improve usage code

more usage example
updating examples
2022-01-18 21:18:17 +05:30 · 2022-01-18 20:58:39 +05:30 · 2022-01-18 20:44:47 +05:30 · 2022-01-18 20:34:21 +05:30 · 2022-01-18 20:14:44 +05:30 · 2022-01-18 20:07:12 +05:30
24 changed files with 1256 additions and 1285 deletions
--- a/.gitignore
+++ b/.gitignore
@@ -1,3 +1,6 @@
 # Files generated while testing
 *-urls-*.txt
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]
--- a/.travis.yml
+++ b/.travis.yml
@@ -1,19 +0,0 @@
 language: python
 os: linux
 dist: xenial
 cache: pip
 python:
  - 2.7
  - 3.6
  - 3.8
 before_install:
  - python --version
  - pip install -U pip
  - pip install -U pytest
  - pip install codecov
  - pip install pytest pytest-cov
 script:
  - cd tests
  - pytest --cov=../waybackpy
 after_success:
  - if [[ $TRAVIS_PYTHON_VERSION == 3.8 ]]; then python -m codecov; fi
--- a/.whitesource
+++ b/.whitesource
@@ -1,6 +1,10 @@
 {
  "scanSettings": {
    "baseBranches": []
  },
  "checkRunSettings": {
-    "vulnerableCheckRunConclusionLevel": "failure"
+    "vulnerableCheckRunConclusionLevel": "failure",
    "displayMode": "diff"
  },
  "issueSettings": {
    "minSeverityLevel": "LOW"
--- a/CONTRIBUTORS.md
+++ b/CONTRIBUTORS.md
@@ -0,0 +1,10 @@
 ## AUTHORS
  - akamhy (<https://github.com/akamhy>)
  - danvalen1 (<https://github.com/danvalen1>)
  - AntiCompositeNumber (<https://github.com/AntiCompositeNumber>)
  - jonasjancarik (<https://github.com/jonasjancarik>)
 ## ACKNOWLEDGEMENTS
  - mhmdiaa (<https://github.com/mhmdiaa>) for <https://gist.github.com/mhmdiaa/adf6bff70142e5091792841d4b372050>. known_urls is based on this gist.
  - datashaman (<https://stackoverflow.com/users/401467/datashaman>) for <https://stackoverflow.com/a/35504626>. _get_response is based on this amazing answer.
  - dequeued0 (<https://github.com/dequeued0>) for reporting bugs and useful feature requests.
--- a/2
+++ b/2
@@ -1,6 +1,6 @@
 MIT License
-Copyright (c) 2020 akamhy
+Copyright (c) 2020 waybackpy contributors ( https://github.com/akamhy/waybackpy/graphs/contributors )
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal
--- a/README.md
+++ b/README.md
@@ -1,288 +1,129 @@
-# waybackpy
+<div align="center">
-![contributions welcome](https://img.shields.io/static/v1.svg?label=Contributions&message=Welcome&color=0059b3&style=flat-square)
+<img src="https://raw.githubusercontent.com/akamhy/waybackpy/master/assets/waybackpy_logo.svg"><br>
-[![Build Status](https://img.shields.io/travis/akamhy/waybackpy.svg?label=Travis%20CI&logo=travis&style=flat-square)](https://travis-ci.org/akamhy/waybackpy)
+
-[![codecov](https://codecov.io/gh/akamhy/waybackpy/branch/master/graph/badge.svg)](https://codecov.io/gh/akamhy/waybackpy)
+<h3>Python package & CLI tool that interfaces with the Wayback Machine API</h3>
-[![Downloads](https://pepy.tech/badge/waybackpy/month)](https://pepy.tech/project/waybackpy/month)
+
-[![Release](https://img.shields.io/github/v/release/akamhy/waybackpy.svg)](https://github.com/akamhy/waybackpy/releases)
+</div>
-[![Codacy Badge](https://api.codacy.com/project/badge/Grade/255459cede9341e39436ec8866d3fb65)](https://www.codacy.com/manual/akamhy/waybackpy?utm_source=github.com&amp;utm_medium=referral&amp;utm_content=akamhy/waybackpy&amp;utm_campaign=Badge_Grade)
+
-[![Maintainability](https://api.codeclimate.com/v1/badges/942f13d8177a56c1c906/maintainability)](https://codeclimate.com/github/akamhy/waybackpy/maintainability)
+<p align="center">
-[![CodeFactor](https://www.codefactor.io/repository/github/akamhy/waybackpy/badge)](https://www.codefactor.io/repository/github/akamhy/waybackpy)
+<a href="https://pypi.org/project/waybackpy/"><img alt="pypi" src="https://img.shields.io/pypi/v/waybackpy.svg"></a>
-[![made-with-python](https://img.shields.io/badge/Made%20with-Python-1f425f.svg)](https://www.python.org/)
+<a href="https://github.com/akamhy/waybackpy/blob/master/CONTRIBUTING.md"><img alt="Contributions Welcome" src="https://img.shields.io/static/v1.svg?label=Contributions&message=Welcome&color=0059b3&style=flat-square"></a>
-[![pypi](https://img.shields.io/pypi/v/waybackpy.svg)](https://pypi.org/project/waybackpy/)
+<a href="https://pepy.tech/project/waybackpy?versions=2*&versions=1*&versions=3*"><img alt="Downloads" src="https://pepy.tech/badge/waybackpy/month"></a>
-![PyPI - Python Version](https://img.shields.io/pypi/pyversions/waybackpy?style=flat-square)
+<a href="https://github.com/akamhy/waybackpy/commits/master"><img alt="GitHub lastest commit" src="https://img.shields.io/github/last-commit/akamhy/waybackpy?color=blue&style=flat-square"></a>
-[![Maintenance](https://img.shields.io/badge/Maintained%3F-yes-green.svg)](https://github.com/akamhy/waybackpy/graphs/commit-activity)
+<a href="#"><img alt="PyPI - Python Version" src="https://img.shields.io/pypi/pyversions/waybackpy?style=flat-square"></a>
-![Repo size](https://img.shields.io/github/repo-size/akamhy/waybackpy.svg?label=Repo%20size&style=flat-square)
+</p>
-[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://github.com/akamhy/waybackpy/blob/master/LICENSE)
+
 -----------------------------------------------------------------------------------------------------------------------------------------------
 ## ⭐️ Introduction
 Waybackpy is a [Python package](https://www.udacity.com/blog/2021/01/what-is-a-python-package.html) and a CLI tool that interfaces with the Wayback Machine API.
 Wayback Machine has 3 client side APIs.
  - Save API
  - Availability API
  - CDX API
 All three of these can be accessed by waybackpy.
-![Internet Archive](https://upload.wikimedia.org/wikipedia/commons/thumb/8/84/Internet_Archive_logo_and_wordmark.svg/84px-Internet_Archive_logo_and_wordmark.svg.png)
+### 🏗 Installation
 ![Wayback Machine](https://upload.wikimedia.org/wikipedia/commons/thumb/0/01/Wayback_Machine_logo_2010.svg/284px-Wayback_Machine_logo_2010.svg.png)
 Waybackpy is a Python library that interfaces with the [Internet Archive](https://en.wikipedia.org/wiki/Internet_Archive)'s [Wayback Machine](https://en.wikipedia.org/wiki/Wayback_Machine) API. Archive pages and retrieve archived pages easily.
 Table of contents
 =================
 <!--ts-->
 * [Installation](#installation)
 * [Usage](#usage)
  * [As a Python package](#as-a-python-package)
    * [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)
    * [Count total archives for an URL using total_archives()](#count-total-archives-for-an-url-using-total_archives)
  * [With Command-line interface](#with-the-command-line-interface)
    * [Save](#save)
    * [Oldest archive](#oldest-archive)
    * [Newest archive](#newest-archive)
    * [Total archives](#total-number-of-archives)
    * [Archive near a time](#archive-near-time)
    * [Get the source code](#get-the-source-code)
 * [Tests](#tests)
 * [Dependency](#dependency)
 * [License](#license)
 <!--te-->
 ## Installation
 Using [pip](https://en.wikipedia.org/wiki/Pip_(package_manager)):
 ```bash
 pip install waybackpy
 ```
-or direct from this repository using git.
+
 Install directly from GitHub:
 ```bash
 pip install git+https://github.com/akamhy/waybackpy.git
 ```
-## Usage
+### Docker Image
 Docker Hub : <https://hub.docker.com/r/secsi/waybackpy>
-### As a Python package
+Docker image is automatically updated on every release by [Regulary and Automatically Updated Docker Images](https://github.com/cybersecsi/RAUDI) (RAUDI). 
-#### Capturing aka Saving an url using save()
+RAUDI is a tool by SecSI (<https://secsi.io>), an Italian cybersecurity startup.
 ### Usage
 #### As a Python package
 ##### Save API aka SavePageNow
 ```python
-import waybackpy
+>>> from waybackpy import WaybackMachineSaveAPI
-
+>>> url = "https://github.com"
-new_archive_url = waybackpy.Url(
+>>> user_agent = "Mozilla/5.0 (Windows NT 5.1; rv:40.0) Gecko/20100101 Firefox/40.0"
-
+>>> 
-    url = "https://en.wikipedia.org/wiki/Multivariable_calculus",
+>>> save_api = WaybackMachineSaveAPI(url, user_agent)
-    user_agent = "Mozilla/5.0 (Windows NT 5.1; rv:40.0) Gecko/20100101 Firefox/40.0"
+>>> save_api.save()
-    
+https://web.archive.org/web/20220118125249/https://github.com/
-).save()
+>>> save_api.cached_save
-
+False
-print(new_archive_url)
+>>> save_api.timestamp()
 datetime.datetime(2022, 1, 18, 12, 52, 49)
 ```
 ##### Availability API
 ```python
 >>> from waybackpy import WaybackMachineAvailabilityAPI
 >>> 
 >>> url = "https://google.com"
 >>> user_agent = "Mozilla/5.0 (Windows NT 5.1; rv:40.0) Gecko/20100101 Firefox/40.0"
 >>> 
 >>> availability_api = WaybackMachineAvailabilityAPI(url, user_agent)
 >>> 
 >>> availability_api.oldest()
 https://web.archive.org/web/19981111184551/http://google.com:80/
 >>> 
 >>> availability_api.newest()
 https://web.archive.org/web/20220118150444/https://www.google.com/
 >>> 
 >>> availability_api.near(year=2010, month=10, day=10, hour=10)
 https://web.archive.org/web/20101010101708/http://www.google.com/
 ```
 ##### CDX API aka CDXServerAPI
 ```python
 >>> from waybackpy import WaybackMachineCDXServerAPI
 >>> url = "https://pypi.org"
 >>> user_agent = "Mozilla/5.0 (Windows NT 5.1; rv:40.0) Gecko/20100101 Firefox/40.0"
 >>> cdx = WaybackMachineCDXServerAPI(url, user_agent, start_timestamp=2016, end_timestamp=2017)
 >>> for item in cdx.snapshots():
 ...     print(item.archive_url)
 ... 
 https://web.archive.org/web/20160110011047/http://pypi.org/
 https://web.archive.org/web/20160305104847/http://pypi.org/
 .
 . # URLS REDACTED FOR READABILITY
 .
 https://web.archive.org/web/20171127171549/https://pypi.org/
 https://web.archive.org/web/20171206002737/http://pypi.org:80/
 ```
 > Documentation at <https://github.com/akamhy/waybackpy/wiki/Python-package-docs>.
