Files
anime_downloader/logic_ohli24.py

1534 lines
57 KiB
Python
Raw Normal View History

2022-02-08 23:17:30 +09:00
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time : 2022/02/08 3:44 PM
# @Author : yommi
2022-04-06 23:45:15 +09:00
# @Site :
2022-02-08 23:17:30 +09:00
# @File : logic_ohli24
# @Software: PyCharm
import os, sys, traceback, re, json, threading
import time
2022-06-07 20:00:29 +09:00
from datetime import datetime, date
2022-02-08 23:17:30 +09:00
import copy
2022-03-27 18:26:18 +09:00
import hashlib
2022-04-06 23:45:15 +09:00
import discord
2022-02-08 23:17:30 +09:00
# third-party
import requests
from discord_webhook import DiscordWebhook, DiscordEmbed
2022-02-10 00:34:14 +09:00
from lxml import html
2022-03-27 18:26:18 +09:00
from urllib import parse
import urllib
2022-04-17 13:45:37 +09:00
import asyncio
# import aiohttp
2022-04-06 23:45:15 +09:00
2022-02-08 23:17:30 +09:00
# third-party
from flask import request, render_template, jsonify
from sqlalchemy import or_, and_, func, not_, desc
2022-03-27 18:26:18 +09:00
from pip._internal import main
from .lib.utils import yommi_timeit
2022-04-17 13:45:37 +09:00
pkgs = ["beautifulsoup4", "jsbeautifier", "aiohttp"]
2022-03-27 18:26:18 +09:00
for pkg in pkgs:
try:
import pkg
except ImportError:
2022-04-06 23:45:15 +09:00
main(["install", pkg])
2022-03-27 18:26:18 +09:00
2022-04-17 13:45:37 +09:00
import aiohttp
2022-03-27 18:26:18 +09:00
from bs4 import BeautifulSoup
import jsbeautifier
2022-02-08 23:17:30 +09:00
# sjva 공용
from framework import db, scheduler, path_data, socketio
from framework.util import Util
from framework.common.util import headers
2022-04-06 23:45:15 +09:00
from plugin import (
LogicModuleBase,
FfmpegQueueEntity,
FfmpegQueue,
default_route_socketio,
)
2022-02-08 23:17:30 +09:00
from tool_base import d
2022-04-06 23:45:15 +09:00
2022-02-08 23:17:30 +09:00
# 패키지
from .plugin import P
logger = P.logger
#########################################################
class LogicOhli24(LogicModuleBase):
db_default = {
"ohli24_db_version": "1.1",
"ohli24_url": "https://a18.ohli24.com",
2022-04-06 23:45:15 +09:00
"ohli24_download_path": os.path.join(path_data, P.package_name, "ohli24"),
"ohli24_auto_make_folder": "True",
"ohli24_auto_make_season_folder": "True",
"ohli24_finished_insert": "[완결]",
"ohli24_max_ffmpeg_process_count": "1",
"ohli24_order_desc": "True",
2022-04-06 23:45:15 +09:00
"ohli24_auto_start": "False",
"ohli24_interval": "* 5 * * *",
"ohli24_auto_mode_all": "False",
"ohli24_auto_code_list": "all",
"ohli24_current_code": "",
"ohli24_uncompleted_auto_enqueue": "False",
2023-01-30 19:26:57 +09:00
"ohli24_image_url_prefix_series": "",
"ohli24_image_url_prefix_episode": "",
"ohli24_discord_notify": "True",
2022-02-08 23:17:30 +09:00
}
current_headers = None
2022-02-10 00:34:14 +09:00
current_data = None
2023-01-13 20:14:11 +09:00
referer = None
origin_url = None
episode_url = None
cookies = None
2022-03-27 18:26:18 +09:00
2022-02-10 00:34:14 +09:00
session = requests.Session()
headers = {
2022-04-06 23:45:15 +09:00
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
"Chrome/71.0.3578.98 Safari/537.36",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
"Accept-Language": "ko-KR,ko;q=0.9,en-US;q=0.8,en;q=0.7",
2023-01-13 20:14:11 +09:00
