Merge pull request #119 from akamhy/akamhy-patch-1

v3.0.0 --> v3.0.1

.github/workflows/build_test.yml

@@ -0,0 +1,30 @@
+# 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: Build
+
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    branches: [ master ]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ['3.6', '3.10']
+    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
+        pip install setuptools wheel
+    - name: Build test the package
+      run: |
+        python setup.py sdist bdist_wheel

.github/workflows/codeql-analysis.yml

@@ -0,0 +1,70 @@
+# For most projects, this workflow file will not need changing; you simply need
+# to commit it to your repository.
+#
+# You may wish to alter this file to override the set of languages analyzed,
+# or to provide custom queries or build logic.
+#
+# ******** NOTE ********
+# We have attempted to detect the languages in your repository. Please check
+# the `language` matrix defined below to confirm you have the correct set of
+# supported CodeQL languages.
+#
+name: "CodeQL"
+
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    # The branches below must be a subset of the branches above
+    branches: [ master ]
+  schedule:
+    - cron: '30 6 * * 1'
+
+jobs:
+  analyze:
+    name: Analyze
+    runs-on: ubuntu-latest
+    permissions:
+      actions: read
+      contents: read
+      security-events: write
+
+    strategy:
+      fail-fast: false
+      matrix:
+        language: [ 'python' ]
+        # CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python', 'ruby' ]
+        # Learn more about CodeQL language support at https://git.io/codeql-language-support
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v2
+
+    # Initializes the CodeQL tools for scanning.
+    - name: Initialize CodeQL
+      uses: github/codeql-action/init@v1
+      with:
+        languages: ${{ matrix.language }}
+        # If you wish to specify custom queries, you can do so here or in a config file.
+        # By default, queries listed here will override any specified in a config file.
+        # Prefix the list here with "+" to use these queries and those in the config file.
+        # queries: ./path/to/local/query, your-org/your-repo/queries@main
+
+    # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
+    # If this step fails, then you should remove it and run the build manually (see below)
+    - name: Autobuild
+      uses: github/codeql-action/autobuild@v1
+
+    # ℹ️ Command-line programs to run using the OS shell.
+    # 📚 https://git.io/JvXDl
+
+    # ✏️ If the Autobuild fails above, remove it and uncomment the following three lines
+    #    and modify them (or add more) to build your code if your project
+    #    uses a compiled language
+
+    #- run: |
+    #   make bootstrap
+    #   make release
+
+    - name: Perform CodeQL Analysis
+      uses: github/codeql-action/analyze@v1

.github/workflows/python-publish.yml

@@ -0,0 +1,31 @@
+# This workflows will upload a Python Package using Twine when a release is created
+# For more information see: https://help.github.com/en/actions/language-and-framework-guides/using-python-with-github-actions#publishing-to-package-registries
+
+name: Upload Python Package
+
+on:
+  release:
+    types: [created]
+
+jobs:
+  deploy:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.x'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install setuptools wheel twine
+    - name: Build and publish
+      env:
+        TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
+        TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
+      run: |
+        python setup.py sdist bdist_wheel
+        twine upload dist/*

.github/workflows/unit_test.yml

@@ -0,0 +1,44 @@
+# 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: Tests
+
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    branches: [ master ]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ['3.9']
+    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
+        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+        if [ -f requirements-dev.txt ]; then pip install -r requirements-dev.txt; fi
+    - name: Lint with flake8
+      run: |
+        # stop the build if there are Python syntax errors or undefined names
+        flake8 waybackpy/ --count --select=E9,F63,F7,F82 --show-source --statistics
+        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+        # flake8 waybackpy/ --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics --per-file-ignores="waybackpy/__init__.py:F401"
+    # - name: Static type test with mypy
+    #   run: |
+    #     mypy
+    - name: Test with pytest
+      run: |
+        pytest
+    # - name: Upload coverage to Codecov
+    #   run: |
+    #     bash <(curl -s https://codecov.io/bash) -t ${{ secrets.CODECOV_TOKEN }}

.gitignore

@@ -1,3 +1,6 @@
+# Files generated while testing
+*-urls-*.txt
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]

.whitesource

@@ -0,0 +1,12 @@
+{
+  "scanSettings": {
+    "baseBranches": []
+  },
+  "checkRunSettings": {
+    "vulnerableCheckRunConclusionLevel": "failure",
+    "displayMode": "diff"
+  },
+  "issueSettings": {
+    "minSeverityLevel": "LOW"
+  }
+}

CONTRIBUTORS.md

@@ -0,0 +1,9 @@
+## AUTHORS
+  - akamhy (<https://github.com/akamhy>)
+  - danvalen1 (<https://github.com/danvalen1>)
+  - AntiCompositeNumber (<https://github.com/AntiCompositeNumber>)
+  - jonasjancarik (<https://github.com/jonasjancarik>)
+
+## ACKNOWLEDGEMENTS
+  - mhmdiaa (<https://github.com/mhmdiaa>) for <https://gist.github.com/mhmdiaa/adf6bff70142e5091792841d4b372050>. known_urls is based on this gist.
+  - dequeued0 (<https://github.com/dequeued0>) for reporting bugs and useful feature requests.

LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2020 akamhy
+Copyright (c) 2020-2022 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

README.md

@@ -1,2 +1,154 @@
-# pywayback
-A python wrapper for Internet Archive's Wayback Machine
+<div align="center">
+
+<img src="https://raw.githubusercontent.com/akamhy/waybackpy/master/assets/waybackpy_logo.svg"><br>
+
+<h3>A Python package & CLI tool that interfaces with the Wayback Machine API</h3>
+
+</div>
+
+<p align="center">
+<a href="https://github.com/akamhy/waybackpy/actions?query=workflow%3ATests"><img alt="Unit Tests" src="https://github.com/akamhy/waybackpy/workflows/Tests/badge.svg"></a>
+<a href="https://pypi.org/project/waybackpy/"><img alt="pypi" src="https://img.shields.io/pypi/v/waybackpy.svg"></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>
+<a href="https://github.com/psf/black"><img alt="Code style: black" src="https://img.shields.io/badge/code%20style-black-000000.svg"></a>
+</p>
+
+-----------------------------------------------------------------------------------------------------------------------------------------------
+
+## ⭐️ Introduction
+Waybackpy is a [Python package](https://www.udacity.com/blog/2021/01/what-is-a-python-package.html) and a [CLI](https://www.w3schools.com/whatis/whatis_cli.asp) tool that interfaces with the [Wayback Machine](https://en.wikipedia.org/wiki/Wayback_Machine) API.
+
+ Wayback Machine has 3 client side [API](https://www.redhat.com/en/topics/api/what-are-application-programming-interfaces)s.
+
+  - [Save API](https://github.com/akamhy/waybackpy/wiki/Wayback-Machine-APIs#save-api)
+  - [Availability API](https://github.com/akamhy/waybackpy/wiki/Wayback-Machine-APIs#availability-api)
+  - [CDX API](https://github.com/akamhy/waybackpy/wiki/Wayback-Machine-APIs#cdx-api)
+
+These three APIs can be accessed via the waybackpy either by importing it in a script or from the CLI.
+
+
+### 🏗 Installation
+
+Using [pip](https://en.wikipedia.org/wiki/Pip_(package_manager)), from [PyPI](https://pypi.org/) (recommended):
+
+```bash
+pip install waybackpy
+```
+
+Install directly from [this git repository](https://github.com/akamhy/waybackpy) (NOT recommended):
+
+```bash
+pip install git+https://github.com/akamhy/waybackpy.git
+```
+
+### 🐳 Docker Image
+Docker Hub : <https://hub.docker.com/r/secsi/waybackpy>
+
+[Docker image](https://searchitoperations.techtarget.com/definition/Docker-image) is automatically updated on every release by [Regulary and Automatically Updated Docker Images](https://github.com/cybersecsi/RAUDI) (RAUDI).
+
+RAUDI is a tool by SecSI (<https://secsi.io>), an Italian cybersecurity startup.
+
+
+### 🚀 Usage
+
+#### As a Python package
+
+##### Save API aka SavePageNow
+```python
+>>> from waybackpy import WaybackMachineSaveAPI
+>>> url = "https://github.com"
+>>> user_agent = "Mozilla/5.0 (Windows NT 5.1; rv:40.0) Gecko/20100101 Firefox/40.0"
+>>>
+>>> save_api = WaybackMachineSaveAPI(url, user_agent)
+>>> save_api.save()
+https://web.archive.org/web/20220118125249/https://github.com/
+>>> save_api.cached_save
+False
+>>> save_api.timestamp()
+datetime.datetime(2022, 1, 18, 12, 52, 49)
+```
+
+##### Availability API
+```python
+>>> from waybackpy import WaybackMachineAvailabilityAPI
+>>>
+>>> url = "https://google.com"
+>>> user_agent = "Mozilla/5.0 (Windows NT 5.1; rv:40.0) Gecko/20100101 Firefox/40.0"
+>>>
+>>> availability_api = WaybackMachineAvailabilityAPI(url, user_agent)
+>>>
+>>> availability_api.oldest()
+https://web.archive.org/web/19981111184551/http://google.com:80/
+>>>
+>>> availability_api.newest()
+https://web.archive.org/web/20220118150444/https://www.google.com/
+>>>
+>>> availability_api.near(year=2010, month=10, day=10, hour=10)
+https://web.archive.org/web/20101010101708/http://www.google.com/
+```
+
+##### CDX API aka CDXServerAPI
+```python
+>>> from waybackpy import WaybackMachineCDXServerAPI
+>>> url = "https://pypi.org"
+>>> user_agent = "Mozilla/5.0 (Windows NT 5.1; rv:40.0) Gecko/20100101 Firefox/40.0"
+>>> cdx = WaybackMachineCDXServerAPI(url, user_agent, start_timestamp=2016, end_timestamp=2017)
+>>> for item in cdx.snapshots():
+...     print(item.archive_url)
+...
+https://web.archive.org/web/20160110011047/http://pypi.org/
+https://web.archive.org/web/20160305104847/http://pypi.org/
+.
+. # URLS REDACTED FOR READABILITY
+.
+https://web.archive.org/web/20171127171549/https://pypi.org/
+https://web.archive.org/web/20171206002737/http://pypi.org:80/
+```
+
+> Documentation is at <https://github.com/akamhy/waybackpy/wiki/Python-package-docs>.
+
+
+#### As a CLI tool
+
+Saving a webpage:
+```bash
+waybackpy --save --url "https://en.wikipedia.org/wiki/Social_media" --user_agent "my-unique-user-agent"
+```
+```bash
+Archive URL:
+https://web.archive.org/web/20220121193801/https://en.wikipedia.org/wiki/Social_media
+Cached save:
+False
+```
+
+
+Retriving the oldest archive and also printing the JSON response of the availability API:
+```bash
+waybackpy --oldest --json --url "https://en.wikipedia.org/wiki/Humanoid" --user_agent "my-unique-user-agent"
+```
+```bash
+Archive URL:
+https://web.archive.org/web/20040415020811/http://en.wikipedia.org:80/wiki/Humanoid
+JSON response:
+{"url": "https://en.wikipedia.org/wiki/Humanoid", "archived_snapshots": {"closest": {"status": "200", "available": true, "url": "http://web.archive.org/web/20040415020811/http://en.wikipedia.org:80/wiki/Humanoid", "timestamp": "20040415020811"}}, "timestamp": "199401212126"}
+```
+
+
+Archive close to a time, minute level precision is supported:
+```bash
+waybackpy --url google.com --user_agent "my-unique-user-agent" --near --year 2008 --month 8 --day 8
+```
+```bash
+Archive URL:
+https://web.archive.org/web/20080808014003/http://www.google.com:80/
+```
+> CLI documentation is at <https://github.com/akamhy/waybackpy/wiki/CLI-docs>.
+
+### 🛡 License
+[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://github.com/akamhy/waybackpy/blob/master/LICENSE)
+
+Copyright (c) 2020-2022 Akash Mahanty Et al.
+
+Released under the MIT License. See [license](https://github.com/akamhy/waybackpy/blob/master/LICENSE) for details.