 #### As a CLI tool
 ```bash
-https://web.archive.org/web/20200504141153/https://github.com/akamhy/waybackpy
+$ waybackpy --save --url "https://en.wikipedia.org/wiki/Social_media" --user_agent "my-unique-user-agent"
 ```
 <sub>Try this out in your browser @ <https://repl.it/@akamhy/WaybackPySaveExample></sub>
 #### Receiving the oldest archive for an URL using oldest()
 ```python
 import waybackpy
 oldest_archive_url = waybackpy.Url(
    "https://www.google.com/",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.8; rv:40.0) Gecko/20100101 Firefox/40.0"
 ).oldest()
 print(oldest_archive_url)
 ```
 ```bash
 http://web.archive.org/web/19981111184551/http://google.com:80/
 ```
 <sub>Try this out in your browser @ <https://repl.it/@akamhy/WaybackPyOldestExample></sub>
 #### Receiving the newest archive for an URL using newest()
 ```python
 import waybackpy
 newest_archive_url = waybackpy.Url(
    "https://www.facebook.com/",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.10; rv:39.0) Gecko/20100101 Firefox/39.0"
 ).newest()
 print(newest_archive_url)
 ```
 ```bash
 https://web.archive.org/web/20200714013225/https://www.facebook.com/
 ```
 <sub>Try this out in your browser @ <https://repl.it/@akamhy/WaybackPyNewestExample></sub>
 #### Receiving archive close to a specified year, month, day, hour, and minute using near()
 ```python
 from waybackpy import Url
 user_agent = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.10; rv:38.0) Gecko/20100101 Firefox/38.0"
 github_url = "https://github.com/"
 github_wayback_obj = Url(github_url, user_agent)
 # 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.
 ```
 ```python
 github_archive_near_2010 = github_wayback_obj.near(year=2010)
 print(github_archive_near_2010)
 ```
 ```bash
 https://web.archive.org/web/20100719134402/http://github.com/
 ```
 ```python
 github_archive_near_2011_may = github_wayback_obj.near(year=2011, month=5)
 print(github_archive_near_2011_may)
 ```
 ```bash
 https://web.archive.org/web/20110519185447/https://github.com/
 ```
 ```python
 github_archive_near_2015_january_26 = github_wayback_obj.near(
    year=2015, month=1, day=26
 )
 print(github_archive_near_2015_january_26)
 ```
 ```bash
 https://web.archive.org/web/20150127031159/https://github.com
 ```
 ```python
 github_archive_near_2018_4_july_9_2_am = github_wayback_obj.near(
    year=2018, month=7, day=4, hour = 9, minute = 2
 )
 print(github_archive_near_2018_4_july_9_2_am)
 ```
 ```bash
 https://web.archive.org/web/20180704090245/https://github.com/
 ```
 <sub>The library doesn't supports seconds yet. You are encourged to create a PR ;)</sub>
 <sub>Try this out in your browser @ <https://repl.it/@akamhy/WaybackPyNearExample></sub>
 #### Get the content of webpage using get()
 ```python
 import waybackpy
 google_url = "https://www.google.com/"
 User_Agent = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.85 Safari/537.36"
 waybackpy_url_object = waybackpy.Url(google_url, User_Agent)
 # If no argument is passed in get(), it gets the source of the Url used to create the object.
 current_google_url_source = waybackpy_url_object.get()
 print(current_google_url_source)
 # The following chunk of code will force a new archive of google.com and get the source of the archived page.
 # waybackpy_url_object.save() type is string.
 google_newest_archive_source = waybackpy_url_object.get(
    waybackpy_url_object.save()
 )
 print(google_newest_archive_source)
 # waybackpy_url_object.oldest() type is str, it's oldest archive of google.com
 google_oldest_archive_source = waybackpy_url_object.get(
    waybackpy_url_object.oldest()
 )
 print(google_oldest_archive_source)
 ```
 <sub>Try this out in your browser @ <https://repl.it/@akamhy/WaybackPyGetExample#main.py></sub>
 #### Count total archives for an URL using total_archives()
 ```python
 import waybackpy
 URL = "https://en.wikipedia.org/wiki/Python (programming language)"
 UA = "Mozilla/5.0 (iPad; CPU OS 8_1_1 like Mac OS X) AppleWebKit/600.1.4 (KHTML, like Gecko) Version/8.0 Mobile/12B435 Safari/600.1.4"
 archive_count = waybackpy.Url(
    url=URL,
    user_agent=UA
 ).total_archives()
 print(archive_count) # total_archives() returns an int
 ```
 ```bash
 2440
 ```
 <sub>Try this out in your browser @ <https://repl.it/@akamhy/WaybackPyTotalArchivesExample></sub>
 ### With the Command-line interface
 #### Save
 ```bash
 $ waybackpy --url "https://en.wikipedia.org/wiki/Social_media" --user_agent "my-unique-user-agent" --save
 https://web.archive.org/web/20200719062108/https://en.wikipedia.org/wiki/Social_media
 $ waybackpy --oldest --url "https://en.wikipedia.org/wiki/Humanoid" --user_agent "my-unique-user-agent"
 https://web.archive.org/web/20040415020811/http://en.wikipedia.org:80/wiki/Humanoid
 $ waybackpy --newest --url "https://en.wikipedia.org/wiki/Remote_sensing" --user_agent "my-unique-user-agent"
 https://web.archive.org/web/20201221130522/https://en.wikipedia.org/wiki/Remote_sensing
 ```
-<sub>Try this out in your browser @ <https://repl.it/@akamhy/WaybackPyBashSave></sub>
+> CLI documentation is at <https://github.com/akamhy/waybackpy/wiki/CLI-docs>.
-#### Oldest archive
+### 🛡 License
-```bash
+[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://github.com/akamhy/waybackpy/blob/master/LICENSE)
 $ waybackpy --url "https://en.wikipedia.org/wiki/SpaceX" --user_agent "my-unique-user-agent" --oldest
 https://web.archive.org/web/20040803000845/http://en.wikipedia.org:80/wiki/SpaceX
 ```
 <sub>Try this out in your browser @ <https://repl.it/@akamhy/WaybackPyBashOldest></sub>
-#### Newest archive
+Released under the MIT License. See [license](https://github.com/akamhy/waybackpy/blob/master/LICENSE) for details.
 ```bash
 $ waybackpy --url "https://en.wikipedia.org/wiki/YouTube" --user_agent "my-unique-user-agent" --newest
 https://web.archive.org/web/20200606044708/https://en.wikipedia.org/wiki/YouTube
 ```
 <sub>Try this out in your browser @ <https://repl.it/@akamhy/WaybackPyBashNewest></sub>
 #### Total number of archives
 ```bash
 $ waybackpy --url "https://en.wikipedia.org/wiki/Linux_kernel" --user_agent "my-unique-user-agent" --total
 853
 ```
 <sub>Try this out in your browser @ <https://repl.it/@akamhy/WaybackPyBashTotal></sub>
 #### Archive near time
 ```bash
 $ waybackpy --url facebook.com --user_agent "my-unique-user-agent" --near --year 2012 --month 5 --day 12
 https://web.archive.org/web/20120512142515/https://www.facebook.com/
 ```
 <sub>Try this out in your browser @ <https://repl.it/@akamhy/WaybackPyBashNear></sub>
 #### Get the source code
 ```bash
 $ waybackpy --url google.com --user_agent "my-unique-user-agent" --get url # Prints the source code of the url
 $ waybackpy --url google.com --user_agent "my-unique-user-agent" --get oldest # Prints the source code of the oldest archive
 $ waybackpy --url google.com --user_agent "my-unique-user-agent" --get newest # Prints the source code of the newest archive
 $ waybackpy --url google.com --user_agent "my-unique-user-agent" --get save # Save a new archive on wayback machine then print the source code of this archive.
 ```
 <sub>Try this out in your browser @ <https://repl.it/@akamhy/WaybackPyBashGet></sub>
 ## Tests
 * [Here](https://github.com/akamhy/waybackpy/tree/master/tests)
 ## Dependency
 * None, just python standard libraries (re, json, urllib, argparse and datetime). Both python 2 and 3 are supported :)
 ## License
 [MIT License](https://github.com/akamhy/waybackpy/blob/master/LICENSE)
--- a/assets/waybackpy_logo.svg
+++ b/assets/waybackpy_logo.svg
@@ -0,0 +1 @@
 <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 176.612 41.908" height="158.392" width="667.51"  xmlns:v="https://github.com/akamhy/waybackpy"><text transform="matrix(.862888 0 0 1.158899 -.748 -98.312)" y="110.937" x="0.931" xml:space="preserve" font-weight="bold" font-size="28.149" font-family="sans-serif" letter-spacing="0" word-spacing="0" writing-mode="lr-tb" fill="#003dff"><tspan y="110.937" x="0.931"><tspan y="110.937" x="0.931" letter-spacing="3.568" writing-mode="lr-tb">waybackpy</tspan></tspan></text><path d="M.749 0h153.787v4.864H.749zm22.076 37.418h153.787v4.49H22.825z" fill="navy"/><path d="M0 37.418h22.825v4.49H0zM154.536 0h21.702v4.864h-21.702z" fill="#f0f"/></svg>
--- a/index.rst
+++ b/index.rst
@@ -1,386 +0,0 @@
 waybackpy
 =========
 |contributions welcome| |Build Status| |codecov| |Downloads| |Release|
 |Codacy Badge| |Maintainability| |CodeFactor| |made-with-python| |pypi|
 |PyPI - Python Version| |Maintenance| |Repo size| |License: MIT|
 |Internet Archive| |Wayback Machine|
 Waybackpy is a Python library that interfaces with the `Internet
 Archive <https://en.wikipedia.org/wiki/Internet_Archive>`__'s `Wayback
 Machine <https://en.wikipedia.org/wiki/Wayback_Machine>`__ API. Archive
 pages and retrieve archived pages easily.
 Table of contents
 =================
 .. raw:: html
   <!--ts-->
 -  `Installation <#installation>`__
 -  `Usage <#usage>`__
 -  `As a Python package <#as-a-python-package>`__
   -  `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>`__
   -  `Count total archives for an URL using
      total\_archives() <#count-total-archives-for-an-url-using-total_archives>`__
 -  `With Command-line interface <#with-the-command-line-interface>`__
   -  `Save <#save>`__
   -  `Oldest archive <#oldest-archive>`__
   -  `Newest archive <#newest-archive>`__
   -  `Total archives <#total-number-of-archives>`__
   -  `Archive near a time <#archive-near-time>`__
   -  `Get the source code <#get-the-source-code>`__
 -  `Tests <#tests>`__
 -  `Dependency <#dependency>`__
 -  `License <#license>`__
 .. raw:: html
   <!--te-->
 Installation
 ------------
 Using `pip <https://en.wikipedia.org/wiki/Pip_(package_manager)>`__:
 .. code:: bash
    pip install waybackpy
 or direct from this repository using git.
 .. code:: bash
    pip install git+https://github.com/akamhy/waybackpy.git
 Usage
 -----
 As a Python package
 ~~~~~~~~~~~~~~~~~~~
 Capturing aka Saving an url using save()
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 .. code:: python
    import waybackpy
    new_archive_url = waybackpy.Url(
        url = "https://en.wikipedia.org/wiki/Multivariable_calculus",
        user_agent = "Mozilla/5.0 (Windows NT 5.1; rv:40.0) Gecko/20100101 Firefox/40.0"
    ).save()
    print(new_archive_url)
 .. code:: bash
    https://web.archive.org/web/20200504141153/https://github.com/akamhy/waybackpy
 Try this out in your browser @
 https://repl.it/@akamhy/WaybackPySaveExample\ 
 Receiving the oldest archive for an URL using oldest()
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 .. code:: python
    import waybackpy
    oldest_archive_url = waybackpy.Url(
        "https://www.google.com/",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.8; rv:40.0) Gecko/20100101 Firefox/40.0"
    ).oldest()
    print(oldest_archive_url)
 .. code:: bash
    http://web.archive.org/web/19981111184551/http://google.com:80/
 Try this out in your browser @
 https://repl.it/@akamhy/WaybackPyOldestExample\ 
 Receiving the newest archive for an URL using newest()
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 .. code:: python
    import waybackpy
    newest_archive_url = waybackpy.Url(
        "https://www.facebook.com/",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.10; rv:39.0) Gecko/20100101 Firefox/39.0"
    ).newest()
    print(newest_archive_url)
 .. code:: bash
    https://web.archive.org/web/20200714013225/https://www.facebook.com/
 Try this out in your browser @
 https://repl.it/@akamhy/WaybackPyNewestExample\ 
 Receiving archive close to a specified year, month, day, hour, and minute using near()
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 .. code:: python
    from waybackpy import Url
    user_agent = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.10; rv:38.0) Gecko/20100101 Firefox/38.0"
    github_url = "https://github.com/"
    github_wayback_obj = Url(github_url, user_agent)
    # 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.
 .. code:: python
    github_archive_near_2010 = github_wayback_obj.near(year=2010)
    print(github_archive_near_2010)
 .. code:: bash
    https://web.archive.org/web/20100719134402/http://github.com/
 .. code:: python
    github_archive_near_2011_may = github_wayback_obj.near(year=2011, month=5)
    print(github_archive_near_2011_may)
 .. code:: bash
    https://web.archive.org/web/20110519185447/https://github.com/
 .. code:: python
    github_archive_near_2015_january_26 = github_wayback_obj.near(
        year=2015, month=1, day=26
    )
    print(github_archive_near_2015_january_26)
 .. code:: bash
    https://web.archive.org/web/20150127031159/https://github.com
 .. code:: python
    github_archive_near_2018_4_july_9_2_am = github_wayback_obj.near(
        year=2018, month=7, day=4, hour = 9, minute = 2
    )
    print(github_archive_near_2018_4_july_9_2_am)
 .. code:: bash
    https://web.archive.org/web/20180704090245/https://github.com/
 The library doesn't supports seconds yet. You are encourged to create a
 PR ;)
 Try this out in your browser @
 https://repl.it/@akamhy/WaybackPyNearExample\ 
 Get the content of webpage using get()
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 .. code:: python
    import waybackpy
    google_url = "https://www.google.com/"
    User_Agent = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.85 Safari/537.36"
    waybackpy_url_object = waybackpy.Url(google_url, User_Agent)
    # If no argument is passed in get(), it gets the source of the Url used to create the object.
    current_google_url_source = waybackpy_url_object.get()
    print(current_google_url_source)
