Update __version__.py

* Update wrapper.py

* Update wrapper.py

* Update wrapper.py

* Update wrapper.py

* Update wrapper.py

* api changed; fix archive url parser

* Update wrapper.py

* - Trailing whitespace

* include the header in exception

README.md

@@ -53,82 +53,170 @@ pip install waybackpy
 
 ## Usage
 
-#### Capturing aka Saving an url Using save()
+#### Capturing aka Saving an url using save()
 ```python
 import waybackpy
-# Capturing a new archive on Wayback machine.
-target_url = waybackpy.Url("https://github.com/akamhy/waybackpy", user_agnet="My-cool-user-agent")
-archived_url = target_url.save()
-print(archived_url)
+
+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)
 ```
-This should print an URL similar to the following archived URL:
-
-> <https://web.archive.org/web/20200504141153/https://github.com/akamhy/waybackpy>
+```bash
+https://web.archive.org/web/20200504141153/https://github.com/akamhy/waybackpy
+```
+<sub>Try this out in your browser @ <https://repl.it/repls/CompassionateRemoteOrigin#main.py></sub>
 
 
-#### Receiving the oldest archive for an URL Using oldest()
+
+#### Receiving the oldest archive for an URL using oldest()
 ```python
 import waybackpy
-# retrieving the oldest archive on Wayback machine.
-target_url = waybackpy.Url("https://www.google.com/", "My-cool-user-agent")
-oldest_archive = target_url.oldest()
-print(oldest_archive)
-```
-This should print the oldest available archive for <https://google.com>.
 
-> <http://web.archive.org/web/19981111184551/http://google.com:80/>
+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/repls/MixedSuperDimensions#main.py></sub>
+
 
 
 #### Receiving the newest archive for an URL using newest()
 ```python
 import waybackpy
-# retrieving the newest/latest archive on Wayback machine.
-target_url = waybackpy.Url(url="https://www.google.com/", user_agnet="My-cool-user-agent")
-newest_archive = target_url.newest()
-print(newest_archive)
-```
-This print the newest available archive for <https://www.microsoft.com/en-us>, something just like this:
 
-> <http://web.archive.org/web/20200429033402/https://www.microsoft.com/en-us/>
+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/repls/OblongMiniInteger#main.py></sub>
+
 
 
 #### Receiving archive close to a specified year, month, day, hour, and minute using near()
 ```python
-import waybackpy
-# retriving the the closest archive from a specified year.
-# supported argumnets are year,month,day,hour and minute
-target_url = waybackpy.Url(https://www.facebook.com/", "Any-User-Agent")
-archive_near_year = target_url.near(year=2010)
-print(archive_near_year)
+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.
 ```
-returns : <http://web.archive.org/web/20100504071154/http://www.facebook.com/>
+```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/
 
-> Please note that if you only specify the year, the current month and day are default arguments for month and day respectively. Just putting the year parameter would not return the archive closer to January but the current month you are using the package. You need to specify the month "1" for January , 2 for february and so on.
+```
+
+<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/repls/SparseDeadlySearchservice#main.py></sub>
 
-> Do not pad (don't use zeros in the month, year, day, minute, and hour arguments). e.g. For January, set month = 1 and not month = 01.
 
 
 #### Get the content of webpage using get()
 ```python
 import waybackpy
-# retriving the webpage from any url including the archived urls. Don't need to import other libraies :)
-# supported argumnets encoding and user_agent
-target = waybackpy.Url("google.com", "any-user_agent")
-oldest_url = target.oldest()
-webpage = target.get(oldest_url) # We are getting the source of oldest archive of google.com.
-print(webpage)
+
+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)
 ```
-> This should print the source code for oldest archive of google.com. If no URL is passed in get() then it should retrive the source code of google.com and not any archive.
+<sub>Try this out in your browser @ <https://repl.it/repls/PinkHoneydewNonagon#main.py></sub>
+
 