# "Referer": "",
# "Cookie": "PHPSESSID=hhhnrora8o9omv1tljq4efv216; 2a0d2363701f23f8a75028924a3af643=NDkuMTYzLjExMS4xMDk=; e1192aefb64683cc97abb83c71057733=aW5n",
2022-04-06 23:45:15 +09:00
}
useragent = {
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, "
"like Gecko) Chrome/96.0.4664.110 Whale/3.12.129.46 Safari/537.36"
2022-02-10 00:34:14 +09:00
}
2022-02-08 23:17:30 +09:00
def __init__(self, P):
2022-04-17 13:45:37 +09:00
super(LogicOhli24, self).__init__(P, "setting", scheduler_desc="ohli24 자동 다운로드")
2022-04-06 23:45:15 +09:00
self.name = "ohli24"
2022-03-27 18:26:18 +09:00
self.queue = None
self.last_post_title = ""
self.discord_webhook_url = "https://discord.com/api/webhooks/1071430127860334663/viCiM5ssS-U1_ONWgdWa-64KgvPfU5jJ8WQAym-4vkiyASB0e8IcnlLnxG4F40nj10kZ"
self.discord_color = "242424"
self.discord_title = "새로운 애니"
self.DISCORD_CHANNEL_ID = "1071430054023798958"
2022-02-08 23:17:30 +09:00
default_route_socketio(P, self)
2023-01-13 20:14:11 +09:00
@staticmethod
async def get_html_playwright(
url: str,
headless: bool = False,
referer: str = "",
engine: str = "chrome",
stealth: bool = False,
):
try:
from playwright.sync_api import sync_playwright
from playwright.async_api import async_playwright
from playwright_stealth import stealth_sync, stealth_async
import time
cookie = None
2023-01-13 21:57:59 +09:00
# browser_args = [
# "--window-size=1300,570",
# "--window-position=000,000",
# "--disable-dev-shm-usage",
# "--no-sandbox",
# "--disable-web-security",
# "--disable-features=site-per-process",
# "--disable-setuid-sandbox",
# "--disable-accelerated-2d-canvas",
# "--no-first-run",
# "--no-zygote",
# # '--single-process',
# "--disable-gpu",
# # "--use-gl=egl",
# "--disable-blink-features=AutomationControlled",
# # "--disable-background-networking",
# # "--enable-features=NetworkService,NetworkServiceInProcess",
# "--disable-background-timer-throttling",
# "--disable-backgrounding-occluded-windows",
# "--disable-breakpad",
# "--disable-client-side-phishing-detection",
# "--disable-component-extensions-with-background-pages",
# "--disable-default-apps",
# "--disable-extensions",
# "--disable-features=Translate",
# "--disable-hang-monitor",
# "--disable-ipc-flooding-protection",
# "--disable-popup-blocking",
# "--disable-prompt-on-repost",
# # "--disable-renderer-backgrounding",
# "--disable-sync",
# "--force-color-profile=srgb",
# # "--metrics-recording-only",
# # "--enable-automation",
# "--password-store=basic",
# # "--use-mock-keychain",
# # "--hide-scrollbars",
# "--mute-audio",
# ]
2023-01-13 20:14:11 +09:00
browser_args = [
"--window-size=1300,570",
2023-01-13 21:57:59 +09:00
"--window-position=0,0",
# "--disable-dev-shm-usage",
2023-01-13 20:14:11 +09:00
"--no-sandbox",
2023-01-13 21:57:59 +09:00
# "--disable-web-security",
# "--disable-features=site-per-process",
# "--disable-setuid-sandbox",
# "--disable-accelerated-2d-canvas",
# "--no-first-run",
# "--no-zygote",
# "--single-process",
2023-01-13 20:14:11 +09:00
"--disable-gpu",
2023-01-13 21:57:59 +09:00
# "--use-gl=egl",
2023-01-13 20:14:11 +09:00
"--mute-audio",
]
# scraper = cloudscraper.create_scraper(
# browser={"browser": "chrome", "platform": "windows", "desktop": True},
# debug=False,
# # sess=LogicAniLife.session,
# delay=10,
# )
#
# cookie_value, user_agent = scraper.get_cookie_string(url)
#
# logger.debug(f"cookie_value:: {cookie_value}")
start = time.time()
