Function _parse_embedded_folder_view

gdown/download_folder.py:205–268

(
    sess: requests.Session,
    folder_id: str,
    verify: bool | str = True,
)

def _parse_embedded_folder_view(
    sess: requests.Session,
    folder_id: str,
    verify: bool | str = True,
) -> tuple[str, list[tuple[str, str, str]]]:
    params = urllib.parse.urlencode({"id": folder_id})
    url = f"https://drive.google.com/embeddedfolderview?{params}"
    res = sess.get(url, verify=verify)
    if res.status_code != 200:
        raise DownloadError(
            f"Failed to retrieve folder contents for folder ID: {folder_id} "
            f"(status code {res.status_code}). "
            "You may need to change the permission to "
            "'Anyone with the link', or have had many accesses. "
            "Check FAQ in https://github.com/wkentaro/gdown?tab=readme-ov-file#faq.",
        )

    soup = bs4.BeautifulSoup(res.text, features="html.parser")

    if soup.title is None or soup.title.string is None:
        raise DownloadError(
            f"Failed to parse folder contents for folder ID: {folder_id}. "
            "The page structure may have changed.",
        )
    folder_name = soup.title.string

    children: list[tuple[str, str, str]] = []
    for a_tag in soup.find_all(name="a"):
        href = a_tag.get("href", "")
        if not isinstance(href, str):
            continue

        file_match = re.match(
            pattern=r"https://drive\.google\.com/file/d/([-\w]{25,})/view",
            string=href,
        )
        if file_match:
            file_id = file_match.group(1)
            file_name = a_tag.get_text(strip=True)
            children.append((file_id, file_name, "application/octet-stream"))
            continue

        # Google-native files (Docs, Sheets, Slides) use docs.google.com
        docs_match = re.match(
            pattern=r"https://docs\.google\.com/\w+/d/([-\w]{25,})/",
            string=href,
        )
        if docs_match:
            file_id = docs_match.group(1)
            file_name = a_tag.get_text(strip=True)
            children.append((file_id, file_name, "application/octet-stream"))
            continue

        folder_match = re.match(
            pattern=r"https://drive\.google\.com/drive/folders/([-\w]{25,})",
            string=href,
        )
        if folder_match: