Benjamin_Loison/waybackpy
1
0
Fork 0
Code Issues 1 Pull Requests Packages Projects Releases Wiki Activity

More pythonic code snippets in README (#36)

Browse Source
This commit is contained in:
Akash Mahanty 2020-10-17 11:49:27 +05:30 committed by GitHub
parent 0a2f97c034
commit d8ec0f5025
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 43 additions and 62 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

103
README.md
View File

@ -17,7 +17,7 @@
![Wayback Machine](https://raw.githubusercontent.com/akamhy/waybackpy/master/assets/waybackpy-colored%20284.png) ![Wayback Machine](https://raw.githubusercontent.com/akamhy/waybackpy/master/assets/waybackpy-colored%20284.png)
Waybackpy is a Python library that interfaces with [Internet Archive](https://en.wikipedia.org/wiki/Internet_Archive)'s [Wayback Machine](https://en.wikipedia.org/wiki/Wayback_Machine) API. Archive webpages and retrieve archived webpages easily. Waybackpy is a Python package that interfaces with [Internet Archive](https://en.wikipedia.org/wiki/Internet_Archive)'s [Wayback Machine](https://en.wikipedia.org/wiki/Wayback_Machine) API. Archive webpages and retrieve archived webpages easily.
Table of contents Table of contents
================= =================
@ -81,18 +81,16 @@ pip install git+https://github.com/akamhy/waybackpy.git
```python ```python
import waybackpy import waybackpy
new_archive_url = waybackpy.Url( url = "https://en.wikipedia.org/wiki/Multivariable_calculus"
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" user_agent = "Mozilla/5.0 (Windows NT 5.1; rv:40.0) Gecko/20100101 Firefox/40.0"
).save() waybackpy_url_obj = waybackpy.Url(url, user_agent)
archive = waybackpy_url_obj.save()
print(new_archive_url) print(archive)
``` ```
```bash ```bash
https://web.archive.org/web/20200504141153/https://github.com/akamhy/waybackpy https://web.archive.org/web/20201016171808/https://en.wikipedia.org/wiki/Multivariable_calculus
``` ```
<sub>Try this out in your browser @ <https://repl.it/@akamhy/WaybackPySaveExample></sub> <sub>Try this out in your browser @ <https://repl.it/@akamhy/WaybackPySaveExample></sub>
@ -102,12 +100,11 @@ https://web.archive.org/web/20200504141153/https://github.com/akamhy/waybackpy
```python ```python
import waybackpy import waybackpy
archive_url = waybackpy.Url( url = "https://www.google.com/"
user_agent = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.8; rv:40.0) Gecko/20100101 Firefox/40.0"
"https://www.google.com/",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.8; rv:40.0) Gecko/20100101 Firefox/40.0"
).archive_url
waybackpy_url_obj = waybackpy.Url(url, user_agent)
archive_url = waybackpy_url_obj.archive_url
print(archive_url) print(archive_url)
``` ```
@ -122,12 +119,11 @@ https://web.archive.org/web/20201016153320/https://www.google.com/
```python ```python
import waybackpy import waybackpy
oldest_archive_url = waybackpy.Url( url = "https://www.google.com/"
user_agent = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.8; rv:40.0) Gecko/20100101 Firefox/40.0"
"https://www.google.com/",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.8; rv:40.0) Gecko/20100101 Firefox/40.0"
).oldest()
waybackpy_url_obj = waybackpy.Url(url, user_agent)
oldest_archive_url = waybackpy_url_obj.oldest()
print(oldest_archive_url) print(oldest_archive_url)
``` ```
@ -142,18 +138,16 @@ http://web.archive.org/web/19981111184551/http://google.com:80/
```python ```python
import waybackpy import waybackpy
newest_archive_url = waybackpy.Url( url = "https://www.facebook.com/"
user_agent = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.10; rv:39.0) Gecko/20100101 Firefox/39.0"
"https://www.facebook.com/",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.10; rv:39.0) Gecko/20100101 Firefox/39.0"
).newest()
waybackpy_url_obj = waybackpy.Url(url, user_agent)
newest_archive_url = waybackpy_url_obj.newest()
print(newest_archive_url) print(newest_archive_url)
``` ```
```bash ```bash
https://web.archive.org/web/20200714013225/https://www.facebook.com/ https://web.archive.org/web/20201016150543/https://www.facebook.com/
``` ```
<sub>Try this out in your browser @ <https://repl.it/@akamhy/WaybackPyNewestExample></sub> <sub>Try this out in your browser @ <https://repl.it/@akamhy/WaybackPyNewestExample></sub>
@ -163,17 +157,16 @@ https://web.archive.org/web/20200714013225/https://www.facebook.com/
```python ```python
import waybackpy import waybackpy
json_dict = waybackpy.Url( url = "https://www.facebook.com/"
user_agent = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.10; rv:39.0) Gecko/20100101 Firefox/39.0"
"https://www.google.com/",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.8; rv:40.0) Gecko/20100101 Firefox/40.0"
).JSON
waybackpy_url_obj = waybackpy.Url(url, user_agent)
json_dict = waybackpy_url_obj.JSON
print(json_dict) print(json_dict)
``` ```
```javascript ```javascript
{'url': 'https://www.google.com/', 'archived_snapshots': {'closest': {'available': True, 'url': 'http://web.archive.org/web/20201016153320/https://www.google.com/', 'timestamp': '20201016153320', 'status': '200'}}} {'url': 'https://www.facebook.com/', 'archived_snapshots': {'closest': {'available': True, 'url': 'http://web.archive.org/web/20201016150543/https://www.facebook.com/', 'timestamp': '20201016150543', 'status': '200'}}}
``` ```
<sub>Try this out in your browser @ <https://repl.it/@akamhy/WaybackPyJSON></sub> <sub>Try this out in your browser @ <https://repl.it/@akamhy/WaybackPyJSON></sub>
@ -184,56 +177,50 @@ print(json_dict)
from waybackpy import Url from waybackpy import Url
user_agent = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.10; rv:38.0) Gecko/20100101 Firefox/38.0" 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/" url = "https://github.com/"
waybackpy_url_obj = Url(url, user_agent)
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. # Do not pad (don't use zeros in the month, year, day, minute, and hour arguments). e.g. For January, set month = 1 and not month = 01.
``` ```
```python ```python
github_archive_near_2010 = github_wayback_obj.near(year=2010) github_archive_near_2010 = waybackpy_url_obj.near(year=2010)
print(github_archive_near_2010) print(github_archive_near_2010)
``` ```
```bash ```bash
https://web.archive.org/web/20100719134402/http://github.com/ https://web.archive.org/web/20101018053604/http://github.com:80/
``` ```
```python ```python
github_archive_near_2011_may = github_wayback_obj.near(year=2011, month=5) github_archive_near_2011_may = waybackpy_url_obj.near(year=2011, month=5)
print(github_archive_near_2011_may) print(github_archive_near_2011_may)
``` ```
```bash ```bash
https://web.archive.org/web/20110519185447/https://github.com/ https://web.archive.org/web/20110518233639/https://github.com/
``` ```
```python ```python
github_archive_near_2015_january_26 = github_wayback_obj.near( github_archive_near_2015_january_26 = waybackpy_url_obj.near(year=2015, month=1, day=26)
year=2015, month=1, day=26
)
print(github_archive_near_2015_january_26) print(github_archive_near_2015_january_26)
``` ```
```bash ```bash
https://web.archive.org/web/20150127031159/https://github.com https://web.archive.org/web/20150125102636/https://github.com/
``` ```
```python ```python
github_archive_near_2018_4_july_9_2_am = github_wayback_obj.near( github_archive_near_2018_4_july_9_2_am = waybackpy_url_obj.near(year=2018, month=7, day=4, hour=9, minute=2)
year=2018, month=7, day=4, hour = 9, minute = 2
)
print(github_archive_near_2018_4_july_9_2_am) print(github_archive_near_2018_4_july_9_2_am)
``` ```
```bash ```bash
https://web.archive.org/web/20180704090245/https://github.com/ https://web.archive.org/web/20180704090245/https://github.com/
``` ```
<sub>The library doesn't supports seconds yet. You are encourged to create a PR ;)</sub> <sub>The package doesn't support second argument yet. You are encourged to create a PR ;)</sub>
<sub>Try this out in your browser @ <https://repl.it/@akamhy/WaybackPyNearExample></sub> <sub>Try this out in your browser @ <https://repl.it/@akamhy/WaybackPyNearExample></sub>
@ -256,16 +243,12 @@ 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. # 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. # waybackpy_url_object.save() type is string.
google_newest_archive_source = waybackpy_url_object.get( google_newest_archive_source = waybackpy_url_object.get(waybackpy_url_object.save())
waybackpy_url_object.save()
)
print(google_newest_archive_source) print(google_newest_archive_source)
# waybackpy_url_object.oldest() type is str, it's oldest archive of google.com # waybackpy_url_object.oldest() type is str, it's oldest archive of google.com
google_oldest_archive_source = waybackpy_url_object.get( google_oldest_archive_source = waybackpy_url_object.get(waybackpy_url_object.oldest())
waybackpy_url_object.oldest()
)
print(google_oldest_archive_source) print(google_oldest_archive_source)
``` ```
@ -277,19 +260,17 @@ print(google_oldest_archive_source)
import waybackpy import waybackpy
URL = "https://en.wikipedia.org/wiki/Python (programming language)" 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" 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( waybackpy_url_object = waybackpy.Url(url=URL, user_agent=UA)
url=URL,
user_agent=UA archive_count = waybackpy_url_object.total_archives()
).total_archives()
print(archive_count) # total_archives() returns an int print(archive_count) # total_archives() returns an int
``` ```
```bash ```bash
2440 2516
``` ```
<sub>Try this out in your browser @ <https://repl.it/@akamhy/WaybackPyTotalArchivesExample></sub> <sub>Try this out in your browser @ <https://repl.it/@akamhy/WaybackPyTotalArchivesExample></sub>
@ -305,8 +286,8 @@ import waybackpy
URL = "akamhy.github.io" URL = "akamhy.github.io"
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" 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"
known_urls = waybackpy.Url(url=URL, user_agent=UA).known_urls(alive=True, subdomain=False) # alive and subdomain are optional. waybackpy_url_object = waybackpy.Url(url=URL, user_agent=UA)
known_urls = waybackpy_url_object.known_urls(alive=True, subdomain=False) # alive and subdomain are optional.
print(known_urls) # known_urls() returns list of URLs print(known_urls) # known_urls() returns list of URLs
``` ```