ua = (
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
"AppleWebKit/537.36 (KHTML, like Gecko) "
"Chrome/69.0.3497.100 Safari/537.36"
)
# from playwright_stealth import stealth_sync
def set_cookie(req):
nonlocal cookie
if "cookie" in req.headers:
cookie = req.headers["cookie"]
async with async_playwright() as p:
try:
if engine == "chrome":
browser = await p.chromium.launch(
channel="chrome", args=browser_args, headless=headless
)
elif engine == "webkit":
browser = await p.webkit.launch(
headless=headless,
args=browser_args,
)
else:
browser = await p.firefox.launch(
headless=headless,
args=browser_args,
)
# context = browser.new_context(
# user_agent=ua,
# )
LogicOhli24.headers["Referer"] = "https://anilife.com/detail/id/471"
2023-01-13 20:14:11 +09:00
# print(LogicAniLife.headers)
LogicOhli24.headers["Referer"] = LogicOhli24.episode_url
if referer is not None:
LogicOhli24.headers["Referer"] = referer
# logger.debug(f"LogicAniLife.headers::: {LogicOhli24.headers}")
context = await browser.new_context(
extra_http_headers=LogicOhli24.headers, ignore_https_errors=True
)
# await context.add_cookies(LogicOhli24.cookies)
# LogicAniLife.headers["Cookie"] = cookie_value
2023-01-13 21:57:59 +09:00
# await context.set_extra_http_headers(LogicOhli24.headers)
2023-01-13 20:14:11 +09:00
page = await context.new_page()
# page.set_extra_http_headers(LogicAniLife.headers)
if stealth:
await stealth_async(page)
# page.on("request", set_cookie)
# stealth_sync(page)
2023-01-13 23:30:54 +09:00
# print(LogicOhli24.headers["Referer"])
2023-01-13 20:14:11 +09:00
2023-01-13 23:30:54 +09:00
# page.on("request", set_cookie)
2023-01-13 20:14:11 +09:00
print(f'Referer:: {LogicOhli24.headers["Referer"]}')
# await page.set_extra_http_headers(LogicAniLife.headers)
# domcontentloaded
# load
# networkidle
await page.goto(
url,
2023-01-14 18:22:57 +09:00
wait_until="load",
2023-01-13 23:30:54 +09:00
# referer=LogicOhli24.headers["Referer"],
2023-01-13 20:14:11 +09:00
)
2023-01-13 23:30:54 +09:00
# await page.wait_for_url(url, wait_until="domcontentloaded")
2023-01-13 20:14:11 +09:00
# page.wait_for_timeout(10000)
# await asyncio.sleep(2.9)
2023-01-13 21:57:59 +09:00
await asyncio.sleep(1)
2023-01-13 20:14:11 +09:00
# await page.reload()
# time.sleep(10)
# cookies = context.cookies
# print(cookies)
print(f"page.url:: {page.url}")
LogicOhli24.origin_url = page.url
2023-01-13 23:30:54 +09:00
temp_content = await page.content()
2023-01-13 20:14:11 +09:00
#
# print(temp_content)
print(f"run at {time.time() - start} sec")
2023-01-13 23:30:54 +09:00
return temp_content
2023-01-13 20:14:11 +09:00
except Exception as e:
logger.error("Exception:%s", e)
logger.error(traceback.format_exc())
finally:
await browser.close()
except Exception as e:
logger.error("Exception:%s", e)
logger.error(traceback.format_exc())
finally:
# browser.close()
pass
2022-02-08 23:17:30 +09:00
@staticmethod
def db_init():
pass
# try:
# for key, value in P.Logic.db_default.items():
# if db.session.query(ModelSetting).filter_by(key=key).count() == 0:
# db.session.add(ModelSetting(key, value))
# db.session.commit()
# except Exception as e:
# logger.error('Exception:%s', e)
# logger.error(traceback.format_exc())
def process_menu(self, sub, req):
