win10-urls.py

#!/usr/bin/python3

import json
import uuid
import lxml.html
import requests


def main():
    """
    Displays URLs for Windows 10 ISO download from Microsoft.
    """
    sessionId = uuid.uuid4()

    r = requests.get(
            'https://www.microsoft.com/en-us/software-download/windows10ISO')
    root = lxml.html.fromstring(r.text)
    downloadPageId = root.xpath('//div[@id="SoftwareDownload_DownloadLinks"]/'
                                '@data-defaultpageid')[0]
    languagePageId = root.xpath('//div[@id="SoftwareDownload_'
                                'LanguageSelectionByProductEdition"]/'
                                '@data-defaultpageid')[0]
    # Get skuId of English
    r = requests.post('https://www.microsoft.com/en-us/api/'
                      'controls/contentinclude/html?'
                      f'pageId={languagePageId}'
                      '&host=www.microsoft.com&'
                      'segments=software-download,windows10ISO'
                      '&query=&action=getskuinformationbyproductedition'
                      f'&sessionId={sessionId}'
                      '&productEditionId=1626&sdVersion=2')
    root = lxml.html.fromstring(r.text)
    for option in root.xpath('//option'):
        if option.text == 'English':
            skuId = json.loads(option.get('value'))['id']
            break

    r = requests.post('https://www.microsoft.com/en-us/api/'
                      'controls/contentinclude/html?'
                      f'pageId={downloadPageId}'
                      '&host=www.microsoft.com&'
                      'segments=software-download,windows10ISO'
                      '&query=&action=GetProductDownloadLinksBySku'
                      f'&sessionId={sessionId}'
                      f'&skuId={skuId}&language=English&sdVersion=2')
    root = lxml.html.fromstring(r.text)
    for url in root.xpath('//div[@class]/a/@href'):
        print(url)


if __name__ == '__main__':
    main()