    # The following chunk of code will force a new archive of google.com and get the source of the archived page.
    # waybackpy_url_object.save() type is string.
    google_newest_archive_source = waybackpy_url_object.get(
        waybackpy_url_object.save()
    )
    print(google_newest_archive_source)
    # waybackpy_url_object.oldest() type is str, it's oldest archive of google.com
    google_oldest_archive_source = waybackpy_url_object.get(
        waybackpy_url_object.oldest()
    )
    print(google_oldest_archive_source)
 Try this out in your browser @
 https://repl.it/@akamhy/WaybackPyGetExample#main.py\ 
 Count total archives for an URL using total\_archives()
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 .. code:: python
    import waybackpy
    URL = "https://en.wikipedia.org/wiki/Python (programming language)"
    UA = "Mozilla/5.0 (iPad; CPU OS 8_1_1 like Mac OS X) AppleWebKit/600.1.4 (KHTML, like Gecko) Version/8.0 Mobile/12B435 Safari/600.1.4"
    archive_count = waybackpy.Url(
        url=URL,
        user_agent=UA
    ).total_archives()
    print(archive_count) # total_archives() returns an int
 .. code:: bash
    2440
 Try this out in your browser @
 https://repl.it/@akamhy/WaybackPyTotalArchivesExample\ 
 With the Command-line interface
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 Save
 ^^^^
 .. code:: bash
    $ waybackpy --url "https://en.wikipedia.org/wiki/Social_media" --user_agent "my-unique-user-agent" --save
    https://web.archive.org/web/20200719062108/https://en.wikipedia.org/wiki/Social_media
 Try this out in your browser @
 https://repl.it/@akamhy/WaybackPyBashSave\ 
 Oldest archive
 ^^^^^^^^^^^^^^
 .. code:: bash
    $ waybackpy --url "https://en.wikipedia.org/wiki/SpaceX" --user_agent "my-unique-user-agent" --oldest
    https://web.archive.org/web/20040803000845/http://en.wikipedia.org:80/wiki/SpaceX
 Try this out in your browser @
 https://repl.it/@akamhy/WaybackPyBashOldest\ 
 Newest archive
 ^^^^^^^^^^^^^^
 .. code:: bash
    $ waybackpy --url "https://en.wikipedia.org/wiki/YouTube" --user_agent "my-unique-user-agent" --newest
    https://web.archive.org/web/20200606044708/https://en.wikipedia.org/wiki/YouTube
 Try this out in your browser @
 https://repl.it/@akamhy/WaybackPyBashNewest\ 
 Total number of archives
 ^^^^^^^^^^^^^^^^^^^^^^^^
 .. code:: bash
    $ waybackpy --url "https://en.wikipedia.org/wiki/Linux_kernel" --user_agent "my-unique-user-agent" --total
    853
 Try this out in your browser @
 https://repl.it/@akamhy/WaybackPyBashTotal\ 
 Archive near time
 ^^^^^^^^^^^^^^^^^
 .. code:: bash
    $ waybackpy --url facebook.com --user_agent "my-unique-user-agent" --near --year 2012 --month 5 --day 12
    https://web.archive.org/web/20120512142515/https://www.facebook.com/
 Try this out in your browser @
 https://repl.it/@akamhy/WaybackPyBashNear\ 
 Get the source code
 ^^^^^^^^^^^^^^^^^^^
 .. code:: bash
    $ waybackpy --url google.com --user_agent "my-unique-user-agent" --get url # Prints the source code of the url
    $ waybackpy --url google.com --user_agent "my-unique-user-agent" --get oldest # Prints the source code of the oldest archive
    $ waybackpy --url google.com --user_agent "my-unique-user-agent" --get newest # Prints the source code of the newest archive
    $ waybackpy --url google.com --user_agent "my-unique-user-agent" --get save # Save a new archive on wayback machine then print the source code of this archive.
 Try this out in your browser @
 https://repl.it/@akamhy/WaybackPyBashGet\ 
 Tests
 -----
 -  `Here <https://github.com/akamhy/waybackpy/tree/master/tests>`__
 Dependency
 ----------
 -  None, just python standard libraries (re, json, urllib, argparse and
   datetime). Both python 2 and 3 are supported :)
 License
 -------
 `MIT
 License <https://github.com/akamhy/waybackpy/blob/master/LICENSE>`__
 .. |contributions welcome| image:: https://img.shields.io/static/v1.svg?label=Contributions&message=Welcome&color=0059b3&style=flat-square
 .. |Build Status| image:: https://img.shields.io/travis/akamhy/waybackpy.svg?label=Travis%20CI&logo=travis&style=flat-square
   :target: https://travis-ci.org/akamhy/waybackpy
 .. |codecov| image:: https://codecov.io/gh/akamhy/waybackpy/branch/master/graph/badge.svg
   :target: https://codecov.io/gh/akamhy/waybackpy
 .. |Downloads| image:: https://pepy.tech/badge/waybackpy/month
   :target: https://pepy.tech/project/waybackpy/month
 .. |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
 .. |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
   :target: https://pypi.org/project/waybackpy/
 .. |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
 .. |Repo size| image:: https://img.shields.io/github/repo-size/akamhy/waybackpy.svg?label=Repo%20size&style=flat-square
 .. |License: MIT| image:: https://img.shields.io/badge/License-MIT-yellow.svg
   :target: https://github.com/akamhy/waybackpy/blob/master/LICENSE
 .. |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
--- a/requirements.txt
+++ b/requirements.txt
@@ -0,0 +1,2 @@
 click
 requests
--- a/setup.py
+++ b/setup.py
@@ -1,54 +1,51 @@
 import os.path
 from setuptools import setup
-with open(os.path.join(os.path.dirname(__file__), 'README.md')) as f:
+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:
+with open(os.path.join(os.path.dirname(__file__), "waybackpy", "__version__.py")) as f:
    exec(f.read(), about)
 setup(
-    name = about['__title__'],
+    name=about["__title__"],
-    packages = ['waybackpy'],
+    packages=["waybackpy"],
-    version = about['__version__'],
+    version=about["__version__"],
-    description = about['__description__'],
+    description=about["__description__"],
    long_description=long_description,
-    long_description_content_type='text/markdown',
+    long_description_content_type="text/markdown",
-    license= about['__license__'],
+    license=about["__license__"],
-    author = about['__author__'],
+    author=about["__author__"],
-    author_email = about['__author_email__'],
+    author_email=about["__author_email__"],
-    url = about['__url__'],
+    url=about["__url__"],
-    download_url = 'https://github.com/akamhy/waybackpy/archive/2.1.7.tar.gz',
+    download_url="https://github.com/akamhy/waybackpy/archive/3.0.0.tar.gz",
-    keywords = ['wayback', 'archive', 'archive website', 'wayback machine', 'Internet Archive'],
+    keywords=[
-    install_requires=[],
+        "Archive Website",
-    python_requires= ">=2.7",
+        "Wayback Machine",
-    classifiers=[
+        "Internet Archive",
        'Development Status :: 5 - Production/Stable',
        'Intended Audience :: Developers',
        'Natural Language :: English',
        'Topic :: Software Development :: Build Tools',
        'License :: OSI Approved :: MIT License',
        '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',
    ],
-    entry_points={
+    install_requires=["requests", "click"],
-        'console_scripts': [
+    python_requires=">=3.4",
-            'waybackpy = waybackpy.cli:main'
+    classifiers=[
-        ]
+        "Development Status :: 4 - Beta",
-    },
+        "Intended Audience :: Developers",
        "Natural Language :: English",
        "License :: OSI Approved :: MIT License",
        "Programming Language :: Python",
        "Programming Language :: Python :: 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 :: 3.9",
        "Programming Language :: Python :: Implementation :: CPython",
    ],
    entry_points={"console_scripts": ["waybackpy = waybackpy.cli:main"]},
    project_urls={
-        'Documentation': 'https://waybackpy.readthedocs.io',
+        "Documentation": "https://github.com/akamhy/waybackpy/wiki",
-        'Source': 'https://github.com/akamhy/waybackpy',
+        "Source": "https://github.com/akamhy/waybackpy",
        "Tracker": "https://github.com/akamhy/waybackpy/issues",
    },
 )
--- a/tests/test_cli.py
+++ b/tests/test_cli.py
@@ -1,97 +0,0 @@
 # -*- coding: utf-8 -*-
 import sys
 import os
 import pytest
 import argparse
 sys.path.append("..")
 import waybackpy.cli as cli  # noqa: E402
 from waybackpy.wrapper import  Url  # noqa: E402
 from waybackpy.__version__ import __version__
 codecov_python = False
 if sys.version_info > (3, 7):
    codecov_python = True
 # Namespace(day=None, get=None, hour=None, minute=None, month=None, near=False,
 # newest=False, oldest=False, save=False, total=False, url=None, user_agent=None, version=False, year=None)
 if codecov_python:
    def test_save():
        args = argparse.Namespace(user_agent=None, url="https://pypi.org/user/akamhy/", total=False, version=False,
        oldest=False, save=True, newest=False, near=False, get=None)
        reply = cli.args_handler(args)
        assert "pypi.org/user/akamhy" in reply
 def test_oldest():
    args = argparse.Namespace(user_agent=None, url="https://pypi.org/user/akamhy/", total=False, version=False,
    oldest=True, save=False, newest=False, near=False, get=None)
    reply = cli.args_handler(args)
    assert "pypi.org/user/akamhy" in 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,
    oldest=False, save=False, newest=True, near=False, get=None)
    reply = cli.args_handler(args)
    assert "pypi.org/user/akamhy" in 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,
    oldest=False, save=False, newest=False, near=False, get=None)
    reply = cli.args_handler(args)
    assert isinstance(reply, int)
 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,
    oldest=False, save=False, newest=False, near=True, get=None, year=2020, month=7, day=15, hour=1, minute=1)
    reply = cli.args_handler(args)
    assert "202007" in 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://pypi.org/user/akamhy/", total=False, version=False,
    oldest=False, save=False, newest=False, near=False, get="url")
    reply = cli.args_handler(args)
    assert "waybackpy" in 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,
    oldest=False, save=False, newest=False, near=False, get="oldest")
    reply = cli.args_handler(args)
    assert "waybackpy" in 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,
    oldest=False, save=False, newest=False, near=False, get="newest")
    reply = cli.args_handler(args)
    assert "waybackpy" in reply
    if codecov_python:
        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,
        oldest=False, save=False, newest=False, near=False, get="save")
        reply = cli.args_handler(args)
        assert "waybackpy" in 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,
    oldest=False, save=False, newest=False, near=False, get="BullShit")
    reply = cli.args_handler(args)
    assert "get the source code of the" in reply
 def test_args_handler():
    args = argparse.Namespace(version=True)
    reply = cli.args_handler(args)
    assert __version__ == reply
    args = argparse.Namespace(url=None, version=False)
    reply = cli.args_handler(args)
    assert "Specify an URL" in reply
 def test_main():
    # This also tests the parse_args method in cli.py
    cli.main(['temp.py', '--version'])
--- a/tests/test_wrapper.py
+++ b/tests/test_wrapper.py
@@ -1,193 +0,0 @@
 # -*- coding: utf-8 -*-
 import sys
 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
    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()
    assert answer == test_result
 def test_dunders():
    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 len(target) == len(url)
    assert str(target) == url
 def test_archive_url_parser():
    request_url = "https://amazon.com"
    hdr = {"User-Agent": user_agent}  # nosec
    req = Request(request_url, headers=hdr)  # nosec
    header = waybackpy._get_response(req).headers
    with pytest.raises(Exception):
        waybackpy._archive_url_parser(header)
 def test_url_check():
    broken_url = "http://wwwgooglecom/"
    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)
    url_list = [
        "en.wikipedia.org",
        "www.wikidata.org",
        "commons.wikimedia.org",
        "www.wiktionary.org",
        "www.w3schools.com",
        "www.ibm.com",
    ]
    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",
    )
    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):
            url2 = "ha ha ha ha"
            waybackpy.Url(url2, user_agent)
        time.sleep(5)
        # Test for urls not allowed to archive by robot.txt. Doesn't works anymore. Find alternatives.
 #         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.save()
 #         time.sleep(5)
        # Non existent urls, test
        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",
    )
    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):
            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())
 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():
    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
    )
    assert target.total_archives() == 0
--- a/waybackpy/init.py
+++ b/waybackpy/init.py
@@ -1,33 +1,7 @@
 # -*- coding: utf-8 -*-
 # ┏┓┏┓┏┓━━━━━━━━━━┏━━┓━━━━━━━━━━┏┓━━┏━━━┓━━━━━
 # ┃┃┃┃┃┃━━━━━━━━━━┃┏┓┃━━━━━━━━━━┃┃━━┃┏━┓┃━━━━━
 # ┃┃┃┃┃┃┏━━┓━┏┓━┏┓┃┗┛┗┓┏━━┓━┏━━┓┃┃┏┓┃┗━┛┃┏┓━┏┓
 # ┃┗┛┗┛┃┗━┓┃━┃┃━┃┃┃┏━┓┃┗━┓┃━┃┏━┛┃┗┛┛┃┏━━┛┃┃━┃┃
 # ┗┓┏┓┏┛┃┗┛┗┓┃┗━┛┃┃┗━┛┃┃┗┛┗┓┃┗━┓┃┏┓┓┃┃━━━┃┗━┛┃
 # ━┗┛┗┛━┗━━━┛┗━┓┏┛┗━━━┛┗━━━┛┗━━┛┗┛┗┛┗┛━━━┗━┓┏┛
 # ━━━━━━━━━━━┏━┛┃━━━━━━━━━━━━━━━━━━━━━━━━┏━┛┃━
 # ━━━━━━━━━━━┗━━┛━━━━━━━━━━━━━━━━━━━━━━━━┗━━┛━
 """
 Waybackpy is a Python library that interfaces with the Internet Archive's Wayback Machine API.