arg = P.ModelSetting.to_dict()
2022-04-06 23:45:15 +09:00
arg["sub"] = self.name
if sub in ["setting", "queue", "list", "category", "request"]:
if sub == "request" and req.args.get("content_code") is not None:
arg["ohli24_current_code"] = req.args.get("content_code")
if sub == "setting":
job_id = "%s_%s" % (self.P.package_name, self.name)
arg["scheduler"] = str(scheduler.is_include(job_id))
arg["is_running"] = str(scheduler.is_running(job_id))
2022-02-08 23:17:30 +09:00
return render_template(
2022-04-06 23:45:15 +09:00
"{package_name}_{module_name}_{sub}.html".format(
package_name=P.package_name, module_name=self.name, sub=sub
),
arg=arg,
)
return render_template("sample.html", title="%s - %s" % (P.package_name, sub))
2022-02-08 23:17:30 +09:00
# @staticmethod
def process_ajax(self, sub, req):
try:
2022-04-06 23:45:15 +09:00
if sub == "analysis":
2022-02-08 23:17:30 +09:00
# code = req.form['code']
2022-04-06 23:45:15 +09:00
code = request.form["code"]
wr_id = request.form.get("wr_id", None)
bo_table = request.form.get("bo_table", None)
2022-02-08 23:17:30 +09:00
data = []
2022-02-10 00:34:14 +09:00
# print(code)
# logger.info("code::: %s", code)
2022-04-06 23:45:15 +09:00
P.ModelSetting.set("ohli24_current_code", code)
data = self.get_series_info(code, wr_id, bo_table)
2022-02-08 23:17:30 +09:00
self.current_data = data
2022-04-06 23:45:15 +09:00
return jsonify({"ret": "success", "data": data, "code": code})
elif sub == "anime_list":
data = []
cate = request.form["type"]
page = request.form["page"]
data = self.get_anime_info(cate, page)
# self.current_data = data
return jsonify(
{"ret": "success", "cate": cate, "page": page, "data": data}
)
elif sub == "complete_list":
data = []
cate = request.form["type"]
logger.debug("cate:: %s", cate)
page = request.form["page"]
2022-04-06 23:45:15 +09:00
data = self.get_anime_info(cate, page)
# self.current_data = data
return jsonify(
{"ret": "success", "cate": cate, "page": page, "data": data}
)
elif sub == "search":
data = []
# cate = request.form["type"]
# page = request.form["page"]
2022-04-17 18:00:43 +09:00
cate = request.form["type"]
query = request.form["query"]
2022-04-17 18:00:43 +09:00
page = request.form["page"]
2022-04-17 18:00:43 +09:00
data = self.get_search_result(query, page, cate)
# self.current_data = data
2022-04-17 18:00:43 +09:00
return jsonify(
{
"ret": "success",
"cate": cate,
"page": page,
"query": query,
"data": data,
}
)
2022-04-06 23:45:15 +09:00
elif sub == "add_queue":
2023-01-30 19:26:57 +09:00
logger.debug(f"linkkf add_queue routine ===============")
2022-02-08 23:17:30 +09:00
ret = {}
2022-04-06 23:45:15 +09:00
info = json.loads(request.form["data"])
2022-05-22 15:06:45 +09:00
logger.info(f"info:: {info}")
2022-04-06 23:45:15 +09:00
ret["ret"] = self.add(info)
2022-02-08 23:17:30 +09:00
return jsonify(ret)
2022-04-06 23:45:15 +09:00
elif sub == "entity_list":
2022-03-27 18:26:18 +09:00
return jsonify(self.queue.get_entity_list())
2022-04-06 23:45:15 +09:00
elif sub == "queue_command":
ret = self.queue.command(
req.form["command"], int(req.form["entity_id"])
)
2022-03-27 18:26:18 +09:00
return jsonify(ret)
2022-04-06 23:45:15 +09:00
elif sub == "add_queue_checked_list":
data = json.loads(request.form["data"])
2022-03-28 18:52:51 +09:00
