downplaylists.py

""" downplaylists.py

Downloads playlists found at remote link into a fixed dir!
"""

import sys
import os
import re
import requests

OUT_DIR = "playlists_output"


def main():
    """ Main script -- caller! """
    do_script(sys.argv[1:])


def do_script(args):
    """ In-caller function """
    res = do_run(args if args else ["play/"])
    return 0 if res else 1

def do_run(param):
    """Main execution flow.

	Hint:
		import downplaylists, importlib; importlib.reload(downplaylists)
		lst = downplaylists.do_run(["play/"])
                print(lst[-1])  # Print the last list string
    """
    lst = []
    suffix = param[0]
    url = f"http://git.declaratived.com/{suffix}"
    output_dir = OUT_DIR
    print("Fetching HTML from:", url)
    html = fetch_html(url)

    print(f"Splitting playlists (sized: {len(html)})")
    playlists = split_playlists(html)
    print(f"Found {len(playlists)} playlists.")
    os.makedirs(output_dir, exist_ok=True)

    for block in playlists:
        save_playlist(block, output_dir)
        lst.append(block)

    print(f"Saved {len(playlists)} files in '{output_dir}' directory.")
    return lst


def fetch_html(url: str) -> str:
    """Fetch raw HTML from the given URL."""
    headers = {
        "User-Agent": (
            "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 "
            "(KHTML, like Gecko) Chrome/120.0 Safari/537.36"
        )
    }
    response = requests.get(url, headers=headers)
    response.raise_for_status()
    return response.text


def split_playlists(html: str) -> list:
    """
    Split the HTML into playlist blocks.
    Each playlist starts with 'Playlist PXX' and continues until the next playlist.
    """
    # Normalize whitespace
    text = re.sub(r"\s+", " ", html)

    # Find all playlist headers
    matches = list(re.finditer(r"(Playlist\s+P\d+)", text))

    playlists = []
    for i, match in enumerate(matches):
        start = match.start()
        end = matches[i + 1].start() if i + 1 < len(matches) else len(text)
        block = text[start:end].strip()
        playlists.append(block)

    return playlists


def extract_playlist_name(block: str) -> str:
    """Extract playlist name like 'Playlist P103'."""
    m = re.match(r"(Playlist\s+P\d+)", block)
    return m.group(1).replace(" ", "_") if m else "UnknownPlaylist"


def save_playlist(block: str, output_dir: str):
    """Save a playlist block to a text file."""
    name = extract_playlist_name(block)
    filename = os.path.join(output_dir, f"{name}.html")

    with open(filename, "w", encoding="utf-8") as fdout:
        fdout.write(block + "\n")
    return True


if __name__ == "__main__":
    main()

plays_varias.md

Videos varios

Playlists

1. (here) Always Never (channel)

proposito_to_prestiani.md

Videos de Gatos Fedorentos

Playlists

1. (here) Playlist: gato-fedorento-quadrado

2. (here) Gato Fedorento - Nao fac,a trocadilhos

3. (here) Gato Fedorento - Individuo que e' javardola, menos quando fala france^s

...a proposito do Prestiani

1. (here) Gato Fedorento - na dúvida a culpa é do ... (censurado)
2. (here) Gato Fedorento - o homem com demasiadas caracteristicas