_config.yml

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

assets/waybackpy_logo.svg

@@ -0,0 +1,14 @@
+<?xml version="1.0" encoding="utf-8"?>
+<svg width="711.80188pt" height="258.30469pt" viewBox="0 0 711.80188 258.30469" version="1.1" id="svg2" xmlns="http://www.w3.org/2000/svg">
+  <g id="surface1" transform="translate(-40.045801,-148)">
+    <path style="fill: rgb(171, 46, 51); fill-opacity: 1; fill-rule: nonzero; stroke: none;" d="M 224.09 309.814 L 224.09 197.997 L 204.768 197.994 L 204.768 312.635 C 204.768 312.635 205.098 312.9 204.105 313.698 C 203.113 314.497 202.408 313.849 202.408 313.849 L 200.518 313.849 L 200.518 197.991 L 181.139 197.991 L 181.139 313.849 L 179.253 313.849 C 179.253 313.849 178.544 314.497 177.551 313.698 C 176.558 312.9 176.888 312.635 176.888 312.635 L 176.888 197.994 L 157.57 197.997 L 157.57 309.814 C 157.57 309.814 156.539 316.772 162.615 321.658 C 168.691 326.546 177.551 326.049 177.551 326.049 L 204.11 326.049 C 204.11 326.049 212.965 326.546 219.041 321.658 C 225.118 316.772 224.09 309.814 224.09 309.814" id="path5"/>
+    <path style="fill: rgb(171, 46, 51); fill-opacity: 1; fill-rule: nonzero; stroke: none;" d="M 253.892 299.821 C 253.892 299.821 253.632 300.965 251.888 300.965 C 250.143 300.965 249.629 299.821 249.629 299.821 L 249.629 278.477 C 249.629 278.477 249.433 278.166 250.078 277.645 C 250.726 277.124 251.243 277.179 251.243 277.179 L 253.892 277.228 Z M 251.588 199.144 C 230.266 199.144 231.071 213.218 231.071 213.218 L 231.071 254.303 L 249.675 254.303 L 249.675 213.69 C 249.675 213.69 249.775 211.276 251.787 211.276 C 253.8 211.276 254 213.542 254 213.542 L 254 265.146 L 246.156 265.146 C 246.156 265.146 240.022 264.579 235.495 268.22 C 230.968 271.858 231.071 276.791 231.071 276.791 L 231.071 298.955 C 231.071 298.955 229.461 308.016 238.914 312.058 C 248.368 316.103 254.805 309.795 254.805 309.795 L 254.805 312.706 L 272.508 312.706 L 272.508 212.895 C 272.508 212.895 272.907 199.144 251.588 199.144" id="path7"/>
+    <path style="fill: rgb(171, 46, 51); fill-opacity: 1; fill-rule: nonzero; stroke: none;" d="M 404.682 318.261 C 404.682 318.261 404.398 319.494 402.485 319.494 C 400.568 319.494 400.001 318.261 400.001 318.261 L 400.001 295.216 C 400.001 295.216 399.786 294.879 400.496 294.315 C 401.208 293.757 401.776 293.812 401.776 293.812 L 404.682 293.868 Z M 402.152 209.568 C 378.728 209.568 379.61 224.761 379.61 224.761 L 379.61 269.117 L 400.051 269.117 L 400.051 225.273 C 400.051 225.273 400.162 222.665 402.374 222.665 C 404.582 222.665 404.805 225.109 404.805 225.109 L 404.805 280.82 L 396.187 280.82 C 396.187 280.82 389.447 280.213 384.475 284.141 C 379.499 288.072 379.61 293.396 379.61 293.396 L 379.61 317.324 C 379.61 317.324 377.843 327.104 388.232 331.469 C 398.616 335.838 405.69 329.027 405.69 329.027 L 405.69 332.169 L 425.133 332.169 L 425.133 224.413 C 425.133 224.413 425.578 209.568 402.152 209.568" id="path9"/>
+    <path style="fill: rgb(171, 46, 51); fill-opacity: 1; fill-rule: nonzero; stroke: none;" d="M 321.114 328.636 L 321.114 206.587 L 302.582 206.587 L 302.582 304.902 C 302.582 304.902 303.211 307.094 300.624 307.094 C 298.035 307.094 298.316 304.902 298.316 304.902 L 298.316 206.587 L 279.784 206.587 C 279.784 206.587 279.922 304.338 279.922 306.756 C 279.922 309.175 280.27 310.526 280.831 312.379 C 281.391 314.238 282.579 318.116 290.901 319.186 C 299.224 320.256 302.44 315.813 302.44 315.813 L 302.44 327.736 C 302.44 327.736 302.862 329.366 300.554 329.366 C 298.246 329.366 298.316 327.849 298.316 327.849 L 298.316 322.957 L 279.642 322.957 L 279.642 327.791 C 279.642 327.791 278.523 341.514 300.274 341.514 C 322.026 341.514 321.114 328.636 321.114 328.636" id="path11"/>
+    <path style="fill: rgb(171, 46, 51); fill-opacity: 1; fill-rule: nonzero; stroke: none;" d="M 352.449 209.811 L 352.449 273.495 C 352.449 277.49 347.911 277.194 347.911 277.194 L 347.911 207.592 C 347.911 207.592 346.929 207.542 349.567 207.542 C 352.817 207.542 352.449 209.811 352.449 209.811 M 352.326 310.393 C 352.326 310.393 352.143 312.366 350.425 312.366 L 348.033 312.366 L 348.033 289.478 L 349.628 289.478 C 349.628 289.478 352.326 289.428 352.326 292.092 Z M 371.341 287.505 C 371.341 284.791 370.727 282.966 368.826 280.993 C 366.925 279.02 363.367 277.441 363.367 277.441 C 363.367 277.441 365.514 276.948 368.704 274.728 C 371.893 272.509 371.525 267.921 371.525 267.921 L 371.525 212.919 C 371.525 212.919 371.801 204.509 366.925 200.587 C 362.049 196.665 352.515 196.363 352.515 196.363 L 328.711 196.363 L 328.711 324.107 L 350.609 324.107 C 360.055 324.107 364.594 322.232 368.336 318.286 C 372.077 314.34 371.341 308.321 371.341 308.321 Z M 371.341 287.505" id="path13"/>
+    <path style="fill: rgb(171, 46, 51); fill-opacity: 1; fill-rule: nonzero; stroke: none;" d="M 452.747 226.744 L 452.747 268.806 L 471.581 268.806 L 471.581 227.459 C 471.581 227.459 471.846 213.532 450.516 213.532 C 429.182 213.532 430.076 227.533 430.076 227.533 L 430.076 313.381 C 430.076 313.381 428.825 327.523 450.872 327.523 C 472.919 327.523 471.401 313.526 471.401 313.526 L 471.401 292.064 L 452.835 292.064 L 452.835 314.389 C 452.835 314.389 452.923 315.61 450.961 315.61 C 448.997 315.61 448.729 314.389 448.729 314.389 L 448.729 226.524 C 448.729 226.524 448.821 225.378 450.692 225.378 C 452.566 225.378 452.747 226.744 452.747 226.744" id="path15"/>
+    <path style="fill: rgb(171, 46, 51); fill-opacity: 1; fill-rule: nonzero; stroke: none;" d="M 520.624 281.841 C 517.672 278.98 514.317 277.904 514.317 277.904 C 514.317 277.904 517.538 277.796 520.489 274.775 C 523.442 271.753 523.173 267.924 523.173 267.924 L 523.173 208.211 L 503.185 208.211 L 503.185 276.014 C 503.185 276.014 503.185 277.361 501.172 277.361 L 498.761 277.309 L 498.761 191.655 L 478.973 191.655 L 478.973 327.905 L 498.692 327.905 L 498.692 290.039 L 501.709 290.039 C 501.709 290.039 502.112 290.039 502.648 290.523 C 503.185 291.01 503.185 291.602 503.185 291.602 L 503.185 327.905 L 523.307 327.905 L 523.307 288.636 C 523.307 288.636 523.576 284.699 520.624 281.841" id="path17"/>
+    <path style="fill-opacity: 1; fill-rule: nonzero; stroke: none; fill: rgb(255, 222, 87);" d="M 638.021 327.182 L 638.021 205.132 L 619.489 205.132 L 619.489 303.448 C 619.489 303.448 620.119 305.64 617.53 305.64 C 614.944 305.64 615.223 303.448 615.223 303.448 L 615.223 205.132 L 596.692 205.132 C 596.692 205.132 596.83 302.884 596.83 305.301 C 596.83 307.721 597.178 309.071 597.738 310.924 C 598.299 312.784 599.487 316.662 607.809 317.732 C 616.132 318.802 619.349 314.359 619.349 314.359 L 619.349 326.281 C 619.349 326.281 619.77 327.913 617.462 327.913 C 615.154 327.913 615.223 326.396 615.223 326.396 L 615.223 321.502 L 596.55 321.502 L 596.55 326.336 C 596.55 326.336 595.43 340.059 617.182 340.059 C 638.934 340.059 638.021 327.182 638.021 327.182" id="path-1"/>
+    <path d="M 592.159 233.846 C 593.222 238.576 593.75 243.873 593.745 249.735 C 593.74 255.598 593.135 261.281 591.931 266.782 C 590.726 272.285 588.901 277.144 586.453 281.361 C 584.006 285.578 580.938 288.946 577.248 291.466 C 573.559 293.985 569.226 295.246 564.25 295.246 C 561.585 295.246 559.008 294.936 556.521 294.32 C 554.033 293.703 551.813 292.854 549.859 291.774 C 547.905 290.694 546.284 289.512 544.997 288.226 C 543.71 286.94 542.934 285.578 542.668 284.138 L 542.629 328.722 L 526.369 328.722 L 526.475 207.466 L 541.003 207.466 L 542.728 216.259 C 544.507 213.38 547.197 211.065 550.797 209.317 C 554.397 207.568 558.374 206.694 562.728 206.694 C 565.66 206.694 568.637 207.157 571.657 208.083 C 574.677 209.008 577.497 210.551 580.116 212.711 C 582.735 214.871 585.11 217.698 587.239 221.196 C 589.369 224.692 591.009 228.909 592.159 233.846 Z M 558.932 280.744 C 561.597 280.744 564.019 279.972 566.197 278.429 C 568.376 276.887 570.243 274.804 571.801 272.182 C 573.358 269.559 574.582 266.423 575.474 262.772 C 576.366 259.121 576.814 255.238 576.817 251.124 C 576.821 247.113 576.424 243.307 575.628 239.708 C 574.831 236.108 573.701 232.92 572.237 230.143 C 570.774 227.366 568.999 225.155 566.912 223.51 C 564.825 221.864 562.405 221.041 559.65 221.041 C 556.985 221.041 554.54 221.813 552.318 223.356 C 550.095 224.898 548.183 226.981 546.581 229.603 C 544.98 232.226 543.755 235.311 542.908 238.86 C 542.061 242.408 541.635 246.239 541.632 250.353 C 541.628 254.466 542.002 258.349 542.754 262 C 543.506 265.651 544.637 268.865 546.145 271.642 C 547.653 274.419 549.472 276.63 551.603 278.276 C 553.734 279.922 556.177 280.744 558.932 280.744 Z" style="fill: rgb(69, 132, 182); white-space: pre;"/>
+  </g>
+</svg>