 #### Count total archives for an URL using total_archives()
 ```python
-from waybackpy import Url
-# retriving the content of a webpage from any url including but not limited to the archived urls.
-count = Url("https://en.wikipedia.org/wiki/Python (programming language)", "User-Agent").total_archives()
-print(count)
-```
-> This should print an integer (int), which is the number of total archives on archive.org
+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/repls/DigitalUnconsciousNumbers#main.py></sub>
 
 ## Tests
 * [Here](https://github.com/akamhy/waybackpy/tree/master/tests)

index.rst

@@ -3,7 +3,268 @@ waybackpy
 
 |Build Status| |Downloads| |Release| |Codacy Badge| |License: MIT|
 |Maintainability| |CodeFactor| |made-with-python| |pypi| |PyPI - Python
-Version| |Maintenance| |codecov| |image1| |contributions welcome|
+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>`__
+-  `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>`__
+
+-  `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
+
+Usage
+-----
+
+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/repls/CompassionateRemoteOrigin#main.py\ 
+
+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/repls/MixedSuperDimensions#main.py\ 
+
+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/repls/OblongMiniInteger#main.py\ 
+
+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/repls/SparseDeadlySearchservice#main.py\ 
+
+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/repls/PinkHoneydewNonagon#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/repls/DigitalUnconsciousNumbers#main.py\ 
+
+Tests
+-----
+
+-  `Here <https://github.com/akamhy/waybackpy/tree/master/tests>`__
+
+Dependency
+----------
+
+-  None, just python standard libraries (re, json, urllib 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
@@ -27,199 +288,7 @@ Version| |Maintenance| |codecov| |image1| |contributions welcome|
    :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
-.. |image1| image:: https://img.shields.io/github/repo-size/akamhy/waybackpy.svg?label=Repo%20size&style=flat-square
+.. |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| |Wayback Machine|
-
-Waybackpy is a Python library that interfaces with the `Internet
-Archive`_\ ’s `Wayback Machine`_ API. Archive pages and retrieve
-archived pages easily.
-
-.. _Internet Archive: https://en.wikipedia.org/wiki/Internet_Archive
-.. _Wayback Machine: https://en.wikipedia.org/wiki/Wayback_Machine
-
 .. |Internet Archive| image:: https://upload.wikimedia.org/wikipedia/commons/thumb/8/84/Internet_Archive_logo_and_wordmark.svg/84px-Internet_Archive_logo_and_wordmark.svg.png
 .. |Wayback Machine| image:: https://upload.wikimedia.org/wikipedia/commons/thumb/0/01/Wayback_Machine_logo_2010.svg/284px-Wayback_Machine_logo_2010.svg.png
-
-Table of contents
-=================
-
-.. raw:: html
-
-   <!--ts-->
-
--  `Installation`_
-
--  `Usage`_
-
-   -  `Saving an url using save()`_
-   -  `Receiving the oldest archive for an URL Using oldest()`_
-   -  `Receiving the recent most/newest archive for an URL using
-      newest()`_
-   -  `Receiving archive close to a specified year, month, day, hour,
-      and minute using near()`_
-   -  `Get the content of webpage using get()`_
-   -  `Count total archives for an URL using total_archives()`_
-
--  `Tests`_
-
--  `Dependency`_
-
--  `License`_
-
-.. raw:: html
-
-   <!--te-->
-
-.. _Installation: #installation
-.. _Usage: #usage
-.. _Saving an url using save(): #capturing-aka-saving-an-url-using-save
-.. _Receiving the oldest archive for an URL Using oldest(): #receiving-the-oldest-archive-for-an-url-using-oldest
-.. _Receiving the recent most/newest archive for an URL using newest(): #receiving-the-newest-archive-for-an-url-using-newest
-.. _Receiving archive close to a specified year, month, day, hour, and minute using near(): #receiving-archive-close-to-a-specified-year-month-day-hour-and-minute-using-near