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 Archive pages and retrieve archived pages easily.
 Usage:
   >>> import waybackpy
   >>> target_url = waybackpy.Url('https://www.python.org', 'Your-apps-cool-user-agent')
   >>> new_archive = target_url.save()
   >>> 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 Url
 from .cdx_api import WaybackMachineCDXServerAPI
 from .save_api import WaybackMachineSaveAPI
 from .availability_api import WaybackMachineAvailabilityAPI
 from .__version__ import (
    __title__,
    __description__,
--- a/waybackpy/version.py
+++ b/waybackpy/version.py
@@ -1,10 +1,11 @@
 # -*- coding: utf-8 -*-
 __title__ = "waybackpy"
-__description__ = "A Python library that interfaces with the Internet Archive's Wayback Machine API. Archive pages and retrieve archived pages easily."
+__description__ = (
    "Python package that interfaces with the Internet Archive's Wayback Machine APIs. "
    "Archive pages and retrieve archived pages easily."
 )
 __url__ = "https://akamhy.github.io/waybackpy/"
-__version__ = "2.1.7"
+__version__ = "3.0.0"
 __author__ = "akamhy"
-__author_email__ = "akash3pro@gmail.com"
+__author_email__ = "akamhy@yahoo.com"
 __license__ = "MIT"
-__copyright__ = "Copyright 2020 akamhy"
+__copyright__ = "Copyright 2020-2022 Akash Mahanty et al."
--- a/waybackpy/availability_api.py
+++ b/waybackpy/availability_api.py
@@ -0,0 +1,109 @@
 import re
 import time
 import requests
 from datetime import datetime
 from .__version__ import __version__
 from .utils import DEFAULT_USER_AGENT
 def full_url(endpoint, params):
    if not params:
        return endpoint.strip()
    full_url = endpoint if endpoint.endswith("?") else (endpoint + "?")
    for key, val in params.items():
        key = "filter" if key.startswith("filter") else key
        key = "collapse" if key.startswith("collapse") else key
        amp = "" if full_url.endswith("?") else "&"
        full_url = (
            full_url
            + amp
            + "{key}={val}".format(key=key, val=requests.utils.quote(str(val)))
        )
    return full_url
 class WaybackMachineAvailabilityAPI:
    def __init__(self, url, user_agent=DEFAULT_USER_AGENT):
        self.url = str(url).strip().replace(" ", "%20")
        self.user_agent = user_agent
        self.headers = {"User-Agent": self.user_agent}
        self.payload = {"url": "{url}".format(url=self.url)}
        self.endpoint = "https://archive.org/wayback/available"
        self.JSON = None
    def unix_timestamp_to_wayback_timestamp(self, unix_timestamp):
        return datetime.utcfromtimestamp(int(unix_timestamp)).strftime("%Y%m%d%H%M%S")
    def __repr__(self):
        return str(self)  # self.__str__()
    def __str__(self):
        if not self.JSON:
            return None
        return self.archive_url
    def json(self):
        self.request_url = full_url(self.endpoint, self.payload)
        self.response = requests.get(self.request_url, self.headers)
        self.JSON = self.response.json()
        return self.JSON
    def timestamp(self):
        if not self.JSON["archived_snapshots"] or not self.JSON:
            return datetime.max
        return datetime.strptime(
            self.JSON["archived_snapshots"]["closest"]["timestamp"], "%Y%m%d%H%M%S"
        )
    @property
    def archive_url(self):
        data = self.JSON
        if not data["archived_snapshots"]:
            archive_url = None
        else:
            archive_url = data["archived_snapshots"]["closest"]["url"]
            archive_url = archive_url.replace(
                "http://web.archive.org/web/", "https://web.archive.org/web/", 1
            )
        return archive_url
    def wayback_timestamp(self, **kwargs):
        return "".join(
            str(kwargs[key]).zfill(2)
            for key in ["year", "month", "day", "hour", "minute"]
        )
    def oldest(self):
        return self.near(year=1994)
    def newest(self):
        return self.near(unix_timestamp=int(time.time()))
    def near(
        self,
        year=None,
        month=None,
        day=None,
        hour=None,
        minute=None,
        unix_timestamp=None,
    ):
        if unix_timestamp:
            timestamp = self.unix_timestamp_to_wayback_timestamp(unix_timestamp)
        else:
            now = datetime.utcnow().timetuple()
            timestamp = self.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,
            )
        self.payload["timestamp"] = timestamp
        self.json()
        return self
--- a/waybackpy/cdx_api.py
+++ b/waybackpy/cdx_api.py
@@ -0,0 +1,185 @@
 from .exceptions import WaybackError
 from .cdx_snapshot import CDXSnapshot
 from .cdx_utils import (
    get_total_pages,
    get_response,
    check_filters,
    check_collapses,
    check_match_type,
 )
 from .utils import DEFAULT_USER_AGENT
 class WaybackMachineCDXServerAPI:
    def __init__(
        self,
        url,
        user_agent=None,
        start_timestamp=None,
        end_timestamp=None,
        filters=[],
        match_type=None,
        gzip=None,
        collapses=[],
        limit=None,
    ):
        self.url = str(url).strip().replace(" ", "%20")
        self.user_agent = str(user_agent) if user_agent else DEFAULT_USER_AGENT
        self.start_timestamp = str(start_timestamp) if start_timestamp else None
        self.end_timestamp = str(end_timestamp) if end_timestamp else None
        self.filters = filters
        check_filters(self.filters)
        self.match_type = str(match_type).strip() if match_type else None
        check_match_type(self.match_type, self.url)
        self.gzip = gzip if gzip else True
        self.collapses = collapses
        check_collapses(self.collapses)
        self.limit = limit if limit else 5000
        self.last_api_request_url = None
        self.use_page = False
        self.endpoint = "https://web.archive.org/cdx/search/cdx"
    def cdx_api_manager(self, payload, headers, use_page=False):
        total_pages = get_total_pages(self.url, self.user_agent)
        # If we only have two or less pages of archives then we care for accuracy
        # pagination API can be lagged sometimes
        if use_page == True and total_pages >= 2:
            blank_pages = 0
            for i in range(total_pages):
                payload["page"] = str(i)
                url, res = get_response(
                    self.endpoint, params=payload, headers=headers, return_full_url=True
                )
                self.last_api_request_url = url
                text = res.text
                if len(text) == 0:
                    blank_pages += 1
                if blank_pages >= 2:
                    break
                yield text
        else:
            payload["showResumeKey"] = "true"
            payload["limit"] = str(self.limit)
            resumeKey = None
            more = True
            while more:
                if resumeKey:
                    payload["resumeKey"] = resumeKey
                url, res = get_response(
                    self.endpoint, params=payload, headers=headers, return_full_url=True
                )
                self.last_api_request_url = url
                text = res.text.strip()
                lines = text.splitlines()
                more = False
                if len(lines) >= 3:
                    second_last_line = lines[-2]
                    if len(second_last_line) == 0:
                        resumeKey = lines[-1].strip()
                        text = text.replace(resumeKey, "", 1).strip()
                        more = True
                yield text
    def add_payload(self, payload):
        if self.start_timestamp:
            payload["from"] = self.start_timestamp
        if self.end_timestamp:
            payload["to"] = self.end_timestamp
        if self.gzip != True:
            payload["gzip"] = "false"
        if self.match_type:
            payload["matchType"] = self.match_type
        if self.filters and len(self.filters) > 0:
            for i, f in enumerate(self.filters):
                payload["filter" + str(i)] = f
        if self.collapses and len(self.collapses) > 0:
            for i, f in enumerate(self.collapses):
                payload["collapse" + str(i)] = f
        # Don't need to return anything as it's dictionary.
        payload["url"] = self.url
    def snapshots(self):
        payload = {}
        headers = {"User-Agent": self.user_agent}
        self.add_payload(payload)
        if not self.start_timestamp or self.end_timestamp:
            self.use_page = True
        if self.collapses != []:
            self.use_page = False
        texts = self.cdx_api_manager(payload, headers, use_page=self.use_page)
        for text in texts:
            if text.isspace() or len(text) <= 1 or not text:
                continue
            snapshot_list = text.split("\n")
            for snapshot in snapshot_list:
                if len(snapshot) < 46:  # 14 + 32 (timestamp+digest)
                    continue
                properties = {
                    "urlkey": None,
                    "timestamp": None,
                    "original": None,
                    "mimetype": None,
                    "statuscode": None,
                    "digest": None,
                    "length": None,
                }
                prop_values = snapshot.split(" ")
                prop_values_len = len(prop_values)
                properties_len = len(properties)
                if prop_values_len != properties_len:
                    raise WaybackError(
                        "Snapshot returned by Cdx API has {prop_values_len} properties instead of expected {properties_len} properties.\nInvolved Snapshot : {snapshot}".format(
                            prop_values_len=prop_values_len,
                            properties_len=properties_len,
                            snapshot=snapshot,
                        )
                    )
                (
                    properties["urlkey"],
                    properties["timestamp"],
                    properties["original"],
                    properties["mimetype"],
                    properties["statuscode"],
                    properties["digest"],
                    properties["length"],
                ) = prop_values
                yield CDXSnapshot(properties)
--- a/waybackpy/cdx_snapshot.py
+++ b/waybackpy/cdx_snapshot.py
@@ -0,0 +1,27 @@
 from datetime import datetime
 class CDXSnapshot:
    def __init__(self, properties):
        self.urlkey = properties["urlkey"]
        self.timestamp = properties["timestamp"]
        self.datetime_timestamp = datetime.strptime(self.timestamp, "%Y%m%d%H%M%S")
        self.original = properties["original"]
        self.mimetype = properties["mimetype"]
        self.statuscode = properties["statuscode"]
        self.digest = properties["digest"]
        self.length = properties["length"]
        self.archive_url = (
            "https://web.archive.org/web/" + self.timestamp + "/" + self.original
        )
    def __str__(self):
        return "{urlkey} {timestamp} {original} {mimetype} {statuscode} {digest} {length}".format(
            urlkey=self.urlkey,
            timestamp=self.timestamp,
            original=self.original,
            mimetype=self.mimetype,
            statuscode=self.statuscode,
            digest=self.digest,
            length=self.length,
        )
--- a/waybackpy/cdx_utils.py
+++ b/waybackpy/cdx_utils.py
@@ -0,0 +1,154 @@
 import re
 import requests
 from urllib3.util.retry import Retry
 from requests.adapters import HTTPAdapter
 from .exceptions import WaybackError
 def get_total_pages(url, user_agent):
    request_url = (
        "https://web.archive.org/cdx/search/cdx?url={url}&showNumPages=true".format(
            url=url
        )
    )
    headers = {"User-Agent": user_agent}
    return int((requests.get(request_url, headers=headers).text).strip())
 def full_url(endpoint, params):
    if not params:
        return endpoint
    full_url = endpoint if endpoint.endswith("?") else (endpoint + "?")
    for key, val in params.items():
        key = "filter" if key.startswith("filter") else key
        key = "collapse" if key.startswith("collapse") else key
        amp = "" if full_url.endswith("?") else "&"
        full_url = (
            full_url
            + amp
            + "{key}={val}".format(key=key, val=requests.utils.quote(str(val)))
        )
    return full_url
 def get_response(
    endpoint,
    params=None,
    headers=None,
    return_full_url=False,
    retries=5,
    backoff_factor=0.5,
    no_raise_on_redirects=False,
 ):
    s = requests.Session()
    retries = Retry(
        total=retries,
        backoff_factor=backoff_factor,
        status_forcelist=[500, 502, 503, 504],
    )
    s.mount("https://", HTTPAdapter(max_retries=retries))
    # The URL with parameters required for the get request
    url = full_url(endpoint, params)
    try:
        if not return_full_url:
            return s.get(url, headers=headers)
        return (url, s.get(url, headers=headers))
    except Exception as e:
        reason = str(e)
        if no_raise_on_redirects:
            if "Exceeded 30 redirects" in reason:
                return
        exc_message = "Error while retrieving {url}.\n{reason}".format(
            url=url, reason=reason
        )
        exc = WaybackError(exc_message)
        exc.__cause__ = e
        raise exc
 def check_filters(filters):
    if not isinstance(filters, list):
        raise WaybackError("filters must be a list.")
