V2.4.0 (#62 )

* v 2.4.0 * v 2.4.0
no need to de-duplicate as we are collapsing the results by urlkey
2021-01-10 11:53:45 +05:30 · 2021-01-10 11:36:46 +05:30 · 2021-01-10 11:34:06 +05:30 · 2021-01-10 11:10:49 +05:30 · 2021-01-10 10:40:32 +05:30 · 2021-01-10 03:18:09 +05:30
30 changed files with 2510 additions and 1038 deletions
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -0,0 +1,42 @@
 # This workflow will install Python dependencies, run tests and lint with a variety of Python versions
 # For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
 name: CI
 on:
  push:
    branches: [ master ]
  pull_request:
    branches: [ master ]
 jobs:
  build:
    runs-on: ubuntu-latest
    strategy:
      matrix:
        python-version: ['3.8']
    steps:
    - uses: actions/checkout@v2
    - name: Set up Python ${{ matrix.python-version }}
      uses: actions/setup-python@v2
      with:
        python-version: ${{ matrix.python-version }}
    - name: Install dependencies
      run: |
        python -m pip install --upgrade pip
        python -m pip install flake8 pytest codecov pytest-cov
        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
    - name: Lint with flake8
      run: |
        # stop the build if there are Python syntax errors or undefined names
        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
    - name: Test with pytest
      run: |
        pytest --cov=waybackpy tests/
    - name: Upload coverage to Codecov
      run: |
        bash <(curl -s https://codecov.io/bash) -t ${{ secrets.CODECOV_TOKEN }}
--- a/.gitignore
+++ b/.gitignore
@@ -1,3 +1,6 @@
 # Files generated while testing
 *-urls-*.txt
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]
--- a/.pep8speaks.yml
+++ b/.pep8speaks.yml
@@ -0,0 +1,4 @@
 # File : .pep8speaks.yml
 scanner:
    diff_only: True  # If True, errors caused by only the patch are shown
--- a/.pyup.yml
+++ b/.pyup.yml
@@ -0,0 +1,5 @@
 # autogenerated pyup.io config file 
 # see https://pyup.io/docs/configuration/ for all available options
 schedule: ''
 update: false
--- 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/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -0,0 +1,58 @@
 # Contributing to waybackpy
 We love your input! We want to make contributing to this project as easy and transparent as possible, whether it's:
 - Reporting a bug
 - Discussing the current state of the code
 - Submitting a fix
 - Proposing new features
 - Becoming a maintainer
 ## We Develop with Github
 We use github to host code, to track issues and feature requests, as well as accept pull requests.
 ## We Use [Github Flow](https://guides.github.com/introduction/flow/index.html), So All Code Changes Happen Through Pull Requests
 Pull requests are the best way to propose changes to the codebase (we use [Github Flow](https://guides.github.com/introduction/flow/index.html)). We actively welcome your pull requests:
 1. Fork the repo and create your branch from `master`.
 2. If you've added code that should be tested, add tests.
 3. If you've changed APIs, update the documentation.
 4. Ensure the test suite passes.
 5. Make sure your code lints.
 6. Issue that pull request!
 ## Any contributions you make will be under the MIT Software License
 In short, when you submit code changes, your submissions are understood to be under the same [MIT License](https://github.com/akamhy/waybackpy/blob/master/LICENSE) that covers the project. Feel free to contact the maintainers if that's a concern.
 ## Report bugs using Github's [issues](https://github.com/akamhy/waybackpy/issues)
 We use GitHub issues to track public bugs. Report a bug by [opening a new issue](https://github.com/akamhy/waybackpy/issues/new); it's that easy!
 ## Write bug reports with detail, background, and sample code
 **Great Bug Reports** tend to have:
 - A quick summary and/or background
 - Steps to reproduce
  - Be specific!
  - Give sample code if you can.
 - What you expected would happen
 - What actually happens
 - Notes (possibly including why you think this might be happening, or stuff you tried that didn't work)
 People *love* thorough bug reports. I'm not even kidding.
 ## Use a Consistent Coding Style
 * You can try running `flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics` for style unification.
 ## License
 By contributing, you agree that your contributions will be licensed under its [MIT License](https://github.com/akamhy/waybackpy/blob/master/LICENSE).
 ## References
 This document is forked from [this gist](https://gist.github.com/briandk/3d2e8b3ec8daf5a27a62) by [briandk](https://github.com/briandk) which was itself adapted from the open-source contribution guidelines for [Facebook's Draft](https://github.com/facebook/draft-js/blob/a9316a723f9e918afde44dea68b5f9f39b7d9b00/CONTRIBUTING.md)
--- a/CONTRIBUTORS.md
+++ b/CONTRIBUTORS.md
@@ -0,0 +1,8 @@
 ## AUTHORS
  - akamhy (<https://github.com/akamhy>)
  - danvalen1 (<https://github.com/danvalen1>)
  - AntiCompositeNumber (<https://github.com/AntiCompositeNumber>)
 ## 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.
--- 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 +1,101 @@
-# waybackpy
+<div align="center">
-[![Build Status](https://img.shields.io/travis/akamhy/waybackpy.svg?label=Travis%20CI&logo=travis&style=flat-square)](https://travis-ci.org/akamhy/waybackpy)
+<img src="https://raw.githubusercontent.com/akamhy/waybackpy/master/assets/waybackpy_logo.svg"><br>
 [![Downloads](https://img.shields.io/pypi/dm/waybackpy.svg)](https://pypistats.org/packages/waybackpy)
 [![Release](https://img.shields.io/github/v/release/akamhy/waybackpy.svg)](https://github.com/akamhy/waybackpy/releases)
 [![Codacy Badge](https://api.codacy.com/project/badge/Grade/255459cede9341e39436ec8866d3fb65)](https://www.codacy.com/manual/akamhy/waybackpy?utm_source=github.com&amp;utm_medium=referral&amp;utm_content=akamhy/waybackpy&amp;utm_campaign=Badge_Grade)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://github.com/akamhy/waybackpy/blob/master/LICENSE)
 [![Maintainability](https://api.codeclimate.com/v1/badges/942f13d8177a56c1c906/maintainability)](https://codeclimate.com/github/akamhy/waybackpy/maintainability)
 [![CodeFactor](https://www.codefactor.io/repository/github/akamhy/waybackpy/badge)](https://www.codefactor.io/repository/github/akamhy/waybackpy)
 [![made-with-python](https://img.shields.io/badge/Made%20with-Python-1f425f.svg)](https://www.python.org/)
 ![pypi](https://img.shields.io/pypi/v/waybackpy.svg)
 ![PyPI - Python Version](https://img.shields.io/pypi/pyversions/waybackpy?style=flat-square)
 [![Maintenance](https://img.shields.io/badge/Maintained%3F-yes-green.svg)](https://github.com/akamhy/waybackpy/graphs/commit-activity)
 [![codecov](https://codecov.io/gh/akamhy/waybackpy/branch/master/graph/badge.svg)](https://codecov.io/gh/akamhy/waybackpy)
 ![](https://img.shields.io/github/repo-size/akamhy/waybackpy.svg?label=Repo%20size&style=flat-square)
 ![contributions welcome](https://img.shields.io/static/v1.svg?label=Contributions&message=Welcome&color=0059b3&style=flat-square)
 <h2>Python package & CLI tool that interfaces with the Wayback Machine API</h2>
-![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)
+</div>
 ![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.
+<p align="center">
 <a href="https://pypi.org/project/waybackpy/"><img alt="pypi" src="https://img.shields.io/pypi/v/waybackpy.svg"></a>
 <a href="https://github.com/akamhy/waybackpy/actions?query=workflow%3ACI"><img alt="Build Status" src="https://github.com/akamhy/waybackpy/workflows/CI/badge.svg"></a>
 <a href="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"><img alt="Codacy Badge" src="https://api.codacy.com/project/badge/Grade/255459cede9341e39436ec8866d3fb65"></a>
 <a href="https://codecov.io/gh/akamhy/waybackpy"><img alt="codecov" src="https://codecov.io/gh/akamhy/waybackpy/branch/master/graph/badge.svg"></a>
 <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>
 <a href="https://pepy.tech/project/waybackpy?versions=2*&versions=1*&versions=3*"><img alt="Downloads" src="https://pepy.tech/badge/waybackpy/month"></a>
 <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>
 <a href="#"><img alt="PyPI - Python Version" src="https://img.shields.io/pypi/pyversions/waybackpy?style=flat-square"></a>
 </p>
-Table of contents
+-----------------------------------------------------------------------------------------------------------------------------------------------
 =================
 <!--ts-->
-* [Installation](#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 CLI](#with-the-cli)
    * [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
+### Usage
-### As a python package
+#### As a Python package
 #### Capturing aka Saving an url using save()
 ```python
-import waybackpy
+>>> 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"
-    url = "https://en.wikipedia.org/wiki/Multivariable_calculus",
+>>> wayback = waybackpy.Url(url, user_agent)
    user_agent = "Mozilla/5.0 (Windows NT 5.1; rv:40.0) Gecko/20100101 Firefox/40.0"
-).save()
+>>> archive = wayback.save()
 >>> archive.archive_url
 'https://web.archive.org/web/20210104173410/https://en.wikipedia.org/wiki/Multivariable_calculus'
-print(new_archive_url)
+>>> archive.timestamp
 datetime.datetime(2021, 1, 4, 17, 35, 12, 691741)
 >>> oldest_archive = wayback.oldest()
 >>> oldest_archive.archive_url
 'https://web.archive.org/web/20050422130129/http://en.wikipedia.org:80/wiki/Multivariable_calculus'
 >>> archive_close_to_2010_feb = wayback.near(year=2010, month=2)
 >>> archive_close_to_2010_feb.archive_url
 'https://web.archive.org/web/20100215001541/http://en.wikipedia.org:80/wiki/Multivariable_calculus'
 >>> wayback.newest().archive_url
 'https://web.archive.org/web/20210104173410/https://en.wikipedia.org/wiki/Multivariable_calculus'
 ```
 > Full Python package documentation can be found 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 CLI
 #### 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
 $ waybackpy --total --url "https://en.wikipedia.org/wiki/Linux_kernel" --user_agent "my-unique-user-agent"
 1904
 $ waybackpy --known_urls --url akamhy.github.io --user_agent "my-unique-user-agent"
 https://akamhy.github.io
 https://akamhy.github.io/assets/js/scale.fix.js
 https://akamhy.github.io/favicon.ico
 https://akamhy.github.io/robots.txt
 https://akamhy.github.io/waybackpy/
 'akamhy.github.io-10-urls-m2a24y.txt' saved in current working directory
 ```
-<sub>Try this out in your browser @ <https://repl.it/@akamhy/WaybackPyBashSave></sub>
+> Full CLI documentation can be found at <https://github.com/akamhy/waybackpy/wiki/CLI-docs>.
 #### Oldest archive
 ```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
 ```
 <sub>Try this out in your browser @ <https://repl.it/@akamhy/WaybackPyBashOldest></sub>
 #### Newest archive
 ```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)
+[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://github.com/akamhy/waybackpy/blob/master/LICENSE)
 Released under the MIT License. See
 [license](https://github.com/akamhy/waybackpy/blob/master/LICENSE) for details.
