assert "Welcome to Google" in oldest_google_page_text
+
+def test_total_archives():
+
+    count1 = waybackpy.total_archives("https://en.wikipedia.org/wiki/Python (programming language)", UA=user_agent)
+    assert count1 > 2000
+
+    count2 = waybackpy.total_archives("https://gaha.e4i3n.m5iai3kip6ied.cima/gahh2718gs/ahkst63t7gad8", UA=user_agent)
+    assert count2 == 0
+
+if __name__ == "__main__":
+    test_clean_url()
+    print(".")
+    test_url_check()
+    print(".")
+    test_get()
+    print(".")
+    test_near()
+    print(".")
+    test_newest()
+    print(".")
+    test_save()
+    print(".")
+    test_oldest()
+    print(".")
+    test_total_archives()
+    print(".")

waybackpy/__init__.py

@@ -1,6 +1,30 @@
 # -*- coding: utf-8 -*-
-from .wrapper import save, near, oldest, newest, get
 
-__version__ = "v1.2"
+# ┏┓┏┓┏┓━━━━━━━━━━┏━━┓━━━━━━━━━━┏┓━━┏━━━┓━━━━━
+# ┃┃┃┃┃┃━━━━━━━━━━┃┏┓┃━━━━━━━━━━┃┃━━┃┏━┓┃━━━━━
+# ┃┃┃┃┃┃┏━━┓━┏┓━┏┓┃┗┛┗┓┏━━┓━┏━━┓┃┃┏┓┃┗━┛┃┏┓━┏┓
+# ┃┗┛┗┛┃┗━┓┃━┃┃━┃┃┃┏━┓┃┗━┓┃━┃┏━┛┃┗┛┛┃┏━━┛┃┃━┃┃
+# ┗┓┏┓┏┛┃┗┛┗┓┃┗━┛┃┃┗━┛┃┃┗┛┗┓┃┗━┓┃┏┓┓┃┃━━━┃┗━┛┃
+# ━┗┛┗┛━┗━━━┛┗━┓┏┛┗━━━┛┗━━━┛┗━━┛┗┛┗┛┗┛━━━┗━┓┏┛
+# ━━━━━━━━━━━┏━┛┃━━━━━━━━━━━━━━━━━━━━━━━━┏━┛┃━
+# ━━━━━━━━━━━┗━━┛━━━━━━━━━━━━━━━━━━━━━━━━┗━━┛━
 
-__all__ = ['wrapper', 'exceptions']
+"""
+A python wrapper for Internet Archive's Wayback Machine API.
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Archive pages and retrieve archived pages easily.
+Usage:
+   >>> import waybackpy
+   >>> new_archive = waybackpy.save('https://www.python.org')
+   >>> print(new_archive)
+   https://web.archive.org/web/20200502170312/https://www.python.org/
+
+Full documentation @ <https://akamhy.github.io/waybackpy/>.
+:copyright: (c) 2020 by akamhy.
+:license: MIT
+"""
+
+from .wrapper import save, near, oldest, newest, get, clean_url, url_check, total_archives
+from .__version__ import __title__, __description__, __url__, __version__
+from .__version__ import __author__, __author_email__, __license__, __copyright__

waybackpy/__version__.py

@@ -0,0 +1,8 @@
+__title__ = "waybackpy"
+__description__ = "A python wrapper for Internet Archive's Wayback Machine API. Archive pages and retrieve archived pages easily."
+__url__ = "https://akamhy.github.io/waybackpy/"
+__version__ = "v1.5"
+__author__ = "akamhy"
+__author_email__ = "akash3pro@gmail.com"
+__license__ = "MIT"
+__copyright__ = "Copyright 2020 akamhy"

waybackpy/exceptions.py

@@ -32,6 +32,11 @@ class BadGateWay(Exception):
     Raised when 502 bad gateway.
     """
 
+class WaybackUnavailable(Exception):
+    """
+    Raised when 503 API Service Temporarily Unavailable.
+    """
+
 class InvalidUrl(Exception):
     """
     Raised when url doesn't follow the standard url format.

waybackpy/wrapper.py

@@ -1,88 +1,143 @@
 # -*- coding: utf-8 -*-
 import json
 from datetime import datetime
-from waybackpy.exceptions import TooManyArchivingRequests, ArchivingNotAllowed, PageNotSaved, ArchiveNotFound, UrlNotFound, BadGateWay, InvalidUrl
+from waybackpy.exceptions import TooManyArchivingRequests, ArchivingNotAllowed, PageNotSaved, ArchiveNotFound, UrlNotFound, BadGateWay, InvalidUrl, WaybackUnavailable
 try:
     from urllib.request import Request, urlopen
-    from urllib.error import HTTPError
+    from urllib.error import HTTPError, URLError
 except ImportError:
-    from urllib2 import Request, urlopen, HTTPError
+    from urllib2 import Request, urlopen, HTTPError, URLError
 
 
 default_UA = "waybackpy python package"
 
+def url_check(url):
+    if "." not in url:
+        raise InvalidUrl("'%s' is not a vaild url." % url)
+
 def clean_url(url):
     return str(url).strip().replace(" ","_")
 