2022-03-27 18:26:18 +09:00
def func():
count = 0
for tmp in data:
add_ret = self.add(tmp)
2022-04-06 23:45:15 +09:00
if add_ret.startswith("enqueue"):
self.socketio_callback("list_refresh", "")
2022-03-27 18:26:18 +09:00
count += 1
2022-04-06 23:45:15 +09:00
notify = {
"type": "success",
"msg": "%s 개의 에피소드를 큐에 추가 하였습니다." % count,
}
socketio.emit(
"notify", notify, namespace="/framework", broadcast=True
)
2022-03-28 18:52:51 +09:00
2022-03-27 18:26:18 +09:00
thread = threading.Thread(target=func, args=())
thread.daemon = True
thread.start()
2022-04-06 23:45:15 +09:00
return jsonify("")
elif sub == "web_list":
2022-03-27 18:26:18 +09:00
return jsonify(ModelOhli24Item.web_list(request))
2022-04-06 23:45:15 +09:00
elif sub == "db_remove":
return jsonify(ModelOhli24Item.delete_by_id(req.form["id"]))
elif sub == "add_whitelist":
try:
# params = request.get_data()
# logger.debug(f"params: {params}")
# data_code = request.args.get("data_code")
params = request.get_json()
logger.debug(f"params:: {params}")
if params is not None:
code = params["data_code"]
logger.debug(f"params: {code}")
ret = LogicOhli24.add_whitelist(code)
else:
ret = LogicOhli24.add_whitelist()
return jsonify(ret)
except Exception as e:
logger.error("Exception:%s", e)
logger.error(traceback.format_exc())
2022-02-08 23:17:30 +09:00
except Exception as e:
2023-01-30 19:26:57 +09:00
P.logger.error(f"Exception: {str(e)}")
2022-02-08 23:17:30 +09:00
P.logger.error(traceback.format_exc())
2022-11-25 19:20:52 +09:00
def process_api(self, sub, req):
logger.debug("here!")
ret = {}
try:
if sub == "anime_list":
logger.debug(f"anime_list =*==")
logger.debug(req)
data = []
cate = req.form["type"]
page = req.form["page"]
data = self.get_anime_info(cate, page)
# self.current_data = data
return jsonify(
{"ret": "success", "cate": cate, "page": page, "data": data}
)
except Exception as exception:
logger.error("Exception:%s", exception)
logger.error(traceback.format_exc())
ret["ret"] = "exception"
ret["data"] = str(exception)
return jsonify(ret)
#########################################################
# API
#########################################################
# @blueprint.route("/api/<sub>", methods=["GET", "POST"])
# @check_api
# def api(self, sub):
# if sub == "ohli24":
# try:
# logger.debug("api ohli24")
# data = {"aaaa"}
# except Exception as e:
# logger.error("Exception:%s", e)
# logger.error(traceback.format_exc())
# return data
@staticmethod
def add_whitelist(*args):
ret = {}
# logger.debug(f"args: {args}")
try:
if len(args) == 0:
code = str(LogicOhli24.current_data["code"])
else:
code = str(args[0])
# print(code)
whitelist_program = P.ModelSetting.get("ohli24_auto_code_list")
whitelist_programs = [
str(x.strip()) for x in whitelist_program.replace("\n", "|").split("|")
]
if code not in whitelist_programs:
whitelist_programs.append(code)
whitelist_programs = filter(
lambda x: x != "", whitelist_programs
) # remove blank code
whitelist_program = "|".join(whitelist_programs)
entity = (
db.session.query(P.ModelSetting)
.filter_by(key="ohli24_auto_code_list")
.with_for_update()
.first()
)
entity.value = whitelist_program
db.session.commit()
ret["ret"] = True
ret["code"] = code
if len(args) == 0:
return LogicOhli24.current_data
else:
return ret
else:
ret["ret"] = False
ret["log"] = "이미 추가되어 있습니다."