 -----------------------------------------------------------------------------------------------------------------------------------------------
--- a/assets/waybackpy
+++ b/assets/waybackpy
@@ -0,0 +1,268 @@
 <?xml version="1.0" standalone="no"?>
 <!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 20010904//EN"
 "http://www.w3.org/TR/2001/REC-SVG-20010904/DTD/svg10.dtd">
 <svg version="1.0" xmlns="http://www.w3.org/2000/svg"
 width="629.000000pt" height="103.000000pt" viewBox="0 0 629.000000 103.000000"
 preserveAspectRatio="xMidYMid meet">
 <g transform="translate(0.000000,103.000000) scale(0.100000,-0.100000)"
 fill="#000000" stroke="none">
 <path d="M0 515 l0 -515 3145 0 3145 0 0 515 0 515 -3145 0 -3145 0 0 -515z
 m5413 439 c31 -6 36 -10 31 -26 -3 -10 0 -26 7 -34 6 -8 10 -17 7 -20 -3 -2
 -17 11 -32 31 -15 19 -41 39 -59 44 -38 11 -10 14 46 5z m150 -11 c-7 -2 -21
 -2 -30 0 -10 3 -4 5 12 5 17 0 24 -2 18 -5z m-4869 -23 c-6 -6 -21 -6 -39 -1
 -30 9 -30 9 10 10 25 1 36 -2 29 -9z m452 -37 c-3 -26 -15 -65 -25 -88 -10
 -22 -21 -64 -25 -94 -3 -29 -14 -72 -26 -95 -11 -23 -20 -51 -20 -61 0 -30
 -39 -152 -53 -163 -6 -5 -45 -12 -85 -14 -72 -5 -102 4 -102 33 0 6 -9 31 -21
 56 -11 25 -26 72 -33 103 -6 31 -17 64 -24 73 -8 9 -22 37 -32 64 l-18 48 -16
 -39 c-9 -21 -16 -44 -16 -50 0 -6 -7 -24 -15 -40 -8 -16 -24 -63 -34 -106 -11
 -43 -26 -93 -34 -112 -14 -34 -15 -35 -108 -46 -70 -9 -96 -9 -106 0 -21 17
 -43 64 -43 92 0 14 -4 27 -9 31 -12 7 -50 120 -66 200 -8 35 -25 81 -40 103
 -14 22 -27 52 -28 68 -2 28 0 29 48 31 28 1 82 5 120 9 54 4 73 3 82 -7 11
 -15 53 -148 53 -170 0 -7 9 -32 21 -56 20 -41 39 -49 39 -17 0 8 -5 12 -10 9
 -6 -3 -13 2 -16 12 -3 10 -10 26 -15 36 -14 26 7 21 29 -8 l20 -26 7 33 c7 35
 41 149 56 185 7 19 16 23 56 23 27 0 80 2 120 6 80 6 88 1 97 -71 3 -20 9 -42
 14 -48 5 -7 20 -43 32 -82 13 -38 24 -72 26 -74 2 -2 13 4 24 14 13 12 20 31
 20 55 0 20 7 56 15 81 7 24 19 63 25 87 12 47 31 60 89 61 l34 1 -7 -47z
 m3131 41 c17 -3 34 -12 37 -20 3 -7 1 -48 -4 -91 -4 -43 -7 -80 -4 -82 2 -2
 11 2 20 10 9 7 24 18 34 24 9 5 55 40 101 77 79 64 87 68 136 68 28 0 54 -4
 58 -10 3 -5 12 -7 20 -3 9 3 15 -1 15 -9 0 -13 -180 -158 -197 -158 -4 0 -14
 -9 -20 -20 -11 -17 -7 -27 27 -76 22 -32 40 -63 40 -70 0 -7 6 -19 14 -26 7
 -8 37 -48 65 -89 l52 -74 -28 -3 c-51 -5 -74 -12 -68 -22 9 -14 -59 -12 -73 2
 -20 20 -13 30 10 14 34 -24 44 -19 17 8 -25 25 -109 140 -109 149 0 7 -60 97
 -64 97 -2 0 -11 -10 -22 -22 -18 -21 -18 -21 0 -15 10 4 25 2 32 -4 18 -15 19
 -35 2 -22 -7 6 -25 13 -39 17 -34 8 -39 -5 -39 -94 0 -38 -3 -75 -6 -84 -6
 -16 -54 -22 -67 -9 -4 3 -40 7 -81 8 -101 2 -110 10 -104 97 3 37 10 73 16 80
 6 8 10 77 10 174 0 89 2 166 6 172 6 11 162 15 213 6z m301 -1 c-25 -2 -52
 -11 -58 -19 -7 -7 -17 -14 -23 -14 -5 0 -2 9 8 20 14 16 29 20 69 18 l51 -2
 -47 -3z m809 -9 c33 -21 65 -89 62 -132 -1 -21 1 -47 5 -59 9 -28 -26 -111
 -51 -120 -10 -3 -25 -12 -33 -19 -10 -8 -70 -15 -170 -21 l-155 -8 4 -73 c4
 -93 -10 -112 -80 -112 -26 0 -60 5 -74 12 -19 8 -31 8 -51 -1 -45 -20 -55 -1
 -55 98 0 47 -1 111 -3 141 -2 30 -5 107 -7 170 l-4 115 65 2 c36 2 103 7 150
 11 150 15 372 13 397 -4z m338 -19 c11 -14 46 -54 78 -88 l58 -62 62 65 c34
 36 75 73 89 83 28 18 113 24 122 9 3 -5 -32 -51 -77 -102 -147 -167 -134 -143
 -139 -253 -3 -54 -10 -103 -16 -109 -8 -8 -8 -17 -1 -30 14 -26 11 -28 -47
 -29 -119 -2 -165 3 -174 22 -6 10 -9 69 -8 131 l2 113 -57 75 c-32 41 -80 102
 -107 134 -27 33 -47 62 -45 66 3 4 58 6 122 4 113 -3 119 -5 138 -29z m-4233
 13 c16 -13 98 -150 98 -164 0 -4 29 -65 65 -135 36 -71 65 -135 65 -143 0 -10
 -14 -17 -37 -21 -21 -4 -48 -10 -61 -16 -40 -16 -51 -10 -77 41 -29 57 -35 59
 -157 38 -65 -11 -71 -14 -84 -43 -10 -25 -21 -34 -46 -38 -41 -6 -61 8 -48 33
 15 28 12 38 -12 42 -18 2 -23 10 -24 36 -1 27 3 35 23 43 13 5 34 9 46 9 23 0
 57 47 57 78 0 9 10 33 22 52 14 24 21 52 22 92 1 49 4 58 24 67 13 6 31 11 40
 11 9 0 26 7 36 15 24 18 28 18 48 3z m1701 0 c16 -12 97 -143 97 -157 0 -3 32
 -69 70 -146 39 -76 67 -142 62 -147 -4 -4 -28 -12 -52 -17 -25 -6 -57 -13 -72
 -17 -25 -6 -29 -2 -50 42 -14 30 -31 50 -43 53 -11 2 -57 -2 -103 -9 -79 -12
 -83 -13 -96 -45 -10 -24 -22 -34 -46 -38 -43 -9 -53 -1 -45 39 5 30 3 34 -15
 34 -17 0 -20 6 -20 39 0 40 13 50 65 51 19 0 55 48 55 72 0 6 8 29 19 52 32
 72 41 107 31 127 -8 14 -5 21 12 33 12 9 32 16 43 16 11 0 29 7 39 15 24 18
 28 18 49 3z m-3021 -11 c-29 -9 -32 -13 -27 -39 8 -36 -11 -37 -20 -1 -8 32
 15 54 54 52 24 -1 23 -2 -7 -12z m3499 4 c-12 -8 -51 -4 -51 5 0 2 15 4 33 4
 22 0 28 -3 18 -9z m1081 -67 c2 -42 0 -78 -4 -81 -5 -2 -8 18 -8 45 0 27 -3
 64 -6 81 -4 19 -2 31 4 31 6 0 12 -32 14 -76z m-1951 46 c12 -7 19 -21 19 -38
 l-1 -27 -15 28 c-8 15 -22 27 -32 27 -9 0 -24 5 -32 10 -21 14 35 13 61 0z
 m1004 -3 c73 -19 135 -61 135 -92 0 -15 -8 -29 -21 -36 -18 -9 -30 -6 -69 15
 -37 20 -62 26 -109 26 -54 0 -62 -3 -78 -26 -21 -32 -33 -130 -25 -191 9 -58
 41 -84 111 -91 38 -3 61 1 97 17 36 17 49 19 60 10 25 -21 15 -48 -28 -76 -38
 -24 -54 -28 -148 -31 -114 -4 -170 10 -190 48 -6 11 -16 20 -23 20 -24 0 -59
 95 -59 159 0 59 20 122 42 136 6 3 10 13 10 22 0 31 80 82 130 83 19 0 42 5
 50 10 21 13 57 12 115 -3z m-1682 -23 c-14 -14 -28 -23 -31 -20 -8 8 29 46 44
 46 7 0 2 -11 -13 -26z m159 -2 c-20 -15 -22 -23 -16 -60 4 -28 3 -42 -5 -42
 -7 0 -11 19 -11 50 0 36 5 52 18 59 28 17 39 12 14 -7z m1224 -28 c-39 -40
 -46 -38 -19 7 15 24 40 41 52 33 2 -2 -13 -20 -33 -40z m-1538 -33 l62 -66 63
 68 c56 59 68 67 100 67 19 0 38 -3 40 -7 3 -5 -32 -53 -76 -108 -88 -108 -84
 -97 -90 -255 l-2 -55 -87 -3 c-49 -1 -88 -1 -89 0 0 2 -3 50 -5 107 -3 75 -8
 109 -19 121 -8 9 -15 20 -15 25 0 4 -18 29 -41 54 -83 94 -89 102 -84 111 3 6
 45 9 93 9 l87 -1 63 -67z m786 59 c33 -12 48 -42 52 -107 3 -43 0 -57 -16 -73
 l-20 -20 20 -28 c26 -35 35 -89 21 -125 -18 -46 -66 -60 -226 -64 -77 -3 -166
 -7 -198 -10 -84 -7 -99 9 -97 102 1 38 -1 125 -4 191 l-5 122 47 5 c26 3 103
 4 171 2 69 -2 134 1 145 5 29 12 80 12 110 0z m-1050 -16 c3 -8 2 -12 -4 -9
 -6 3 -10 10 -10 16 0 14 7 11 14 -7z m-374 -22 c0 -9 -5 -24 -10 -32 -7 -11
 -10 -5 -10 23 0 23 4 36 10 32 6 -3 10 -14 10 -23z m1701 16 c2 -21 -2 -43
 -10 -51 -4 -4 -7 9 -8 28 -1 32 15 52 18 23z m2859 -28 c-11 -20 -50 -28 -50
 -10 0 6 9 10 19 10 11 0 23 5 26 10 12 19 16 10 5 -10z m-4759 -47 c-8 -15
 -10 -15 -11 -2 0 17 10 32 18 25 2 -3 -1 -13 -7 -23z m2599 9 c0 -9 -40 -35
 -46 -29 -6 6 25 37 37 37 5 0 9 -3 9 -8z m316 -127 c-4 -19 -12 -37 -18 -41
 -8 -5 -9 -1 -5 10 4 10 7 36 7 59 1 35 2 39 11 24 6 -10 8 -34 5 -52z m1942
 38 c-15 -16 -30 -45 -33 -65 -4 -21 -12 -38 -17 -38 -19 0 3 74 30 103 14 15
 30 27 36 27 5 0 -2 -12 -16 -27z m-3855 -16 c-6 -12 -15 -33 -20 -47 -9 -23
 -10 -23 -15 -3 -3 12 3 34 14 52 23 35 37 34 21 -2z m3282 -82 c-23 -18 -81
 -35 -115 -34 -17 1 -11 5 21 13 25 7 54 18 65 24 30 18 53 15 29 -3z m-2585
 -130 c-7 -8 -19 -15 -27 -15 -10 0 -7 8 9 31 18 24 24 27 26 14 2 -9 -2 -22
 -8 -30z m-1775 -5 c-4 -12 -9 -19 -12 -17 -3 3 -2 15 2 27 4 12 9 19 12 17 3
 -3 2 -15 -2 -27z m820 -29 c-9 -8 -25 21 -25 44 0 16 3 14 15 -9 9 -16 13 -32
 10 -35z m2085 47 c0 -17 -31 -48 -47 -48 -11 0 -8 8 9 29 24 32 38 38 38 19z
 m-1655 -47 c-11 -10 -35 11 -35 30 0 21 0 21 19 -2 11 -13 18 -26 16 -28z
 m1221 24 c13 -14 21 -25 18 -25 -11 0 -54 33 -54 41 0 15 12 10 36 -16z
 m-1428 -7 c-3 -7 -18 -14 -34 -15 -20 -1 -22 0 -6 4 12 2 22 9 22 14 0 5 5 9
 11 9 6 0 9 -6 7 -12z m3574 -45 c8 -10 6 -13 -11 -13 -18 0 -21 6 -20 38 0 34
 1 35 10 13 5 -14 15 -31 21 -38z m-4097 14 c19 -4 19 -4 2 -12 -18 -7 -46 16
 -47 39 0 6 6 3 13 -6 6 -9 21 -18 32 -21z m1700 1 c19 -5 19 -5 2 -13 -18 -7
 -46 17 -46 40 0 6 5 3 12 -6 7 -9 21 -19 32 -21z m-1970 12 c-3 -5 -21 -9 -38
 -9 l-32 2 35 7 c19 4 36 8 38 9 2 0 0 -3 -3 -9z m350 0 c-27 -12 -35 -12 -35
 0 0 6 12 10 28 9 24 0 25 -1 7 -9z m1350 0 c-3 -5 -18 -9 -33 -9 l-27 1 30 8
 c17 4 31 8 33 9 2 0 0 -3 -3 -9z m355 0 c-19 -13 -30 -13 -30 0 0 6 10 10 23
 10 18 0 19 -2 7 -10z m-2324 -35 c-6 -22 -11 -25 -44 -24 -31 2 -32 3 -9 6 18
 3 32 14 39 29 14 30 23 24 14 -11z m2839 16 c-14 -14 -73 -26 -60 -13 6 5 19
 12 30 15 34 8 40 8 30 -2z m212 -21 l48 -8 -47 -1 c-56 -1 -78 6 -78 26 0 12
 3 13 14 3 8 -6 36 -15 63 -20z m116 -1 c-6 -6 -18 -6 -28 -3 -18 7 -18 8 1 14
 23 9 39 1 27 -11z m633 -14 c31 5 35 4 21 -5 -9 -6 -34 -10 -55 -8 -31 3 -37
 7 -40 28 l-3 25 19 -23 c16 -20 24 -23 58 -17z m939 15 c16 -7 11 -9 -20 -9
 -29 -1 -36 2 -25 9 17 11 19 11 45 0z m-5445 -24 c6 -8 21 -16 33 -18 19 -3
 20 -4 5 -10 -12 -5 -27 1 -45 17 -16 13 -23 25 -17 25 6 0 17 -6 24 -14z m150
 -76 c0 -11 -4 -20 -10 -20 -14 0 -13 -103 1 -117 21 -21 2 -43 -36 -43 -19 0
 -35 5 -35 11 0 8 -5 7 -15 -1 -21 -17 -44 2 -28 22 22 26 20 128 -2 128 -8 0
 -15 9 -15 19 0 18 8 20 70 20 63 0 70 -2 70 -19z m1189 -63 c17 -32 31 -62 31
 -66 0 -14 -43 -21 -57 -9 -7 6 -29 12 -48 14 -26 2 -35 -1 -40 -16 -4 -12 -12
 -17 -21 -13 -8 3 -13 12 -10 19 3 8 1 14 -4 14 -18 0 -10 22 9 27 22 6 43 46
 35 67 -3 9 5 20 23 30 34 18 38 14 82 -67z m2146 -8 l34 -67 -25 -6 c-14 -4
 -31 -3 -37 2 -7 5 -29 12 -49 16 -31 6 -38 4 -38 -9 0 -8 -7 -15 -15 -15 -8 0
 -15 7 -15 15 0 8 -4 15 -10 15 -19 0 -10 21 14 30 16 6 27 20 31 40 4 18 16
 41 27 52 26 26 40 14 83 -73z m-3205 51 c8 -10 20 -26 27 -36 10 -17 12 -14
 12 19 1 36 2 37 37 37 l37 0 -8 -72 c-3 -40 -11 -76 -17 -79 -20 -13 -43 3
 -62 42 -27 56 -34 56 -41 4 -7 -42 -9 -44 -34 -39 -35 9 -34 6 -35 71 -1 41 4
 62 14 70 18 15 50 7 70 -17z m280 11 c-5 -11 -15 -21 -21 -23 -13 -4 -14 -101
 -3 -120 5 -8 1 -9 -10 -5 -10 4 -29 7 -42 7 -22 0 -24 3 -24 55 0 52 -1 55
 -26 55 -19 0 -25 5 -22 18 2 13 17 18 68 23 36 3 71 6 78 7 9 2 10 -3 2 -17z
 m178 -3 c3 -15 -4 -18 -32 -18 -25 0 -36 -4 -36 -15 0 -10 11 -15 35 -15 24 0
 35 -5 35 -15 0 -11 -11 -15 -41 -15 -55 0 -47 -24 9 -28 29 -2 42 -8 42 -18 0
 -16 -25 -17 -108 -7 l-53 6 2 56 c3 92 1 90 77 88 55 -2 67 -5 70 -19z m230
 10 c18 -18 14 -56 -7 -77 -17 -17 -18 -21 -5 -40 14 -19 13 -21 -4 -21 -10 0
 -28 11 -40 25 -24 27 -52 24 -52 -5 0 -24 -9 -29 -43 -23 -26 5 -27 7 -27 73
 0 45 4 70 13 73 26 11 153 7 165 -5z m557 -2 c47 -20 47 -40 0 -32 -53 10 -77
 -7 -73 -52 l3 -37 48 1 c26 0 47 -3 47 -6 0 -35 -108 -42 -140 -10 -29 29 -27
 94 5 125 28 28 60 31 110 11z m213 -8 c3 -15 -4 -18 -38 -18 -50 0 -51 -22 -1
 -30 44 -7 44 -24 -1 -28 -54 -5 -52 -32 2 -32 29 0 40 -4 40 -15 0 -17 -28
 -19 -104 -9 l-46 7 0 72 0 72 72 -1 c61 -1 73 -4 76 -18z m312 6 c0 -9 -9 -18
 -21 -21 -19 -5 -20 -12 -17 -69 3 -63 3 -63 -22 -58 -49 11 -50 12 -50 64 0
 43 -3 50 -20 50 -13 0 -20 7 -20 20 0 17 8 20 68 23 37 2 70 4 75 5 4 1 7 -5
 7 -14z m155 6 c65 -15 94 -73 62 -125 -14 -24 -25 -28 -92 -33 -44 -3 -54 0
 -78 24 -34 34 -36 82 -4 111 37 34 53 37 112 23z m505 -3 c0 -8 -9 -40 -20
 -72 -11 -31 -18 -60 -16 -64 3 -4 -9 -8 -25 -9 -25 -2 -31 3 -51 45 l-22 47
 -21 -46 c-17 -38 -25 -47 -51 -50 -24 -3 -30 0 -32 17 -1 12 -8 40 -17 64 -21
 59 -20 61 20 61 27 0 35 -4 35 -17 0 -10 4 -24 9 -32 7 -11 13 -6 25 23 14 35
 18 37 53 34 32 -2 39 -7 41 -28 6 -43 19 -43 36 -1 15 40 36 55 36 28z m136
 -4 c27 -45 64 -115 64 -122 0 -13 -42 -22 -54 -12 -6 5 -28 11 -49 15 -32 6
 -38 4 -45 -13 -8 -24 -26 -16 -36 16 -5 16 -2 25 13 32 11 6 25 28 32 48 17
 55 53 71 75 36z m840 -4 c22 -18 16 -32 -11 -25 -59 15 -94 -18 -74 -71 8 -21
 15 -24 47 -22 40 3 66 -7 57 -21 -3 -5 -12 -7 -20 -3 -8 3 -15 1 -15 -4 0 -17
 -111 4 -126 24 -26 34 -13 100 25 131 18 14 96 9 117 -9z m816 -54 l37 -70
 -25 -8 c-16 -6 -30 -5 -40 3 -22 19 -81 22 -88 4 -7 -19 -26 -18 -26 1 0 8 -4
 15 -10 15 -20 0 -9 21 15 30 24 9 30 24 27 63 -1 10 2 16 7 13 5 -3 12 1 15
 10 4 9 15 14 28 12 17 -2 33 -22 60 -73z m183 61 c47 -20 47 -40 0 -32 -46 9
 -75 -7 -75 -42 0 -45 13 -56 59 -49 30 4 41 2 41 -8 0 -32 -95 -35 -134 -4
 -30 24 -34 64 -11 109 22 43 60 51 120 26z m398 4 c19 0 24 -26 6 -32 -13 -4
 -16 -42 -5 -84 l7 -32 -55 -1 c-57 0 -68 7 -41 29 17 14 21 90 5 90 -5 0 -10
 10 -10 21 0 19 4 21 38 15 20 -3 45 -6 55 -6z m117 0 c5 0 17 -13 27 -30 9
 -16 21 -30 25 -30 4 0 8 14 8 30 0 28 3 30 36 30 l36 0 -5 -71 c-2 -42 -9 -74
 -17 -79 -15 -9 -50 -1 -50 12 0 5 -11 25 -24 45 l-24 35 -9 -42 c-4 -23 -11
 -41 -15 -41 -5 1 -19 1 -32 1 -23 0 -23 2 -20 67 3 66 15 88 42 78 8 -3 18 -5
 22 -5z m317 -3 c21 -15 4 -27 -38 -27 -50 0 -49 -23 1 -30 50 -8 51 -30 1 -30
 -30 0 -41 -4 -41 -15 0 -11 12 -15 45 -15 33 0 45 -4 45 -15 0 -17 -24 -19
 -108 -8 l-54 6 6 66 c3 36 5 69 6 72 0 11 124 7 137 -4z m-4374 -7 c9 0 17 -4
 17 -10 0 -5 -16 -10 -35 -10 -28 0 -35 -4 -35 -19 0 -15 8 -21 35 -23 20 -2
 35 -7 35 -13 0 -5 -15 -11 -35 -13 -30 -3 -35 -7 -35 -28 0 -18 -5 -24 -23
 -24 -13 0 -28 -5 -33 -10 -7 -7 -11 9 -13 51 -1 35 -6 70 -11 79 -7 13 -2 16
 28 18 20 2 39 5 41 8 3 3 15 3 26 0 11 -3 28 -6 38 -6z m1856 -14 c23 -21 38
 -20 51 4 6 11 17 20 25 20 16 0 20 -16 6 -24 -17 -11 -50 -94 -44 -114 4 -18
 0 -20 -34 -19 l-38 2 3 40 c3 33 -1 45 -22 64 -36 34 -34 53 5 47 17 -2 39
 -12 48 -20z m299 -18 c-3 -24 -1 -55 3 -70 6 -24 4 -29 -14 -32 -41 -9 -155
 -14 -163 -7 -5 3 -10 36 -12 73 l-2 67 67 4 c38 2 81 4 97 5 27 2 28 1 24 -40z
 m512 22 c0 -11 4 -20 9 -20 4 0 20 9 34 20 25 20 57 27 57 12 0 -5 -14 -18
 -30 -31 l-30 -22 26 -44 c24 -41 24 -45 7 -45 -10 0 -27 14 -37 31 -21 35 -40
 34 -44 -4 -3 -22 -8 -27 -32 -27 -39 0 -43 11 -35 86 l7 64 34 0 c27 0 34 -4
 34 -20z m511 12 c0 -4 1 -36 2 -72 l2 -65 -32 -3 c-28 -3 -32 0 -39 30 l-7 33
 -14 -33 c-16 -40 -34 -41 -51 -2 -16 35 -35 31 -26 -6 6 -22 3 -24 -30 -24
 l-36 0 -1 55 c-1 30 -2 61 -3 68 -1 7 14 13 34 15 33 3 38 -1 59 -39 l24 -42
 18 24 c10 13 19 29 19 35 0 5 4 14 10 20 11 11 70 16 71 6z m509 -28 c0 -31 3
 -35 23 -32 17 2 23 11 25 36 3 29 6 32 36 32 l34 0 1 -75 1 -75 -29 0 c-23 0
 -30 5 -35 26 -5 19 -12 25 -29 22 -17 -2 -22 -10 -22 -30 1 -24 -2 -27 -25
 -22 -45 10 -50 13 -50 33 0 11 -6 21 -12 24 -10 4 -10 7 0 18 6 7 12 25 12 39
 0 34 7 40 42 40 25 0 28 -3 28 -36z"/>
 <path d="M800 860 c30 -24 44 -25 36 -4 -3 9 -6 18 -6 20 0 2 -12 4 -27 4
 l-28 0 25 -20z"/>
 <path d="M310 850 c0 -5 5 -10 10 -10 6 0 10 5 10 10 0 6 -4 10 -10 10 -5 0
 -10 -4 -10 -10z"/>
 <path d="M366 851 c-8 -12 21 -34 33 -27 6 4 8 13 4 21 -6 17 -29 20 -37 6z"/>
 <path d="M920 586 c0 -9 7 -16 16 -16 9 0 14 5 12 12 -6 18 -28 21 -28 4z"/>
 <path d="M965 419 c-4 -6 -5 -13 -2 -16 7 -7 27 6 27 18 0 12 -17 12 -25 -2z"/>
 <path d="M362 388 c3 -7 15 -14 29 -16 24 -4 24 -3 4 12 -24 19 -38 20 -33 4z"/>
 <path d="M4106 883 c-14 -14 -5 -31 14 -26 11 3 20 9 20 13 0 10 -26 20 -34
 13z"/>
 <path d="M4590 870 c-14 -10 -22 -22 -18 -25 7 -8 57 25 58 38 0 12 -14 8 -40
 -13z"/>
 <path d="M4380 655 c7 -8 17 -15 22 -15 6 0 5 7 -2 15 -7 8 -17 15 -22 15 -6
 0 -5 -7 2 -15z"/>
 <path d="M4082 560 c-6 -11 -12 -28 -12 -37 0 -13 6 -10 20 12 11 17 20 33 20
 38 0 14 -15 7 -28 -13z"/>
 <path d="M4496 466 c3 -9 11 -16 16 -16 13 0 5 23 -10 28 -7 2 -10 -2 -6 -12z"/>
 <path d="M4236 445 c-9 -24 5 -41 16 -20 7 11 7 20 0 27 -6 6 -12 3 -16 -7z"/>
 <path d="M4540 400 c0 -5 5 -10 11 -10 5 0 7 5 4 10 -3 6 -8 10 -11 10 -2 0
 -4 -4 -4 -10z"/>
 <path d="M5330 891 c0 -11 26 -22 34 -14 3 3 3 10 0 14 -7 12 -34 11 -34 0z"/>
 <path d="M4805 880 c-8 -13 4 -32 16 -25 12 8 12 35 0 35 -6 0 -13 -4 -16 -10z"/>
 <path d="M5070 821 l-35 -6 0 -75 0 -75 40 -3 c22 -2 58 3 80 10 38 12 40 16
 47 63 12 88 -16 107 -132 86z m109 -36 c3 -19 2 -19 -15 -4 -11 9 -26 19 -34
 22 -8 4 -2 5 15 4 21 -1 31 -8 34 -22z"/>
 <path d="M5411 694 c0 -11 3 -14 6 -6 3 7 2 16 -1 19 -3 4 -6 -2 -5 -13z"/>
 <path d="M5223 674 c-10 -22 -10 -25 3 -20 9 3 18 6 20 6 2 0 4 9 4 20 0 28
 -13 25 -27 -6z"/>
 <path d="M5001 422 c-14 -27 -12 -35 8 -23 7 5 11 17 9 27 -4 17 -5 17 -17 -4z"/>
 <path d="M5673 883 c9 -9 19 -14 23 -11 10 10 -6 28 -24 28 -15 0 -15 -1 1
 -17z"/>
 <path d="M5866 717 c-14 -10 -16 -16 -7 -22 15 -9 35 8 30 24 -3 8 -10 7 -23
 -2z"/>
 <path d="M5700 520 c0 -5 5 -10 10 -10 6 0 10 5 10 10 0 6 -4 10 -10 10 -5 0
 -10 -4 -10 -10z"/>
 <path d="M5700 451 c0 -23 25 -46 34 -32 4 6 -2 19 -14 31 -19 19 -20 19 -20
 1z"/>
 <path d="M1375 850 c-3 -5 -1 -10 4 -10 6 0 11 5 11 10 0 6 -2 10 -4 10 -3 0
 -8 -4 -11 -10z"/>
 <path d="M1391 687 c-5 -12 -7 -35 -6 -50 2 -15 -1 -27 -7 -27 -5 0 -6 9 -3
 21 5 15 4 19 -4 15 -6 -4 -11 -18 -11 -30 0 -19 7 -25 33 -29 17 -2 42 1 55 7
 l22 12 -27 52 c-29 57 -39 63 -52 29z"/>
 <path d="M1240 520 c0 -5 5 -10 10 -10 6 0 10 5 10 10 0 6 -4 10 -10 10 -5 0
 -10 -4 -10 -10z"/>
 <path d="M1575 490 c4 -14 9 -27 11 -29 7 -7 34 9 34 20 0 7 -3 9 -7 6 -3 -4
 -15 1 -26 10 -19 17 -19 17 -12 -7z"/>
 <path d="M3094 688 c-4 -13 -7 -35 -6 -50 1 -16 -2 -28 -8 -28 -5 0 -6 7 -3
 17 4 11 3 14 -5 9 -16 -10 -15 -49 1 -43 6 2 20 0 29 -4 10 -6 27 -5 41 2 28
 13 26 30 -8 86 -24 39 -31 41 -41 11z"/>
 <path d="M3270 502 c0 -19 29 -47 39 -37 6 7 1 16 -15 28 -13 10 -24 14 -24 9z"/>
 <path d="M3570 812 c-13 -10 -21 -24 -19 -31 3 -7 15 0 34 19 31 33 21 41 -15
 12z"/>
 <path d="M3855 480 c-3 -5 -1 -10 4 -10 6 0 11 5 11 10 0 6 -2 10 -4 10 -3 0
 -8 -4 -11 -10z"/>
 <path d="M3585 450 c3 -5 13 -10 21 -10 8 0 12 5 9 10 -3 6 -13 10 -21 10 -8
 0 -12 -4 -9 -10z"/>
 <path d="M1880 820 c0 -5 7 -10 16 -10 8 0 12 5 9 10 -3 6 -10 10 -16 10 -5 0
 -9 -4 -9 -10z"/>
 <path d="M2042 668 c-7 -7 -12 -23 -12 -37 1 -24 2 -24 16 8 16 37 14 47 -4
 29z"/>
 <path d="M2015 560 c4 -6 11 -8 16 -5 14 9 11 15 -7 15 -8 0 -12 -5 -9 -10z"/>
 <path d="M1915 470 c4 -6 11 -8 16 -5 14 9 11 15 -7 15 -8 0 -12 -5 -9 -10z"/>
 <path d="M2320 795 c0 -14 5 -25 10 -25 6 0 10 11 10 25 0 14 -4 25 -10 25 -5
 0 -10 -11 -10 -25z"/>
 <path d="M2660 771 c0 -6 5 -13 10 -16 6 -3 10 1 10 9 0 9 -4 16 -10 16 -5 0
 -10 -4 -10 -9z"/>
 <path d="M2487 763 c-4 -3 -7 -23 -7 -43 0 -36 1 -38 40 -43 68 -9 116 20 102
 61 -3 10 -7 10 -18 1 -11 -9 -14 -7 -14 10 0 18 -6 21 -48 21 -27 0 -52 -3
 -55 -7z"/>
 <path d="M2320 719 c0 -5 5 -7 10 -4 6 3 10 8 10 11 0 2 -4 4 -10 4 -5 0 -10
 -5 -10 -11z"/>
 <path d="M2480 550 l0 -40 66 1 c58 1 67 4 76 25 18 39 -4 54 -78 54 l-64 0 0
 -40z m40 15 c-7 -8 -16 -15 -21 -15 -5 0 -6 7 -3 15 4 8 13 15 21 15 13 0 13
 -3 3 -15z"/>
 <path d="M2665 527 c-4 -10 -5 -21 -1 -24 10 -10 18 4 13 24 -4 17 -4 17 -12
 0z"/>
 <path d="M1586 205 c-9 -23 -8 -25 9 -25 17 0 19 9 6 28 -7 11 -10 10 -15 -3z"/>
 <path d="M3727 200 c-3 -13 0 -20 9 -20 15 0 19 26 5 34 -5 3 -11 -3 -14 -14z"/>
 <path d="M1194 229 c-3 -6 -2 -15 3 -20 13 -13 43 -1 43 17 0 16 -36 19 -46 3z"/>
 <path d="M2470 224 c-18 -46 -12 -73 15 -80 37 -9 52 1 59 40 5 26 3 41 -8 51
 -23 24 -55 18 -66 -11z"/>
 <path d="M3120 196 c0 -9 7 -16 16 -16 17 0 14 22 -4 28 -7 2 -12 -3 -12 -12z"/>
 <path d="M4750 201 c0 -12 5 -21 10 -21 6 0 10 6 10 14 0 8 -4 18 -10 21 -5 3
 -10 -3 -10 -14z"/>
 <path d="M3515 229 c-8 -12 14 -31 30 -26 6 2 10 10 10 18 0 17 -31 24 -40 8z"/>
 <path d="M3521 161 c-7 -5 -9 -11 -4 -14 14 -9 54 4 47 14 -7 11 -25 11 -43 0z"/>
 </g>
 </svg>
--- a/assets/waybackpy-black-white-ls-400.png
+++ b/assets/waybackpy-black-white-ls-400.png
--- a/assets/waybackpy_logo.svg
+++ b/assets/waybackpy_logo.svg
@@ -0,0 +1,85 @@
 <?xml version="1.0" encoding="UTF-8" standalone="no"?>
 <svg
   xmlns:dc="http://purl.org/dc/elements/1.1/"
   xmlns:cc="http://creativecommons.org/ns#"
   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
   xmlns:svg="http://www.w3.org/2000/svg"
   xmlns="http://www.w3.org/2000/svg"
   id="svg8"
   version="1.1"
   viewBox="0 0 176.61171 41.907883"
   height="41.907883mm"
   width="176.61171mm">
  <defs