-.. _Get the content of webpage using get(): #get-the-content-of-webpage-using-get
-.. _Count total archives for an URL using total_archives(): #count-total-archives-for-an-url-using-total_archives
-.. _Tests: #tests
-.. _Dependency: #dependency
-.. _License: #license
-
-Installation
-------------
-
-Using `pip`_:
-
-.. code:: bash
-
-   pip install waybackpy
-
-Usage
------
-
-Capturing aka Saving an url Using save()
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-.. code:: python
-
-   import waybackpy
-   # Capturing a new archive on Wayback machine.
-   target_url = waybackpy.Url("https://github.com/akamhy/waybackpy", user_agnet="My-cool-user-agent")
-   archived_url = target_url.save()
-   print(archived_url)
-
-This should print an URL similar to the following archived URL:
-
-   https://web.archive.org/web/20200504141153/https://github.com/akamhy/waybackpy
-
-.. _pip: https://en.wikipedia.org/wiki/Pip_(package_manager)
-
-Receiving the oldest archive for an URL Using oldest()
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-.. code:: python
-
-   import waybackpy
-   # retrieving the oldest archive on Wayback machine.
-   target_url = waybackpy.Url("https://www.google.com/", "My-cool-user-agent")
-   oldest_archive = target_url.oldest()
-   print(oldest_archive)
-
-This should print the oldest available archive for https://google.com.
-
-   http://web.archive.org/web/19981111184551/http://google.com:80/
-
-Receiving the newest archive for an URL using newest()
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-.. code:: python
-
-   import waybackpy
-   # retrieving the newest/latest archive on Wayback machine.
-   target_url = waybackpy.Url(url="https://www.google.com/", user_agnet="My-cool-user-agent")
-   newest_archive = target_url.newest()
-   print(newest_archive)
-
-This print the newest available archive for
-https://www.microsoft.com/en-us, something just like this:
-
-   http://web.archive.org/web/20200429033402/https://www.microsoft.com/en-us/
-
-Receiving archive close to a specified year, month, day, hour, and minute using near()
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-.. code:: python
-
-   import waybackpy
-   # retriving the the closest archive from a specified year.
-   # supported argumnets are year,month,day,hour and minute
-   target_url = waybackpy.Url(https://www.facebook.com/", "Any-User-Agent")
-   archive_near_year = target_url.near(year=2010)
-   print(archive_near_year)
-
-returns :
-http://web.archive.org/web/20100504071154/http://www.facebook.com/
-
-   Please note that if you only specify the year, the current month and
-   day are default arguments for month and day respectively. Just
-   putting the year parameter would not return the archive closer to
-   January but the current month you are using the package. You need to
-   specify the month “1” for January , 2 for february and so on.
-
-..
-
-   Do not pad (don’t use zeros in the month, year, day, minute, and hour
-   arguments). e.g. For January, set month = 1 and not month = 01.
-
-Get the content of webpage using get()
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-.. code:: python
-
-   import waybackpy
-   # retriving the webpage from any url including the archived urls. Don't need to import other libraies :)
-   # supported argumnets encoding and user_agent
-   target = waybackpy.Url("google.com", "any-user_agent")
-   oldest_url = target.oldest()
-   webpage = target.get(oldest_url) # We are getting the source of oldest archive of google.com.
-   print(webpage)
-
-..
-
-   This should print the source code for oldest archive of google.com.
-   If no URL is passed in get() then it should retrive the source code
-   of google.com and not any archive.
-
-Count total archives for an URL using total_archives()
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-.. code:: python
-
-   from waybackpy import Url
-   # retriving the content of a webpage from any url including but not limited to the archived urls.
-   count = Url("https://en.wikipedia.org/wiki/Python (programming language)", "User-Agent").total_archives()
-   print(count)
-
-..
-
-   This should print an integer (int), which is the number of total
-   archives on archive.org
-
-Tests
------
-
--  `Here`_
-
-Dependency
-----------
-
--  None, just python standard libraries (re, json, urllib and datetime).
-   Both python 2 and 3 are supported :)
-
-License
--------
-
-`MIT License`_
-
-.. _Here: https://github.com/akamhy/waybackpy/tree/master/tests
-.. _MIT License: https://github.com/akamhy/waybackpy/blob/master/LICENSE

setup.py

@@ -19,7 +19,7 @@ setup(
     author = about['__author__'],
     author_email = about['__author_email__'],
     url = about['__url__'],
-    download_url = 'https://github.com/akamhy/waybackpy/archive/v1.6.tar.gz',
+    download_url = 'https://github.com/akamhy/waybackpy/archive/2.0.2.tar.gz',
     keywords = ['wayback', 'archive', 'archive website', 'wayback machine', 'Internet Archive'],
     install_requires=[],
     python_requires= ">=2.7",

tests/test_1.py

@@ -4,10 +4,12 @@ sys.path.append("..")
 import waybackpy
 import pytest
 import random
+import time
 
 user_agent = "Mozilla/5.0 (Windows NT 6.2; rv:20.0) Gecko/20121202 Firefox/20.0"
 
 def test_clean_url():
+    time.sleep(10)
     test_url = " https://en.wikipedia.org/wiki/Network security "
     answer = "https://en.wikipedia.org/wiki/Network_security"
     target = waybackpy.Url(test_url, user_agent)
@@ -15,12 +17,14 @@ def test_clean_url():
     assert answer == test_result
 
 def test_url_check():
+    time.sleep(10)
     broken_url = "http://wwwgooglecom/"
     with pytest.raises(Exception) as e_info:
         waybackpy.Url(broken_url, user_agent)
 
 def test_save():
     # Test for urls that exist and can be archived.
+    time.sleep(10)
 
     url_list = [
         "en.wikipedia.org",
@@ -36,63 +40,77 @@ def test_save():
     archived_url1 = target.save()
     assert url1 in archived_url1
 
-    # Test for urls that are incorrect.
-    with pytest.raises(Exception) as e_info:
-        url2 = "ha ha ha ha"
-        waybackpy.Url(url2, user_agent)
+    if sys.version_info > (3, 6):
 
-    # Test for urls not allowed to archive by robot.txt.
-    with pytest.raises(Exception) as e_info:
-        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()
+        # Test for urls that are incorrect.
+        with pytest.raises(Exception) as e_info:
+            url2 = "ha ha ha ha"
+            waybackpy.Url(url2, user_agent)
+        time.sleep(5)
+        # Test for urls not allowed to archive by robot.txt.
+        with pytest.raises(Exception) as e_info:
+            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()
 
-    # Non existent urls, test
-    with pytest.raises(Exception) as e_info:
-        url4 = "https://githfgdhshajagjstgeths537agajaajgsagudadhuss8762346887adsiugujsdgahub.us"
-        target = waybackpy.Url(url3, "Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/533.20.25 (KHTML, like Gecko) Version/5.0.4 Safari/533.20.27")
-        target.save()
+        time.sleep(5)
+        # Non existent urls, test
+        with pytest.raises(Exception) as e_info:
+            url4 = "https://githfgdhshajagjstgeths537agajaajgsagudadhuss8762346887adsiugujsdgahub.us"
+            target = waybackpy.Url(url3, "Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/533.20.25 (KHTML, like Gecko) Version/5.0.4 Safari/533.20.27")
+            target.save()
+
+    else:
+        pass
 
 def test_near():
+    time.sleep(10)
     url = "google.com"
     target = waybackpy.Url(url, "Mozilla/5.0 (Windows; U; Windows NT 6.0; de-DE) AppleWebKit/533.20.25 (KHTML, like Gecko) Version/5.0.3 Safari/533.19.4")
     archive_near_year = target.near(year=2010)
     assert "2010" in archive_near_year
 