pytest.ini

@@ -0,0 +1,11 @@
+[pytest]
+addopts =
+    # show summary of all tests that did not pass
+    -ra
+    # enable all warnings
+    -Wd
+    # coverage and html report
+    --cov=waybackpy
+    --cov-report=html
+testpaths =
+    tests

requirements-dev.txt

@@ -0,0 +1,8 @@
+click
+requests
+pytest
+pytest-cov
+codecov
+flake8
+mypy
+black

requirements.txt

@@ -0,0 +1,2 @@
+click
+requests

setup.cfg

@@ -0,0 +1,7 @@
+[metadata]
+description-file = README.md
+license_file = LICENSE
+
+[flake8]
+max-line-length = 88
+extend-ignore = E203,W503

setup.py

@@ -0,0 +1,66 @@
+import os.path
+from setuptools import setup
+
+readme_path = os.path.join(os.path.dirname(__file__), "README.md")
+with open(readme_path, encoding="utf-8") as f:
+    long_description = f.read()
+
+about = {}
+version_path = os.path.join(os.path.dirname(__file__), "waybackpy", "__version__.py")
+with open(version_path, encoding="utf-8") as f:
+    exec(f.read(), about)
+
+version = str(about["__version__"])
+
+download_url = "https://github.com/akamhy/waybackpy/archive/{version}.tar.gz".format(
+    version=version
+)
+
+setup(
+    name=about["__title__"],
+    packages=["waybackpy"],
+    version=version,
+    description=about["__description__"],
+    long_description=long_description,
+    long_description_content_type="text/markdown",
+    license=about["__license__"],
+    author=about["__author__"],
+    author_email=about["__author_email__"],
+    url=about["__url__"],
+    download_url=download_url,
+    keywords=[
+        "Archive Website",
+        "Wayback Machine",
+        "Internet Archive",
+        "Wayback Machine CLI",
+        "Wayback Machine Python",
+        "Internet Archiving",
+        "Availability API",
+        "CDX API",
+        "savepagenow",
+    ],
+    install_requires=["requests", "click"],
+    python_requires=">=3.4",
+    classifiers=[
+        "Development Status :: 4 - Beta",
+        "Intended Audience :: Developers",
+        "Natural Language :: English",
+        "License :: OSI Approved :: MIT License",
+        "Programming Language :: Python",
+        "Programming Language :: Python :: 3",
+        "Programming Language :: Python :: 3.4",
+        "Programming Language :: Python :: 3.5",
+        "Programming Language :: Python :: 3.6",
+        "Programming Language :: Python :: 3.7",
+        "Programming Language :: Python :: 3.8",
+        "Programming Language :: Python :: 3.9",
+        "Programming Language :: Python :: 3.10",
+        "Programming Language :: Python :: Implementation :: CPython",
+    ],
+    entry_points={"console_scripts": ["waybackpy = waybackpy.cli:main"]},
+    project_urls={
+        "Documentation": "https://github.com/akamhy/waybackpy/wiki",
+        "Source": "https://github.com/akamhy/waybackpy",
+        "Tracker": "https://github.com/akamhy/waybackpy/issues",
+    },
+)

tests/test_availability_api.py

@@ -0,0 +1,100 @@
+import pytest
+import random
+import string
+from datetime import datetime, timedelta
+
+from waybackpy.availability_api import WaybackMachineAvailabilityAPI
+from waybackpy.exceptions import (
+    InvalidJSONInAvailabilityAPIResponse,
+    ArchiveNotInAvailabilityAPIResponse,
+)
+
+now = datetime.utcnow()
+url = "https://example.com/"
+user_agent = "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.99 Safari/537.36"
+
+rndstr = lambda n: "".join(
+    random.choice(string.ascii_uppercase + string.digits) for _ in range(n)
+)
+
+
+def test_oldest():
+    """
+    Test the oldest archive of Google.com and also checks the attributes.
+    """
+    url = "https://example.com/"
+    user_agent = "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.99 Safari/537.36"
+    availability_api = WaybackMachineAvailabilityAPI(url, user_agent)
+    oldest = availability_api.oldest()
+    oldest_archive_url = oldest.archive_url
+    assert "2002" in oldest_archive_url
+    oldest_timestamp = oldest.timestamp()
+    assert abs(oldest_timestamp - now) > timedelta(days=7000)  # More than 19 years
+    assert availability_api.JSON["archived_snapshots"]["closest"]["available"] is True
+    assert repr(oldest).find("example.com") != -1
+    assert "2002" in str(oldest)
+
+
+def test_newest():
+    """
+    Assuming that the recent most Google Archive was made no more earlier than
+    last one day which is 86400 seconds.
+    """
+    url = "https://www.youtube.com/"
+    user_agent = "Mozilla/5.0 (X11; Linux x86_64; rv:96.0) Gecko/20100101 Firefox/96.0"
+    availability_api = WaybackMachineAvailabilityAPI(url, user_agent)
+    newest = availability_api.newest()
+    newest_timestamp = newest.timestamp()
+    # betting in favor that latest youtube archive was not before the last 3 days
+    # high tarffic sites like youtube are archived mnay times a day, so seems
+    # very reasonable to me.
+    assert abs(newest_timestamp - now) < timedelta(seconds=86400 * 3)
+
+
+def test_invalid_json():
+    """
+    When the API is malfunctioning or we don't pass a URL it may return invalid JSON data.
+    """
+    with pytest.raises(InvalidJSONInAvailabilityAPIResponse):
+        availability_api = WaybackMachineAvailabilityAPI(url="", user_agent=user_agent)
+        archive_url = availability_api.archive_url
+
+
+def test_no_archive():
+    """
+    ArchiveNotInAvailabilityAPIResponse may be raised if Wayback Machine did not
+    replied with the archive despite the fact that we know the site has million
+    of archives. Don't know the reason for this wierd behavior.
+
+    And also if really there are no archives for the passed URL this exception
+    is raised.
+    """
+    with pytest.raises(ArchiveNotInAvailabilityAPIResponse):
+        availability_api = WaybackMachineAvailabilityAPI(
+            url="https://%s.cn" % rndstr(30), user_agent=user_agent
+        )
+        archive_url = availability_api.archive_url
+
+
+def test_no_api_call_str_repr():
+    """
+    Some entitled users maybe want to see what is the string representation
+    if they don’t make any API requests.
+
+    str() must not return None so we return ""
+    """
+    availability_api = WaybackMachineAvailabilityAPI(
+        url="https://%s.gov" % rndstr(30), user_agent=user_agent
+    )
+    assert "" == str(availability_api)
+
+
+def test_no_call_timestamp():
+    """
+    If no API requests were made the bound timestamp() method returns
+    the datetime.max as a default value.
+    """
+    availability_api = WaybackMachineAvailabilityAPI(
+        url="https://%s.in" % rndstr(30), user_agent=user_agent
+    )
+    assert datetime.max == availability_api.timestamp()

tests/test_cdx_snapshot.py

@@ -0,0 +1,41 @@
+import pytest
+from datetime import datetime
+
+from waybackpy.cdx_snapshot import CDXSnapshot
+
+
+def test_CDXSnapshot():
+    sample_input = "org,archive)/ 20080126045828 http://github.com text/html 200 Q4YULN754FHV2U6Q5JUT6Q2P57WEWNNY 1415"
+    prop_values = sample_input.split(" ")
+    properties = {}
+    (
+        properties["urlkey"],
+        properties["timestamp"],
+        properties["original"],
+        properties["mimetype"],
+        properties["statuscode"],
+        properties["digest"],
+        properties["length"],
+    ) = prop_values
+
+    snapshot = CDXSnapshot(properties)
+
+    assert properties["urlkey"] == snapshot.urlkey
+    assert properties["timestamp"] == snapshot.timestamp
+    assert properties["original"] == snapshot.original
+    assert properties["mimetype"] == snapshot.mimetype
+    assert properties["statuscode"] == snapshot.statuscode
+    assert properties["digest"] == snapshot.digest
+    assert properties["length"] == snapshot.length
+    assert (
+        datetime.strptime(properties["timestamp"], "%Y%m%d%H%M%S")
+        == snapshot.datetime_timestamp
+    )
+    archive_url = (
+        "https://web.archive.org/web/"
+        + properties["timestamp"]
+        + "/"
+        + properties["original"]
+    )
+    assert archive_url == snapshot.archive_url
+    assert sample_input == str(snapshot)