     id="defs2" />
  <metadata
     id="metadata5">
    <rdf:RDF>
      <cc:Work
         rdf:about="">
        <dc:format>image/svg+xml</dc:format>
        <dc:type
           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
        <dc:title></dc:title>
      </cc:Work>
    </rdf:RDF>
  </metadata>
  <g
     transform="translate(-0.74835286,-98.31182)"
     id="layer1">
    <flowRoot
       transform="scale(0.26458333)"
       style="font-style:normal;font-weight:normal;font-size:40px;line-height:1.25;font-family:sans-serif;letter-spacing:0px;word-spacing:0px;fill:#000000;fill-opacity:1;stroke:none"
       id="flowRoot4598"
       xml:space="preserve"><flowRegion
         id="flowRegion4600"><rect
           y="415.4129"
           x="-38.183765"
           height="48.08326"
           width="257.38687"
           id="rect4602" /></flowRegion><flowPara
         id="flowPara4604"></flowPara></flowRoot>    <text
       transform="scale(0.86288797,1.158899)"
       id="text4777"
       y="110.93711"
       x="0.93061"
       style="font-style:normal;font-variant:normal;font-weight:bold;font-stretch:normal;font-size:28.14887619px;line-height:4.25;font-family:sans-serif;-inkscape-font-specification:'sans-serif, Bold';font-variant-ligatures:normal;font-variant-caps:normal;font-variant-numeric:normal;font-feature-settings:normal;text-align:start;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:start;fill:#003dff;fill-opacity:1;stroke:none;stroke-width:7.51955223;stroke-miterlimit:4;stroke-dasharray:none"
       xml:space="preserve"><tspan
         style="stroke-width:7.51955223"
         id="tspan4775"
         y="110.93711"
         x="0.93061"><tspan
           id="tspan4773"
           style="font-style:normal;font-variant:normal;font-weight:bold;font-stretch:normal;font-size:28.14887619px;font-family:sans-serif;-inkscape-font-specification:'sans-serif, Bold';font-variant-ligatures:normal;font-variant-caps:normal;font-variant-numeric:normal;font-feature-settings:normal;text-align:start;letter-spacing:3.56786728px;writing-mode:lr-tb;text-anchor:start;fill:#003dff;fill-opacity:1;stroke-width:7.51955223;stroke-miterlimit:4;stroke-dasharray:none"
           y="110.93711"
           x="0.93061">waybackpy</tspan></tspan></text>
    <rect
       y="98.311821"
       x="1.4967092"
       height="4.8643045"
       width="153.78688"
       id="rect4644"
       style="opacity:1;fill:#000080;fill-opacity:1;stroke:#00ff00;stroke-width:0;stroke-miterlimit:4;stroke-dasharray:none" />
    <rect
       style="opacity:1;fill:#000080;fill-opacity:1;stroke:#00ff00;stroke-width:0;stroke-miterlimit:4;stroke-dasharray:none"
       id="rect4648"
       width="153.78688"
       height="4.490128"
       x="23.573174"
       y="135.72957" />
    <rect
       y="135.72957"
       x="0.74835336"
       height="4.4901319"
       width="22.82482"
       id="rect4650"
       style="opacity:1;fill:#ff00ff;fill-opacity:1;stroke:#00ff00;stroke-width:0;stroke-miterlimit:4;stroke-dasharray:none" />
    <rect
       style="opacity:1;fill:#ff00ff;fill-opacity:1;stroke:#00ff00;stroke-width:0;stroke-miterlimit:4;stroke-dasharray:none"
       id="rect4652"
       width="21.702286"
       height="4.8643003"
       x="155.2836"
       y="98.311821" />
  </g>
 </svg>
--- a/index.rst
+++ b/index.rst
@@ -1,385 +0,0 @@
 waybackpy
 =========
 |Build Status| |Downloads| |Release| |Codacy Badge| |License: MIT|
 |Maintainability| |CodeFactor| |made-with-python| |pypi| |PyPI - Python
 Version| |Maintenance| |codecov| |image12| |contributions welcome|
 |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 CLI <#with-the-cli>`__
   -  `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 CLI
 ~~~~~~~~~~~~
 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>`__
 .. |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
 .. |Downloads| image:: https://img.shields.io/pypi/dm/waybackpy.svg
   :target: https://pypistats.org/packages/waybackpy
 .. |Release| image:: https://img.shields.io/github/v/release/akamhy/waybackpy.svg
   :target: https://github.com/akamhy/waybackpy/releases
 .. |Codacy Badge| image:: https://api.codacy.com/project/badge/Grade/255459cede9341e39436ec8866d3fb65
   :target: https://www.codacy.com/manual/akamhy/waybackpy?utm_source=github.com&utm_medium=referral&utm_content=akamhy/waybackpy&utm_campaign=Badge_Grade
 .. |License: MIT| image:: https://img.shields.io/badge/License-MIT-yellow.svg
   :target: https://github.com/akamhy/waybackpy/blob/master/LICENSE
 .. |Maintainability| image:: https://api.codeclimate.com/v1/badges/942f13d8177a56c1c906/maintainability
   :target: https://codeclimate.com/github/akamhy/waybackpy/maintainability
 .. |CodeFactor| image:: https://www.codefactor.io/repository/github/akamhy/waybackpy/badge
   :target: https://www.codefactor.io/repository/github/akamhy/waybackpy
 .. |made-with-python| image:: https://img.shields.io/badge/Made%20with-Python-1f425f.svg
   :target: https://www.python.org/
 .. |pypi| image:: https://img.shields.io/pypi/v/waybackpy.svg
 .. |PyPI - Python Version| image:: https://img.shields.io/pypi/pyversions/waybackpy?style=flat-square
 .. |Maintenance| image:: https://img.shields.io/badge/Maintained%3F-yes-green.svg
   :target: https://github.com/akamhy/waybackpy/graphs/commit-activity
 .. |codecov| image:: https://codecov.io/gh/akamhy/waybackpy/branch/master/graph/badge.svg
   :target: https://codecov.io/gh/akamhy/waybackpy
 .. |image12| image:: https://img.shields.io/github/repo-size/akamhy/waybackpy.svg?label=Repo%20size&style=flat-square
 .. |contributions welcome| image:: https://img.shields.io/static/v1.svg?label=Contributions&message=Welcome&color=0059b3&style=flat-square
 .. |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 @@
 requests>=2.24.0
--- a/setup.py
+++ b/setup.py
@@ -1,54 +1,54 @@
 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/2.1.3.tar.gz',
+    download_url="https://github.com/akamhy/waybackpy/archive/2.4.0.tar.gz",
-    keywords = ['wayback', 'archive', 'archive website', 'wayback machine', 'Internet Archive'],
+    keywords=[
-    install_requires=[],
+        "Archive It",
-    python_requires= ">=2.7",
+        "Archive Website",
-    classifiers=[
+        "Wayback Machine",
-        'Development Status :: 5 - Production/Stable',
+        "waybackurls",
-        'Intended Audience :: Developers',
+        "Internet Archive",
        '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"],
-        'console_scripts': [
+    python_requires=">=3.4",
-            'waybackpy = waybackpy.cli:main'
+    classifiers=[
-        ]
+        "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 :: 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/init.py
+++ b/tests/init.py
--- a/tests/test_cdx.py
+++ b/tests/test_cdx.py
@@ -0,0 +1,93 @@
 import pytest
 from waybackpy.cdx import Cdx
 from waybackpy.exceptions import WaybackError
 def test_all_cdx():
    url = "akamhy.github.io"
    user_agent = "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, \
    like Gecko) Chrome/45.0.2454.85 Safari/537.36"
    cdx = Cdx(
        url=url,
        user_agent=user_agent,
        start_timestamp=2017,
        end_timestamp=2020,
        filters=[
            "statuscode:200",
            "mimetype:text/html",
            "timestamp:20201002182319",
            "original:https://akamhy.github.io/",
        ],
        gzip=False,
        collapses=["timestamp:10", "digest"],
        limit=50,
        match_type="prefix",
    )
    snapshots = cdx.snapshots()
    for snapshot in snapshots:
        ans = snapshot.archive_url
    assert "https://web.archive.org/web/20201002182319/https://akamhy.github.io/" == ans
    url = "akahfjgjkmhy.gihthub.ip"
    cdx = Cdx(
        url=url,
        user_agent=user_agent,
        start_timestamp=None,
        end_timestamp=None,
        filters=[],
        match_type=None,
        gzip=True,
        collapses=[],
        limit=10,
    )
    snapshots = cdx.snapshots()
    print(snapshots)
    i = 0
    for _ in snapshots:
        i += 1
    assert i == 0
    url = "https://github.com/akamhy/waybackpy/*"
    cdx = Cdx(url=url, user_agent=user_agent, limit=50)
    snapshots = cdx.snapshots()
    for snapshot in snapshots:
        print(snapshot.archive_url)
    url = "https://github.com/akamhy/waybackpy"
    with pytest.raises(WaybackError):
        cdx = Cdx(url=url, user_agent=user_agent, limit=50, filters=["ghddhfhj"])
        snapshots = cdx.snapshots()
    with pytest.raises(WaybackError):
        cdx = Cdx(url=url, user_agent=user_agent, collapses=["timestamp", "ghdd:hfhj"])
        snapshots = cdx.snapshots()
    url = "https://github.com"
    cdx = Cdx(url=url, user_agent=user_agent, limit=50)
    snapshots = cdx.snapshots()
    c = 0
    for snapshot in snapshots:
        c += 1
        if c > 100:
            break
    url = "https://github.com/*"
    cdx = Cdx(url=url, user_agent=user_agent, collapses=["timestamp"])
    snapshots = cdx.snapshots()
    c = 0
    for snapshot in snapshots:
        c += 1
        if c > 30_529:  # deafult limit is 10k
            break
    url = "https://github.com/*"
    cdx = Cdx(url=url, user_agent=user_agent)
    c = 0
    snapshots = cdx.snapshots()
    for snapshot in snapshots:
        c += 1
        if c > 100_529:
            break
--- a/tests/test_cli.py
+++ b/tests/test_cli.py
@@ -0,0 +1,418 @@
 import sys
 import os
 import pytest
 import random
 import string
 import argparse
 sys.path.append("..")