except Exception as e:
logger.error("Exception:%s", e)
logger.error(traceback.format_exc())
ret["ret"] = False
ret["log"] = str(e)
return ret
2022-03-27 18:26:18 +09:00
def setting_save_after(self):
2022-04-06 23:45:15 +09:00
if self.queue.get_max_ffmpeg_count() != P.ModelSetting.get_int(
"ohli24_max_ffmpeg_process_count"
):
self.queue.set_max_ffmpeg_count(
P.ModelSetting.get_int("ohli24_max_ffmpeg_process_count")
)
2022-03-27 18:26:18 +09:00
2022-04-17 13:45:37 +09:00
def scheduler_function(self):
# Todo: 스케쥴링 함수 미구현
2022-06-07 20:00:29 +09:00
logger.debug(f"ohli24 scheduler_function::=========================")
2022-04-17 13:45:37 +09:00
content_code_list = P.ModelSetting.get_list("ohli24_auto_code_list", "|")
logger.debug(f"content_code_list::: {content_code_list}")
url_list = ["https://www.naver.com/", "https://www.daum.net/"]
2022-06-07 20:00:29 +09:00
week = ["월요일", "화요일", "수요일", "목요일", "금요일", "토요일", "일요일"]
today = date.today()
print(today)
print()
print(today.weekday())
url = f'{P.ModelSetting.get("ohli24_url")}/bbs/board.php?bo_table=ing&sca={week[today.weekday()]}'
# print(url)
2022-06-07 20:00:29 +09:00
if "all" in content_code_list:
2022-06-26 21:46:16 +09:00
ret_data = LogicOhli24.get_auto_anime_info(self, url=url)
logger.debug(f"today_info:: {ret_data}")
for item in ret_data["anime_list"]:
# wr_id = request.form.get("wr_id", None)
# bo_table = request.form.get("bo_table", None)
wr_id = None
bo_table = None
data = []
# print(code)
# logger.info("code::: %s", code)
# logger.debug(item)
2022-06-26 21:46:16 +09:00
# 잠시 중지
# data = self.get_series_info(item["code"], wr_id, bo_table)
# logger.debug(data)
2022-06-26 21:46:16 +09:00
2022-04-17 13:45:37 +09:00
# result = asyncio.run(LogicOhli24.main(url_list))
# logger.debug(f"result:: {result}")
elif len(content_code_list) > 0:
for item in content_code_list:
url = P.ModelSetting.get("ohli24_url") + "/c/" + item
print("scheduling url: %s", url)
# ret_data = LogicOhli24.get_auto_anime_info(self, url=url)
print("debug===")
print(item)
content_info = self.get_series_info(item, "", "")
# logger.debug(content_info)
for episode_info in content_info["episode"]:
add_ret = self.add(episode_info)
if add_ret.startswith("enqueue"):
self.socketio_callback("list_refresh", "")
# logger.debug(f"data: {data}")
# self.current_data = data
# db에서 다운로드 완료 유무 체크
2022-04-17 13:45:37 +09:00
@staticmethod
2022-06-26 21:46:16 +09:00
async def get_data(url) -> str:
2022-04-17 13:45:37 +09:00
async with aiohttp.ClientSession() as session:
async with session.get(url) as response:
content = await response.text()
# print(response)
return content
@staticmethod
2022-06-26 21:46:16 +09:00
async def main(url_list: list):
2022-04-17 13:45:37 +09:00
input_coroutines = [LogicOhli24.get_data(url_) for url_ in url_list]
res = await asyncio.gather(*input_coroutines)
return res
def get_series_info(self, code, wr_id, bo_table):
2022-04-06 23:45:15 +09:00
code_type = "c"
code = urllib.parse.quote(code)
2022-02-10 00:34:14 +09:00
try:
2022-04-06 23:45:15 +09:00
if (
self.current_data is not None
and "code" in self.current_data
and self.current_data["code"] == code
):
2022-02-10 00:34:14 +09:00
return self.current_data
2022-04-06 23:45:15 +09:00
if code.startswith("http"):
2022-03-28 14:40:38 +09:00
2022-03-28 19:14:25 +09:00