tests/test_cdx_utils.py

@@ -0,0 +1,99 @@
+import pytest
+from waybackpy.exceptions import WaybackError
+from waybackpy.cdx_utils import (
+    get_total_pages,
+    full_url,
+    get_response,
+    check_filters,
+    check_collapses,
+    check_match_type,
+)
+
+
+def test_get_total_pages():
+    url = "twitter.com"
+    user_agent = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_6) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.0.2 Safari/605.1.15"
+    assert get_total_pages(url=url, user_agent=user_agent) >= 56
+
+
+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_response():
+    url = "https://github.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(url, headers=headers)
+    assert response.status_code == 200
+
+    url = "http/wwhfhfvhvjhmom"
+    with pytest.raises(WaybackError):
+        get_response(url, headers=headers)
+
+
+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")
+
+    with pytest.raises(WaybackError):
+        check_filters(["invalid"])
+
+
+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")

tests/test_save_api.py

@@ -0,0 +1,133 @@
+import pytest
+import time
+import random
+import string
+from datetime import datetime
+
+from waybackpy.save_api import WaybackMachineSaveAPI
+from waybackpy.exceptions import MaximumSaveRetriesExceeded
+
+rndstr = lambda n: "".join(
+    random.choice(string.ascii_uppercase + string.digits) for _ in range(n)
+)
+
+
+def test_save():
+    url = "https://github.com/akamhy/waybackpy"
+    user_agent = "Mozilla/5.0 (MacBook Air; M1 Mac OS X 11_4) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.1.1 Safari/604.1"
+    save_api = WaybackMachineSaveAPI(url, user_agent)
+    save_api.save()
+    archive_url = save_api.archive_url
+    timestamp = save_api.timestamp()
+    headers = save_api.headers  # CaseInsensitiveDict
+    cached_save = save_api.cached_save
+    assert cached_save in [True, False]
+    assert archive_url.find("github.com/akamhy/waybackpy") != -1
+    assert str(headers).find("github.com/akamhy/waybackpy") != -1
+    assert type(save_api.timestamp()) == type(datetime(year=2020, month=10, day=2))
+
+
+def test_max_redirect_exceeded():
+    with pytest.raises(MaximumSaveRetriesExceeded):
+        url = "https://%s.gov" % rndstr
+        user_agent = "Mozilla/5.0 (MacBook Air; M1 Mac OS X 11_4) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.1.1 Safari/604.1"
+        save_api = WaybackMachineSaveAPI(url, user_agent, max_tries=3)
+        save_api.save()
+
+
+def test_sleep():
+    """
+    sleeping is actually very important for SaveAPI
+    interface stability.
+    The test checks that the time taken by sleep method
+    is as intended.
+    """
+    url = "https://example.com"
+    user_agent = "Mozilla/5.0 (MacBook Air; M1 Mac OS X 11_4) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.1.1 Safari/604.1"
+    save_api = WaybackMachineSaveAPI(url, user_agent)
+    s_time = int(time.time())
+    save_api.sleep(6)  # multiple of 3 sleep for 10 seconds
+    e_time = int(time.time())
+    assert (e_time - s_time) >= 10
+
+    s_time = int(time.time())
+    save_api.sleep(7)  # sleeps for 5 seconds
+    e_time = int(time.time())
+    assert (e_time - s_time) >= 5
+
+
+def test_timestamp():
+    url = "https://example.com"
+    user_agent = "Mozilla/5.0 (MacBook Air; M1 Mac OS X 11_4) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.1.1 Safari/604.1"
+    save_api = WaybackMachineSaveAPI(url, user_agent)
+    now = datetime.utcnow()
+    save_api._archive_url = (
+        "https://web.archive.org/web/%s/" % now.strftime("%Y%m%d%H%M%S") + url
+    )
+    save_api.timestamp()
+    assert save_api.cached_save is False
+    save_api._archive_url = "https://web.archive.org/web/%s/" % "20100124063622" + url
+    save_api.timestamp()
+    assert save_api.cached_save is True
+
+
+def test_archive_url_parser():
+    """
+    Testing three regex for matches and also tests the response URL.
+    """
+    url = "https://example.com"
+    user_agent = "Mozilla/5.0 (MacBook Air; M1 Mac OS X 11_4) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.1.1 Safari/604.1"
+    save_api = WaybackMachineSaveAPI(url, user_agent)
+
+    save_api.headers = """
+    START
+    Content-Location: /web/20201126185327/https://www.scribbr.com/citing-sources/et-al
+    END
+    """
+
+    assert (
+        save_api.archive_url_parser()
+        == "https://web.archive.org/web/20201126185327/https://www.scribbr.com/citing-sources/et-al"
+    )
+
+    save_api.headers = """
+    {'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'}
+    """
+
+    assert (
+        save_api.archive_url_parser()
+        == "https://web.archive.org/web/20210102094009/https://www.scribbr.com/citing-sources/et-al/"
+    )
+
+    save_api.headers = """
+    START
+    X-Cache-Key: https://web.archive.org/web/20171128185327/https://www.scribbr.com/citing-sources/et-al/US
+    END
+    """
+
+    assert (
+        save_api.archive_url_parser()
+        == "https://web.archive.org/web/20171128185327/https://www.scribbr.com/citing-sources/et-al/"
+    )
+
+    save_api.headers = "TEST TEST TEST AND NO MATCH - TEST FOR RESPONSE URL MATCHING"
+    save_api.response_url = "https://web.archive.org/web/20171128185327/https://www.scribbr.com/citing-sources/et-al"
+    assert (
+        save_api.archive_url_parser()
+        == "https://web.archive.org/web/20171128185327/https://www.scribbr.com/citing-sources/et-al"
+    )
+
+
+def test_archive_url():
+    """
+    Checks the attribute archive_url's value when the save method was not
+    explicitly invoked by the end-user but the save method was invoked implicitly
+    by the archive_url method which is an attribute due to @property.
+    """
+    url = "https://example.com"
+    user_agent = "Mozilla/5.0 (MacBook Air; M1 Mac OS X 11_4) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.1.1 Safari/604.1"
+    save_api = WaybackMachineSaveAPI(url, user_agent)
+    save_api.saved_archive = (
+        "https://web.archive.org/web/20220124063056/https://example.com/"
+    )
+    assert save_api.archive_url == save_api.saved_archive

tests/test_utils.py

@@ -0,0 +1,13 @@
+from waybackpy.utils import latest_version, DEFAULT_USER_AGENT
+from waybackpy.__version__ import __version__
+
+
+def test_default_user_agent():
+    assert (
+        DEFAULT_USER_AGENT
+        == "waybackpy %s - https://github.com/akamhy/waybackpy" % __version__
+    )
+
+
+def test_latest_version():
+    assert __version__ == latest_version(package_name="waybackpy")

waybackpy/__init__.py

@@ -1,6 +1,14 @@
-# -*- coding: utf-8 -*-
-from .wrapper import save, near, oldest, newest
-
-__version__ = "1.1"
-
-__all__ = ['wrapper', 'exceptions']
+from .wrapper import Url
+from .cdx_api import WaybackMachineCDXServerAPI
+from .save_api import WaybackMachineSaveAPI
+from .availability_api import WaybackMachineAvailabilityAPI
+from .__version__ import (
+    __title__,
+    __description__,
+    __url__,
+    __version__,
+    __author__,
+    __author_email__,
+    __license__,
+    __copyright__,
+)

waybackpy/__version__.py

@@ -0,0 +1,11 @@
+__title__ = "waybackpy"
+__description__ = (
+    "Python package that interfaces with the Internet Archive's Wayback Machine APIs. "
+    "Archive pages and retrieve archived pages easily."
+)
+__url__ = "https://akamhy.github.io/waybackpy/"
+__version__ = "3.0.1"
+__author__ = "Akash Mahanty"
+__author_email__ = "akamhy@yahoo.com"
+__license__ = "MIT"
+__copyright__ = "Copyright 2020-2022 Akash Mahanty et al."