 import waybackpy.cli as cli  # noqa: E402
 from waybackpy.wrapper import Url  # noqa: E402
 from waybackpy.__version__ import __version__
 def test_save():
    args = argparse.Namespace(
        user_agent=None,
        url="https://pypi.org/user/akamhy/",
        total=False,
        version=False,
        oldest=False,
        save=True,
        json=False,
        archive_url=False,
        newest=False,
        near=False,
        alive=False,
        subdomain=False,
        known_urls=False,
        get=None,
    )
    reply = cli.args_handler(args)
    assert "pypi.org/user/akamhy" in str(reply)
    args = argparse.Namespace(
        user_agent=None,
        url="https://hfjfjfjfyu6r6rfjvj.fjhgjhfjgvjm",
        total=False,
        version=False,
        oldest=False,
        save=True,
        json=False,
        archive_url=False,
        newest=False,
        near=False,
        alive=False,
        subdomain=False,
        known_urls=False,
        get=None,
    )
    reply = cli.args_handler(args)
    assert "could happen because either your waybackpy" in str(reply)
 def test_json():
    args = argparse.Namespace(
        user_agent=None,
        url="https://pypi.org/user/akamhy/",
        total=False,
        version=False,
        oldest=False,
        save=False,
        json=True,
        archive_url=False,
        newest=False,
        near=False,
        alive=False,
        subdomain=False,
        known_urls=False,
        get=None,
    )
    reply = cli.args_handler(args)
    assert "archived_snapshots" in str(reply)
 def test_archive_url():
    args = argparse.Namespace(
        user_agent=None,
        url="https://pypi.org/user/akamhy/",
        total=False,
        version=False,
        oldest=False,
        save=False,
        json=False,
        archive_url=True,
        newest=False,
        near=False,
        alive=False,
        subdomain=False,
        known_urls=False,
        get=None,
    )
    reply = cli.args_handler(args)
    assert "https://web.archive.org/web/" in str(reply)
 def test_oldest():
    args = argparse.Namespace(
        user_agent=None,
        url="https://pypi.org/user/akamhy/",
        total=False,
        version=False,
        oldest=True,
        save=False,
        json=False,
        archive_url=False,
        newest=False,
        near=False,
        alive=False,
        subdomain=False,
        known_urls=False,
        get=None,
    )
    reply = cli.args_handler(args)
    assert "pypi.org/user/akamhy" in str(reply)
    uid = "".join(
        random.choice(string.ascii_lowercase + string.digits) for _ in range(6)
    )
    url = "https://pypi.org/yfvjvycyc667r67ed67r" + uid
    args = argparse.Namespace(
        user_agent=None,
        url=url,
        total=False,
        version=False,
        oldest=True,
        save=False,
        json=False,
        archive_url=False,
        newest=False,
        near=False,
        alive=False,
        subdomain=False,
        known_urls=False,
        get=None,
    )
    reply = cli.args_handler(args)
    assert "Can not find archive for" in str(reply)
 def test_newest():
    args = argparse.Namespace(
        user_agent="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/600.8.9 \
    (KHTML, like Gecko) Version/8.0.8 Safari/600.8.9",
        url="https://pypi.org/user/akamhy/",
        total=False,
        version=False,
        oldest=False,
        save=False,
        json=False,
        archive_url=False,
        newest=True,
        near=False,
        alive=False,
        subdomain=False,
        known_urls=False,
        get=None,
    )
    reply = cli.args_handler(args)
    assert "pypi.org/user/akamhy" in str(reply)
    uid = "".join(
        random.choice(string.ascii_lowercase + string.digits) for _ in range(6)
    )
    url = "https://pypi.org/yfvjvycyc667r67ed67r" + uid
    args = argparse.Namespace(
        user_agent=None,
        url=url,
        total=False,
        version=False,
        oldest=False,
        save=False,
        json=False,
        archive_url=False,
        newest=True,
        near=False,
        alive=False,
        subdomain=False,
        known_urls=False,
        get=None,
    )
    reply = cli.args_handler(args)
    assert "Can not find archive for" in str(reply)
 def test_total_archives():
    args = argparse.Namespace(
        user_agent="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/600.8.9 \
    (KHTML, like Gecko) Version/8.0.8 Safari/600.8.9",
        url="https://pypi.org/user/akamhy/",
        total=True,
        version=False,
        oldest=False,
        save=False,
        json=False,
        archive_url=False,
        newest=False,
        near=False,
        alive=False,
        subdomain=False,
        known_urls=False,
        get=None,
    )
    reply = cli.args_handler(args)
    assert isinstance(reply, int)
 def test_known_urls():
    args = argparse.Namespace(
        user_agent="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/600.8.9 \
    (KHTML, like Gecko) Version/8.0.8 Safari/600.8.9",
        url="https://www.keybr.com",
        total=False,
        version=False,
        oldest=False,
        save=False,
        json=False,
        archive_url=False,
        newest=False,
        near=False,
        alive=False,
        subdomain=False,
        known_urls=True,
        get=None,
    )
    reply = cli.args_handler(args)
    assert "keybr" in str(reply)
    args = argparse.Namespace(
        user_agent="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/600.8.9 \
    (KHTML, like Gecko) Version/8.0.8 Safari/600.8.9",
        url="https://akfyfufyjcujfufu6576r76r6amhy.gitd6r67r6u6hub.yfjyfjio",
        total=False,
        version=False,
        oldest=False,
        save=False,
        json=False,
        archive_url=False,
        newest=False,
        near=False,
        alive=True,
        subdomain=True,
        known_urls=True,
        get=None,
    )
    reply = cli.args_handler(args)
    assert "No known URLs found" in str(reply)
 def test_near():
    args = argparse.Namespace(
        user_agent="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/600.8.9 \
    (KHTML, like Gecko) Version/8.0.8 Safari/600.8.9",
        url="https://pypi.org/user/akamhy/",
        total=False,
        version=False,
        oldest=False,
        save=False,
        json=False,
        archive_url=False,
        newest=False,
        near=True,
        alive=False,
        subdomain=False,
        known_urls=False,
        get=None,
        year=2020,
        month=7,
        day=15,
        hour=1,
        minute=1,
    )
    reply = cli.args_handler(args)
    assert "202007" in str(reply)
    uid = "".join(
        random.choice(string.ascii_lowercase + string.digits) for _ in range(6)
    )
    url = "https://pypi.org/yfvjvycyc667r67ed67r" + uid
    args = argparse.Namespace(
        user_agent=None,
        url=url,
        total=False,
        version=False,
        oldest=False,
        save=False,
        json=False,
        archive_url=False,
        newest=False,
        near=True,
        alive=False,
        subdomain=False,
        known_urls=False,
        get=None,
        year=2020,
        month=7,
        day=15,
        hour=1,
        minute=1,
    )
    reply = cli.args_handler(args)
    assert "Can not find archive for" in str(reply)
 def test_get():
    args = argparse.Namespace(
        user_agent="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/600.8.9 \
    (KHTML, like Gecko) Version/8.0.8 Safari/600.8.9",
        url="https://github.com/akamhy",
        total=False,
        version=False,
        oldest=False,
        save=False,
        json=False,
        archive_url=False,
        newest=False,
        near=False,
        alive=False,
        subdomain=False,
        known_urls=False,
        get="url",
    )
    reply = cli.args_handler(args)
    assert "waybackpy" in str(reply)
    args = argparse.Namespace(
        user_agent="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/600.8.9 \
    (KHTML, like Gecko) Version/8.0.8 Safari/600.8.9",
        url="https://github.com/akamhy/waybackpy",
        total=False,
        version=False,
        oldest=False,
        save=False,
        json=False,
        archive_url=False,
        newest=False,
        near=False,
        alive=False,
        subdomain=False,
        known_urls=False,
        get="oldest",
    )
    reply = cli.args_handler(args)
    assert "waybackpy" in str(reply)
    args = argparse.Namespace(
        user_agent="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/600.8.9 \
    (KHTML, like Gecko) Version/8.0.8 Safari/600.8.9",
        url="https://akamhy.github.io/waybackpy/",
        total=False,
        version=False,
        oldest=False,
        save=False,
        json=False,
        archive_url=False,
        newest=False,
        near=False,
        alive=False,
        subdomain=False,
        known_urls=False,
        get="newest",
    )
    reply = cli.args_handler(args)
    assert "waybackpy" in str(reply)
    args = argparse.Namespace(
        user_agent="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/600.8.9 \
    (KHTML, like Gecko) Version/8.0.8 Safari/600.8.9",
        url="https://pypi.org/user/akamhy/",
        total=False,
        version=False,
        oldest=False,
        save=False,
        json=False,
        archive_url=False,
        newest=False,
        near=False,
        alive=False,
        subdomain=False,
        known_urls=False,
        get="save",
    )
    reply = cli.args_handler(args)
    assert "waybackpy" in str(reply)
    args = argparse.Namespace(
        user_agent="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/600.8.9 \
    (KHTML, like Gecko) Version/8.0.8 Safari/600.8.9",
        url="https://pypi.org/user/akamhy/",
        total=False,
        version=False,
        oldest=False,
        save=False,
        json=False,
        archive_url=False,
        newest=False,
        near=False,
        alive=False,
        subdomain=False,
        known_urls=False,
        get="foobar",
    )
    reply = cli.args_handler(args)
    assert "get the source code of the" in str(reply)
 def test_args_handler():
    args = argparse.Namespace(version=True)
    reply = cli.args_handler(args)
    assert ("waybackpy version %s" % (__version__)) == reply
    args = argparse.Namespace(url=None, version=False)
    reply = cli.args_handler(args)
    assert ("waybackpy %s" % (__version__)) in str(reply)
 def test_main():
    # This also tests the parse_args method in cli.py
    cli.main(["temp.py", "--version"])
--- a/tests/test_snapshot.py
+++ b/tests/test_snapshot.py
@@ -0,0 +1,32 @@
 import pytest
 from waybackpy.snapshot import CdxSnapshot, datetime
 def test_CdxSnapshot():
    sample_input = "org,archive)/ 20080126045828 http://github.com text/html 200 Q4YULN754FHV2U6Q5JUT6Q2P57WEWNNY 1415"
    prop_values = sample_input.split(" ")
    properties = {}
    (
        properties["urlkey"],
        properties["timestamp"],
        properties["original"],
        properties["mimetype"],
        properties["statuscode"],
        properties["digest"],
        properties["length"],
    ) = prop_values
    snapshot = CdxSnapshot(properties)
    assert properties["urlkey"] == snapshot.urlkey
    assert properties["timestamp"] == snapshot.timestamp
    assert properties["original"] == snapshot.original
    assert properties["mimetype"] == snapshot.mimetype
    assert properties["statuscode"] == snapshot.statuscode
    assert properties["digest"] == snapshot.digest
    assert properties["length"] == snapshot.length
    assert datetime.strptime(properties["timestamp"], "%Y%m%d%H%M%S") == snapshot.datetime_timestamp
    archive_url = "https://web.archive.org/web/" + properties["timestamp"] + "/" + properties["original"]
    assert archive_url == snapshot.archive_url
    assert archive_url == str(snapshot)
--- a/tests/test_utils.py
+++ b/tests/test_utils.py
@@ -0,0 +1,186 @@
 import pytest
 import json
 from waybackpy.utils import (
    _cleaned_url,
    _url_check,
    _full_url,
    URLError,
    WaybackError,
    _get_total_pages,
    _archive_url_parser,
    _wayback_timestamp,
    _get_response,
    _check_match_type,
    _check_collapses,
    _check_filters,
    _ts,
 )
 def test_ts():
    timestamp = True
    data = {}
    assert _ts(timestamp, data)
    data = """
    {"archived_snapshots": {"closest": {"timestamp": "20210109155628", "available": true, "status": "200", "url": "http://web.archive.org/web/20210109155628/https://www.google.com/"}}, "url": "https://www.google.com/"}
    """
    data = json.loads(data)
    assert data["archived_snapshots"]["closest"]["timestamp"] == "20210109155628"
 def test_check_filters():
    filters = []
    _check_filters(filters)
    filters = ["statuscode:200", "timestamp:20215678901234", "original:https://url.com"]
    _check_filters(filters)
    with pytest.raises(WaybackError):
        _check_filters("not-list")
 def test_check_collapses():
    collapses = []
    _check_collapses(collapses)
    collapses = ["timestamp:10"]
    _check_collapses(collapses)
    collapses = ["urlkey"]
    _check_collapses(collapses)
    collapses = "urlkey"  # NOT LIST
    with pytest.raises(WaybackError):
        _check_collapses(collapses)
    collapses = ["also illegal collapse"]
    with pytest.raises(WaybackError):
        _check_collapses(collapses)
 def test_check_match_type():
    assert None == _check_match_type(None, "url")
    match_type = "exact"
    url = "test_url"
    assert None == _check_match_type(match_type, url)
    url = "has * in it"
    with pytest.raises(WaybackError):
        _check_match_type("domain", url)
    with pytest.raises(WaybackError):
        _check_match_type("not a valid type", "url")
 def test_cleaned_url():
    test_url = " https://en.wikipedia.org/wiki/Network security "
    answer = "https://en.wikipedia.org/wiki/Network%20security"
    assert answer == _cleaned_url(test_url)
 def test_url_check():
    good_url = "https://akamhy.github.io"
    assert None == _url_check(good_url)
    bad_url = "https://github-com"
    with pytest.raises(URLError):
        _url_check(bad_url)
 def test_full_url():
    params = {}
    endpoint = "https://web.archive.org/cdx/search/cdx"
    assert endpoint == _full_url(endpoint, params)
    params = {"a": "1"}
    assert "https://web.archive.org/cdx/search/cdx?a=1" == _full_url(endpoint, params)
    assert "https://web.archive.org/cdx/search/cdx?a=1" == _full_url(
        endpoint + "?", params
    )
    params["b"] = 2
    assert "https://web.archive.org/cdx/search/cdx?a=1&b=2" == _full_url(
        endpoint + "?", params
    )
    params["c"] = "foo bar"
    assert "https://web.archive.org/cdx/search/cdx?a=1&b=2&c=foo%20bar" == _full_url(
        endpoint + "?", params
    )
 def test_get_total_pages():
    user_agent = "Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko"
    url = "github.com*"
    assert 212890 <= _get_total_pages(url, user_agent)
    url = "https://zenodo.org/record/4416138"
    assert 2 >= _get_total_pages(url, user_agent)
 def test_archive_url_parser():
    perfect_header = """
    {'Server': 'nginx/1.15.8', 'Date': 'Sat, 02 Jan 2021 09:40:25 GMT', 'Content-Type': 'text/html; charset=UTF-8', 'Transfer-Encoding': 'chunked', 'Connection': 'keep-alive', 'X-Archive-Orig-Server': 'nginx', 'X-Archive-Orig-Date': 'Sat, 02 Jan 2021 09:40:09 GMT', 'X-Archive-Orig-Transfer-Encoding': 'chunked', 'X-Archive-Orig-Connection': 'keep-alive', 'X-Archive-Orig-Vary': 'Accept-Encoding', 'X-Archive-Orig-Last-Modified': 'Fri, 01 Jan 2021 12:19:00 GMT', 'X-Archive-Orig-Strict-Transport-Security': 'max-age=31536000, max-age=0;', 'X-Archive-Guessed-Content-Type': 'text/html', 'X-Archive-Guessed-Charset': 'utf-8', 'Memento-Datetime': 'Sat, 02 Jan 2021 09:40:09 GMT', 'Link': '<https://www.scribbr.com/citing-sources/et-al/>; rel="original", <https://web.archive.org/web/timemap/link/https://www.scribbr.com/citing-sources/et-al/>; rel="timemap"; type="application/link-format", <https://web.archive.org/web/https://www.scribbr.com/citing-sources/et-al/>; rel="timegate", <https://web.archive.org/web/20200601082911/https://www.scribbr.com/citing-sources/et-al/>; rel="first memento"; datetime="Mon, 01 Jun 2020 08:29:11 GMT", <https://web.archive.org/web/20201126185327/https://www.scribbr.com/citing-sources/et-al/>; rel="prev memento"; datetime="Thu, 26 Nov 2020 18:53:27 GMT", <https://web.archive.org/web/20210102094009/https://www.scribbr.com/citing-sources/et-al/>; rel="memento"; datetime="Sat, 02 Jan 2021 09:40:09 GMT", <https://web.archive.org/web/20210102094009/https://www.scribbr.com/citing-sources/et-al/>; rel="last memento"; datetime="Sat, 02 Jan 2021 09:40:09 GMT"', 'Content-Security-Policy': "default-src 'self' 'unsafe-eval' 'unsafe-inline' data: blob: archive.org web.archive.org analytics.archive.org pragma.archivelab.org", 'X-Archive-Src': 'spn2-20210102092956-wwwb-spn20.us.archive.org-8001.warc.gz', 'Server-Timing': 'captures_list;dur=112.646325, exclusion.robots;dur=0.172010, exclusion.robots.policy;dur=0.158205, RedisCDXSource;dur=2.205932, esindex;dur=0.014647, LoadShardBlock;dur=82.205012, PetaboxLoader3.datanode;dur=70.750239, CDXLines.iter;dur=24.306278, load_resource;dur=26.520179', 'X-App-Server': 'wwwb-app200', 'X-ts': '200', 'X-location': 'All', 'X-Cache-Key': 'httpsweb.archive.org/web/20210102094009/https://www.scribbr.com/citing-sources/et-al/IN', 'X-RL': '0', 'X-Page-Cache': 'MISS', 'X-Archive-Screenname': '0', 'Content-Encoding': 'gzip'}
    """
    archive = _archive_url_parser(
        perfect_header, "https://www.scribbr.com/citing-sources/et-al/"
    )
    assert "web.archive.org/web/20210102094009" in archive
    header = """
    vhgvkjv
    Content-Location: /web/20201126185327/https://www.scribbr.com/citing-sources/et-al
    ghvjkbjmmcmhj
    """
    archive = _archive_url_parser(
        header, "https://www.scribbr.com/citing-sources/et-al/"
    )
    assert "20201126185327" in archive
    header = """
    hfjkfjfcjhmghmvjm
    X-Cache-Key: https://web.archive.org/web/20171128185327/https://www.scribbr.com/citing-sources/et-al/US
    yfu,u,gikgkikik
    """
    archive = _archive_url_parser(
        header, "https://www.scribbr.com/citing-sources/et-al/"
    )
    assert "20171128185327" in archive
    # The below header should result in Exception
    no_archive_header = """
    {'Server': 'nginx/1.15.8', 'Date': 'Sat, 02 Jan 2021 09:42:45 GMT', 'Content-Type': 'text/html; charset=utf-8', 'Transfer-Encoding': 'chunked', 'Connection': 'keep-alive', 'Cache-Control': 'no-cache', 'X-App-Server': 'wwwb-app52', 'X-ts': '523', 'X-RL': '0', 'X-Page-Cache': 'MISS', 'X-Archive-Screenname': '0'}
    """
    with pytest.raises(WaybackError):
        _archive_url_parser(
            no_archive_header, "https://www.scribbr.com/citing-sources/et-al/"
        )
 def test_wayback_timestamp():
    ts = _wayback_timestamp(year=2020, month=1, day=2, hour=3, minute=4)
    assert "202001020304" in str(ts)
 def test_get_response():
    endpoint = "https://www.google.com"
    user_agent = (
        "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:78.0) Gecko/20100101 Firefox/78.0"
    )
    headers = {"User-Agent": "%s" % user_agent}
    response = _get_response(endpoint, params=None, headers=headers)
    assert response.status_code == 200
    endpoint = "http/wwhfhfvhvjhmom"
    with pytest.raises(WaybackError):
        _get_response(endpoint, params=None, headers=headers)
    endpoint = "https://akamhy.github.io"
    url, response = _get_response(
        endpoint, params=None, headers=headers, return_full_url=True
    )
    assert endpoint == url
--- a/tests/test_wrapper.py
+++ b/tests/test_wrapper.py
@@ -1,82 +1,50 @@
 # -*- coding: utf-8 -*-
 import sys
 import pytest
 import random
-import time
+import requests
 from datetime import datetime
-sys.path.append("..")
