Download latest GNU GCC compiler from ARM's website (for Cortex-M and Cortex-R processors).

get-gcc-arm-none-eabi.py

#!/usr/bin/env python3
"""Download latest GNU Toolchain from ARM's website

Author: Alex Hogen ([email protected])

MIT License
Copyright (c) 2019 Alexander Hogen

Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
"""
import sys
import requests
import wget
import time
import regex as re
import hashlib
from bs4 import BeautifulSoup

LINUX_64 = {
    "title": 'Linux 64-bit Tarball',
    "fname_regex": r'gcc-arm-none-eabi-.+-linux\.tar\.bz2'}

WIN_7p = {
    "title": 'Windows 32-bit Installer Signed for Windows 7 and later)',
    "fname_regex": r'gcc-arm-none-eabi-.+-win32-sha2\.exe'}


def get_fname_and_md5_hash(soup: BeautifulSoup, platform_config: dict):

    fname = ''
    md5 = ''

    for dl in soup.find_all("dl"):
        # both <dt> and <dd> children of <dl>
        for i in dl:
            if re.match(platform_config['fname_regex'], i.string) is not None:
                fname = i.string

            md5_match = re.match(r'MD5:\s([0-9a-f]{32})', i.string)
            if (fname != '') and (md5_match is not None):
                md5 = md5_match[1]
                # Got 'em
                return (fname, md5)

        if fname != '':
            if re.match(re.escape(platform_config['title']), dl.dd.text) is None:
                print("<dd> doesn't look right. skipping this <dt> match")
                fname = ''
            else:
                break

    raise RuntimeWarning("Couldn't find filename and MD5 hash for platform")

def get_file_download_url(soup: BeautifulSoup, platform_config: dict, fname: str):
    url = ''
    regex = re.compile(r'(\/-\/media\/Files\/downloads\/.*' + re.escape(fname) + r').*')

    dl_buttons = soup.find_all(class_='c-button')

    for b in dl_buttons:
        try:
            match = re.match(regex, b['data-href'])
            if match is not None:
                url = match[1]
                break
        except KeyError:
            pass

    url = "https://developer.arm.com" + url
    return (url)

def verify_md5(fname: str, expected_md5: str):
    hash_md5 = hashlib.md5()
    with open(fname, 'rb') as f:
        for chunk in iter(lambda: f.read(4096), b""):
            hash_md5.update(chunk)

    print("\nMD5: ", end='')
    if expected_md5 != hash_md5.hexdigest():
        print("FAIL!!")
        print("   expected: ", expected_md5)
        print("   actual:   ", hash_md5.hexdigest())
    else:
        print("okay")
    return hash_md5.hexdigest()

if __name__ == "__main__":

    if sys.version_info < (3, 5, 0):
        sys.stderr.write("You need python 3.5 or later to run this script\n")
        sys.exit(1)

    url = 'https://developer.arm.com/tools-and-software/open-source-software/developer-tools/gnu-toolchain/gnu-rm/downloads'

    platform = LINUX_64
    response = requests.get(url)

    soup = BeautifulSoup(response.text, "html.parser")

    file = {
        "name": '',
        "md5": '',
        "url": "",
        "platform_conf": "LINUX_64"
    }

    file['name'], file['md5'] = get_fname_and_md5_hash(soup, platform)
    file['url'] = get_file_download_url(soup, platform, file['name'])

    print(file)

    fname_downloaded = wget.download(file['url'])
    print("Downloaded:", fname_downloaded)
    verify_md5(fname_downloaded, file['md5'])

todo.md

• Parameterize & command line ops
• After scraping, see if file with matching MD5 already exists in output dir
• Allow for downloading -major releases, not just -update
• Clean up (this is currently just a hacked-together script)