    # [!]field:regex
    for _filter in filters:
        try:
            match = re.search(
                r"(\!?(?:urlkey|timestamp|original|mimetype|statuscode|digest|length)):(.*)",
                _filter,
            )
            key = match.group(1)
            val = match.group(2)
        except Exception:
            exc_message = (
                "Filter '{_filter}' is not following the cdx filter syntax.".format(
                    _filter=_filter
                )
            )
            raise WaybackError(exc_message)
 def check_collapses(collapses):
    if not isinstance(collapses, list):
        raise WaybackError("collapses must be a list.")
    if len(collapses) == 0:
        return
    for collapse in collapses:
        try:
            match = re.search(
                r"(urlkey|timestamp|original|mimetype|statuscode|digest|length)(:?[0-9]{1,99})?",
                collapse,
            )
            field = match.group(1)
            N = None
            if 2 == len(match.groups()):
                N = match.group(2)
            if N:
                if not (field + N == collapse):
                    raise Exception
            else:
                if not (field == collapse):
                    raise Exception
        except Exception:
            exc_message = "collapse argument '{collapse}' is not following the cdx collapse syntax.".format(
                collapse=collapse
            )
            raise WaybackError(exc_message)
 def check_match_type(match_type, url):
    if not match_type:
        return
    if "*" in url:
        raise WaybackError("Can not use wildcard with match_type argument")
    legal_match_type = ["exact", "prefix", "host", "domain"]
    if match_type not in legal_match_type:
        exc_message = "{match_type} is not an allowed match type.\nUse one from 'exact', 'prefix', 'host' or 'domain'".format(
            match_type=match_type
        )
        raise WaybackError(exc_message)
--- a/waybackpy/cli.py
+++ b/waybackpy/cli.py
@@ -1,105 +1,347 @@
-# -*- coding: utf-8 -*-
+import click
-from __future__ import print_function
+import re
-import sys
+import os
-import argparse
+import json as JSON
-from waybackpy.wrapper import Url
+import random
-from waybackpy.__version__ import __version__
+import string
 from .__version__ import __version__
 from .utils import DEFAULT_USER_AGENT
 from .cdx_api import WaybackMachineCDXServerAPI
 from .save_api import WaybackMachineSaveAPI
 from .availability_api import WaybackMachineAvailabilityAPI
 from .wrapper import Url
 def _save(obj):
    return (obj.save())
-def _oldest(obj):
+@click.command()
-    return (obj.oldest())
+@click.option(
    "-u", "--url", help="URL on which Wayback machine operations are to be performed."
 )
@click.option(
    "-ua",
    "--user-agent",
    "--user_agent",
    default=DEFAULT_USER_AGENT,
    help="User agent, default user agent is '%s' " % DEFAULT_USER_AGENT,
 )
@click.option(
    "-v", "--version", is_flag=True, default=False, help="Print waybackpy version."
 )
@click.option(
    "-n",
    "--newest",
    "-au",
    "--archive_url",
    "--archive-url",
    default=False,
    is_flag=True,
    help="Fetch the newest archive of the specified URL",
 )
@click.option(
    "-o",
    "--oldest",
    default=False,
    is_flag=True,
    help="Fetch the oldest archive of the specified URL",
 )
@click.option(
    "-j",
    "--json",
    default=False,
    is_flag=True,
    help="Spit out the JSON data for availability_api commands.",
 )
@click.option(
    "-N", "--near", default=False, is_flag=True, help="Archive near specified time."
 )
@click.option("-Y", "--year", type=click.IntRange(1994, 9999), help="Year in integer.")
@click.option("-M", "--month", type=click.IntRange(1, 12), help="Month in integer.")
@click.option("-D", "--day", type=click.IntRange(1, 31), help="Day in integer.")
@click.option("-H", "--hour", type=click.IntRange(0, 24), help="Hour in integer.")
@click.option("-MIN", "--minute", type=click.IntRange(0, 60), help="Minute in integer.")
@click.option(
    "-s",
    "--save",
    default=False,
    is_flag=True,
    help="Save the specified URL's webpage and print the archive URL.",
 )
@click.option(
    "-h",
    "--headers",
    default=False,
    is_flag=True,
    help="Spit out the headers data for save_api commands.",
 )
@click.option(
    "-ku",
    "--known-urls",
    "--known_urls",
    default=False,
    is_flag=True,
    help="List known URLs. Uses CDX API.",
 )
@click.option(
    "-sub",
    "--subdomain",
    default=False,
    is_flag=True,
    help="Use with '--known_urls' to include known URLs for subdomains.",
 )
@click.option(
    "-f",
    "--file",
    default=False,
    is_flag=True,
    help="Use with '--known_urls' to save the URLs in file at current directory.",
 )
@click.option(
    "-c",
    "--cdx",
    default=False,
    is_flag=True,
    help="Spit out the headers data for save_api commands.",
 )
@click.option(
    "-st",
    "--start-timestamp",
    "--start_timestamp",
 )
@click.option(
    "-et",
    "--end-timestamp",
    "--end_timestamp",
 )
@click.option(
    "-f",
    "--filters",
    multiple=True,
 )
@click.option(
    "-mt",
    "--match-type",
    "--match_type",
 )
@click.option(
    "-gz",
    "--gzip",
 )
@click.option(
    "-c",
    "--collapses",
    multiple=True,
 )
@click.option(
    "-l",
    "--limit",
 )
@click.option(
    "-cp",
    "--cdx-print",
    "--cdx_print",
    multiple=True,
 )
 def main(
    url,
    user_agent,
    version,
    newest,
    oldest,
    json,
    near,
    year,
    month,
    day,
    hour,
    minute,
    save,
    headers,
    known_urls,
    subdomain,
    file,
    cdx,
    start_timestamp,
    end_timestamp,
    filters,
    match_type,
    gzip,
    collapses,
    limit,
    cdx_print,
 ):
    """
    ┏┓┏┓┏┓━━━━━━━━━━┏━━┓━━━━━━━━━━┏┓━━┏━━━┓━━━━━
    ┃┃┃┃┃┃━━━━━━━━━━┃┏┓┃━━━━━━━━━━┃┃━━┃┏━┓┃━━━━━
    ┃┃┃┃┃┃┏━━┓━┏┓━┏┓┃┗┛┗┓┏━━┓━┏━━┓┃┃┏┓┃┗━┛┃┏┓━┏┓
    ┃┗┛┗┛┃┗━┓┃━┃┃━┃┃┃┏━┓┃┗━┓┃━┃┏━┛┃┗┛┛┃┏━━┛┃┃━┃┃
    ┗┓┏┓┏┛┃┗┛┗┓┃┗━┛┃┃┗━┛┃┃┗┛┗┓┃┗━┓┃┏┓┓┃┃━━━┃┗━┛┃
    ━┗┛┗┛━┗━━━┛┗━┓┏┛┗━━━┛┗━━━┛┗━━┛┗┛┗┛┗┛━━━┗━┓┏┛
    ━━━━━━━━━━━┏━┛┃━━━━━━━━━━━━━━━━━━━━━━━━┏━┛┃━
    ━━━━━━━━━━━┗━━┛━━━━━━━━━━━━━━━━━━━━━━━━┗━━┛━
-def _newest(obj):
+    waybackpy : Python package & CLI tool that interfaces the Wayback Machine API
    return (obj.newest())
-def _total_archives(obj):
+    Released under the MIT License.
-    return (obj.total_archives())
+    License @ https://github.com/akamhy/waybackpy/blob/master/LICENSE
-def _near(obj, args):
+    Copyright (c) 2020 waybackpy contributors. Contributors list @
-    _near_args = {}
+    https://github.com/akamhy/waybackpy/graphs/contributors
    if args.year:
        _near_args["year"] = args.year
    if args.month:
        _near_args["month"] = args.month
    if args.day:
        _near_args["day"] = args.day
    if args.hour:
        _near_args["hour"] = args.hour
    if args.minute:
        _near_args["minute"] = args.minute
    return (obj.near(**_near_args))
-def _get(obj, args):
+    https://github.com/akamhy/waybackpy
    if args.get.lower() == "url":
        return (obj.get())
-    if args.get.lower() == "oldest":
+    https://pypi.org/project/waybackpy
        return (obj.get(obj.oldest()))
-    if args.get.lower() == "latest" or args.get.lower() == "newest":
+    """
        return (obj.get(obj.newest()))
-    if args.get.lower() == "save":
+    if version:
-        return (obj.get(obj.save()))
+        click.echo("waybackpy version %s" % __version__)
        return
-    return ("Use get as \"--get 'source'\", 'source' can be one of the followings: \
+    if not url:
-        \n1) url - get the source code of the url specified using --url/-u.\
+        click.echo("No URL detected. Please pass an URL.")
-        \n2) oldest - get the source code of the oldest archive for the supplied url.\
+        return
        \n3) newest - get the source code of the newest archive for the supplied url.\
        \n4) save - Create a new archive and get the source code of this new archive for the supplied url.")
-def args_handler(args):
+    def echo_availability_api(availability_api_instance):
-    if args.version:
+        click.echo("Archive URL:")
-        return (__version__)
+        if not availability_api_instance.archive_url:
-
+            archive_url = (
-    if not args.url:
+                "NO ARCHIVE FOUND - The requested URL is probably "
-        return ("Specify an URL. See --help for help using waybackpy.")
+                + "not yet archived or if the URL was recently archived then it is "
-
+                + "not yet available via the Wayback Machine's availability API "
-    if args.user_agent:
+                + "because of database lag and should be available after some time."
-        obj = Url(args.url, args.user_agent)
+            )
        else:
-        obj = Url(args.url)
+            archive_url = availability_api_instance.archive_url
        click.echo(archive_url)
        if json:
            click.echo("JSON response:")
            click.echo(JSON.dumps(availability_api_instance.JSON))
-    if args.save:
+    availability_api = WaybackMachineAvailabilityAPI(url, user_agent=user_agent)
        return _save(obj)
    if args.oldest:
        return _oldest(obj)
    if args.newest:
        return _newest(obj)
    if args.total:
        return _total_archives(obj)
    if args.near:
        return _near(obj, args)
    if args.get:
        return _get(obj, args)
    return ("Usage: waybackpy --url [URL] --user_agent [USER AGENT] [OPTIONS]. See --help for help using waybackpy.")
-def parse_args(argv):
+    if oldest:
-    parser = argparse.ArgumentParser()
+        availability_api.oldest()
-    parser.add_argument("-u", "--url", help="URL on which Wayback machine operations would occur.")
+        echo_availability_api(availability_api)
-    parser.add_argument("-ua", "--user_agent", help="User agent, default user_agent is \"waybackpy python package - https://github.com/akamhy/waybackpy\".")
+        return
-    parser.add_argument("-s", "--save", action='store_true', help="Save the URL on the Wayback machine.")
+
-    parser.add_argument("-o", "--oldest", action='store_true', help="Oldest archive for the specified URL.")
+    if newest:
-    parser.add_argument("-n", "--newest", action='store_true', help="Newest archive for the specified URL.")
+        availability_api.newest()
-    parser.add_argument("-t", "--total", action='store_true', help="Total number of archives for the specified URL.")
+        echo_availability_api(availability_api)
-    parser.add_argument("-g", "--get", help="Prints the source code of the supplied url. Use '--get help' for extended usage.")
+        return
-    parser.add_argument("-v", "--version", action='store_true', help="Prints the waybackpy version.")
+
-    parser.add_argument("-N", "--near", action='store_true', help="Latest/Newest archive for the specified URL.")
+    if near:
-    parser.add_argument("-Y", "--year", type=int, help="Year in integer. For use with --near.")
+        near_args = {}
-    parser.add_argument("-M", "--month", type=int, help="Month in integer. For use with --near.")
+        keys = ["year", "month", "day", "hour", "minute"]
-    parser.add_argument("-D", "--day", type=int, help="Day in integer. For use with --near.")
+        args_arr = [year, month, day, hour, minute]
-    parser.add_argument("-H", "--hour", type=int, help="Hour in integer. For use with --near.")
+        for key, arg in zip(keys, args_arr):
-    parser.add_argument("-MIN", "--minute", type=int, help="Minute in integer. For use with --near.")
+            if arg:
-    return parser.parse_args(argv[1:])
+                near_args[key] = arg
        availability_api.near(**near_args)
        echo_availability_api(availability_api)
        return
    if save:
        save_api = WaybackMachineSaveAPI(url, user_agent=user_agent)
        save_api.save()
        click.echo("Archive URL:")
        click.echo(save_api.archive_url)
        click.echo("Cached save:")
        click.echo(save_api.cached_save)
        if headers:
            click.echo("Save API headers:")
            click.echo(save_api.headers)
        return
    def save_urls_on_file(url_gen):
        domain = None
        sys_random = random.SystemRandom()
        uid = "".join(
            sys_random.choice(string.ascii_lowercase + string.digits) for _ in range(6)
        )
        url_count = 0
        for url in url_gen:
            url_count += 1
            if not domain:
                match = re.search("https?://([A-Za-z_0-9.-]+).*", url)
                domain = "domain-unknown"
                if match:
                    domain = match.group(1)
                file_name = "{domain}-urls-{uid}.txt".format(domain=domain, uid=uid)
                file_path = os.path.join(os.getcwd(), file_name)
                if not os.path.isfile(file_path):
                    open(file_path, "w+").close()
            with open(file_path, "a") as f:
                f.write("{url}\n".format(url=url))
            click.echo(url)
        if url_count > 0:
            click.echo(
                "\n\n'{file_name}' saved in current working directory".format(
                    file_name=file_name
                )
            )
        else:
            click.echo("No known URLs found. Please try a diffrent input!")
    if known_urls:
        wayback = Url(url, user_agent)
        url_gen = wayback.known_urls(subdomain=subdomain)
        if file:
            return save_urls_on_file(url_gen)
        else:
            for url in url_gen:
                click.echo(url)
    if cdx:
        filters = list(filters)
        collapses = list(collapses)
        cdx_print = list(cdx_print)
        cdx_api = WaybackMachineCDXServerAPI(
            url,
            user_agent=user_agent,
            start_timestamp=start_timestamp,
            end_timestamp=end_timestamp,
            filters=filters,
            match_type=match_type,
            gzip=gzip,
            collapses=collapses,
            limit=limit,
        )
        snapshots = cdx_api.snapshots()
        for snapshot in snapshots:
            if len(cdx_print) == 0:
                click.echo(snapshot)
            else:
                output_string = ""
                if "urlkey" or "url-key" or "url_key" in cdx_print:
                    output_string = output_string + snapshot.urlkey + " "
                if "timestamp" or "time-stamp" or "time_stamp" in cdx_print:
                    output_string = output_string + snapshot.timestamp + " "
                if "original" in cdx_print:
                    output_string = output_string + snapshot.original + " "
                if "original" in cdx_print:
                    output_string = output_string + snapshot.original + " "
                if "mimetype" or "mime-type" or "mime_type" in cdx_print:
                    output_string = output_string + snapshot.mimetype + " "
                if "statuscode" or "status-code" or "status_code" in cdx_print:
                    output_string = output_string + snapshot.statuscode + " "
                if "digest" in cdx_print:
                    output_string = output_string + snapshot.digest + " "
                if "length" in cdx_print:
                    output_string = output_string + snapshot.length + " "
                if "archiveurl" or "archive-url" or "archive_url" in cdx_print:
                    output_string = output_string + snapshot.archive_url + " "
                click.echo(output_string)
 def main(argv=None):
    if argv is None:
        argv = sys.argv
    args = parse_args(argv)
    output = args_handler(args)
    print(output)
 if __name__ == "__main__":
-    sys.exit(main(sys.argv))
+    main()
--- a/waybackpy/exceptions.py
+++ b/waybackpy/exceptions.py
@@ -1,6 +1,38 @@
-# -*- coding: utf-8 -*-
+"""
 waybackpy.exceptions
 ~~~~~~~~~~~~~~~~~~~
 This module contains the set of Waybackpy's exceptions.
 """
 class WaybackError(Exception):
    """
-    Raised when API Service error.
+    Raised when Waybackpy can not return what you asked for.
     1) Wayback Machine API Service is unreachable/down.
     2) You passed illegal arguments.
    """
 class RedirectSaveError(WaybackError):
    """
    Raised when the original URL is redirected and the
    redirect URL is archived but not the original URL.
    """
 class URLError(Exception):
    """
    Raised when malformed URLs are passed as arguments.
    """
 class MaximumRetriesExceeded(WaybackError):
    """
    MaximumRetriesExceeded
    """
 class MaximumSaveRetriesExceeded(MaximumRetriesExceeded):
    """
    MaximumSaveRetriesExceeded
    """
--- a/waybackpy/save_api.py
+++ b/waybackpy/save_api.py
@@ -0,0 +1,131 @@
 import re
 import time
 import requests
 from datetime import datetime
 from urllib3.util.retry import Retry
 from requests.adapters import HTTPAdapter
 from .utils import DEFAULT_USER_AGENT
 from .exceptions import MaximumSaveRetriesExceeded
 class WaybackMachineSaveAPI:
    """
    WaybackMachineSaveAPI class provides an interface for saving URLs on the
    Wayback Machine.
    """
    def __init__(self, url, user_agent=DEFAULT_USER_AGENT, max_tries=8):
        self.url = str(url).strip().replace(" ", "%20")
        self.request_url = "https://web.archive.org/save/" + self.url
        self.user_agent = user_agent
        self.request_headers = {"User-Agent": self.user_agent}
        self.max_tries = max_tries
        self.total_save_retries = 5
        self.backoff_factor = 0.5
        self.status_forcelist = [500, 502, 503, 504]
        self._archive_url = None
        self.instance_birth_time = datetime.utcnow()
    @property
    def archive_url(self):
        if self._archive_url:
            return self._archive_url
        else:
            return self.save()
    def get_save_request_headers(self):
        session = requests.Session()
        retries = Retry(
            total=self.total_save_retries,
            backoff_factor=self.backoff_factor,
            status_forcelist=self.status_forcelist,
        )
        session.mount("https://", HTTPAdapter(max_retries=retries))
        self.response = session.get(self.request_url, headers=self.request_headers)
        self.headers = self.response.headers
        self.status_code = self.response.status_code
        self.response_url = self.response.url
    def archive_url_parser(self):
        regex1 = r"Content-Location: (/web/[0-9]{14}/.*)"
        match = re.search(regex1, str(self.headers))
        if match:
            return "https://web.archive.org" + match.group(1)
        regex2 = r"rel=\"memento.*?(web\.archive\.org/web/[0-9]{14}/.*?)>"
        match = re.search(regex2, str(self.headers))
        if match:
            return "https://" + match.group(1)
        regex3 = r"X-Cache-Key:\shttps(.*)[A-Z]{2}"
        match = re.search(regex3, str(self.headers))
        if match:
            return "https://" + match.group(1)
        if self.response_url:
            self.response_url = self.response_url.strip()
            if "web.archive.org/web" in self.response_url:
                regex = r"web\.archive\.org/web/(?:[0-9]*?)/(?:.*)$"
                match = re.search(regex, self.response_url)
                if match:
                    return "https://" + match.group(0)
    def sleep(self, tries):
        sleep_seconds = 5
        if tries % 3 == 0:
            sleep_seconds = 10
        time.sleep(sleep_seconds)
    def timestamp(self):
        m = re.search(
            r"https?://web.archive.org/web/([0-9]{14})/http", self._archive_url
        )
        string_timestamp = m.group(1)
        timestamp = datetime.strptime(string_timestamp, "%Y%m%d%H%M%S")
        timestamp_unixtime = time.mktime(timestamp.timetuple())
        instance_birth_time_unixtime = time.mktime(self.instance_birth_time.timetuple())
        if timestamp_unixtime < instance_birth_time_unixtime:
            self.cached_save = True
        else:
            self.cached_save = False
        return timestamp
    def save(self):
        saved_archive = None
        tries = 0
        while True:
            tries += 1
            if tries >= self.max_tries:
                raise MaximumSaveRetriesExceeded(
                    "Tried %s times but failed to save and return the archive for %s.\nResponse URL:\n%s \nResponse Header:\n%s\n"
                    % (str(tries), self.url, self.response_url, str(self.headers)),
                )
            if not saved_archive:
                if tries > 1:
                    self.sleep(tries)
                self.get_save_request_headers()
                saved_archive = self.archive_url_parser()
                if not saved_archive:
                    continue
                else:
                    self._archive_url = saved_archive
                    self.timestamp()
                    return saved_archive
--- a/waybackpy/utils.py
+++ b/waybackpy/utils.py
@@ -0,0 +1,11 @@
 import requests
 from .__version__ import __version__
 DEFAULT_USER_AGENT = "waybackpy %s - https://github.com/akamhy/waybackpy" % __version__
 def latest_version(package_name, headers):
    request_url = "https://pypi.org/pypi/" + package_name + "/json"
    response = requests.get(request_url, headers=headers)
    data = response.json()
    return data["info"]["version"]
--- a/waybackpy/wrapper.py
+++ b/waybackpy/wrapper.py
@@ -1,175 +1,117 @@
-# -*- coding: utf-8 -*-
+from .save_api import WaybackMachineSaveAPI
 from .availability_api import WaybackMachineAvailabilityAPI
 from .cdx_api import WaybackMachineCDXServerAPI
 from .utils import DEFAULT_USER_AGENT
 from .exceptions import WaybackError
 from datetime import datetime, timedelta
 import re
 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
    from urllib2 import Request, urlopen, URLError
 default_UA = "waybackpy python package - https://github.com/akamhy/waybackpy"
 def _archive_url_parser(header):
    """Parse out the archive from header."""
    # Regex1
    arch = re.search(
        r"Content-Location: (/web/[0-9]{14}/.*)", str(header)
    )
    if arch:
        return "web.archive.org" + arch.group(1)
    # Regex2
    arch = re.search(
        r"rel=\"memento.*?(web\.archive\.org/web/[0-9]{14}/.*?)>", str(header)
    )
    if arch:
        return arch.group(1)
    # Regex3
    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:
            exc = WaybackError("Error while retrieving %s" % req.full_url)
            exc.__cause__ = e
            raise exc
    return response
 class Url:
-    """waybackpy Url object"""
+    def __init__(self, url, user_agent=DEFAULT_USER_AGENT):
    def __init__(self, url, user_agent=default_UA):
        self.url = url
-        self.user_agent = user_agent
+        self.user_agent = str(user_agent)
-        self._url_check()  # checks url validity on init.
+        self.archive_url = None
-
+        self.wayback_machine_availability_api = WaybackMachineAvailabilityAPI(
-    def __repr__(self):
+            self.url, user_agent=self.user_agent
-        return "waybackpy.Url(url=%s, user_agent=%s)" % (self.url, self.user_agent)
+        )
    def __str__(self):
-        return "%s" % self._clean_url()
+        if not self.archive_url:
            self.newest()
        return self.archive_url
    def __len__(self):
-        return len(self._clean_url())
+        td_max = timedelta(
            days=999999999, hours=23, minutes=59, seconds=59, microseconds=999999
        )
-    def _url_check(self):
+        if not self.timestamp:
-        """Check for common URL problems."""
+            self.oldest()
        if "." not in self.url:
            raise URLError("'%s' is not a vaild URL." % self.url)
-    def _clean_url(self):
+        if self.timestamp == datetime.max:
-        """Fix the URL, if possible."""
+            return td_max.days
-        return str(self.url).strip().replace(" ", "_")
+
        return (datetime.utcnow() - self.timestamp).days
    def save(self):
-        """Create a new Wayback Machine archive for this URL."""
+        self.wayback_machine_save_api = WaybackMachineSaveAPI(
-        request_url = "https://web.archive.org/save/" + self._clean_url()
+            self.url, user_agent=self.user_agent
        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()
        if not user_agent:
            user_agent = self.user_agent
        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]
            except AttributeError:
                encoding = "UTF-8"
        return response.read().decode(encoding.replace("text/html", "UTF-8", 1))
    def near(self, year=None, month=None, day=None, hour=None, minute=None):
        """ Return the closest Wayback Machine archive to the time supplied.
