Created
September 15, 2022 12:54
-
-
Save sgraaf/9df4a2b2aa3fb7c3ee67626f07d12359 to your computer and use it in GitHub Desktop.
Scrape recent Chrome and Firefox version numbers
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"cells": [ | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"# Get Firefox versions (Major)" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"## Imports" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"import requests\n", | |
"from lxml import html" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"## Preamble" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"url = \"https://www.mozilla.org/en-US/firefox/releases/\"" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"## Main" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"with open(\"firefox_versions.txt\", \"r\", encoding=\"utf-8\") as fh:\n", | |
" versions = fh.read().splitlines()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"versions = []" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"r = requests.get(url)\n", | |
"tree = html.fromstring(r.content)\n", | |
"\n", | |
"new_versions = [version for version in tree.xpath('//ol[@class=\"c-release-list\"]/li/strong/a/text()') if version not in versions]\n", | |
"new_versions.remove(\"14.0.1\")\n", | |
"new_versions = sorted(new_versions, key=float)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"new_versions" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"if new_versions:\n", | |
" with open(\"firefox_versions.txt\", \"a\", encoding=\"utf-8\") as fh:\n", | |
" for version in sorted(new_versions):\n", | |
" fh.write(version + \"\\n\")" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [] | |
} | |
], | |
"metadata": { | |
"interpreter": { | |
"hash": "304af0c388573785794e9f0a925230dd9ce2d854780d50013a3eb97f55f45953" | |
}, | |
"kernelspec": { | |
"display_name": "Python 3.9.9 64-bit ('.venv': venv)", | |
"language": "python", | |
"name": "python3" | |
}, | |
"language_info": { | |
"codemirror_mode": { | |
"name": "ipython", | |
"version": 3 | |
}, | |
"file_extension": ".py", | |
"mimetype": "text/x-python", | |
"name": "python", | |
"nbconvert_exporter": "python", | |
"pygments_lexer": "ipython3", | |
"version": "3.9.9" | |
}, | |
"orig_nbformat": 4 | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 2 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment