Archive a website to Drive as Markdown

from google.oauth2.credentials import Credentials
from googleapiclient.discovery import build
from bs4 import BeautifulSoup
from googleapiclient.http import MediaInMemoryUpload
from clickruntime import on_trigger, credentials, http

SITEMAP, FOLDER = "https://example.com/sitemap.xml", "site-archive-folder-id"

def to_markdown(html):
    soup = BeautifulSoup(html, "lxml")
    lines = []
    for el in soup.select("h1, h2, h3, p, li"):
        text = el.get_text(" ", strip=True)
        prefix = {"h1": "# ", "h2": "## ", "h3": "### ", "li": "- "}.get(el.name, "")
        if text:
            lines.append(prefix + text)
    return "\n\n".join(lines)

@on_trigger
def run(event):
    drive = build("drive", "v3", credentials=Credentials(credentials.connection("google", "work")), cache_discovery=False)
    urls = [loc.text for loc in BeautifulSoup(http.get(SITEMAP).text, "xml").find_all("loc")]
    existing = {f["name"]: f["id"] for f in drive.files().list(q=f"'{FOLDER}' in parents and trashed = false",
                                                               fields="files(id,name)", pageSize=1000).execute()["files"]}
    for url in urls:
        name = (url.split("://", 1)[1].strip("/").replace("/", "_") or "home") + ".md"
        media = MediaInMemoryUpload(to_markdown(http.get(url).text).encode(), "text/markdown")
        if name in existing:
            drive.files().update(fileId=existing[name], media_body=media).execute()
        else:
            drive.files().create(body={"name": name, "parents": [FOLDER]}, media_body=media).execute()
    return {"pages": len(urls)}