dl/commands/2hdp.py

#!/usr/bin/env python3
from argparse import ArgumentParser
from csv import DictWriter
from datetime import datetime
from sys import stdout
from time import sleep
from xml.etree import ElementTree

from bs4 import BeautifulSoup
from requests import get

parser = ArgumentParser()
parser.add_argument(
    "--keyword", action="append", default=["mhdgz"], help="Prefered words to search on names"
)
parser.add_argument("--cookie", required=True, help="Cookies to bypass CloudFlare")
parser.add_argument("--user-agent", required=True, help="User Agent to bypass CloudFlare")
parser.add_argument(
    "--feed", required=True, action="append", help="RSS feed to search for new movies"
)
args = parser.parse_args()


def nb_files(id: int):
    response = get(
        f"https://www.ygg.re/engine/get_files?torrent={id}",
        headers={"Cookie": args.cookie, "User-Agent": args.user_agent},
    )
    sleep(1)

    json = response.json()
    soup = BeautifulSoup(json["html"], "html.parser")
    rows = soup.find_all("tr")
    is_mkv = False

    for row in rows:
        columns = row.find_all("td")

        if columns[1].text.strip()[-3:] == "mkv":
            is_mkv = True
            break

    return is_mkv and len(rows) == 1


def parse_size(size):
    # https://stackoverflow.com/a/42865957
    units = {"Ko": 10**3, "Mo": 10**6, "Go": 10**9, "To": 10**12}
    number = size[:-2]
    unit = size[-2:]

    return int(float(number) * units[unit])


def is_valid(id: int, size: int, completed: int):
    return size < parse_size("10Go") and completed > 100 and nb_files(id)


writer = DictWriter(stdout, fieldnames=["title", "season", "episode", "name", "link"])
writer.writeheader()

for feed in args.feed:
    tree = ElementTree.fromstring(get(feed).text)
    loop = 0

    for item in tree.findall(".//item")[::-1]:
        loop += 1
        title = str(item.findtext("title")).strip()
        season = int(
            item.findtext(
                "itunes:season", namespaces={"itunes": "http://www.itunes.com/dtds/podcast-1.0.dtd"}
            )
            or datetime.strptime(item.findtext("pubDate") or "", "%a, %d %b %Y %H:%M:%S %z").year
        )
        episode = int(
            item.findtext(
                "itunes:episode",
                namespaces={"itunes": "http://www.itunes.com/dtds/podcast-1.0.dtd"},
            )
            or loop
        )

        response = get(
            f"https://www.ygg.re/engine/search?name={title}"
            "&description=&file=&uploader=&category=2145&sub_category=2183"
            "&do=search&order=asc&sort=publish_date",
            headers={"Cookie": args.cookie, "User-Agent": args.user_agent},
        )
        sleep(1)

        soup = BeautifulSoup(response.text, "html.parser")
        rows = soup.select("table.table tr")
        column = None

        for row in rows:
            columns = row.find_all("td")

            if len(columns) == 0:
                continue

            if any(keyword.lower() in columns[1].text.strip().lower() for keyword in args.keyword):
                if is_valid(
                    int(columns[2].a["target"]),
                    parse_size(columns[5].text.strip()),
                    int(columns[6].text.strip()),
                ):
                    column = columns
                    break

        if not column:
            for row in rows:
                columns = row.find_all("td")

                if len(columns) == 0:
                    continue

                if "multi" in columns[1].text.strip().lower():
                    if is_valid(
                        int(columns[2].a["target"]),
                        parse_size(columns[5].text.strip()),
                        int(columns[6].text.strip()),
                    ):
                        column = columns
                        break

        writer.writerow(
            {
                "title": title,
                "season": season,
                "episode": episode,
                "name": column[1].text.strip() if column else "",
                "link": column[1].a["href"] if column else "",
            }
        )
        stdout.flush()