+from waybackpy.wrapper import Url, Cdx
 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_url_check():
    """No API Use"""
    broken_url = "http://wwwgooglecom/"
    with pytest.raises(Exception):
-        waybackpy.Url(broken_url, user_agent)
+        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",
+        "akamhy.github.io",
        "commons.wikimedia.org",
        "www.wiktionary.org",
        "www.w3schools.com",
-        "twitter.com",
+        "youtube.com",
    ]
    x = random.randint(0, len(url_list) - 1)
    url1 = url_list[x]
-    target = waybackpy.Url(
+    target = Url(
        url1,
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.36 "
        "(KHTML, like Gecko) Chrome/36.0.1944.0 Safari/537.36",
    )
-    archived_url1 = target.save()
+    archived_url1 = str(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)
+        Url(url2, user_agent)
        time.sleep(5)
        # Test for urls not allowed to archive by robot.txt.
        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 = (
+        target = Url(
                "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 "
@@ -84,37 +52,31 @@ def test_save():
        )
        target.save()
    else:
        pass
 def test_near():
    time.sleep(10)
    url = "google.com"
-    target = waybackpy.Url(
+    target = Url(
        url,
        "Mozilla/5.0 (Windows; U; Windows NT 6.0; de-DE) AppleWebKit/533.20.25 "
        "(KHTML, like Gecko) Version/5.0.3 Safari/533.19.4",
    )
    archive_near_year = target.near(year=2010)
-    assert "2010" in archive_near_year
+    assert "2010" in str(archive_near_year.timestamp)
-    if sys.version_info > (3, 6):
+    archive_near_month_year = str(target.near(year=2015, month=2).timestamp)
        time.sleep(5)
        archive_near_month_year = target.near(year=2015, month=2)
    assert (
-            ("201502" in archive_near_month_year)
+        ("2015-02" in archive_near_month_year)
-            or ("201501" in archive_near_month_year)
+        or ("2015-01" in archive_near_month_year)
-            or ("201503" in archive_near_month_year)
+        or ("2015-03" in archive_near_month_year)
    )
-        target = waybackpy.Url(
+    target = Url(
        "www.python.org",
        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 "
        "(KHTML, like Gecko) Chrome/42.0.2311.135 Safari/537.36 Edge/12.246",
    )
-        archive_near_hour_day_month_year = target.near(
+    archive_near_hour_day_month_year = str(
-            year=2008, month=5, day=9, hour=15
+        target.near(year=2008, month=5, day=9, hour=15)
    )
    assert (
        ("2008050915" in archive_near_hour_day_month_year)
@@ -126,54 +88,58 @@ def test_near():
        NeverArchivedUrl = (
            "https://ee_3n.wrihkeipef4edia.org/rwti5r_ki/Nertr6w_rork_rse7c_urity"
        )
-            target = waybackpy.Url(NeverArchivedUrl, user_agent)
+        target = Url(NeverArchivedUrl, user_agent)
        target.near(year=2010)
    else:
        pass
 def test_oldest():
    url = "github.com/akamhy/waybackpy"
-    target = waybackpy.Url(url, user_agent)
+    target = Url(url, user_agent)
-    assert "20200504141153" in target.oldest()
+    o = target.oldest()
    assert "20200504141153" in str(o)
    assert "2020-05-04" in str(o._timestamp)
 def test_json():
    url = "github.com/akamhy/waybackpy"
    target = Url(url, user_agent)
    assert "archived_snapshots" in str(target.JSON)
 def test_archive_url():
    url = "github.com/akamhy/waybackpy"
    target = Url(url, user_agent)
    assert "github.com/akamhy" in str(target.archive_url)
 def test_newest():
    url = "github.com/akamhy/waybackpy"
-    target = waybackpy.Url(url, user_agent)
+    target = Url(url, user_agent)
-    assert url in target.newest()
+    assert url in str(target.newest())
 def test_get():
-    target = waybackpy.Url("google.com", user_agent)
+    target = Url("google.com", user_agent)
    assert "Welcome to Google" in target.get(target.oldest())
 def test_wayback_timestamp():
    ts = waybackpy._wayback_timestamp(
        year=2020, month=1, day=2, hour=3, minute=4
    )
    assert "202001020304" in str(ts)
 def test_get_response():
    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):
+    user_agent = (
-        target = waybackpy.Url(" https://google.com ", user_agent)
+        "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:78.0) Gecko/20100101 Firefox/78.0"
-        assert target.total_archives() > 500000
+    )
-    else:
+    target = Url(" https://outlook.com ", user_agent)
-        pass
+    assert target.total_archives() > 80000
-    target = waybackpy.Url(
+
    target = Url(
        " https://gaha.e4i3n.m5iai3kip6ied.cima/gahh2718gs/ahkst63t7gad8 ", user_agent
    )
    assert target.total_archives() == 0
 def test_known_urls():
    target = Url("akamhy.github.io", user_agent)
    assert len(target.known_urls(alive=True, subdomain=False)) > 2
    target = Url("akamhy.github.io", user_agent)
    assert len(target.known_urls()) > 3
--- a/waybackpy/init.py
+++ b/waybackpy/init.py
@@ -1,5 +1,3 @@
 # -*- coding: utf-8 -*-
 # ┏┓┏┓┏┓━━━━━━━━━━┏━━┓━━━━━━━━━━┏┓━━┏━━━┓━━━━━
 # ┃┃┃┃┃┃━━━━━━━━━━┃┏┓┃━━━━━━━━━━┃┃━━┃┏━┓┃━━━━━
 # ┃┃┃┃┃┃┏━━┓━┏┓━┏┓┃┗┛┗┓┏━━┓━┏━━┓┃┃┏┓┃┗━┛┃┏┓━┏┓
@@ -10,24 +8,43 @@
 # ━━━━━━━━━━━┗━━┛━━━━━━━━━━━━━━━━━━━━━━━━┗━━┛━
 """
-Waybackpy is a Python library that interfaces with the Internet Archive's Wayback Machine API.
+Waybackpy is a Python package & command-line program that interfaces with the Internet Archive's Wayback Machine API.
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-Archive pages and retrieve archived pages easily.
+Archive webpage and retrieve archived URLs 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/>.
+    >>> url = "https://en.wikipedia.org/wiki/Multivariable_calculus"
-:copyright: (c) 2020 by akamhy.
+    >>> user_agent = "Mozilla/5.0 (Windows NT 5.1; rv:40.0) Gecko/20100101 Firefox/40.0"
    >>> wayback = waybackpy.Url(url, user_agent)
    >>> archive = wayback.save()
    >>> str(archive)
    'https://web.archive.org/web/20210104173410/https://en.wikipedia.org/wiki/Multivariable_calculus'
    >>> archive.timestamp
    datetime.datetime(2021, 1, 4, 17, 35, 12, 691741)
    >>> oldest_archive = wayback.oldest()
    >>> str(oldest_archive)
    'https://web.archive.org/web/20050422130129/http://en.wikipedia.org:80/wiki/Multivariable_calculus'
    >>> archive_close_to_2010_feb = wayback.near(year=2010, month=2)
    >>> str(archive_close_to_2010_feb)
    'https://web.archive.org/web/20100215001541/http://en.wikipedia.org:80/wiki/Multivariable_calculus'
    >>> str(wayback.newest())
    'https://web.archive.org/web/20210104173410/https://en.wikipedia.org/wiki/Multivariable_calculus'
 Full documentation @ <https://github.com/akamhy/waybackpy/wiki>.
 :copyright: (c) 2020-2021 AKash Mahanty Et al.
 :license: MIT
 """
-from .wrapper import Url
+from .wrapper import Url, Cdx
 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__ = (
    "A Python package that interfaces with the Internet Archive's Wayback Machine API. "
    "Archive pages and retrieve archived pages easily."
 )
 __url__ = "https://akamhy.github.io/waybackpy/"
-__version__ = "2.1.3"
+__version__ = "2.4.0"
 __author__ = "akamhy"
-__author_email__ = "akash3pro@gmail.com"
+__author_email__ = "akamhy@yahoo.com"
 __license__ = "MIT"
-__copyright__ = "Copyright 2020 akamhy"
+__copyright__ = "Copyright 2020-2021 Akash Mahanty et al."
--- a/waybackpy/cdx.py
+++ b/waybackpy/cdx.py
@@ -0,0 +1,205 @@
 from .snapshot import CdxSnapshot
 from .exceptions import WaybackError
 from .utils import (
    _get_total_pages,
    _get_response,
    default_user_agent,
    _check_filters,
    _check_collapses,
    _check_match_type,
    _add_payload,
 )
 # TODO : Threading support for pagination API. It's designed for Threading.
 class Cdx:
    def __init__(
        self,
        url,
        user_agent=default_user_agent,
        start_timestamp=None,
        end_timestamp=None,
        filters=[],
        match_type=None,
        gzip=True,
        collapses=[],
        limit=10000,
    ):
        self.url = str(url).strip()
        self.user_agent = str(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
        self.collapses = collapses
        _check_collapses(self.collapses)
        self.limit = limit
        self.last_api_request_url = None
        self.use_page = False
    def cdx_api_manager(self, payload, headers, use_page=False):
        """
        We have two options to get the snapshots, we use this
        method to make a selection between pagination API and
        the normal one with Resumption Key, sequential querying
        of CDX data. For very large querying (for example domain query),
        it may be useful to perform queries in parallel and also estimate
        the total size of the query.
        read more about the pagination API at:
        https://web.archive.org/web/20201228063237/https://github.com/internetarchive/wayback/blob/master/wayback-cdx-server/README.md#pagination-api
        if use_page is false if will use the normal sequential query API,
        else use the pagination API.
        two mutually exclusive cases possible:
        1) pagination API is selected
            a) get the total number of pages to read, using _get_total_pages()
            b) then we use a for loop to get all the pages and yield the response text
        2) normal sequential query API is selected.
            a) get use showResumeKey=true to ask the API to add a query resumption key
               at the bottom of response
            b) check if the page has more than 3 lines, if not return the text
            c) if it has atleast three lines, we check the second last line for zero length.
            d) if the second last line has length zero than we assume that the last line contains
               the resumption key, we set the resumeKey and remove the resumeKey from text
            e) if the second line has non zero length we return the text as there will no resumption key
            f) if we find the resumption key we set the "more" variable status to True which is always set
               to False on each iteration. If more is not True the iteration stops and function returns.
        """
        endpoint = "https://web.archive.org/cdx/search/cdx"
        if use_page == True:
            total_pages = _get_total_pages(self.url, self.user_agent)
            for i in range(total_pages):
                payload["page"] = str(i)
                url, res = _get_response(
                    endpoint, params=payload, headers=headers, return_full_url=True
                )
                self.last_api_request_url = url
                yield res.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(
                    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 snapshots(self):
        """
        This function yeilds snapshots encapsulated
        in CdxSnapshot for more usability.
        All the get request values are set if the conditions match
        And we use logic that if someone's only inputs don't have any
        of [start_timestamp, end_timestamp] and don't use any collapses
        then we use the pagination API as it returns archives starting
        from the first archive and the recent most archive will be on
        the last page.
        """
        payload = {}
        headers = {"User-Agent": self.user_agent}
        _add_payload(self, 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(" ")
                # Making sure that we get the same number of
                # property values as the number of properties
                prop_values_len = len(prop_values)
                properties_len = len(properties)
                if prop_values_len != properties_len:
                    raise WaybackError(
                        "Snapshot returned by Cdx API has %s properties instead of expected %s properties.\nInvolved Snapshot : %s"
                        % (prop_values_len, properties_len, snapshot)
                    )
                (
                    properties["urlkey"],
                    properties["timestamp"],
                    properties["original"],
                    properties["mimetype"],
                    properties["statuscode"],
                    properties["digest"],
                    properties["length"],
                ) = prop_values
                yield CdxSnapshot(properties)
--- a/waybackpy/cli.py
+++ b/waybackpy/cli.py
@@ -1,104 +1,312 @@
-# -*- coding: utf-8 -*-
+import os
-from __future__ import print_function
+import re
 import sys
 import random
 import string
 import argparse
-from waybackpy.wrapper import Url
+from .wrapper import Url
-from waybackpy.__version__ import __version__
+from .exceptions import WaybackError
 from .__version__ import __version__
 def _save(obj):
-    print(obj.save())
+    try:
        return obj.save()
    except Exception as err:
        e = str(err)
        m = re.search(r"Header:\n(.*)", e)
        if m:
            header = m.group(1)
        if "No archive URL found in the API response" in e:
            return (
                "\n[waybackpy] Can not save/archive your link.\n[waybackpy] This "
                "could happen because either your waybackpy (%s) is likely out of "
                "date or Wayback Machine is malfunctioning.\n[waybackpy] Visit "
                "https://github.com/akamhy/waybackpy for the latest version of "
                "waybackpy.\n[waybackpy] API response Header :\n%s"
                % (__version__, header)
            )
        return WaybackError(err)
 def _archive_url(obj):
    return obj.archive_url
 def _json(obj):
    return obj.JSON
 def no_archive_handler(e, obj):
    m = re.search(r"archive\sfor\s\'(.*?)\'\stry", str(e))
    if m:
        url = m.group(1)
        ua = obj.user_agent
        if "github.com/akamhy/waybackpy" in ua:
            ua = "YOUR_USER_AGENT_HERE"
        return (
            "\n[Waybackpy] Can not find archive for '%s'.\n[Waybackpy] You can"
            " save the URL using the following command:\n[Waybackpy] waybackpy --"
            'user_agent "%s" --url "%s" --save' % (url, ua, url)
        )
    return WaybackError(e)
 def _oldest(obj):
-    print(obj.oldest())
+    try:
        return obj.oldest()
    except Exception as e:
        return no_archive_handler(e, obj)
 def _newest(obj):
-    print(obj.newest())
+    try:
        return obj.newest()
    except Exception as e:
        return no_archive_handler(e, obj)
 def _total_archives(obj):
-    print(obj.total_archives())
+    return obj.total_archives()
 def _near(obj, args):
    _near_args = {}
-    if args.year:
+    args_arr = [args.year, args.month, args.day, args.hour, args.minute]
-        _near_args["year"] = args.year
+    keys = ["year", "month", "day", "hour", "minute"]
-    if args.month:
+
-        _near_args["month"] = args.month
+    for key, arg in zip(keys, args_arr):
-    if args.day:
+        if arg:
-        _near_args["day"] = args.day
+            _near_args[key] = arg
-    if args.hour:
+
-        _near_args["hour"] = args.hour
+    try:
-    if args.minute:
+        return obj.near(**_near_args)
-        _near_args["minute"] = args.minute
+    except Exception as e:
-    print(obj.near(**_near_args))
+        return no_archive_handler(e, obj)
 def _save_urls_on_file(input_list, live_url_count):
    m = re.search("https?://([A-Za-z_0-9.-]+).*", input_list[0])
    domain = "domain-unknown"
    if m:
        domain = m.group(1)
    uid = "".join(
        random.choice(string.ascii_lowercase + string.digits) for _ in range(6)
    )
    file_name = "%s-%d-urls-%s.txt" % (domain, live_url_count, uid)
    file_content = "\n".join(input_list)
    file_path = os.path.join(os.getcwd(), file_name)
    with open(file_path, "w+") as f:
        f.write(file_content)
    return "%s\n\n'%s' saved in current working directory" % (file_content, file_name)
 def _known_urls(obj, args):
    """
    Known urls for a domain.
