From c29e21101ea53df7d2940275691a4d66ee735f81 Mon Sep 17 00:00:00 2001 From: yasir Date: Sun, 15 Jan 2023 16:10:39 +0700 Subject: [PATCH] Tes --- misskaty/helper/http.py | 19 ------ misskaty/helper/kuso_utils.py | 102 ++++++++++++++++++++++++++++++++ misskaty/plugins/web_scraper.py | 57 +++++++++++++++--- 3 files changed, 152 insertions(+), 26 deletions(-) create mode 100644 misskaty/helper/kuso_utils.py diff --git a/misskaty/helper/http.py b/misskaty/helper/http.py index b0ab4b0b..e385c76a 100644 --- a/misskaty/helper/http.py +++ b/misskaty/helper/http.py @@ -1,22 +1,3 @@ -""" -MIT License -Copyright (c) 2021 TheHamkerCat -Permission is hereby granted, free of charge, to any person obtaining a copy -of this software and associated documentation files (the "Software"), to deal -in the Software without restriction, including without limitation the rights -to use, copy, modify, merge, publish, distribute, sublicense, and/or sell -copies of the Software, and to permit persons to whom the Software is -furnished to do so, subject to the following conditions: -The above copyright notice and this permission notice shall be included in all -copies or substantial portions of the Software. -THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR -IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, -FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE -AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER -LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, -OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE -SOFTWARE. -""" from asyncio import gather import httpx diff --git a/misskaty/helper/kuso_utils.py b/misskaty/helper/kuso_utils.py new file mode 100644 index 00000000..5e43fca2 --- /dev/null +++ b/misskaty/helper/kuso_utils.py @@ -0,0 +1,102 @@ +import re +import subprocess +import sys + +import chevron +import telegraph +import logging +from aiohttp import ClientSession +from misskaty import BOT_USERNAME +from ..plugins.web_scraper import headers +from bs4 import BeautifulSoup as bs4 + +LOGGER = logging.getLogger(__name__) + +telegraph = telegraph.Telegraph() +if telegraph.get_access_token() == None: + token_ph = telegraph.create_account(short_name=BOT_USERNAME) + LOGGER.info(f"kuso_utils: Create TGH Account ..") + +headers = {"Accept": "*/*", "User-Agent": headers} + + +async def kusonimeBypass(url: str, slug=None): + hasil = {} + _url = url + request = ClientSession(headers=headers) + if slug: + noslug_url = "https://kusonime.com/{slug}" + _url = noslug_url.format({"slug": slug}) + try: + test = await request.get(_url) + page = await test.text() + soup = bs4(page, "html.parser") + thumb = soup.find("div", {"class": "post-thumb"}).find("img").get("src") + data = [] + # title = soup.select("#venkonten > div.vezone > div.venser > div.venutama > div.lexot > p:nth-child(3) > strong")[0].text.strip() + title = soup.find("h1", {"class": "jdlz"}).text # fix title njing haha + num = 1 + genre = [] + for _genre in soup.select("#venkonten > div.vezone > div.venser > div.venutama > div.lexot > div.info > p:nth-child(2)"): + gen = _genre.text.split(":").pop().strip().split(", ") + genre = gen + status_anime = soup.select("#venkonten > div.vezone > div.venser > div.venutama > div.lexot > div.info > p:nth-child(6)")[0].text.split(":").pop().strip() + for smokedl in soup.find("div", {"class": "dlbod"}).find_all("div", {"class": "smokeddl"}): + titl = soup.select(f"#venkonten > div.vezone > div.venser > div.venutama > div.lexot > div.dlbod > div:nth-child({num}) > div.smokettl")[0].text + titl = re.sub(f"Download", "", titl).strip() + mendata = {"name": titl, "links": []} + for smokeurl in smokedl.find_all("div", {"class": "smokeurl"}): + quality = smokeurl.find("strong").text + links = [] + for link in smokeurl.find_all("a"): + url = link.get("href") + client = link.text + links.append({"client": client, "url": url}) + mendata["links"].append(dict(quality=quality, link_download=links)) + data.append(mendata) + num += 1 + hasil.update({"error": False, "title": title, "thumb": thumb, "genre": genre, "genre_string": ", ".join(genre), "status_anim": status_anime, "data": data}) + except: + hasil.update({"error": True, "error_message": "kuso bypass error"}) + finally: + await request.close() + return hasil + + +async def byPassPh(url: str, msg_id: int): + kusonime = await kusonimeBypass(url) + results = {"error": True, "error_message": "Post to or create TGH error"} + template = """ + +

Title : {{title}}

+

Genre : {{genre_string}}

+

Status : {{status_anime}}

+
+{{#data}} +

{{name}}

+ {{#links}} +

Resolution: {{quality}}

+ {{#link_download}} +

✗ {{client}}

+ {{/link_download}} + {{/links}} +
+{{/data}} +""".strip() + if not kusonime["error"]: + html = chevron.render(template, kusonime) + page = telegraph.create_page(f"{kusonime.get('title')}-{msg_id}", html_content=html) + results.update({"error": False, "url": "https://telegra.ph/{}".format(page["path"])}) + del results["error_message"] + return results + + +class Kusonime: + def __init__(self): + pass + + async def byPass(self, url): + return await kusonimeBypass(url) + + async def telegraph(self, url, msg_id): + return await byPassPh(url, msg_id) \ No newline at end of file diff --git a/misskaty/plugins/web_scraper.py b/misskaty/plugins/web_scraper.py index d01c929d..9706cb70 100644 --- a/misskaty/plugins/web_scraper.py +++ b/misskaty/plugins/web_scraper.py @@ -12,6 +12,7 @@ from pykeyboard import InlineKeyboard, InlineButton from pyrogram import filters from pyrogram.types import InlineKeyboardButton, InlineKeyboardMarkup from misskaty.helper.http import http +from misskaty.helper.kuso_utils import Kusonime from misskaty import app from misskaty.vars import COMMAND_HANDLER from misskaty.core.message_utils import * @@ -162,7 +163,7 @@ async def getDataNodrakor(msg, kueri, CurrentPage): return None, None # Kusonime GetData -async def getDataKuso(msg, kueri, CurrentPage): +async def getDataKuso(msg, kueri, CurrentPage, user): if not SCRAP_DICT.get(msg.id): kusodata = [] data = await http.get(f'https://kusonime.com/?s={kueri}', headers=headers) @@ -174,21 +175,25 @@ async def getDataKuso(msg, kueri, CurrentPage): kusodata.append({"title": title, "link": link}) if not kusodata: await editPesan(msg, "Sorry could not find any results!") - return None, None + return None, 0, None SCRAP_DICT[msg.id] = [split_arr(kusodata, 6), kueri] try: index = int(CurrentPage - 1) PageLen = len(SCRAP_DICT[msg.id][0]) - + extractbtn = [] + kusoResult = f"#Kusonime Results For: {kueri}\n\n" if kueri == "" else f"#Kusonime Results For: {kueri}\n\n" for c, i in enumerate(SCRAP_DICT[msg.id][0][index], start=1): kusoResult += f"{c}. {i['title']}\n{i['link']}\n\n" + extractbtn.append( + InlineButton(c, f"kusoextract#{CurrentPage}#{c}#{user}#{msg.id}") + ) IGNORE_CHAR = "[]" kusoResult = ''.join(i for i in kusoResult if not i in IGNORE_CHAR) return kusoResult, PageLen except (IndexError, KeyError): await editPesan(msg, "Sorry could not find any matching results!") - return None, None + return None, 0, None # Movieku GetData async def getDataMovieku(msg, kueri, CurrentPage): @@ -542,10 +547,12 @@ async def kusonime_s(client, message): kueri = "" pesan = await kirimPesan(message, "âŗ Please wait, scraping data from Kusonime..", quote=True) CurrentPage = 1 - kusores, PageLen = await getDataKuso(pesan, kueri, CurrentPage) + kusores, PageLen, btn = await getDataKuso(pesan, kueri, CurrentPage, message.from_user.id) if not kusores: return keyboard = InlineKeyboard() keyboard.paginate(PageLen, CurrentPage, 'page_kuso#{number}' + f'#{pesan.id}#{message.from_user.id}') + keyboard.row(InlineButton("👇 Extract Data ", "Hmmm")) + keyboard.row(*btn) keyboard.row( InlineButton("❌ Close", f"close#{message.from_user.id}") ) @@ -624,12 +631,14 @@ async def kusopage_callback(client, callback_query): return await callback_query.answer("Invalid callback data, please send CMD again..") try: - kusores, PageLen = await getDataKuso(callback_query.message, kueri, CurrentPage) + kusores, PageLen, btn = await getDataKuso(callback_query.message, kueri, CurrentPage, callback_query.from_user.id) except TypeError: return keyboard = InlineKeyboard() keyboard.paginate(PageLen, CurrentPage, 'page_kuso#{number}' + f'#{message_id}#{callback_query.from_user.id}') + keyboard.row(InlineButton("👇 Extract Data ", "Hmmm")) + keyboard.row(*btn) keyboard.row( InlineButton("❌ Close", f"close#{callback_query.from_user.id}") ) @@ -852,6 +861,40 @@ async def zonafilmpage_callback(client, callback_query): await editPesan(callback_query.message, zonafilmres, reply_markup=keyboard) ### Scrape DDL Link From Web ### +# Kusonime DDL +@app.on_callback_query(filters.create(lambda _, __, query: 'kusoextract#' in query.data)) +async def kusonime_scrap(_, callback_query): + if callback_query.from_user.id != int(callback_query.data.split('#')[3]): + return await callback_query.answer("Not yours..", True) + idlink = int(callback_query.data.split("#")[2]) + message_id = int(callback_query.data.split('#')[4]) + CurrentPage = int(callback_query.data.split('#')[1]) + try: + link = SCRAP_DICT[message_id][0][CurrentPage-1][idlink-1].get("link") + except KeyError: + return await callback_query.answer("Invalid callback data, please send CMD again..") + + data_kuso = {} + kuso = Kusonime() + keyboard = InlineKeyboard() + keyboard.row( + InlineButton("↩ī¸ Back", f"page_kuso#{CurrentPage}#{message_id}#{callback_query.from_user.id}"), + InlineButton("❌ Close", f"close#{callback_query.from_user.id}") + ) + try: + init_url = data_kuso.get(link, None) + if init_url: + ph = init_url.get("ph_url") + await editPesan(callback_query.message, f"Scrape result from {link}:\n\n{ph}", reply_markup=keyboard) + tgh = await kuso.telegraph(link, message_id) + if tgh["error"]: + await editPesan(callback_query.message, f"ERROR: {tgh['error_message']}", reply_markup=keyboard) + return + except Exception as err: + await editPesan(callback_query.message, f"ERROR: {err}", reply_markup=keyboard) + return + data_kuso[link] = {"ph_url": tgh["url"]} + await editPesan(callback_query.message, f"Scrape result from {link}:\n\n{tgh['url']}", reply_markup=keyboard) # Savefilm21 DDL @app.on_callback_query(filters.create(lambda _, __, query: 'sf21extract#' in query.data)) @@ -879,7 +922,7 @@ async def savefilm21_scrap(_, callback_query): except Exception as err: await editPesan(callback_query.message, f"ERROR: {err}", reply_markup=keyboard) return - await editPesan(callback_query.message, f"Hasil Scrap dari {link}:\n\n{res}", reply_markup=keyboard) + await editPesan(callback_query.message, f"Scrape result from {link}:\n\n{res}", reply_markup=keyboard) # Scrape DDL Link Nodrakor @app.on_message(filters.command(["nodrakor_scrap"], COMMAND_HANDLER))