waybackpy/availability_api.py

@@ -0,0 +1,198 @@
+import time
+import json
+import requests
+from datetime import datetime
+from .utils import DEFAULT_USER_AGENT
+from .exceptions import (
+    ArchiveNotInAvailabilityAPIResponse,
+    InvalidJSONInAvailabilityAPIResponse,
+)
+
+
+class WaybackMachineAvailabilityAPI:
+    """
+    Class that interfaces the availability API of the Wayback Machine.
+    """
+
+    def __init__(self, url, user_agent=DEFAULT_USER_AGENT, max_tries=3):
+        self.url = str(url).strip().replace(" ", "%20")
+        self.user_agent = user_agent
+        self.headers = {"User-Agent": self.user_agent}
+        self.payload = {"url": "{url}".format(url=self.url)}
+        self.endpoint = "https://archive.org/wayback/available"
+        self.max_tries = max_tries
+        self.tries = 0
+        self.last_api_call_unix_time = int(time.time())
+        self.api_call_time_gap = 5
+        self.JSON = None
+
+    def unix_timestamp_to_wayback_timestamp(self, unix_timestamp):
+        """
+        Converts Unix time to wayback Machine timestamp.
+        """
+        return datetime.utcfromtimestamp(int(unix_timestamp)).strftime("%Y%m%d%H%M%S")
+
+    def __repr__(self):
+        """
+        Same as string representation, just return the archive URL as a string.
+        """
+        return str(self)
+
+    def __str__(self):
+        """
+        String representation of the class. If atleast one API call was successfully
+        made then return the archive URL as a string. Else returns None.
+        """
+
+        # String must not return anything other than a string object
+        # So, if some asks for string repr before making the API requests
+        # just return ""
+        if not self.JSON:
+            return ""
+
+        return self.archive_url
+
+    def json(self):
+        """
+        Makes the API call to the availability API can set the JSON response
+        to the JSON attribute of the instance and also returns the JSON attribute.
+        """
+        time_diff = int(time.time()) - self.last_api_call_unix_time
+        sleep_time = self.api_call_time_gap - time_diff
+
+        if sleep_time > 0:
+            time.sleep(sleep_time)
+
+        self.response = requests.get(
+            self.endpoint, params=self.payload, headers=self.headers
+        )
+        self.last_api_call_unix_time = int(time.time())
+        self.tries += 1
+        try:
+            self.JSON = self.response.json()
+        except json.decoder.JSONDecodeError:
+            raise InvalidJSONInAvailabilityAPIResponse(
+                "Response data:\n{text}".format(text=self.response.text)
+            )
+
+        return self.JSON
+
+    def timestamp(self):
+        """
+        Converts the timestamp form the JSON response to datetime object.
+        If JSON attribute of the instance is None it implies that the either
+        the the last API call failed or one was never made.
+
+        If not JSON or if JSON but no timestamp in the JSON response then returns
+        the maximum value for datetime object that is possible.
+
+        If you get an URL as a response form the availability API it is guaranteed
+        that you can get the datetime object from the timestamp.
+        """
+        if not self.JSON or not self.JSON["archived_snapshots"]:
+            return datetime.max
+
+        return datetime.strptime(
+            self.JSON["archived_snapshots"]["closest"]["timestamp"], "%Y%m%d%H%M%S"
+        )
+
+    @property
+    def archive_url(self):
+        """
+        Reads the the JSON response data and tries to get the timestamp and returns
+        the timestamp if found else returns None.
+        """
+        data = self.JSON
+
+        # If the user didn't used oldest, newest or near but tries to access the
+        # archive_url attribute then, we assume they are fine with any archive
+        # and invoke the oldest archive function.
+        if not data:
+            self.oldest()
+
+        # If data is still not none then probably there are no
+        # archive for the requested URL.
+        if not data or not data["archived_snapshots"]:
+            while (self.tries < self.max_tries) and (
+                not data or not data["archived_snapshots"]
+            ):
+                self.json()  # It makes a new API call
+                data = self.JSON  # json() updated the value of JSON attribute
+
+            # Even if after we exhausted teh max_tries, then we give up and
+            # raise exception.
+
+            if not data or not data["archived_snapshots"]:
+                raise ArchiveNotInAvailabilityAPIResponse(
+                    "Archive not found in the availability "
+                    + "API response, the URL you requested may not have any "
+                    + "archives yet. You may retry after some time or archive the webpage now."
+                    + "\nResponse data:\n{response}".format(response=self.response.text)
+                )
+        else:
+            archive_url = data["archived_snapshots"]["closest"]["url"]
+            archive_url = archive_url.replace(
+                "http://web.archive.org/web/", "https://web.archive.org/web/", 1
+            )
+        return archive_url
+
+    def wayback_timestamp(self, **kwargs):
+        """
+        Prepends zero before the year, month, day, hour and minute so that they
+        are conformable with the YYYYMMDDhhmmss wayback machine timestamp format.
+        """
+        return "".join(
+            str(kwargs[key]).zfill(2)
+            for key in ["year", "month", "day", "hour", "minute"]
+        )
+
+    def oldest(self):
+        """
+        Passing the year 1994 should return the oldest archive because
+        wayback machine was started in May, 1996 and there should be no archive
+        before the year 1994.
+        """
+        return self.near(year=1994)
+
+    def newest(self):
+        """
+        Passing the current UNIX time should be sufficient to get the newest
+        archive considering the API request-response time delay and also the
+        database lags on Wayback machine.
+        """
+        return self.near(unix_timestamp=int(time.time()))
+
+    def near(
+        self,
+        year=None,
+        month=None,
+        day=None,
+        hour=None,
+        minute=None,
+        unix_timestamp=None,
+    ):
+        """
+        The main method for this Class, oldest and newest methods are dependent on this
+        method.
+
+        It generates the timestamp based on the input either by calling the
+        unix_timestamp_to_wayback_timestamp or wayback_timestamp method with
+        appropriate arguments for their respective parameters.
+        Adds the timestamp to the payload dictionary.
+        And finally invoking the json method to make the API call then returns the instance.
+        """
+        if unix_timestamp:
+            timestamp = self.unix_timestamp_to_wayback_timestamp(unix_timestamp)
+        else:
+            now = datetime.utcnow().timetuple()
+            timestamp = self.wayback_timestamp(
+                year=year if year else now.tm_year,
+                month=month if month else now.tm_mon,
+                day=day if day else now.tm_mday,
+                hour=hour if hour else now.tm_hour,
+                minute=minute if minute else now.tm_min,
+            )
+
+        self.payload["timestamp"] = timestamp
+        self.json()
+        return self

waybackpy/cdx_api.py

@@ -0,0 +1,194 @@
+from .exceptions import WaybackError
+from .cdx_snapshot import CDXSnapshot
+from .cdx_utils import (
+    get_total_pages,
+    get_response,
+    check_filters,
+    check_collapses,
+    check_match_type,
+    full_url,
+)
+
+from .utils import DEFAULT_USER_AGENT
+
+
+class WaybackMachineCDXServerAPI:
+    """
+    Class that interfaces the CDX server API of the Wayback Machine.
+    """
+
+    def __init__(
+        self,
+        url,
+        user_agent=DEFAULT_USER_AGENT,
+        start_timestamp=None,  # from, can not use from as it's a keyword
+        end_timestamp=None,  # to, not using to as can not use from
+        filters=[],
+        match_type=None,
+        gzip=None,
+        collapses=[],
+        limit=None,
+        max_tries=3,
+    ):
+        self.url = str(url).strip().replace(" ", "%20")
+        self.user_agent = user_agent
+        self.start_timestamp = str(start_timestamp) if start_timestamp else None
+        self.end_timestamp = str(end_timestamp) if end_timestamp else None
+        self.filters = filters
+        check_filters(self.filters)
+        self.match_type = str(match_type).strip() if match_type else None
+        check_match_type(self.match_type, self.url)
+        self.gzip = gzip if gzip else True
+        self.collapses = collapses
+        check_collapses(self.collapses)
+        self.limit = limit if limit else 5000
+        self.max_tries = max_tries
+        self.last_api_request_url = None
+        self.use_page = False
+        self.endpoint = "https://web.archive.org/cdx/search/cdx"
+
+    def cdx_api_manager(self, payload, headers, use_page=False):
+
+        total_pages = get_total_pages(self.url, self.user_agent)
+        # If we only have two or less pages of archives then we care for more accuracy
+        # pagination API is lagged sometimes
+        if use_page is True and total_pages >= 2:
+            blank_pages = 0
+            for i in range(total_pages):
+                payload["page"] = str(i)
+
+                url = full_url(self.endpoint, params=payload)
+                res = get_response(url, headers=headers)
+
+                self.last_api_request_url = url
+                text = res.text
+                if len(text) == 0:
+                    blank_pages += 1
+
+                if blank_pages >= 2:
+                    break
+
+                yield text
+        else:
+
+            payload["showResumeKey"] = "true"
+            payload["limit"] = str(self.limit)
+            resumeKey = None
+
+            more = True
+            while more:
+
+                if resumeKey:
+                    payload["resumeKey"] = resumeKey
+
+                url = full_url(self.endpoint, params=payload)
+                res = get_response(url, headers=headers)
+
+                self.last_api_request_url = url
+
+                text = res.text.strip()
+                lines = text.splitlines()
+
+                more = False
+
+                if len(lines) >= 3:
+
+                    second_last_line = lines[-2]
+
+                    if len(second_last_line) == 0:
+
+                        resumeKey = lines[-1].strip()
+                        text = text.replace(resumeKey, "", 1).strip()
+                        more = True
+
+                yield text
+
+    def add_payload(self, payload):
+        if self.start_timestamp:
+            payload["from"] = self.start_timestamp
+
+        if self.end_timestamp:
+            payload["to"] = self.end_timestamp
+
+        if self.gzip is not True:
+            payload["gzip"] = "false"
+
+        if self.match_type:
+            payload["matchType"] = self.match_type
+
+        if self.filters and len(self.filters) > 0:
+            for i, f in enumerate(self.filters):
+                payload["filter" + str(i)] = f
+
+        if self.collapses and len(self.collapses) > 0:
+            for i, f in enumerate(self.collapses):
+                payload["collapse" + str(i)] = f
+
+        # Don't need to return anything as it's dictionary.
+        payload["url"] = self.url
+
+    def snapshots(self):
+        payload = {}
+        headers = {"User-Agent": self.user_agent}
+
+        self.add_payload(payload)
+
+        if not self.start_timestamp or self.end_timestamp:
+            self.use_page = True
+
+        if self.collapses != []:
+            self.use_page = False
+
+        texts = self.cdx_api_manager(payload, headers, use_page=self.use_page)
+
+        for text in texts:
+
+            if text.isspace() or len(text) <= 1 or not text:
+                continue
+
+            snapshot_list = text.split("\n")
+
+            for snapshot in snapshot_list:
+
+                if len(snapshot) < 46:  # 14 + 32 (timestamp+digest)
+                    continue
+
+                properties = {
+                    "urlkey": None,
+                    "timestamp": None,
+                    "original": None,
+                    "mimetype": None,
+                    "statuscode": None,
+                    "digest": None,
+                    "length": None,
+                }
+
+                prop_values = snapshot.split(" ")
+
+                prop_values_len = len(prop_values)
+                properties_len = len(properties)
+
+                if prop_values_len != properties_len:
+                    raise WaybackError(
+                        "Snapshot returned by Cdx API has {prop_values_len} properties".format(
+                            prop_values_len=prop_values_len
+                        )
+                        + " instead of expected {properties_len} ".format(
+                            properties_len=properties_len
+                        )
+                        + "properties.\nProblematic Snapshot : {snapshot}".format(
+                            snapshot=snapshot
+                        )
+                    )
+
+                (
+                    properties["urlkey"],
+                    properties["timestamp"],
+                    properties["original"],
+                    properties["mimetype"],
+                    properties["statuscode"],
+                    properties["digest"],
+                    properties["length"],
+                ) = prop_values
+
+                yield CDXSnapshot(properties)