    """
    subdomain = False
    if args.subdomain:
        subdomain = True
    alive = False
    if args.alive:
        alive = True
    url_list = obj.known_urls(alive=alive, subdomain=subdomain)
    total_urls = len(url_list)
    if total_urls > 0:
        return _save_urls_on_file(url_list, total_urls)
    return "No known URLs found. Please try a diffrent domain!"
 def _get(obj, args):
    if args.get.lower() == "url":
-        print(obj.get())
+        return obj.get()
-
+    if args.get.lower() == "archive_url":
-    elif args.get.lower() == "oldest":
+        return obj.get(obj.archive_url)
-        print(obj.get(obj.oldest()))
+    if args.get.lower() == "oldest":
-
+        return obj.get(obj.oldest())
-    elif args.get.lower() == "latest" or args.get.lower() == "newest":
+    if args.get.lower() == "latest" or args.get.lower() == "newest":
-        print(obj.get(obj.newest()))
+        return obj.get(obj.newest())
-
+    if args.get.lower() == "save":
-    elif args.get.lower() == "save":
+        return obj.get(obj.save())
-        print(obj.get(obj.save()))
+    return "Use get as \"--get 'source'\", 'source' can be one of the followings: \
    else:
        print("Use get as \"--get 'source'\", 'source' can be one of the followings: \
        \n1) url - get the source code of the url specified using --url/-u.\
-        \n2) oldest - get the source code of the oldest archive for the supplied url.\
+        \n2) archive_url - get the source code of the newest archive for the supplied url, alias of newest.\
-        \n3) newest - get the source code of the newest archive for the supplied url.\
+        \n3) oldest - get the source code of the oldest archive for the supplied url.\
-        \n4) save - Create a new archive and get the source code of this new archive for the supplied url.")
+        \n4) newest - get the source code of the newest archive for the supplied url.\
        \n5) save - Create a new archive and get the source code of this new archive for the supplied url."
 def main():
    parser = argparse.ArgumentParser()
    parser.add_argument("-u", "--url", help="URL on which Wayback machine operations would occur.")
    parser.add_argument("-ua", "--user_agent", help="User agent, default user_agent is \"waybackpy python package - https://github.com/akamhy/waybackpy\".")
    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.")
    parser.add_argument("-n", "--newest", action='store_true', help="Newest archive for the specified URL.")
    parser.add_argument("-t", "--total", action='store_true', help="Total number of archives for the specified URL.")
    parser.add_argument("-g", "--get", help="Prints the source code of the supplied url. Use '--get help' for extended usage.")
    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.")
    parser.add_argument("-Y", "--year", type=int, help="Year in integer. For use with --near.")
    parser.add_argument("-M", "--month", type=int, help="Month in integer. For use with --near.")
    parser.add_argument("-D", "--day", type=int, help="Day in integer. For use with --near.")
    parser.add_argument("-H", "--hour", type=int, help="Hour in integer. For use with --near.")
    parser.add_argument("-MIN", "--minute", type=int, help="Minute in integer. For use with --near.")
    args = parser.parse_args()
 def args_handler(args):
    if args.version:
-        print(__version__)
+        return "waybackpy version %s" % __version__
        return
    if not args.url:
-        print("Specify an URL. See --help")
+        return (
-        return
+            "waybackpy %s \nSee 'waybackpy --help' for help using this tool."
            % __version__
        )
-    # create the object with or without the user_agent
+    obj = Url(args.url)
    if args.user_agent:
        obj = Url(args.url, args.user_agent)
    else:
        obj = Url(args.url)
    if args.save:
-        _save(obj)
+        output = _save(obj)
    elif args.archive_url:
        output = _archive_url(obj)
    elif args.json:
        output = _json(obj)
    elif args.oldest:
-        _oldest(obj)
+        output = _oldest(obj)
    elif args.newest:
-        _newest(obj)
+        output = _newest(obj)
    elif args.known_urls:
        output = _known_urls(obj, args)
    elif args.total:
-        _total_archives(obj)
+        output = _total_archives(obj)
    elif args.near:
-        _near(obj, args)
+        return _near(obj, args)
    elif args.get:
-        _get(obj, args)
+        output = _get(obj, args)
    else:
-        print("Usage: waybackpy --url [URL] --user_agent [USER AGENT] [OPTIONS]. See --help")
+        output = (
            "You only specified the URL. But you also need to specify the operation."
            "\nSee 'waybackpy --help' for help using this tool."
        )
    return output
 def add_requiredArgs(requiredArgs):
    requiredArgs.add_argument(
        "--url", "-u", help="URL on which Wayback machine operations would occur"
    )
 def add_userAgentArg(userAgentArg):
    help_text = 'User agent, default user_agent is "waybackpy python package - https://github.com/akamhy/waybackpy"'
    userAgentArg.add_argument("--user_agent", "-ua", help=help_text)
 def add_saveArg(saveArg):
    saveArg.add_argument(
        "--save", "-s", action="store_true", help="Save the URL on the Wayback machine"
    )
 def add_auArg(auArg):
    auArg.add_argument(
        "--archive_url",
        "-au",
        action="store_true",
        help="Get the latest archive URL, alias for --newest",
    )
 def add_jsonArg(jsonArg):
    jsonArg.add_argument(
        "--json",
        "-j",
        action="store_true",
        help="JSON data of the availability API request",
    )
 def add_oldestArg(oldestArg):
    oldestArg.add_argument(
        "--oldest",
        "-o",
        action="store_true",
        help="Oldest archive for the specified URL",
    )
 def add_newestArg(newestArg):
    newestArg.add_argument(
        "--newest",
        "-n",
        action="store_true",
        help="Newest archive for the specified URL",
    )
 def add_totalArg(totalArg):
    totalArg.add_argument(
        "--total",
        "-t",
        action="store_true",
        help="Total number of archives for the specified URL",
    )
 def add_getArg(getArg):
    getArg.add_argument(
        "--get",
        "-g",
        help="Prints the source code of the supplied url. Use '--get help' for extended usage",
    )
 def add_knownUrlArg(knownUrlArg):
    knownUrlArg.add_argument(
        "--known_urls", "-ku", action="store_true", help="URLs known for the domain."
    )
    help_text = "Use with '--known_urls' to include known URLs for subdomains."
    knownUrlArg.add_argument("--subdomain", "-sub", action="store_true", help=help_text)
    help_text = "Only include live URLs. Will not inlclude dead links."
    knownUrlArg.add_argument("--alive", "-a", action="store_true", help=help_text)
 def add_nearArg(nearArg):
    nearArg.add_argument(
        "--near", "-N", action="store_true", help="Archive near specified time"
    )
 def add_nearArgs(nearArgs):
    nearArgs.add_argument("--year", "-Y", type=int, help="Year in integer")
    nearArgs.add_argument("--month", "-M", type=int, help="Month in integer")
    nearArgs.add_argument("--day", "-D", type=int, help="Day in integer.")
    nearArgs.add_argument("--hour", "-H", type=int, help="Hour in intege")
    nearArgs.add_argument("--minute", "-MIN", type=int, help="Minute in integer")
 def parse_args(argv):
    parser = argparse.ArgumentParser()
    add_requiredArgs(parser.add_argument_group("URL argument (required)"))
    add_userAgentArg(parser.add_argument_group("User Agent"))
    add_saveArg(parser.add_argument_group("Create new archive/save URL"))
    add_auArg(parser.add_argument_group("Get the latest Archive"))
    add_jsonArg(parser.add_argument_group("Get the JSON data"))
    add_oldestArg(parser.add_argument_group("Oldest archive"))
    add_newestArg(parser.add_argument_group("Newest archive"))
    add_totalArg(parser.add_argument_group("Total number of archives"))
    add_getArg(parser.add_argument_group("Get source code"))
    add_knownUrlArg(
        parser.add_argument_group(
            "URLs known and archived to Waybcak Machine for the site."
        )
    )
    add_nearArg(parser.add_argument_group("Archive close to time specified"))
    add_nearArgs(parser.add_argument_group("Arguments that are used only with --near"))
    parser.add_argument(
        "--version", "-v", action="store_true", help="Waybackpy version"
    )
    return parser.parse_args(argv[1:])
 def main(argv=None):
    argv = sys.argv if argv is None else argv
    print(args_handler(parse_args(argv)))
 if __name__ == "__main__":
-    main()
+    sys.exit(main(sys.argv))
--- a/waybackpy/exceptions.py
+++ b/waybackpy/exceptions.py
@@ -1,6 +1,19 @@
-# -*- 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 URLError(Exception):
    """
    Raised when malformed URLs are passed as arguments.
    """
--- a/waybackpy/snapshot.py
+++ b/waybackpy/snapshot.py
@@ -0,0 +1,28 @@
 from datetime import datetime
 class CdxSnapshot:
    """
    This class helps to use the Cdx Snapshots easily.
    Raw Snapshot data looks like:
    org,archive)/ 20080126045828 http://github.com text/html 200 Q4YULN754FHV2U6Q5JUT6Q2P57WEWNNY 1415
    properties is a dict containg all of the 7 cdx snapshot properties.
    """
    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 self.archive_url
--- a/waybackpy/utils.py
+++ b/waybackpy/utils.py
@@ -0,0 +1,286 @@
 import re
 import requests
 from .exceptions import WaybackError, URLError
 from datetime import datetime
 from urllib3.util.retry import Retry
 from requests.adapters import HTTPAdapter
 from .__version__ import __version__
 quote = requests.utils.quote
 default_user_agent = "waybackpy python package - https://github.com/akamhy/waybackpy"
 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
    payload["url"] = self.url
 def _ts(timestamp, data):
    """
    Get timestamp of last fetched archive.
    If used before fetching any archive, will
    use whatever self.JSON returns.
    self.timestamp is None implies that
    self.JSON will return any archive's JSON
    that wayback machine provides it.
    """
    if timestamp:
        return timestamp
    if not data["archived_snapshots"]:
        return datetime.max
    return datetime.strptime(
        data["archived_snapshots"]["closest"]["timestamp"], "%Y%m%d%H%M%S"
    )
 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:
        raise WaybackError(
            "%s is not an allowed match type.\nUse one from 'exact', 'prefix', 'host' or 'domain'"
            % match_type
        )
 def _check_collapses(collapses):
    if not isinstance(collapses, list):
        raise WaybackError("collapses must be a list.")
    if len(collapses) == 0:
        return
    for c in collapses:
        try:
            match = re.search(
                r"(urlkey|timestamp|original|mimetype|statuscode|digest|length)(:?[0-9]{1,99})?",
                c,
            )
            field = match.group(1)
            N = None
            if 2 == len(match.groups()):
                N = match.group(2)
            if N:
                if not (field + N == c):
                    raise Exception
            else:
                if not (field == c):
                    raise Exception
        except Exception:
            e = "collapse argument '%s' is not following the cdx collapse syntax." % c
            raise WaybackError(e)
 def _check_filters(filters):
    if not isinstance(filters, list):
        raise WaybackError("filters must be a list.")
    # [!]field:regex
    for f in filters:
        try:
            match = re.search(
                r"(\!?(?:urlkey|timestamp|original|mimetype|statuscode|digest|length)):(.*)",
                f,
            )
            key = match.group(1)
            val = match.group(2)
        except Exception:
            e = "Filter '%s' not following the cdx filter syntax." % f
            raise WaybackError(e)
 def _cleaned_url(url):
    return str(url).strip().replace(" ", "%20")
 def _url_check(url):
    """
    Check for common URL problems.
    What we are checking:
    1) '.' in self.url, no url that ain't '.' in it.
    If you known any others, please create a PR on the github repo.
    """
    if "." not in url:
        raise URLError("'%s' is not a vaild URL." % url)
 def _full_url(endpoint, params):
    full_url = endpoint
    if params:
        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 + "%s=%s" % (key, quote(str(val)))
    return full_url
 def _get_total_pages(url, user_agent):
    """
    If showNumPages is passed in cdx API, it returns
    'number of archive pages'and each page has many archives.
    This func returns number of pages of archives (type int).
    """
    total_pages_url = (
        "https://web.archive.org/cdx/search/cdx?url=%s&showNumPages=true" % url
    )
    headers = {"User-Agent": user_agent}
    return int((_get_response(total_pages_url, headers=headers).text).strip())
 def _archive_url_parser(header, url):
    """
    The wayback machine's save API doesn't
    return JSON response, we are required
    to read the header of the API response
    and look for the archive URL.
    This method has some regexen (or regexes)
    that search for archive url in header.
    This method is used when you try to
    save a webpage on wayback machine.
    Two cases are possible:
    1) Either we find the archive url in
       the header.
    2) Or we didn't find the archive url in
       API header.
    If we found the archive URL we return it.
    And if we couldn't find it, we raise
    WaybackError with an error message.
    """
    # Regex1
    m = re.search(r"Content-Location: (/web/[0-9]{14}/.*)", str(header))
    if m:
        return "web.archive.org" + m.group(1)
    # Regex2
    m = re.search(
        r"rel=\"memento.*?(web\.archive\.org/web/[0-9]{14}/.*?)>", str(header)
    )
    if m:
        return m.group(1)
    # Regex3
    m = re.search(r"X-Cache-Key:\shttps(.*)[A-Z]{2}", str(header))
    if m:
        return m.group(1)
    raise WaybackError(
        "No archive URL found in the API response. "
        "If '%s' can be accessed via your web browser then either "
        "this version of waybackpy (%s) is out of date or WayBack Machine is malfunctioning. Visit "
        "'https://github.com/akamhy/waybackpy' for the latest version "
        "of waybackpy.\nHeader:\n%s" % (url, __version__, str(header))
    )
 def _wayback_timestamp(**kwargs):
    """
    Wayback Machine archive URLs
    have a timestamp in them.
    The standard archive URL format is
    https://web.archive.org/web/20191214041711/https://www.youtube.com
    If we break it down in three parts:
    1 ) The start (https://web.archive.org/web/)
    2 ) timestamp (20191214041711)
    3 ) https://www.youtube.com, the original URL
    The near method takes year, month, day, hour and minute
    as Arguments, their type is int.