-def save(url,UA=default_UA):
-    base_save_url = "https://web.archive.org/save/"
-    request_url = (base_save_url + clean_url(url))
+def wayback_timestamp(**kwargs):
+    return (
+      str(kwargs["year"])
+      +
+      str(kwargs["month"]).zfill(2)
+      +
+      str(kwargs["day"]).zfill(2)
+      +
+      str(kwargs["hour"]).zfill(2)
+      +
+      str(kwargs["minute"]).zfill(2)
+      )
+
+def handle_HTTPError(e):
+    if e.code == 502:
+        raise BadGateWay(e)
+    elif e.code == 503:
+        raise WaybackUnavailable(e)
+    elif e.code == 429:
+        raise TooManyArchivingRequests(e)
+    elif e.code == 404:
+        raise UrlNotFound(e)
+
+def save(url, UA=default_UA):
+    url_check(url)
+    request_url = ("https://web.archive.org/save/" + clean_url(url))
+
     hdr = { 'User-Agent' : '%s' % UA } #nosec
     req = Request(request_url, headers=hdr) #nosec
-    if "." not in url:
-        raise InvalidUrl("'%s' is not a vaild url." % url)
+
+
     try:
         response = urlopen(req) #nosec
     except HTTPError as e:
-        if e.code == 502:
-            raise BadGateWay(e)
-        elif e.code == 429:
-            raise TooManyArchivingRequests(e)
-        elif e.code == 404:
+        if handle_HTTPError(e) is None:
+            raise PageNotSaved(e)
+    except URLError:
+        try:
+            response = urlopen(req) #nosec
+        except URLError as e:
             raise UrlNotFound(e)
-        else:
-          raise PageNotSaved(e)
 
     header = response.headers
+
     if "exclusion.robots.policy" in str(header):
         raise ArchivingNotAllowed("Can not archive %s. Disabled by site owner." % (url))
-    archive_id = header['Content-Location']
-    archived_url = "https://web.archive.org" + archive_id
-    return archived_url
 
-def get(url,encoding=None,UA=default_UA):
+    return "https://web.archive.org" + header['Content-Location']
+
+def get(url, encoding=None, UA=default_UA):
+    url_check(url)
     hdr = { 'User-Agent' : '%s' % UA }
-    request_url = clean_url(url)
-    req = Request(request_url, headers=hdr) #nosec
-    resp=urlopen(req) #nosec
+    req = Request(clean_url(url), headers=hdr) #nosec
+
+    try:
+        resp=urlopen(req) #nosec
+    except URLError:
+        try:
+            resp=urlopen(req) #nosec
+        except URLError as e:
+            raise UrlNotFound(e)
+
     if encoding is None:
         try:
             encoding= resp.headers['content-type'].split('charset=')[-1]
         except AttributeError:
             encoding = "UTF-8"
-    return resp.read().decode(encoding)
 
-def wayback_timestamp(year,month,day,hour,minute):
-    year = str(year)
-    month = str(month).zfill(2)
-    day = str(day).zfill(2)
-    hour = str(hour).zfill(2)
-    minute = str(minute).zfill(2)
-    return (year+month+day+hour+minute)
+    return resp.read().decode(encoding.replace("text/html", "UTF-8", 1))
 
-def near(
-    url,
-    year=datetime.utcnow().strftime('%Y'),
-    month=datetime.utcnow().strftime('%m'),
-    day=datetime.utcnow().strftime('%d'),
-    hour=datetime.utcnow().strftime('%H'),
-    minute=datetime.utcnow().strftime('%M'),
-    UA=default_UA,
-    ):
-    timestamp = wayback_timestamp(year,month,day,hour,minute)
+def near(url, **kwargs):
+
+    try:
+        url = kwargs["url"]
+    except KeyError:
+        url = url
+
+    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'))
+    UA=kwargs.get("UA", default_UA)
+
+    url_check(url)
+    timestamp = wayback_timestamp(year=year,month=month,day=day,hour=hour,minute=minute)
     request_url = "https://archive.org/wayback/available?url=%s&timestamp=%s" % (clean_url(url), str(timestamp))
     hdr = { 'User-Agent' : '%s' % UA }
     req = Request(request_url, headers=hdr) # nosec
-    response = urlopen(req) #nosec
+
+    try:
+        response = urlopen(req) #nosec
+    except HTTPError as e:
+        handle_HTTPError(e)
+
     data = json.loads(response.read().decode("UTF-8"))
     if not data["archived_snapshots"]:
         raise ArchiveNotFound("'%s' is not yet archived." % 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)
     return archive_url
 
-def oldest(url,UA=default_UA,year=1994):
-    return near(url,year=year,UA=UA)
+def oldest(url, UA=default_UA, year=1994):
+    return near(url, year=year, UA=UA)
 
-def newest(url,UA=default_UA):
-    return near(url,UA=UA)
+def newest(url, UA=default_UA):
+    return near(url, UA=UA)
+
+def total_archives(url, UA=default_UA):
+    url_check(url)
+
+    hdr = { 'User-Agent' : '%s' % UA }
+    request_url = "https://web.archive.org/cdx/search/cdx?url=%s&output=json" % clean_url(url)
+    req = Request(request_url, headers=hdr) # nosec
+
+    try:
+        response = urlopen(req) #nosec
+    except HTTPError as e:
+        handle_HTTPError(e)
+
+    return (len(json.loads(response.read())))