            Supported params are year, month, day, hour and minute.
            Any non-supplied parameters default to the current time.
        """
        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,
        )
        self.archive_url = self.wayback_machine_save_api.archive_url
        self.timestamp = self.wayback_machine_save_api.timestamp()
        self.headers = self.wayback_machine_save_api.headers
        return self
-        request_url = "https://archive.org/wayback/available?url=%s&timestamp=%s" % (
+    def near(
-            self._clean_url(),
+        self,
-            timestamp,
+        year=None,
-        )
+        month=None,
-        hdr = {"User-Agent": "%s" % self.user_agent}
+        day=None,
-        req = Request(request_url, headers=hdr)  # nosec
+        hour=None,
-        response = _get_response(req)
+        minute=None,
-        data = json.loads(response.read().decode("UTF-8"))
+        unix_timestamp=None,
-        if not data["archived_snapshots"]:
+    ):
            raise WaybackError(
                "Can not find archive for '%s' try later or 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
        )
        return archive_url
-    def oldest(self, year=1994):
+        self.wayback_machine_availability_api.near(
-        """Return the oldest Wayback Machine archive for this URL."""
+            year=year,
-        return self.near(year=year)
+            month=month,
            day=day,
            hour=hour,
            minute=minute,
            unix_timestamp=unix_timestamp,
        )
        self.set_availability_api_attrs()
        return self
    def oldest(self):
        self.wayback_machine_availability_api.oldest()
        self.set_availability_api_attrs()
        return self
    def newest(self):
-        """Return the newest Wayback Machine archive available for this URL.
+        self.wayback_machine_availability_api.newest()
        self.set_availability_api_attrs()
        return self
-        Due to Wayback Machine database lag, this may not always be the
+    def set_availability_api_attrs(self):
-        most recent archive.
+        self.archive_url = self.wayback_machine_availability_api.archive_url
-        """
+        self.JSON = self.wayback_machine_availability_api.JSON
-        return self.near()
+        self.timestamp = self.wayback_machine_availability_api.timestamp()
-    def total_archives(self):
+    def total_archives(self, start_timestamp=None, end_timestamp=None):
-        """Returns the total number of Wayback Machine archives for this URL."""
+        cdx = WaybackMachineCDXServerAPI(
-        hdr = {"User-Agent": "%s" % self.user_agent}
+            self.url,
-        request_url = (
+            user_agent=self.user_agent,
-            "https://web.archive.org/cdx/search/cdx?url=%s&output=json&fl=statuscode"
+            start_timestamp=start_timestamp,
-            % self._clean_url()
+            end_timestamp=end_timestamp,
        )
-        req = Request(request_url, headers=hdr)  # nosec
+
-        response = _get_response(req)
+        count = 0
-        # Most efficient method to count number of archives (yet)
+        for _ in cdx.snapshots():
-        return str(response.read()).count(",")
+            count = count + 1
        return count
    def known_urls(
        self,
        subdomain=False,
        host=False,
        start_timestamp=None,
        end_timestamp=None,
        match_type="prefix",
    ):
        if subdomain:
            match_type = "domain"
        if host:
            match_type = "host"
        cdx = WaybackMachineCDXServerAPI(
            self.url,
            user_agent=self.user_agent,
            start_timestamp=start_timestamp,
            end_timestamp=end_timestamp,
            match_type=match_type,
            collapses=["urlkey"],
        )
        for snapshot in cdx.snapshots():
            yield (snapshot.original)
Author	SHA1	Message	Date
Akash Mahanty	de5a3e1561	improve usage code	2022-01-18 21:18:17 +05:30
Akash Mahanty	52e46fecc2	more usage example	2022-01-18 20:58:39 +05:30
Akash Mahanty	3b6415abc7	updating examples	2022-01-18 20:44:47 +05:30
Akash Mahanty	66e16d6d89	define __repr__ for the Availability API class	2022-01-18 20:34:21 +05:30
Akash Mahanty	16b9bdd7f9	output the file name if known_url and file flag are passed.	2022-01-18 20:14:44 +05:30
Akash Mahanty	7adc01bff2	implement known_urls for cli from the newer interface. Although use of CDX is recommended but backward-compatibility matters.	2022-01-18 20:07:12 +05:30
Akash Mahanty	9bbd056268	Update README.md	2022-01-17 02:15:38 +05:30
Akash Mahanty	2ab44391cf	close #107 , added link to SecSI/Docker image	2022-01-16 23:01:31 +05:30
Akash Mahanty	cc3628ae18	define __str__ for objects of WaybackMachineAvailabilityAPI class, the check for self.JSON ensures that the API was atleast called.	2022-01-16 22:28:12 +05:30
Akash Mahanty	1d751b942b	invoke json, was a bad idea removing it the earlier commit as the end user should not have to call it	2022-01-16 22:15:25 +05:30
Akash Mahanty	261a867a21	near() method of WaybackMachineAvailabilityAPI return self to preserve past behaviour	2022-01-16 21:53:54 +05:30
Akash Mahanty	2e487e88d3	define __len__ on Url objects, if any method not used prior to len op then default to len of oldest archive.	2022-01-16 21:29:43 +05:30
Akash Mahanty	c8d0ad493a	defined __str__ for Url objects, print func should print the url.	2022-01-16 21:22:43 +05:30
Akash Mahanty	ce869177fd	Merge pull request #103 from akamhy/whitesource/configure Configure WhiteSource Bolt for GitHub	2022-01-02 16:04:15 +05:30
whitesource-bolt-for-github[bot]	58616fb986	Add .whitesource configuration file	2022-01-02 08:45:07 +00:00
Akash Mahanty	4e68cd5743	Create separate module for the 3 different APIs also CDX is now CLI supported.	2022-01-02 14:14:45 +05:30
akamhy	a7b805292d	changes made for v2.4.4 (update download_url) (#100 ) * v2.4.4 (update download_url) * v2.4.4 (update __version__) * +1 add jonasjancarik	2021-09-03 11:28:26 +05:30
Jonáš Jančařík	6dc6124dc4	Raise error on a 509 response (too many sessions) (#99 ) * Raise error on a 509 response (too many sessions) When the response code is 509, raise an error with an explanation (based on the actual error message contained in the response HTML). * Raise error on a 509 response (too many sessions) - linting	2021-09-03 08:04:36 +05:30
Jens Finkhaeuser	5a7fc7d568	Fix typo (#95 )	2021-04-13 16:58:34 +05:30
Akash Mahanty	5a9c861cad	v2.4.3 (#94 ) * 2.4.3 * 2.4.3	2021-04-02 10:41:59 +05:30
Akash Mahanty	dd1917c77e	added RedirectSaveError - for failed saves if the URL is a permanent … (#93 ) * added RedirectSaveError - for failed saves if the URL is a permanent redirect. * check if url is redirect before throwing exceptions, res.url is the redirect url if redirected at all * update tests and cli errors	2021-04-02 10:38:17 +05:30
Akash Mahanty	db8f902cff	Add doc strings (#90 ) * Added some docstrings in utils.py * renamed some func/meth to better names and added doc strings + lint * added more docstrings * more docstrings * improve docstrings * docstrings * added more docstrings, lint * fix import error	2021-01-26 11:56:03 +05:30
Akash Mahanty	88cda94c0b	v2.4.2 (#89 ) * v2.4.2 * v2.4.2	2021-01-24 17:03:35 +05:30
Akash Mahanty	09290f88d1	fix one more error	2021-01-24 16:58:53 +05:30
Akash Mahanty	e5835091c9	import re	2021-01-24 16:56:59 +05:30
Akash Mahanty	7312ed1f4f	set cached_save to True if archive older than 3 mins.	2021-01-24 16:53:36 +05:30
Akash Mahanty	6ae8f843d3	add --file to --known_urls	2021-01-24 16:15:11 +05:30
Akash Mahanty	36b936820b	known urls now yileds, more reliable. And save the file in chucks wrt to response. --file arg can be used to create output file, if --file not used no output will be saved in any file. (#88 )	2021-01-24 16:11:39 +05:30
Akash Mahanty	a3bc6aad2b	too much API usage by duplicate tests was causing too much tests failure	2021-01-23 21:08:21 +05:30
Akash Mahanty	edc2f63d93	Output valid JSON, dumps python dict. Make JSON valid.	2021-01-23 20:43:52 +05:30
Akash Mahanty	ffe0810b12	flag to check if the archive saved is 30 mins older or not	2021-01-16 12:06:08 +05:30
Akash Mahanty	40233eb115	improve code quality, remove unused imports, use system randomness etc	2021-01-16 11:35:13 +05:30
Akash Mahanty	d549d31421	improve save method, now we know that 302 errors indicates that wayback machine is archiving the URL and hasn't yet archived. We construct an artifical archive with the current UTC time and check for HTTP status code 20* or 30*. If we verify the archival, we return the artifical archive. The artificial archive will automatically point to the new archive or in best case will be the new archive after some time.	2021-01-16 10:47:43 +05:30
Akash Mahanty	0725163af8	mimify the logo, remove ugly old logos	2021-01-15 18:14:48 +05:30
Akash Mahanty	712471176b	better error messages(str), check latest version before asking for an upgrade and rm alive checking	2021-01-15 16:47:26 +05:30
Akash Mahanty	dcd7b03302	getting rid of c style str formatting, now using .format	2021-01-14 19:30:07 +05:30
Akash Mahanty	76205d9cf6	backoff_factor=2 for save, incr success by 25%	2021-01-13 10:13:16 +05:30
Akash Mahanty	ec0a0d04cc	+ dequeued0 dequeued0 (https://github.com/dequeued0) for reporting bugs and useful feature requests.	2021-01-12 10:52:41 +05:30
Akash Mahanty	7bb01df846	v2.4.1	2021-01-12 10:18:09 +05:30
Akash Mahanty	6142e0b353	get should retrive the last fetched archive by default	2021-01-12 10:07:14 +05:30
Akash Mahanty	a65990aee3	don't use pagination API if total pages <= 2	2021-01-12 09:46:07 +05:30
Akash Mahanty	259a024eb1	joke? they changed their robots.txt	2021-01-11 23:17:01 +05:30
Akash Mahanty	91402792e6	+ Supported Features tell what the package can do, many users probably do not read the full usage.	2021-01-11 23:01:18 +05:30
Akash Mahanty	eabf4dc046	don't fetch more pages if >=2 pages are empty	2021-01-11 22:43:14 +05:30
Akash Mahanty	5a7bd73565	support unix ts as an arg in near	2021-01-11 19:53:37 +05:30
Akash Mahanty	4693dbf9c1	change str repr of cdxsnapshot to cdx line	2021-01-11 09:34:37 +05:30
Akash Mahanty	f4f2e51315	V2.4.0 (#62 ) * v 2.4.0 * v 2.4.0	2021-01-10 11:53:45 +05:30
Akash Mahanty	d6b7df6837	no need to de-duplicate as we are collapsing the results by urlkey Same urls aren't recieved	2021-01-10 11:36:46 +05:30
Akash Mahanty	dafba5d0cb	collapses=["urlkey"] for known urls	2021-01-10 11:34:06 +05:30
Akash Mahanty	6c71dfbe41	use cdx matchtype for domain and host	2021-01-10 11:10:49 +05:30
Akash Mahanty	a6470b1036	not passing dict to cdxsnapshot	2021-01-10 10:40:32 +05:30
Akash Mahanty	04cda4558e	fix test	2021-01-10 03:18:09 +05:30
Akash Mahanty	625ed63482	remove asserts stmnts	2021-01-10 03:05:48 +05:30
Akash Mahanty	a03813315f	full cdx api support	2021-01-10 02:23:53 +05:30