waybackpy/cdx_snapshot.py

@@ -0,0 +1,35 @@
+from datetime import datetime
+
+
+class CDXSnapshot:
+    """
+    Class for the CDX snapshot lines returned by the CDX API,
+    Each valid line of the CDX API is casted to an CDXSnapshot object
+    by the CDX API interface.
+    This provides the end-user the ease of using the data as attributes
+    of the CDXSnapshot.
+    """
+
+    def __init__(self, properties):
+        self.urlkey = properties["urlkey"]
+        self.timestamp = properties["timestamp"]
+        self.datetime_timestamp = datetime.strptime(self.timestamp, "%Y%m%d%H%M%S")
+        self.original = properties["original"]
+        self.mimetype = properties["mimetype"]
+        self.statuscode = properties["statuscode"]
+        self.digest = properties["digest"]
+        self.length = properties["length"]
+        self.archive_url = (
+            "https://web.archive.org/web/" + self.timestamp + "/" + self.original
+        )
+
+    def __str__(self):
+        return "{urlkey} {timestamp} {original} {mimetype} {statuscode} {digest} {length}".format(
+            urlkey=self.urlkey,
+            timestamp=self.timestamp,
+            original=self.original,
+            mimetype=self.mimetype,
+            statuscode=self.statuscode,
+            digest=self.digest,
+            length=self.length,
+        )

waybackpy/cdx_utils.py

@@ -0,0 +1,128 @@
+import re
+import requests
+from urllib3.util.retry import Retry
+from requests.adapters import HTTPAdapter
+from .exceptions import WaybackError
+from .utils import DEFAULT_USER_AGENT
+
+
+def get_total_pages(url, user_agent=DEFAULT_USER_AGENT):
+    endpoint = "https://web.archive.org/cdx/search/cdx?"
+    payload = {"showNumPages": "true", "url": str(url)}
+    headers = {"User-Agent": user_agent}
+    request_url = full_url(endpoint, params=payload)
+    response = get_response(request_url, headers=headers)
+    return int(response.text.strip())
+
+
+def full_url(endpoint, params):
+    if not params:
+        return endpoint
+    full_url = endpoint if endpoint.endswith("?") else (endpoint + "?")
+    for key, val in params.items():
+        key = "filter" if key.startswith("filter") else key
+        key = "collapse" if key.startswith("collapse") else key
+        amp = "" if full_url.endswith("?") else "&"
+        full_url = (
+            full_url
+            + amp
+            + "{key}={val}".format(key=key, val=requests.utils.quote(str(val)))
+        )
+    return full_url
+
+
+def get_response(
+    url,
+    headers=None,
+    retries=5,
+    backoff_factor=0.5,
+    no_raise_on_redirects=False,
+):
+    session = requests.Session()
+    retries = Retry(
+        total=retries,
+        backoff_factor=backoff_factor,
+        status_forcelist=[500, 502, 503, 504],
+    )
+    session.mount("https://", HTTPAdapter(max_retries=retries))
+
+    try:
+        response = session.get(url, headers=headers)
+        session.close()
+        return response
+    except Exception as e:
+        reason = str(e)
+        exc_message = "Error while retrieving {url}.\n{reason}".format(
+            url=url, reason=reason
+        )
+        exc = WaybackError(exc_message)
+        exc.__cause__ = e
+        raise exc
+
+
+def check_filters(filters):
+    if not isinstance(filters, list):
+        raise WaybackError("filters must be a list.")
+
+    # [!]field:regex
+    for _filter in filters:
+        try:
+
+            match = re.search(
+                r"(\!?(?:urlkey|timestamp|original|mimetype|statuscode|digest|length)):(.*)",
+                _filter,
+            )
+
+            match.group(1)
+            match.group(2)
+
+        except Exception:
+
+            exc_message = (
+                "Filter '{_filter}' is not following the cdx filter syntax.".format(
+                    _filter=_filter
+                )
+            )
+            raise WaybackError(exc_message)
+
+
+def check_collapses(collapses):
+
+    if not isinstance(collapses, list):
+        raise WaybackError("collapses must be a list.")
+
+    if len(collapses) == 0:
+        return
+
+    for collapse in collapses:
+        try:
+            match = re.search(
+                r"(urlkey|timestamp|original|mimetype|statuscode|digest|length)(:?[0-9]{1,99})?",
+                collapse,
+            )
+            match.group(1)
+            if 2 == len(match.groups()):
+                match.group(2)
+        except Exception:
+            exc_message = "collapse argument '{collapse}' is not following the cdx collapse syntax.".format(
+                collapse=collapse
+            )
+            raise WaybackError(exc_message)
+
+
+def check_match_type(match_type, url):
+    if not match_type:
+        return
+
+    if "*" in url:
+        raise WaybackError(
+            "Can not use wildcard in the URL along with the match_type arguments."
+        )
+
+    legal_match_type = ["exact", "prefix", "host", "domain"]
+
+    if match_type not in legal_match_type:
+        exc_message = "{match_type} is not an allowed match type.\nUse one from 'exact', 'prefix', 'host' or 'domain'".format(
+            match_type=match_type
+        )
+        raise WaybackError(exc_message)

