render_google_docs.py

import sys
from urllib.parse import urlparse
import requests
import pandas as pd
from io import StringIO


def save(df: pd.DataFrame, path: str = "table.csv"):
    df.to_csv(path, index=False)
    return path

def download(url: str, table: int = 0):
    parts = urlparse(url).path.split("/")

    if len(parts) >= 5 and parts[1] == "document" and parts[2] == "d" and parts[3] == "e":
        doc_id = parts[4]
        export_url = f"https://docs.google.com/document/d/e/{doc_id}/pub"
    elif len(parts) >= 4 and parts[1] == "document" and parts[2] == "d":
        doc_id = parts[3]
        export_url = f"https://docs.google.com/document/d/{doc_id}/export?format=html"
    elif len(parts) >= 4 and parts[1] == "spreadsheets" and parts[2] == "d":
        doc_id = parts[3]
        export_url = f"https://docs.google.com/spreadsheets/d/{doc_id}/gviz/tq?tqx=out:html&gid=0"
    else:
        raise ValueError("URL does not contain the expected 'document'/'spreadsheets' segments.")

    response = requests.get(export_url, timeout=30)
    response.raise_for_status()

    tables = pd.read_html(StringIO(response.text), header=0)

    if table >= len(tables):
        raise IndexError(
            f"The document contains only {len(tables)} table(s)."
        )

    return tables[table]

def load(file: str = "table.csv"):
    try:
        return pd.read_csv(file)
    except FileNotFoundError:
        raise FileNotFoundError(f"'{file}' not found.")
        

def render(df: pd.DataFrame):
    data = df.copy()
    if str(data.iloc[0, 0]).strip().lower() == "x-coordinate":
        data.columns = data.iloc[0].astype(str).str.strip()
        data = data.iloc[1:].reset_index(drop=True)

    data = data.rename(columns={
        coluna: coluna.strip().lower().replace("-", "_")
        for coluna in data.columns
    })

    positions_x = data["x_coordinate"].astype(int).to_numpy()
    positions_y = data["y_coordinate"].astype(int).to_numpy()
    characters = data["character"].astype(str).to_numpy()

    largura = positions_x.max() + 1
    altura = positions_y.max() + 1

    grade = []
    for _ in range(altura):
        grade.append([" "] * largura)

    for caractere, position_x, position_y in zip(characters, positions_x, positions_y):
        grade[position_y][position_x] = caractere

    rows = []
    for row in grade:
        rows.append("".join(row))

    return "\n".join(rows)

def save_rendered_text(text: str, path: str = "rendered.txt") -> None:
    with open(path, "w", encoding="utf-8") as f:
        f.write(text)

def main():
    if len(sys.argv) > 1:
        url = " ".join(sys.argv[1:])
    else:
        print("This program downloads a table from a Google Docs document and renders it as text.")
        url = input("Enter the Google Docs URL: ")

    if not url:
        raise SystemExit("No URL provided.")

    save(download(url))
    rendered = render(load("table.csv"))
    print(rendered)
    save_rendered_text(rendered)

if __name__ == "__main__":
    main()