dl/commands/pygg.py

#!/usr/bin/env python3
import argparse
import io
import json
import os
import re
import urllib

import bs4
import requests


YGGTORRENT_BASE_URL = "https://www6.yggtorrent.lol"
CLOUDPROXY_ENDPOINT = os.getenv("CLOUDPROXY_ENDPOINT")


class FlareRequests(requests.Session):
    def request(self, method, url, params=None, data=None, **kwargs):
        if not CLOUDPROXY_ENDPOINT:
            return super().request(method, url, params, data, **kwargs)

        sessions = requests.post(
            CLOUDPROXY_ENDPOINT, json={"cmd": "sessions.list"}
        ).json()

        if "sessions" in sessions and len(sessions["sessions"]) > 0:
            FLARESESSION = sessions["sessions"][0]
        else:
            response = requests.post(
                CLOUDPROXY_ENDPOINT, json={"cmd": "sessions.create"}
            )
            session = response.json()

            if "session" in session:
                FLARESESSION = session["session"]
            else:
                raise requests.RequestException(response)

        if params:
            url += "&" if len(url.split("?")) > 1 else "?"
            url = f"{url}{urllib.parse.urlencode(params)}"

        post_data = {
            "cmd": f"request.{method.lower()}",
            "session": FLARESESSION,
            "url": url,
        }

        if data:
            post_data["postData"] = urllib.parse.urlencode(data)

        try:
            response = requests.post(
                CLOUDPROXY_ENDPOINT,
                json=post_data,
            )

            solution = response.json()

            if "solution" in solution:
                if "content-type" in solution["solution"]["headers"]:
                    content_type = solution["solution"]["headers"][
                        "content-type"
                    ].split(";")
                    if len(content_type) > 1:
                        charset = content_type[1].split("=")
                        if len(charset) > 1:
                            encoding = charset[1]

                resolved = requests.Response()

                resolved.status_code = solution["solution"]["status"]
                resolved.headers = solution["solution"]["headers"]
                resolved.raw = io.BytesIO(solution["solution"]["response"].encode())
                resolved.url = url
                resolved.encoding = encoding or None
                resolved.reason = solution["status"]
                resolved.cookies = solution["solution"]["cookies"]

                return resolved

            raise requests.RequestException(response)
        except requests.RequestException:
            session = requests.post(
                CLOUDPROXY_ENDPOINT,
                json={"cmd": "sessions.destroy", "session": FLARESESSION},
            )

            raise requests.RequestException(solution)


parser = argparse.ArgumentParser()
parser.add_argument("-u", "--uploader", action="append")
parser.add_argument("-b", "--blacklist", action="append", default=["dvd", "iso"])
parser.add_argument("-y", "--year", type=int)
parser.add_argument("-s", "--size", type=int, default=10)
parser.add_argument("-d", "--downloads", type=int, default=20)
parser.add_argument("query")
args = parser.parse_args()


def parse_size(size):
    units = {"o": 1, "Ko": 10**3, "Mo": 10**6, "Go": 10**9, "To": 10**12}
    match = re.search("([0-9.]+)([^0-9]+)", size)
    number = match.group(1).strip()
    unit = match.group(2).strip()
    return int(float(number) * units[unit])


session = FlareRequests()


def check_files(id):
    req = session.get(f"{YGGTORRENT_BASE_URL}/engine/get_files", params={"torrent": id})
    res = bs4.BeautifulSoup(req.text, "html.parser")
    pre = res.select_one("pre")
    jhtml = json.loads(pre.get_text())
    html = bs4.BeautifulSoup(jhtml["html"], "html.parser")
    trs = html.select("tr")
    return len(trs) == 1 and "mkv" in trs[0].get_text().lower()


def search_ygg(query, multi, full):
    ygg_params = {
        "name": query,
        "description": "",
        "file": "",
        "uploader": "",
        "category": "2145",
        "sub_category": "2183",
        "do": "search",
        "order": "asc",
        "sort": "publish_date",
    }

    if full and args.year:
        ygg_params["name"] += f" {args.year}"

    if multi:
        ygg_params["option_langue:multiple[]"] = "4"

    req = session.get(f"{YGGTORRENT_BASE_URL}/engine/search", params=ygg_params)
    html = bs4.BeautifulSoup(
        req.text,
        "html.parser",
    )
    trs = html.select("table.table tr")

    if len(trs) > 1:
        for i, tr in enumerate(trs):
            if not i:
                continue

            tds = tr.find_all("td")
            size = tds[5].get_text()
            downloads = tds[6].get_text()
            name = tds[1].get_text().lower().strip()

            if parse_size(size) > parse_size(f"{args.size}Go"):
                continue

            if int(downloads) < args.downloads:
                continue

            if any(word.lower() in name for word in args.blacklist):
                continue

            if args.year and str(args.year) not in name:
                continue

            if args.uploader and not any(
                uploader.lower() in name for uploader in args.uploader
            ):
                continue

            link = tds[1].a["href"]
            id = link.split("/")[-1].split("-")[0]

            if not check_files(id):
                continue

            print(f"{name} {link}")
            exit(0)


query_string = {"query": args.query, "filters": "type:movie"}

if args.year:
    query_string["filters"] += f" AND year:{args.year}"

tvdb = requests.post(
    "https://tvshowtime-dsn.algolia.net/1/indexes/TVDB/query",
    params={
        "x-algolia-application-id": "tvshowtime",
        "x-algolia-api-key": "c9d5ec1316cec12f093754c69dd879d3",
    },
    json={"params": urllib.parse.urlencode(query_string)},
)

tvdata = tvdb.json()

if not tvdata["nbHits"] > 0:
    print("Can't find query on TheTVDB")
    exit(1)

eng = tvdata["hits"][0]["name"]

fra = (
    tvdata["hits"][0]["translations"]["fra"]
    if "fra" in tvdata["hits"][0]["translations"]
    else args.query
)


search_ygg(args.query, True, True)
search_ygg(fra, True, True)
search_ygg(eng, True, True)
search_ygg(args.query, False, True)
search_ygg(fra, False, True)
search_ygg(eng, False, True)

if args.year:
    search_ygg(args.query, True, False)
    search_ygg(fra, True, False)
    search_ygg(eng, True, False)
    search_ygg(args.query, False, False)
    search_ygg(fra, False, False)
    search_ygg(eng, False, False)

print("No results :(")