Extract information from GitHub release notes

parse_gh_release.py

# SPDX-FileCopyrightText: 2023 geisserml <geisserml@gmail.com>
# SPDX-License-Identifier: CC-BY-4.0 OR Apache-2.0 OR BSD-3-Clause

# Unlike repository files, there is no "raw view" for GH releases, but we can extract the plain markdown content using GH web API
# See also https://stackoverflow.com/q/76995969/15547292

# The following code snippet shows how to get a release title from pdfium-binaries to extract the full version

import re
import json
import urllib.request as url_request

ReleaseRepo    = "https://github.com/bblanchon/pdfium-binaries"
ReleaseURL     = ReleaseRepo + "/releases/download/chromium%2F"
ReleaseInfoURL = ReleaseURL.replace("github.com/", "api.github.com/repos/").replace("download/", "tags/")

def get_full_version(v_short):
    info = url_request.urlopen(ReleaseInfoURL+v_short).read().decode("utf-8")
    info = json.loads(info)
    title = info["name"]
    # note: description would be info["body"]
    match = re.match(fr"PDFium (\d+.\d+.{v_short}.\d+)", title)
    return match.group(1)