waybackpy/cli.py

@@ -0,0 +1,347 @@
+import click
+import re
+import os
+import json as JSON
+import random
+import string
+from .__version__ import __version__
+from .utils import DEFAULT_USER_AGENT
+from .cdx_api import WaybackMachineCDXServerAPI
+from .save_api import WaybackMachineSaveAPI
+from .availability_api import WaybackMachineAvailabilityAPI
+from .wrapper import Url
+
+
+@click.command()
+@click.option(
+    "-u", "--url", help="URL on which Wayback machine operations are to be performed."
+)
+@click.option(
+    "-ua",
+    "--user-agent",
+    "--user_agent",
+    default=DEFAULT_USER_AGENT,
+    help="User agent, default user agent is '%s' " % DEFAULT_USER_AGENT,
+)
+@click.option(
+    "-v", "--version", is_flag=True, default=False, help="Print waybackpy version."
+)
+@click.option(
+    "-n",
+    "--newest",
+    "-au",
+    "--archive_url",
+    "--archive-url",
+    default=False,
+    is_flag=True,
+    help="Fetch the newest archive of the specified URL",
+)
+@click.option(
+    "-o",
+    "--oldest",
+    default=False,
+    is_flag=True,
+    help="Fetch the oldest archive of the specified URL",
+)
+@click.option(
+    "-j",
+    "--json",
+    default=False,
+    is_flag=True,
+    help="Spit out the JSON data for availability_api commands.",
+)
+@click.option(
+    "-N", "--near", default=False, is_flag=True, help="Archive near specified time."
+)
+@click.option("-Y", "--year", type=click.IntRange(1994, 9999), help="Year in integer.")
+@click.option("-M", "--month", type=click.IntRange(1, 12), help="Month in integer.")
+@click.option("-D", "--day", type=click.IntRange(1, 31), help="Day in integer.")
+@click.option("-H", "--hour", type=click.IntRange(0, 24), help="Hour in integer.")
+@click.option("-MIN", "--minute", type=click.IntRange(0, 60), help="Minute in integer.")
+@click.option(
+    "-s",
+    "--save",
+    default=False,
+    is_flag=True,
+    help="Save the specified URL's webpage and print the archive URL.",
+)
+@click.option(
+    "-h",
+    "--headers",
+    default=False,
+    is_flag=True,
+    help="Spit out the headers data for save_api commands.",
+)
+@click.option(
+    "-ku",
+    "--known-urls",
+    "--known_urls",
+    default=False,
+    is_flag=True,
+    help="List known URLs. Uses CDX API.",
+)
+@click.option(
+    "-sub",
+    "--subdomain",
+    default=False,
+    is_flag=True,
+    help="Use with '--known_urls' to include known URLs for subdomains.",
+)
+@click.option(
+    "-f",
+    "--file",
+    default=False,
+    is_flag=True,
+    help="Use with '--known_urls' to save the URLs in file at current directory.",
+)
+@click.option(
+    "-c",
+    "--cdx",
+    default=False,
+    is_flag=True,
+    help="Spit out the headers data for save_api commands.",
+)
+@click.option(
+    "-st",
+    "--start-timestamp",
+    "--start_timestamp",
+)
+@click.option(
+    "-et",
+    "--end-timestamp",
+    "--end_timestamp",
+)
+@click.option(
+    "-f",
+    "--filters",
+    multiple=True,
+)
+@click.option(
+    "-mt",
+    "--match-type",
+    "--match_type",
+)
+@click.option(
+    "-gz",
+    "--gzip",
+)
+@click.option(
+    "-c",
+    "--collapses",
+    multiple=True,
+)
+@click.option(
+    "-l",
+    "--limit",
+)
+@click.option(
+    "-cp",
+    "--cdx-print",
+    "--cdx_print",
+    multiple=True,
+)
+def main(
+    url,
+    user_agent,
+    version,
+    newest,
+    oldest,
+    json,
+    near,
+    year,
+    month,
+    day,
+    hour,
+    minute,
+    save,
+    headers,
+    known_urls,
+    subdomain,
+    file,
+    cdx,
+    start_timestamp,
+    end_timestamp,
+    filters,
+    match_type,
+    gzip,
+    collapses,
+    limit,
+    cdx_print,
+):
+    """
+    ┏┓┏┓┏┓━━━━━━━━━━┏━━┓━━━━━━━━━━┏┓━━┏━━━┓━━━━━
+    ┃┃┃┃┃┃━━━━━━━━━━┃┏┓┃━━━━━━━━━━┃┃━━┃┏━┓┃━━━━━
+    ┃┃┃┃┃┃┏━━┓━┏┓━┏┓┃┗┛┗┓┏━━┓━┏━━┓┃┃┏┓┃┗━┛┃┏┓━┏┓
+    ┃┗┛┗┛┃┗━┓┃━┃┃━┃┃┃┏━┓┃┗━┓┃━┃┏━┛┃┗┛┛┃┏━━┛┃┃━┃┃
+    ┗┓┏┓┏┛┃┗┛┗┓┃┗━┛┃┃┗━┛┃┃┗┛┗┓┃┗━┓┃┏┓┓┃┃━━━┃┗━┛┃
+    ━┗┛┗┛━┗━━━┛┗━┓┏┛┗━━━┛┗━━━┛┗━━┛┗┛┗┛┗┛━━━┗━┓┏┛
+    ━━━━━━━━━━━┏━┛┃━━━━━━━━━━━━━━━━━━━━━━━━┏━┛┃━
+    ━━━━━━━━━━━┗━━┛━━━━━━━━━━━━━━━━━━━━━━━━┗━━┛━
+
+    waybackpy : Python package & CLI tool that interfaces the Wayback Machine API
+
+    Released under the MIT License.
+    License @ https://github.com/akamhy/waybackpy/blob/master/LICENSE
+
+    Copyright (c) 2020 waybackpy contributors. Contributors list @
+    https://github.com/akamhy/waybackpy/graphs/contributors
+
+    https://github.com/akamhy/waybackpy
+
+    https://pypi.org/project/waybackpy
+
+    """
+
+    if version:
+        click.echo("waybackpy version %s" % __version__)
+        return
+
+    if not url:
+        click.echo("No URL detected. Please pass an URL.")
+        return
+
+    def echo_availability_api(availability_api_instance):
+        click.echo("Archive URL:")
+        if not availability_api_instance.archive_url:
+            archive_url = (
+                "NO ARCHIVE FOUND - The requested URL is probably "
+                + "not yet archived or if the URL was recently archived then it is "
+                + "not yet available via the Wayback Machine's availability API "
+                + "because of database lag and should be available after some time."
+            )
+        else:
+            archive_url = availability_api_instance.archive_url
+        click.echo(archive_url)
+        if json:
+            click.echo("JSON response:")
+            click.echo(JSON.dumps(availability_api_instance.JSON))
+
+    availability_api = WaybackMachineAvailabilityAPI(url, user_agent=user_agent)
+
+    if oldest:
+        availability_api.oldest()
+        echo_availability_api(availability_api)
+        return
+
+    if newest:
+        availability_api.newest()
+        echo_availability_api(availability_api)
+        return
+
+    if near:
+        near_args = {}
+        keys = ["year", "month", "day", "hour", "minute"]
+        args_arr = [year, month, day, hour, minute]
+        for key, arg in zip(keys, args_arr):
+            if arg:
+                near_args[key] = arg
+        availability_api.near(**near_args)
+        echo_availability_api(availability_api)
+        return
+
+    if save:
+        save_api = WaybackMachineSaveAPI(url, user_agent=user_agent)
+        save_api.save()
+        click.echo("Archive URL:")
+        click.echo(save_api.archive_url)
+        click.echo("Cached save:")
+        click.echo(save_api.cached_save)
+        if headers:
+            click.echo("Save API headers:")
+            click.echo(save_api.headers)
+        return
+
+    def save_urls_on_file(url_gen):
+        domain = None
+        sys_random = random.SystemRandom()
+        uid = "".join(
+            sys_random.choice(string.ascii_lowercase + string.digits) for _ in range(6)
+        )
+        url_count = 0
+
+        for url in url_gen:
+            url_count += 1
+            if not domain:
+                match = re.search("https?://([A-Za-z_0-9.-]+).*", url)
+
+                domain = "domain-unknown"
+
+                if match:
+                    domain = match.group(1)
+
+                file_name = "{domain}-urls-{uid}.txt".format(domain=domain, uid=uid)
+                file_path = os.path.join(os.getcwd(), file_name)
+                if not os.path.isfile(file_path):
+                    open(file_path, "w+").close()
+
+            with open(file_path, "a") as f:
+                f.write("{url}\n".format(url=url))
+
+            click.echo(url)
+
+        if url_count > 0:
+            click.echo(
+                "\n\n'{file_name}' saved in current working directory".format(
+                    file_name=file_name
+                )
+            )
+        else:
+            click.echo("No known URLs found. Please try a diffrent input!")
+
+    if known_urls:
+        wayback = Url(url, user_agent)
+        url_gen = wayback.known_urls(subdomain=subdomain)
+
+        if file:
+            return save_urls_on_file(url_gen)
+        else:
+            for url in url_gen:
+                click.echo(url)
+
+    if cdx:
+        filters = list(filters)
+        collapses = list(collapses)
+        cdx_print = list(cdx_print)
+
+        cdx_api = WaybackMachineCDXServerAPI(
+            url,
+            user_agent=user_agent,
+            start_timestamp=start_timestamp,
+            end_timestamp=end_timestamp,
+            filters=filters,
+            match_type=match_type,
+            gzip=gzip,
+            collapses=collapses,
+            limit=limit,
+        )
+
+        snapshots = cdx_api.snapshots()
+
+        for snapshot in snapshots:
+            if len(cdx_print) == 0:
+                click.echo(snapshot)
+            else:
+                output_string = ""
+                if "urlkey" or "url-key" or "url_key" in cdx_print:
+                    output_string = output_string + snapshot.urlkey + " "
+                if "timestamp" or "time-stamp" or "time_stamp" in cdx_print:
+                    output_string = output_string + snapshot.timestamp + " "
+                if "original" in cdx_print:
+                    output_string = output_string + snapshot.original + " "
+                if "original" in cdx_print:
+                    output_string = output_string + snapshot.original + " "
+                if "mimetype" or "mime-type" or "mime_type" in cdx_print:
+                    output_string = output_string + snapshot.mimetype + " "
+                if "statuscode" or "status-code" or "status_code" in cdx_print:
+                    output_string = output_string + snapshot.statuscode + " "
+                if "digest" in cdx_print:
+                    output_string = output_string + snapshot.digest + " "
+                if "length" in cdx_print:
+                    output_string = output_string + snapshot.length + " "
+                if "archiveurl" or "archive-url" or "archive_url" in cdx_print:
+                    output_string = output_string + snapshot.archive_url + " "
+                click.echo(output_string)
+
+
+if __name__ == "__main__":
+    main()

waybackpy/exceptions.py

@@ -1,38 +1,52 @@
-# -*- coding: utf-8 -*-
+"""
+waybackpy.exceptions
+~~~~~~~~~~~~~~~~~~~
+This module contains the set of Waybackpy's exceptions.
+"""
 
-class TooManyArchivingRequests(Exception):
+
+class WaybackError(Exception):
     """
-    Error when a single url reqeusted for archiving too many times in a short timespam.
-    Wayback machine doesn't supports archivng any url too many times in a short period of time.
+    Raised when Waybackpy can not return what you asked for.
+     1) Wayback Machine API Service is unreachable/down.
+     2) You passed illegal arguments.
+
+     All other exceptions are inherited from this class.
     """
 
-class ArchivingNotAllowed(Exception):
+
+class RedirectSaveError(WaybackError):
     """
-    Files like robots.txt are set to deny robot archiving.
-    Wayback machine respects these file, will not archive.
+    Raised when the original URL is redirected and the
+    redirect URL is archived but not the original URL.
     """
 
-class PageNotSaved(Exception):
+
+class URLError(Exception):
     """
-    When unable to save a webpage.
+    Raised when malformed URLs are passed as arguments.
     """
 
-class ArchiveNotFound(Exception):
+
+class MaximumRetriesExceeded(WaybackError):
     """
-    When a page was never archived but client asks for old archive.
+    MaximumRetriesExceeded
     """
 
-class UrlNotFound(Exception):
+
+class MaximumSaveRetriesExceeded(MaximumRetriesExceeded):
     """
-    Raised when 404 UrlNotFound.
+    MaximumSaveRetriesExceeded
     """
 
-class BadGateWay(Exception):
+
+class ArchiveNotInAvailabilityAPIResponse(WaybackError):
     """
-    Raised when 502 bad gateway.
+    Could not parse the archive in the JSON response of the availability API.
     """
 
-class InvalidUrl(Exception):
+
+class InvalidJSONInAvailabilityAPIResponse(WaybackError):
     """
-    Raised when url doesn't follow the standard url format.
+    availability api returned invalid JSON
     """

waybackpy/save_api.py

@@ -0,0 +1,186 @@
+import re
+import time
+import requests
+
+from datetime import datetime
+from urllib3.util.retry import Retry
+from requests.adapters import HTTPAdapter
+
+from .utils import DEFAULT_USER_AGENT
+from .exceptions import MaximumSaveRetriesExceeded
+
+
+class WaybackMachineSaveAPI:
+
+    """
+    WaybackMachineSaveAPI class provides an interface for saving URLs on the
+    Wayback Machine.
+    """
+
+    def __init__(self, url, user_agent=DEFAULT_USER_AGENT, max_tries=8):
+        self.url = str(url).strip().replace(" ", "%20")
+        self.request_url = "https://web.archive.org/save/" + self.url
+        self.user_agent = user_agent
+        self.request_headers = {"User-Agent": self.user_agent}
+        self.max_tries = max_tries
+        self.total_save_retries = 5
+        self.backoff_factor = 0.5
+        self.status_forcelist = [500, 502, 503, 504]
+        self._archive_url = None
+        self.instance_birth_time = datetime.utcnow()
+
+    @property
+    def archive_url(self):
+        """
+        Returns the archive URL is already cached by _archive_url
+        else invoke the save method to save the archive which returns the
+        archive thus we return the methods return value.
+        """
+
+        if self._archive_url:
+            return self._archive_url
+        else:
+            return self.save()
+
+    def get_save_request_headers(self):
+        """
+        Creates a session and tries 'retries' number of times to
+        retrieve the archive.
+
+        If successful in getting the response, sets the headers, status_code
+        and response_url attributes.
+
+        The archive is usually in the headers but it can also be the response URL
+        as the Wayback Machine redirects to the archive after a successful capture
+        of the webpage.
+
+        Wayback Machine's save API is known
+        to be very unreliable thus if it fails first check opening
+        the response URL yourself in the browser.
+        """
+        session = requests.Session()
+        retries = Retry(
+            total=self.total_save_retries,
+            backoff_factor=self.backoff_factor,
+            status_forcelist=self.status_forcelist,
+        )
+        session.mount("https://", HTTPAdapter(max_retries=retries))
+        self.response = session.get(self.request_url, headers=self.request_headers)
+        self.headers = (
+            self.response.headers
+        )  # <class 'requests.structures.CaseInsensitiveDict'>
+        self.status_code = self.response.status_code
+        self.response_url = self.response.url
+        session.close()
+
+    def archive_url_parser(self):
+        """
+        Three regexen (like oxen?) are used to search for the
+        archive URL in the headers and finally look in the response URL
+        for the archive URL.
+        """
+
+        regex1 = r"Content-Location: (/web/[0-9]{14}/.*)"
+        match = re.search(regex1, str(self.headers))
+        if match:
+            return "https://web.archive.org" + match.group(1)
+
+        regex2 = r"rel=\"memento.*?(web\.archive\.org/web/[0-9]{14}/.*?)>"
+        match = re.search(regex2, str(self.headers))
+        if match:
+            return "https://" + match.group(1)
+
+        regex3 = r"X-Cache-Key:\shttps(.*)[A-Z]{2}"
+        match = re.search(regex3, str(self.headers))
+        if match:
+            return "https" + match.group(1)
+
+        if self.response_url:
+            self.response_url = self.response_url.strip()
+            if "web.archive.org/web" in self.response_url:
+                regex = r"web\.archive\.org/web/(?:[0-9]*?)/(?:.*)$"
+                match = re.search(regex, self.response_url)
+                if match:
+                    return "https://" + match.group(0)
+
+    def sleep(self, tries):
+        """
+        Ensure that the we wait some time before succesive retries so that we
+        don't waste the retries before the page is even captured by the Wayback
+        Machine crawlers also ensures that we are not putting too much load on
+        the Wayback Machine's save API.
+
+        If tries are multiple of 3 sleep 10 seconds else sleep 5 seconds.
+        """
+
+        sleep_seconds = 5
+        if tries % 3 == 0:
+            sleep_seconds = 10
+        time.sleep(sleep_seconds)
+
+    def timestamp(self):
+        """
+        Read the timestamp off the archive URL and convert the Wayback Machine
+        timestamp to datetime object.
+
+        Also check if the time on archive is URL and compare it to instance birth
+        time.
+
+        If time on the archive is older than the instance creation time set the cached_save
+        to True else set it to False. The flag can be used to check if the Wayback Machine
+        didn't serve a Cached URL. It is quite common for the Wayback Machine to serve
+        cached archive if last archive was captured before last 45 minutes.
+        """
+        m = re.search(
+            r"https?://web\.archive.org/web/([0-9]{14})/http", self._archive_url
+        )
+        string_timestamp = m.group(1)
+        timestamp = datetime.strptime(string_timestamp, "%Y%m%d%H%M%S")
+
+        timestamp_unixtime = time.mktime(timestamp.timetuple())
+        instance_birth_time_unixtime = time.mktime(self.instance_birth_time.timetuple())
+
+        if timestamp_unixtime < instance_birth_time_unixtime:
+            self.cached_save = True
+        else:
+            self.cached_save = False
+
+        return timestamp
+
+    def save(self):
+        """
+        Calls the SavePageNow API of the Wayback Machine with required parameters
+        and headers to save the URL.
+
+        Raises MaximumSaveRetriesExceeded is maximum retries are exhausted but still
+        we were unable to retrieve the archive from the Wayback Machine.
+        """
+
+        self.saved_archive = None
+        tries = 0
+
+        while True:
+
+            tries += 1
+
+            if tries >= self.max_tries:
+                raise MaximumSaveRetriesExceeded(
+                    "Tried %s times but failed to save and retrieve the" % str(tries)
+                    + " archive for %s.\nResponse URL:\n%s \nResponse Header:\n%s\n"
+                    % (self.url, self.response_url, str(self.headers)),
+                )
+
+            if not self.saved_archive:
+
+                if tries > 1:
+                    self.sleep(tries)
+
+                self.get_save_request_headers()
+                self.saved_archive = self.archive_url_parser()
+
+                if not self.saved_archive:
+                    continue
+                else:
+                    self._archive_url = self.saved_archive
+                    self.timestamp()
+                    return self.saved_archive

waybackpy/utils.py

@@ -0,0 +1,12 @@
+import requests
+from .__version__ import __version__
+
+DEFAULT_USER_AGENT = "waybackpy %s - https://github.com/akamhy/waybackpy" % __version__
+
+
+def latest_version(package_name, user_agent=DEFAULT_USER_AGENT):
+    request_url = "https://pypi.org/pypi/" + package_name + "/json"
+    headers = {"User-Agent": user_agent}
+    response = requests.get(request_url, headers=headers)
+    data = response.json()
+    return data["info"]["version"]

waybackpy/wrapper.py

@@ -1,68 +1,129 @@
-# -*- coding: utf-8 -*-
-from datetime import datetime
-from waybackpy.exceptions import *
-try:
-    from urllib.request import Request, urlopen
-    from urllib.error import HTTPError
-except ImportError:
-    from urllib2 import Request, urlopen, HTTPError
+from .save_api import WaybackMachineSaveAPI
+from .availability_api import WaybackMachineAvailabilityAPI
+from .cdx_api import WaybackMachineCDXServerAPI
+from .utils import DEFAULT_USER_AGENT
+from datetime import datetime, timedelta
+
+"""
+The Url class is not recommended to be used anymore, instead use the
+WaybackMachineSaveAPI, WaybackMachineAvailabilityAPI and WaybackMachineCDXServerAPI.
+
+The reason it is still in the code is backwards compatibility with 2.x.x versions.
+
+If were are using the Url before the update to version 3.x.x, your code should still be
+working fine and there is no hurry to update the interface but is recommended that you
+do not use the Url class for new code as it would be removed after 2025 also the first
+3.x.x versions was released in January 2022 and three years are more than enough to update
+the older interface code.
+"""
 
 
-default_UA = "waybackpy python package"
+class Url:
+    def __init__(self, url, user_agent=DEFAULT_USER_AGENT):
+        self.url = url
+        self.user_agent = str(user_agent)
+        self.archive_url = None
+        self.wayback_machine_availability_api = WaybackMachineAvailabilityAPI(
+            self.url, user_agent=self.user_agent
+        )
 
-def clean_url(url):
-    return str(url).strip().replace(" ","_")
+    def __str__(self):
+        if not self.archive_url:
+            self.newest()
+        return self.archive_url
 
-def save(url,UA=default_UA):
-    base_save_url = "https://web.archive.org/save/"
-    request_url = (base_save_url + clean_url(url))
-    hdr = { 'User-Agent' : '%s' % UA }
-    req = Request(request_url, headers=hdr)
-    if "." not in url:
-        raise InvalidUrl("'%s' is not a vaild url." % url)
-    try:
-        response = urlopen(req) #nosec
-    except HTTPError as e:
-        if e.code == 502:
-            raise BadGateWay(e)
-        elif e.code == 429:
-            raise TooManyArchivingRequests(e)
-        elif e.code == 404:
-            raise UrlNotFound(e)
-        else:
-          raise PageNotSaved(e)
+    def __len__(self):
+        td_max = timedelta(
+            days=999999999, hours=23, minutes=59, seconds=59, microseconds=999999
+        )
 
-    header = response.headers
-    if "exclusion.robots.policy" in str(header):
-        raise ArchivingNotAllowed("Can not archive %s. Disabled by site owner." % (url))
-    archive_id = header['Content-Location']
-    archived_url = "https://web.archive.org" + archive_id
-    return archived_url
+        if not self.timestamp:
+            self.oldest()
 
-def near(
-    url,
-    year=datetime.utcnow().strftime('%Y'),
-    month=datetime.utcnow().strftime('%m'),
-    day=datetime.utcnow().strftime('%d'),
-    hour=datetime.utcnow().strftime('%H'),
-    minute=datetime.utcnow().strftime('%M'),
-    UA=default_UA,
+        if self.timestamp == datetime.max:
+            return td_max.days
+
+        return (datetime.utcnow() - self.timestamp).days
+
+    def save(self):
+        self.wayback_machine_save_api = WaybackMachineSaveAPI(
+            self.url, user_agent=self.user_agent
+        )
+        self.archive_url = self.wayback_machine_save_api.archive_url
+        self.timestamp = self.wayback_machine_save_api.timestamp()
+        self.headers = self.wayback_machine_save_api.headers
+        return self
+
+    def near(
+        self,
+        year=None,
+        month=None,
+        day=None,
+        hour=None,
+        minute=None,
+        unix_timestamp=None,
     ):
-    timestamp = str(year)+str(month)+str(day)+str(hour)+str(minute)
-    request_url = "https://archive.org/wayback/available?url=%s&timestamp=%s" % (clean_url(url), str(timestamp))
-    hdr = { 'User-Agent' : '%s' % UA }
-    req = Request(request_url, headers=hdr)
-    response = urlopen(req) #nosec
-    import json
-    data = json.loads(response.read().decode('utf8'))
-    if not data["archived_snapshots"]:
-        raise ArchiveNotFound("'%s' is not yet archived." % url)
-    
-    archive_url = (data["archived_snapshots"]["closest"]["url"])
-    return archive_url
 
-def oldest(url,UA=default_UA,year=1994):
-    return near(url,year=year,UA=UA)
+        self.wayback_machine_availability_api.near(
+            year=year,
+            month=month,
+            day=day,
+            hour=hour,
+            minute=minute,
+            unix_timestamp=unix_timestamp,
+        )
+        self.set_availability_api_attrs()
+        return self
 
-def newest(url,UA=default_UA):
-    return near(url,UA=UA)
+    def oldest(self):
+        self.wayback_machine_availability_api.oldest()
+        self.set_availability_api_attrs()
+        return self
+
+    def newest(self):
+        self.wayback_machine_availability_api.newest()
+        self.set_availability_api_attrs()
+        return self
+
+    def set_availability_api_attrs(self):
+        self.archive_url = self.wayback_machine_availability_api.archive_url
+        self.JSON = self.wayback_machine_availability_api.JSON
+        self.timestamp = self.wayback_machine_availability_api.timestamp()
+
+    def total_archives(self, start_timestamp=None, end_timestamp=None):
+        cdx = WaybackMachineCDXServerAPI(
+            self.url,
+            user_agent=self.user_agent,
+            start_timestamp=start_timestamp,
+            end_timestamp=end_timestamp,
+        )
+
+        count = 0
+        for _ in cdx.snapshots():
+            count = count + 1
+        return count
+
+    def known_urls(
+        self,
+        subdomain=False,
+        host=False,
+        start_timestamp=None,
+        end_timestamp=None,
+        match_type="prefix",
+    ):
+        if subdomain:
+            match_type = "domain"
+        if host:
+            match_type = "host"
+
+        cdx = WaybackMachineCDXServerAPI(
+            self.url,
+            user_agent=self.user_agent,
+            start_timestamp=start_timestamp,
+            end_timestamp=end_timestamp,
+            match_type=match_type,
+            collapses=["urlkey"],
+        )
+
+        for snapshot in cdx.snapshots():
+            yield (snapshot.original)