Akash Mahanty	a2550f17d7	retries support for get requests	2021-01-06 01:58:38 +05:30
Akash Mahanty	15ef5816db	Always cast url to string, avoid passing waybackpy objects to _get_response	2021-01-05 19:46:17 +05:30
Akash Mahanty	93b52bd0fe	FIX : don't use self.user_agent if user_agent passed in get()	2021-01-05 19:31:27 +05:30
Akash Mahanty	28ff877081	Update README.md	2021-01-05 19:08:35 +05:30
Akash Mahanty	3e3ecff9df	l2 heading and lint	2021-01-05 01:59:29 +05:30
Akash Mahanty	ce64135ba8	ce	2021-01-05 01:52:35 +05:30
Akash Mahanty	2af6580ffb	docs link	2021-01-05 01:51:53 +05:30
Akash Mahanty	8a3c515176	v2.3.3	2021-01-05 01:49:26 +05:30
Akash Mahanty	d98c4f32ad	v2.3.3	2021-01-05 01:48:54 +05:30
Akash Mahanty	e0a4b007d5	improve docs	2021-01-05 01:46:12 +05:30
Akash Mahanty	6fb6b2deee	Update readme + new file CONTRIBUTORS.md (#59 ) * remove some badges * remove made with python button, obvious * - maintained badge, we already have latest commit badge - [![Maintenance](https://img.shields.io/badge/Maintained%3F-yes-green.svg)](https://github.com/akamhy/waybackpy/graphs/commit-activity) * re arranged order of badges * a bit more re odering * - release badge * - license section * center h1 * try once more' * removed the TOC * move the hr * Update README.md * + hr * h1 --> h2 * remove tests and pacakging info from here to docs/wiki * Update README.md * example inspired by psf/requests * CLI tool example gist * Update README.md * Update README.md * + license * Update README.md * authors list * Update CONTRIBUTORS.md * fix code * Update README.md * Update README.md * center the button	2021-01-05 00:30:07 +05:30
Akash Mahanty	1882862992	now using cdx Pagination API	2021-01-04 20:46:54 +05:30
Akash Mahanty	0c6107e675	increase coverage	2021-01-04 01:54:40 +05:30
Akash Mahanty	bd079978bf	inc coverage	2021-01-04 00:44:55 +05:30
Akash Mahanty	5dec4927cd	refactoring, try to code complexity	2021-01-04 00:14:38 +05:30
Akash Mahanty	62e5217b9e	reduce code complexity: refactoring, less flow breaking structures	2021-01-03 19:38:25 +05:30
Akash Mahanty	9823c809e9	Added doc strings in wrapper.py, documenting code and improving docs.	2021-01-03 17:11:32 +05:30
Akash Mahanty	db5737a857	JSON is now available for near and other other methods that call it	2021-01-02 18:52:46 +05:30
Akash Mahanty	ca0821a466	Wiki docs (#58 ) * move docs to wiki * Update README.md * Update setup.py	2021-01-02 12:20:43 +05:30
Akash Mahanty	bb4dbc7d3c	rm url = obj.url	2021-01-02 11:19:09 +05:30
Akash Mahanty	7c7fd75376	No need to fetch archive_url and timestamp from availability API on init (#55 ) * No need to fetch archive_url and timestamp from availability API on init. Not useful if all I want is to archive a page * Update test_wrapper.py * Update wrapper.py * Update test_wrapper.py * Update wrapper.py * Update cli.py * Update wrapper.py * Update __version__.py * Update __version__.py * Update __version__.py * Update __version__.py * Update setup.py * Update README.md	2021-01-02 11:10:23 +05:30
Akash Mahanty	0b71433667	v2.3.1 (#54 ) * 2.3.1 * 2.3.1	2021-01-01 19:15:23 +05:30
Akash Mahanty	1b499a7594	removed JSON from init, this was resulting in too much unnecessary taffic. Some users who are thousands of URLs were blocked by IA (#53 ) closes #52	2021-01-01 16:38:57 +05:30
Akash Mahanty	da390ee8a3	improve maintainability and reduce code cognitive complexity (#49 )	2020-12-15 10:24:13 +05:30
Akash Mahanty	d3e68d0e70	code formated with black (#47 )	2020-12-14 01:18:04 +05:30
Akash Mahanty	fde28d57aa	Update CONTRIBUTING.md	2020-12-14 00:16:29 +05:30
Akash Mahanty	6092e504c8	Update CONTRIBUTING.md	2020-12-14 00:15:51 +05:30
Akash Mahanty	93ef60ecd2	v2.3.0 (#46 ) * v2.3.0 * v2.3.0 * decrease line length	2020-12-14 00:14:54 +05:30
Akash Mahanty	461b3f74c9	UPDATE header image url	2020-12-13 23:09:59 +05:30
Akash Mahanty	3c53b411b0	Improve the appearance of readme (#45 ) * replaced text header wth image * svg * Update README.md * Update README.md * Update README.md * level 2 * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Create CONTRIBUTING.md * Update README.md * Add files via upload * Update README.md * Delete waybackpy-colored 284.png * Delete waybackpy colored.png * Update README.md * Update index.rst * Update index.rst * Update index.rst * Update setup.py * Delete index.rst * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md	2020-12-13 23:08:16 +05:30
pyup.io bot	8125526061	create pyup.io config file (#44 )	2020-12-13 22:31:49 +05:30
Akash Mahanty	2dc81569a8	Create .pep8speaks.yml	2020-12-13 17:58:09 +05:30
Akash Mahanty	fd163f3d36	Update wrapper.py	2020-12-13 17:12:32 +05:30
Akash Mahanty	a0a918cf0d	.	2020-12-13 17:10:28 +05:30
Akash Mahanty	4943cf6873	remove print stmnt, update ci	2020-12-13 16:37:35 +05:30
Akash Mahanty	bc3efc7d63	now using requests lib as it handles errors nicely (#42 ) * now using requests lib as it handles errors nicely * remove unused import (urllib) * FIX : replaced full_url with endpoint (not using urlib) * LINT : Found in waybackpy\wrapper.py:88 Unnecessary else after return	2020-12-13 15:44:37 +05:30
Akash Mahanty	f89368f16d	LINT : Found in waybackpy\wrapper.py:88 Unnecessary else after return	2020-12-13 15:39:23 +05:30
Akash Mahanty	c919a6a605	FIX : replaced full_url with endpoint (not using urlib)	2020-12-13 15:22:56 +05:30
Akash Mahanty	0280fca189	remove unused import (urllib)	2020-12-13 15:13:51 +05:30
Akash Mahanty	60ee8b95a8	now using requests lib as it handles errors nicely	2020-12-13 15:05:57 +05:30
Akash Mahanty	ca51c14332	deleted .travis.yml, link with flake (#41 ) close #38	2020-11-26 13:06:50 +05:30
Akash Mahanty	525cf17c6f	Update ci.yml	2020-11-26 12:14:15 +05:30
Akash Mahanty	406e03c52f	Update ci.yml	2020-11-26 12:04:45 +05:30
Akash Mahanty	672b33e83a	Update ci.yml	2020-11-26 10:10:10 +05:30
Akash Mahanty	b19b840628	Update ci.yml	2020-11-26 10:01:55 +05:30
Akash Mahanty	a6df4f899c	Update ci.yml	2020-11-26 09:26:11 +05:30
Akash Mahanty	7686e9c20d	Update README.md (#40 )	2020-11-26 09:18:26 +05:30
Akash Mahanty	3c5932bc39	now using gh actions (#39 )	2020-11-26 09:09:53 +05:30
Akash Mahanty	f9a986f489	Create ci.yml	2020-11-26 08:55:23 +05:30
Akash Mahanty	0d7458ee90	per https://docs.travis-ci.com/user/languages/python/, Python builds are not available on the macOS	2020-11-26 08:08:59 +05:30
Akash Mahanty	ac8b9d6a50	use osx, huge backlog on .org travis for linux builds	2020-11-26 08:03:27 +05:30
Akash Mahanty	58cd9c28e7	Threading enabled checking for URLs	2020-11-26 06:15:42 +05:30
Akash Mahanty	5088305a58	removed python2 compatibility code	2020-11-21 17:00:11 +05:30
Akash Mahanty	9f847a5e55	change pepy.tech download count link, they removed the month page	2020-11-11 10:44:14 +05:30
Akash Mahanty	6c04c2f3d3	+ https://github.com/akamhy/waybackpy/graphs/contributors	2020-11-04 08:09:30 +05:30
Akash Mahanty	925be7b17e	V2.2.0	2020-10-17 17:10:46 +05:30
Akash Mahanty	2b132456ac	updated index.rst and minor docs updated.	2020-10-17 16:56:51 +05:30
Akash Mahanty	50e3154a4e	lint README.md	2020-10-17 12:01:49 +05:30
Akash Mahanty	7aef50428f	add link to the repo	2020-10-17 11:51:56 +05:30
Akash Mahanty	d8ec0f5025	More pythonic code snippets in README (#36 )	2020-10-17 11:49:27 +05:30
Akash Mahanty	0a2f97c034	Update README, drop python 2 support * Drop python 2 support * updated docs * added new docs	2020-10-16 22:37:32 +05:30
Akash Mahanty	3e9cf23578	3.9 archive doesn't not exist yet.	2020-10-16 19:43:06 +05:30
Akash Mahanty	7f927ec7be	added tests for json and archive_url, updated broken tests (#34 ) * added tests for json and archive_url, updated broken tests * drop 2.7 support	2020-10-16 19:25:45 +05:30
Akash Mahanty	9de6393cd5	Add support for JSON and archive_url (#33 ) CLI support for JSON and archive_url attributes	2020-10-16 15:16:18 +05:30
danvalen1	91e7f65617	Fixing len() bug (#32 ) * added class functionality * Update wrapper.py * style edits * fixed bug with len() of url() * fixing len() bug * fixing len() bug * squashing bug * removed test notebook	2020-10-16 10:04:13 +05:30
danvalen1	d465454019	Adding attributes to Url class (#28 ) * added class functionality * Update wrapper.py * style edits	2020-10-15 22:10:32 +05:30
Akash Mahanty	1a81eb97fb	lint	2020-10-03 16:58:11 +05:30
Akash Mahanty	6b3b2e2a7d	tests for newly added known_urls feature	2020-10-03 09:33:50 +05:30
Akash Mahanty	82c65454e6	2.1.9	2020-10-03 01:34:15 +05:30
Akash Mahanty	19710461b6	Update setup.py	2020-10-03 01:33:46 +05:30
Akash Mahanty	a3661d6b85	Update index.rst	2020-10-03 01:33:15 +05:30
Akash Mahanty	58375e4ef4	fix broken links	2020-10-03 01:31:28 +05:30
Akash Mahanty	ea023e98da	update	2020-10-03 01:22:51 +05:30
Akash Mahanty	f1065ed1c8	v2.1.8	2020-10-03 01:18:30 +05:30
Akash Mahanty	315519b21f	2.1.8	2020-10-03 01:18:08 +05:30
Akash Mahanty	07c98661de	add usage for known urls (#26 ) * Update README.md * Update README.md * Update README.md * bash example for known urls * python examples / usage for known urls :) * Update README.md * Update README.md * Update README.md * Update README.md	2020-10-03 01:16:19 +05:30
Akash Mahanty	2cd991a54e	lint markdown	2020-10-02 23:34:06 +05:30
Akash Mahanty	ede251afb3	update tests	2020-10-02 23:10:48 +05:30
Akash Mahanty	a8ce970ca0	fixed yet another issue with tests :(	2020-10-02 23:01:59 +05:30
Akash Mahanty	243af26bf6	update version format in tests	2020-10-02 22:23:58 +05:30
Akash Mahanty	0f1db94884	license & packaging info	2020-10-02 22:10:30 +05:30
Akash Mahanty	c304f58ea2	update tests	2020-10-02 21:35:39 +05:30
Akash Mahanty	23f7222cb5	tweak	2020-10-02 21:01:32 +05:30
Akash Mahanty	ce7294d990	Implemented new feature, known urls for domain.	2020-10-02 20:27:28 +05:30
Akash Mahanty	c9fa114d2e	grammar	2020-10-01 23:50:03 +05:30
Akash	8b6bacb28e	Add files via upload	2020-09-08 09:23:59 +05:30
Akash	32d8ad7780	Update README.md (#24 ) - IA and Wayback machine logo, added new waybackpy logo. + changed pages to webpages in lead	2020-09-08 09:12:48 +05:30
Akash	cbf2f90faa	Add files via upload	2020-09-08 09:06:33 +05:30
Akash	4dde3e3134	Delete a.txt	2020-09-08 09:02:36 +05:30
Akash	1551e8f1c6	Add files via upload	2020-09-08 09:02:19 +05:30
Akash	c84f09e2d2	Create a.txt	2020-09-08 08:59:28 +05:30
		`@@ -0,0 +1 @@`
							<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 176.612 41.908" height="158.392" width="667.51" xmlns:v="https://github.com/akamhy/waybackpy"><text transform="matrix(.862888 0 0 1.158899 -.748 -98.312)" y="110.937" x="0.931" xml:space="preserve" font-weight="bold" font-size="28.149" font-family="sans-serif" letter-spacing="0" word-spacing="0" writing-mode="lr-tb" fill="#003dff"><tspan y="110.937" x="0.931"><tspan y="110.937" x="0.931" letter-spacing="3.568" writing-mode="lr-tb">waybackpy</tspan></tspan></text><path d="M.749 0h153.787v4.864H.749zm22.076 37.418h153.787v4.49H22.825z" fill="navy"/><path d="M0 37.418h22.825v4.49H0zM154.536 0h21.702v4.864h-21.702z" fill="#f0f"/></svg>