    This method takes those integers and converts it to
    wayback machine timestamp and returns it.
    Return format is string.
    """
    return "".join(
        str(kwargs[key]).zfill(2) for key in ["year", "month", "day", "hour", "minute"]
    )
 def _get_response(
    endpoint, params=None, headers=None, retries=5, return_full_url=False
 ):
    """
    This function is used make get request.
    We use the requests package to make the
    requests.
    We try five times and if it fails it raises
    WaybackError exception.
    You can handles WaybackError by importing:
    from waybackpy.exceptions import WaybackError
    try:
        ...
    except WaybackError as e:
        # handle it
    """
    # From https://stackoverflow.com/a/35504626
    # By https://stackoverflow.com/users/401467/datashaman
    s = requests.Session()
    retries = Retry(
        total=retries, backoff_factor=0.5, status_forcelist=[500, 502, 503, 504]
    )
    s.mount("https://", HTTPAdapter(max_retries=retries))
    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:
        exc = WaybackError("Error while retrieving %s" % url)
        exc.__cause__ = e
        raise exc
--- a/waybackpy/wrapper.py
+++ b/waybackpy/wrapper.py
@@ -1,131 +1,191 @@
-# -*- coding: utf-8 -*-
+import requests
-
+import concurrent.futures
-import re
+from datetime import datetime, timedelta
-import sys
+from .exceptions import WaybackError
-import json
+from .cdx import Cdx
-from datetime import datetime
+from .utils import (
-from waybackpy.exceptions import WaybackError
+    _archive_url_parser,
-from waybackpy.__version__ import __version__
+    _wayback_timestamp,
-
+    _get_response,
-if sys.version_info >= (3, 0):  # If the python ver >= 3
+    default_user_agent,
-    from urllib.request import Request, urlopen
+    _url_check,
-    from urllib.error import URLError
+    _cleaned_url,
-else:  # For python2.x
+    _ts,
    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"rel=\"memento.*?(web\.archive\.org/web/[0-9]{14}/.*?)>", str(header)
 )
    if arch:
        return arch.group(1)
    # Regex2
    arch = re.search(r"X-Cache-Key:\shttps(.*)[A-Z]{2}", str(header))
    if arch:
        return arch.group(1)
    raise WaybackError(
        "No archive URL found in the API response. "
        "This version of waybackpy (%s) is likely out of date. Visit "
        "https://github.com/akamhy/waybackpy for the latest version "
        "of waybackpy.\nHeader:\n%s" % (__version__, str(header))
    )
 def _wayback_timestamp(**kwargs):
    """Return a formatted timestamp."""
    return "".join(
        str(kwargs[key]).zfill(2) for key in ["year", "month", "day", "hour", "minute"]
    )
 def _get_response(req):
    """Get response for the supplied request."""
    try:
        response = urlopen(req)  # nosec
    except Exception:
        try:
            response = urlopen(req)  # nosec
        except Exception as e:
            raise WaybackError(e)
    return response
 class Url:
-    """waybackpy Url object"""
+    def __init__(self, url, user_agent=default_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.
+        _url_check(self.url)
        self._archive_url = None
        self.timestamp = None
        self._JSON = None
        self._alive_url_list = []
    def __repr__(self):
        return "waybackpy.Url(url=%s, user_agent=%s)" % (self.url, self.user_agent)
    def __str__(self):
-        return "%s" % self._clean_url()
+        """
        Output when print() is used on <class 'waybackpy.wrapper.Url'>
        This should print an archive URL.
        We check if self._archive_url is not None.
        If not None, good. We return string of self._archive_url.
        If self._archive_url is None, it means we ain't used any method that
        sets self._archive_url, we now set self._archive_url to self.archive_url
        and return it.
        """
        if not self._archive_url:
            self._archive_url = self.archive_url
        return "%s" % self._archive_url
    def __len__(self):
-        return len(self._clean_url())
+        """
        Why do we have len here?
-    def _url_check(self):
+        Applying len() on <class 'waybackpy.wrapper.Url'>
-        """Check for common URL problems."""
+        will calculate the number of days between today and
-        if "." not in self.url:
+        the archive timestamp.
            raise URLError("'%s' is not a vaild URL." % self.url)
-    def _clean_url(self):
+        Can be applied on return values of near and its
-        """Fix the URL, if possible."""
+        childs (e.g. oldest) and if applied on waybackpy.Url()
-        return str(self.url).strip().replace(" ", "_")
+        whithout using any functions, it just grabs
        self._timestamp and def _timestamp gets it
        from def JSON.
        """
        td_max = timedelta(
            days=999999999, hours=23, minutes=59, seconds=59, microseconds=999999
        )
        if not self.timestamp:
            self.timestamp = self._timestamp
        if self.timestamp == datetime.max:
            return td_max.days
        return (datetime.utcnow() - self.timestamp).days
    @property
    def JSON(self):
        """
        If the end user has used near() or its childs like oldest, newest
        and archive_url then the JSON response of these are cached in self._JSON
        If we find that self._JSON is not None we return it.
        else we get the response of 'https://archive.org/wayback/available?url=YOUR-URL'
        and return it.
        """
        if self._JSON:
            return self._JSON
        endpoint = "https://archive.org/wayback/available"
        headers = {"User-Agent": self.user_agent}
        payload = {"url": "%s" % _cleaned_url(self.url)}
        response = _get_response(endpoint, params=payload, headers=headers)
        return response.json()
    @property
    def archive_url(self):
        """
        Returns any random archive for the instance.
        But if near, oldest, newest were used before
        then it returns the same archive again.
        We cache archive in self._archive_url
        """
        if self._archive_url:
            return self._archive_url
        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
            )
        self._archive_url = archive_url
        return archive_url
    @property
    def _timestamp(self):
        self.timestamp = _ts(self.timestamp, self.JSON)
        return self.timestamp
    def save(self):
-        """Create a new Wayback Machine archive for this URL."""
+        """
-        request_url = "https://web.archive.org/save/" + self._clean_url()
+        To save a webpage on WayBack machine we
-        hdr = {"User-Agent": "%s" % self.user_agent}  # nosec
+        need to send get request to https://web.archive.org/save/
-        req = Request(request_url, headers=hdr)  # nosec
+
-        header = _get_response(req).headers
+        And to get the archive URL we are required to read the
-        return "https://" + _archive_url_parser(header)
+        header of the API response.
        _get_response() takes care of the get requests. It uses requests
        package.
        _archive_url_parser() parses the archive from the header.
        """
        request_url = "https://web.archive.org/save/" + _cleaned_url(self.url)
        headers = {"User-Agent": self.user_agent}
        response = _get_response(request_url, params=None, headers=headers)
        self._archive_url = "https://" + _archive_url_parser(response.headers, self.url)
        self.timestamp = datetime.utcnow()
        return self
    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.
        """
        Return the source code of the supplied URL.
        If encoding is not supplied, it is auto-detected
         from the response itself by requests package.
        """
        if not url:
-            url = self._clean_url()
+            url = _cleaned_url(self.url)
        if not user_agent:
            user_agent = self.user_agent
-        hdr = {"User-Agent": "%s" % user_agent}
+        headers = {"User-Agent": str(user_agent)}
-        req = Request(url, headers=hdr)  # nosec
+        response = _get_response(str(url), params=None, headers=headers)
-        response = _get_response(req)
+
        if not encoding:
            try:
-                encoding = response.headers["content-type"].split("charset=")[-1]
+                encoding = response.encoding
            except AttributeError:
                encoding = "UTF-8"
        return response.read().decode(encoding.replace("text/html", "UTF-8", 1))
-    def get_response(self, req):
+        return response.content.decode(encoding.replace("text/html", "UTF-8", 1))
        """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
    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.
+        Wayback Machine can have many archives of a webpage,
-            Any non-supplied parameters default to the current time.
+        sometimes we want archive close to a specific time.
        This method takes year, month, day, hour and minute as input.
        The input type must be integer. Any non-supplied parameters
        default to the current time.
        We convert the input to a wayback machine timestamp using
        _wayback_timestamp(), it returns a string.
        We use the wayback machine's availability API
        (https://archive.org/wayback/available)
        to get the closest archive from the timestamp.
        We set self._archive_url to the archive found, if any.
        If archive found, we set self.timestamp to its timestamp.
        We self._JSON to the response of the availability API.
        And finally return self.
        """
        now = datetime.utcnow().timetuple()
        timestamp = _wayback_timestamp(
@@ -136,46 +196,122 @@ class Url:
            minute=minute if minute else now.tm_min,
        )
-        request_url = "https://archive.org/wayback/available?url=%s&timestamp=%s" % (
+        endpoint = "https://archive.org/wayback/available"
-            self._clean_url(),
+        headers = {"User-Agent": self.user_agent}
-            timestamp,
+        payload = {"url": "%s" % _cleaned_url(self.url), "timestamp": timestamp}
-        )
+        response = _get_response(endpoint, params=payload, headers=headers)
-        hdr = {"User-Agent": "%s" % self.user_agent}
+        data = response.json()
-        req = Request(request_url, headers=hdr)  # nosec
+
        response = _get_response(req)
        data = json.loads(response.read().decode("UTF-8"))
        if not data["archived_snapshots"]:
            raise WaybackError(
-                "'%s' is not yet archived. Use wayback.Url(url, user_agent).save() "
+                "Can not find archive for '%s' try later or use wayback.Url(url, user_agent).save() "
-                "to create a new archive." % self._clean_url()
+                "to create a new archive.\nAPI response:\n%s"
                % (_cleaned_url(self.url), response.text)
            )
        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
+
        self._archive_url = archive_url
        self.timestamp = datetime.strptime(
            data["archived_snapshots"]["closest"]["timestamp"], "%Y%m%d%H%M%S"
        )
        self._JSON = data
        return self
    def oldest(self, year=1994):
-        """Return the oldest Wayback Machine archive for this URL."""
+        """
        Returns the earliest/oldest Wayback Machine archive for the webpage.
        Wayback machine has started archiving the internet around 1997 and
        therefore we can't have any archive older than 1997, we use 1994 as the
        deafult year to look for the oldest archive.
        We simply pass the year in near() and return it.
        """
        return self.near(year=year)
    def newest(self):
-        """Return the newest Wayback Machine archive available for this URL.
+        """
        Return the newest Wayback Machine archive available for this URL.
        We return the output of self.near() as it deafults to current utc time.
        Due to Wayback Machine database lag, this may not always be the
        most recent archive.
        """
        return self.near()
-    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."""
+        """
-        hdr = {"User-Agent": "%s" % self.user_agent}
+        A webpage can have multiple archives on the wayback machine
-        request_url = (
+        If someone wants to count the total number of archives of a
-            "https://web.archive.org/cdx/search/cdx?url=%s&output=json&fl=statuscode"
+        webpage on wayback machine they can use this method.
-            % self._clean_url()
+
        Returns the total number of Wayback Machine archives for the URL.
        Return type in integer.
        """
        cdx = Cdx(
            _cleaned_url(self.url),
            user_agent=self.user_agent,
            start_timestamp=start_timestamp,
            end_timestamp=end_timestamp,
        )
-        req = Request(request_url, headers=hdr)  # nosec
+        i = 0
-        response = _get_response(req)
+        for _ in cdx.snapshots():
-        # Most efficient method to count number of archives (yet)
+            i = i + 1
-        return str(response.read()).count(",")
+        return i
    def live_urls_finder(self, url):
        """
        This method is used to check if supplied url
        is >= 400.
        """
        try:
            response_code = requests.get(url).status_code
        except Exception:
            return  # we don't care if Exception
        # 200s are OK and 300s are usually redirects, if you don't want redirects replace 400 with 300
        if response_code >= 400:
            return
        self._alive_url_list.append(url)
    def known_urls(
        self, alive=False, subdomain=False, start_timestamp=None, end_timestamp=None
    ):
        """
        Returns list of URLs known to exist for given domain name
        because these URLs were crawled by WayBack Machine spider.
        Useful for pen-testing.
        """
        # Idea by Mohammed Diaa (https://github.com/mhmdiaa) from:
        # https://gist.github.com/mhmdiaa/adf6bff70142e5091792841d4b372050
        url_list = []
        if subdomain:
            cdx = Cdx(_cleaned_url(self.url), user_agent=self.user_agent, start_timestamp=start_timestamp, end_timestamp=end_timestamp, match_type="domain", collapses=["urlkey"])
        else:
            cdx = Cdx(_cleaned_url(self.url), user_agent=self.user_agent, start_timestamp=start_timestamp, end_timestamp=end_timestamp, match_type="host", collapses=["urlkey"])
        snapshots = cdx.snapshots()
        url_list = []
        for snapshot in snapshots:
            url_list.append(snapshot.original)
        # Remove all deadURLs from url_list if alive=True
        if alive:
            with concurrent.futures.ThreadPoolExecutor() as executor:
                executor.map(self.live_urls_finder, url_list)
            url_list = self._alive_url_list
        return url_list
Author	SHA1	Message	Date
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
Akash	57a32669b5	v2.1.7	2020-08-09 11:06:29 +05:30
Akash	fe017cbcc8	v2.1.7	2020-08-09 11:06:04 +05:30
Akash	5edb03d24b	update docs	2020-08-09 11:05:04 +05:30
Akash	c5de2232ba	Update test_wrapper.py	2020-08-09 10:53:00 +05:30
Akash	ca9186c301	update message, sometimes raised for poor performance by wayback machine even if the url is archived.	2020-08-09 10:43:16 +05:30
Akash	8a4b631c13	new regex to parse archive, IA changed the header again :(	2020-08-09 10:36:25 +05:30
Akash	ec9ce92f48	Update README.md (#23 ) * Update README.md * fix grammar	2020-07-26 10:30:54 +05:30
Akash	e95d35c37f	re arrange the badges, moved contributions welcome to top	2020-07-26 10:24:31 +05:30
Akash	36d662b961	Update __version__.py	2020-07-24 16:24:57 +05:30
Akash	2835f8877e	Update setup.py	2020-07-24 16:24:38 +05:30
Akash	18cbd2fd30	Update cli.py	2020-07-24 16:10:29 +05:30
Akash	a2812fb56f	patch for cli	2020-07-24 16:09:47 +05:30
Akash	77effcf649	Update setup.py	2020-07-24 15:34:14 +05:30
Akash	7272ef45a0	Update __version__.py	2020-07-24 15:33:58 +05:30
Akash	56116551ac	Coverge improvements (#22 ) * Update cli.py * improved tests * chnages for proper testing * Type check using isinstance * Replace elifs with if when used after return * twitter.com --> www.ibm.com * fix typo * test archive urll parser and dunders * Update test_wrapper.py	2020-07-24 15:31:21 +05:30
Akash	4dcda94cb0	v2.1.4	2020-07-24 01:03:44 +05:30
Akash	09f59b0182	v2.1.4	2020-07-24 01:03:04 +05:30
Akash	ed24184b99	Remove duplicate get response method	2020-07-24 00:57:22 +05:30
Akash	56bef064b1	only test save on >3.7	2020-07-23 20:51:46 +05:30
Akash	44bb2cf5e4	some cli tests	2020-07-23 20:44:14 +05:30