Sitges scrapper

sitges2025.py

import csv
import bs4


def parse_node(m: bs4.Tag, *, row_n: int) -> dict:
    day = m.select_one(".day").text
    start = m.select_one(".time").text
    duration_min = m.select_one(".duration-text").text
    titles = [x.text for x in m.select("li.movie-title")]
    title = ", ".join(titles)
    sections = ", ".join([x.text for x in m.select("ul.movie-sections li")])
    location = m.select_one(".location").text
    link = (
        "https://sitgesfilmfestival.com" + m.select_one(".movie-title a").attrs["href"]
    )
    has_talent = "has-talent" in m.attrs.get("class", [])
    is_maraton = "one-movie-session" not in m.attrs.get("class", [])
    return {
        "Dia semana": f'=Text(B{row_n};"dddd")',
        "Dia": f"{day}/10/2025",
        "Hora inicio": start,
        "Hora fin": f"=C{row_n}+E{row_n}/60/24",
        "Duración (minutos)": duration_min,
        "Duración": f"=E{row_n}/24/60",
        "Título (+link)": f"=HYPERLINK(M{row_n};L{row_n})",
        "Maratón": "si" if is_maraton else "",
        "Talento": "si" if has_talent else "",
        "Cine": location,
        "Secciones": sections,
        "Título": title,
        "URL": link,
    }


def main():
    import argparse
    import sys

    parser = argparse.ArgumentParser()
    parser.add_argument("html")
    args = parser.parse_args()

    with open(args.html, "r", encoding="utf-8") as fh:
        buff = fh.read()

    soup = bs4.BeautifulSoup(buff, features="html.parser")
    movies = soup.select("ul li.c-event-item")
    rows = (parse_node(node, row_n=idx + 2) for (idx, node) in enumerate(movies))

    out = csv.DictWriter(
        sys.stdout,
        fieldnames=[
            "Dia semana",
            "Dia",
            "Hora inicio",
            "Hora fin",
            "Duración (minutos)",
            "Duración",
            "Maratón",
            "Título (+link)",
            "Talento",
            "Cine",
            "Secciones",
            "Título",
            "URL",
        ],
    )
    out.writeheader()
    out.writerows(rows)


if __name__ == "__main__":
    main()