-    archive_near_month_year = target.near( year=2015, month=2)
-    assert ("201502" in archive_near_month_year) or ("201501" in archive_near_month_year) or ("201503" in archive_near_month_year)
-
-    archive_near_day_month_year = target.near(year=2006, month=11, day=15)
-    assert ("20061114" in archive_near_day_month_year) or ("20061115" in archive_near_day_month_year) or ("2006116" in archive_near_day_month_year)
-
-    target = waybackpy.Url("www.python.org", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.135 Safari/537.36 Edge/12.246")
-    archive_near_hour_day_month_year = target.near(year=2008, month=5, day=9, hour=15)
-    assert ("2008050915" in archive_near_hour_day_month_year) or ("2008050914" in archive_near_hour_day_month_year) or ("2008050913" in archive_near_hour_day_month_year)
-
-    with pytest.raises(Exception) as e_info:
-        NeverArchivedUrl = "https://ee_3n.wrihkeipef4edia.org/rwti5r_ki/Nertr6w_rork_rse7c_urity"
-        target = waybackpy.Url(NeverArchivedUrl, user_agent)
-        target.near(year=2010)
+    if sys.version_info > (3, 6):
+        time.sleep(5)
+        archive_near_month_year = target.near( year=2015, month=2)
+        assert ("201502" in archive_near_month_year) or ("201501" in archive_near_month_year) or ("201503" in archive_near_month_year)
+    
+        target = waybackpy.Url("www.python.org", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.135 Safari/537.36 Edge/12.246")
+        archive_near_hour_day_month_year = target.near(year=2008, month=5, day=9, hour=15)
+        assert ("2008050915" in archive_near_hour_day_month_year) or ("2008050914" in archive_near_hour_day_month_year) or ("2008050913" in archive_near_hour_day_month_year)
+    
+        with pytest.raises(Exception) as e_info:
+            NeverArchivedUrl = "https://ee_3n.wrihkeipef4edia.org/rwti5r_ki/Nertr6w_rork_rse7c_urity"
+            target = waybackpy.Url(NeverArchivedUrl, user_agent)
+            target.near(year=2010)
+    else:
+        pass
 
 def test_oldest():
+    time.sleep(10)
     url = "github.com/akamhy/waybackpy"
     target = waybackpy.Url(url, user_agent)
     assert "20200504141153" in target.oldest()
 
 def test_newest():
+    time.sleep(10)
     url = "github.com/akamhy/waybackpy"
     target = waybackpy.Url(url, user_agent)
     assert url in target.newest()
 
 def test_get():
+    time.sleep(10)
     target = waybackpy.Url("google.com", user_agent)
     assert "Welcome to Google" in target.get(target.oldest())
 
 def test_total_archives():
-
-    target = waybackpy.Url(" https://google.com ", user_agent)
-    assert target.total_archives() > 500000
-
+    time.sleep(10)
+    if sys.version_info > (3, 6):
+        target = waybackpy.Url(" https://google.com ", user_agent)
+        assert target.total_archives() > 500000
+    else:
+        pass
+    time.sleep(5)
     target = waybackpy.Url(" https://gaha.e4i3n.m5iai3kip6ied.cima/gahh2718gs/ahkst63t7gad8 ", user_agent)
     assert target.total_archives() == 0
 

waybackpy/__version__.py

@@ -3,7 +3,7 @@
 __title__ = "waybackpy"
 __description__ = "A Python library that interfaces with the Internet Archive's Wayback Machine API. Archive pages and retrieve archived pages easily."
 __url__ = "https://akamhy.github.io/waybackpy/"
-__version__ = "2.0.0"
+__version__ = "2.1.0"
 __author__ = "akamhy"
 __author_email__ = "akash3pro@gmail.com"
 __license__ = "MIT"

waybackpy/wrapper.py

@@ -8,9 +8,9 @@ from waybackpy.exceptions import WaybackError
 
 if sys.version_info >= (3, 0):  # If the python ver >= 3
     from urllib.request import Request, urlopen
-    from urllib.error import HTTPError, URLError
+    from urllib.error import URLError
 else: # For python2.x
-    from urllib2 import Request, urlopen, HTTPError, URLError
+    from urllib2 import Request, urlopen, URLError
 
 default_UA = "waybackpy python package - https://github.com/akamhy/waybackpy"
 
@@ -59,13 +59,6 @@ class Url():
           str(kwargs["minute"]).zfill(2)
           )
 
-    def handle_HTTPError(self, e):
-        """Handle some common HTTPErrors."""
-        if e.code == 404:
-            raise HTTPError(e)
-        if e.code >= 400:
-            raise WaybackError(e)
-
     def save(self):
         """Create a new archives for an URL on the Wayback Machine."""
         request_url = ("https://web.archive.org/save/" + self.clean_url())
@@ -75,36 +68,46 @@ class Url():
             response = urlopen(req, timeout=30) #nosec
         except Exception:
             try:
-                response = urlopen(req, timeout=300) #nosec
+                response = urlopen(req) #nosec
             except Exception as e:
                 raise WaybackError(e)
         header = response.headers
-        try:
-            arch = re.search(r"rel=\"memento.*?web\.archive\.org(/web/[0-9]{14}/.*?)>", str(header)).group(1)
-        except KeyError as e:
-            raise WaybackError(e)
-        return "https://web.archive.org" + arch
+
+        def archive_url_parser(header):
+            arch = re.search(r"X-Cache-Key:\shttps(.*)[A-Z]{2}", str(header))
+            if arch:
+                return arch.group(1)
+            raise WaybackError(
+                "No archive url found in the API response. Visit https://github.com/akamhy/waybackpy for latest version of waybackpy.\nHeader:\n%s" % str(header)
+            )
+
+        return "https://" + archive_url_parser(header)
 
     def get(self, url=None, user_agent=None, encoding=None):
         """Returns the source code of the supplied URL. Auto detects the encoding if not supplied."""
+
         if not url:
             url = self.clean_url()
         if not user_agent:
             user_agent = self.user_agent
+
         hdr = { 'User-Agent' : '%s' % user_agent }
         req = Request(url, headers=hdr) #nosec
+
         try:
             resp=urlopen(req) #nosec
-        except URLError:
+        except Exception:
             try:
                 resp=urlopen(req) #nosec
-            except URLError as e:
-                raise HTTPError(e)
+            except Exception as e:
+                raise WaybackError(e)
+
         if not encoding:
             try:
                 encoding= resp.headers['content-type'].split('charset=')[-1]
             except AttributeError:
                 encoding = "UTF-8"
+
         return resp.read().decode(encoding.replace("text/html", "UTF-8", 1))
 
     def near(self, **kwargs):
@@ -121,10 +124,15 @@ class Url():
         request_url = "https://archive.org/wayback/available?url=%s&timestamp=%s" % (self.clean_url(), str(timestamp))
         hdr = { 'User-Agent' : '%s' % self.user_agent }
         req = Request(request_url, headers=hdr) # nosec
+
         try:
             response = urlopen(req) #nosec
-        except Exception as e:
-            self.handle_HTTPError(e)
+        except Exception:
+            try:
+                 response = urlopen(req) #nosec
+            except Exception as e:
+                WaybackError(e)
+
         data = json.loads(response.read().decode("UTF-8"))
         if not data["archived_snapshots"]:
             raise WaybackError("'%s' is not yet archived." % url)
@@ -146,8 +154,13 @@ class Url():
         hdr = { 'User-Agent' : '%s' % self.user_agent }
         request_url = "https://web.archive.org/cdx/search/cdx?url=%s&output=json&fl=statuscode" % self.clean_url()
         req = Request(request_url, headers=hdr) # nosec
+
         try:
             response = urlopen(req) #nosec
-        except Exception as e:
-            self.handle_HTTPError(e)
+        except Exception:
+            try:
+                response = urlopen(req) #nosec
+            except Exception as e:
+                WaybackError(e)
+
         return str(response.read()).count(",") # Most efficient method to count number of archives (yet)