# if code.split('c/')[1] is not None:
# code = code.split('c/')[1]
# code_type = 'c'
# elif code.split('e/')[1] is not None:
# code_type = 'e'
# code = code.split('e/')[1]
2022-04-06 23:45:15 +09:00
if "/c/" in code:
code = code.split("c/")[1]
code_type = "c"
elif "/e/" in code:
code = code.split("e/")[1]
code_type = "e"
logger.info(f"code:::: {code}")
if code_type == "c":
url = P.ModelSetting.get("ohli24_url") + "/c/" + code
elif code_type == "e":
url = P.ModelSetting.get("ohli24_url") + "/e/" + code
2022-03-28 18:43:12 +09:00
else:
2022-04-06 23:45:15 +09:00
url = P.ModelSetting.get("ohli24_url") + "/e/" + code
if wr_id is not None:
# print(len(wr_id))
if len(wr_id) > 0:
url = (
P.ModelSetting.get("ohli24_url")
+ "/bbs/board.php?bo_table="
+ bo_table
+ "&wr_id="
+ wr_id
)
else:
pass
# logger.debug("url:::> %s", url)
2022-02-10 00:34:14 +09:00
# self.current_headers = { 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7)
# AppleWebKit/537.36 (KHTML, like Gecko) ' 'Chrome/96.0.4664.110 Whale/3.12.129.46 Safari/537.36',
# 'Referer': url }
response_data = LogicOhli24.get_html(url, timeout=10)
tree = html.fromstring(response_data)
title = tree.xpath('//div[@class="view-title"]/h1/text()')[0]
# image = tree.xpath('//div[@class="view-info"]/div[@class="image"]/div/img')[0]['src']
image = tree.xpath('//div[@class="image"]/div/img/@src')[0]
2022-04-06 23:45:15 +09:00
image = image.replace("..", P.ModelSetting.get("ohli24_url"))
2022-02-10 00:34:14 +09:00
des_items = tree.xpath('//div[@class="list"]/p')
des = {}
2022-04-06 23:45:15 +09:00
des_key = [
"_otit",
"_dir",
"_pub",
"_tag",
"_classifi",
"_country",
"_grade",
"_total_chapter",
"_show_time",
"_release_year",
2022-04-06 23:45:15 +09:00
]
2022-03-27 18:26:18 +09:00
description_dict = {
2022-04-06 23:45:15 +09:00
"원제": "_otit",
"원작": "_org",
"감독": "_dir",
"각본": "_scr",
"캐릭터 디자인": "_character_design",
"음악": "_sound",
"제작사": "_pub",
"장르": "_tag",
"분류": "_classifi",
"제작국가": "_country",
"방영일": "_date",
"등급": "_grade",
"총화수": "_total_chapter",
"상영시간": "_show_time",
2022-08-05 19:33:24 +09:00
"상영일": "_release_date",
"개봉년도": "_release_year",
"개봉일": "_opening_date",
"런타임": "_run_time",
2022-03-27 18:26:18 +09:00
}
list_body_li = tree.xpath('//ul[@class="list-body"]/li')
2022-04-17 13:45:37 +09:00
# logger.debug(f"list_body_li:: {list_body_li}")
2022-03-27 18:26:18 +09:00
episodes = []
vi = None
for li in list_body_li:
2022-04-17 13:45:37 +09:00
# logger.debug(li)
2022-04-06 23:45:15 +09:00
title = li.xpath(".//a/text()")[0].strip()
2022-03-27 18:26:18 +09:00
thumbnail = image
2022-04-17 13:45:37 +09:00
# logger.info(li.xpath('//a[@class="item-subject"]/@href'))
2022-04-06 23:45:15 +09:00
link = (
P.ModelSetting.get("ohli24_url")
2022-04-17 13:45:37 +09:00
+ li.xpath('.//a[@class="item-subject"]/@href')[0]
2022-04-06 23:45:15 +09:00
)
2022-04-17 13:45:37 +09:00
# logger.debug(f"link:: {link}")
_date = li.xpath('.//div[@class="wr-date"]/text()')[0]
2022-04-06 23:45:15 +09:00
m = hashlib.md5(title.encode("utf-8"))
2022-03-27 18:26:18 +09:00
# _vi = hashlib.md5(title.encode('utf-8').hexdigest())
2022-04-17 13:45:37 +09:00
# logger.info(m.hexdigest())
2022-03-27 18:26:18 +09:00
_vi = m.hexdigest()
2022-04-06 23:45:15 +09:00
episodes.append(
{
"title": title,
"link": link,
"thumbnail": image,
"date": _date,
"day": _date,
2022-04-06 23:45:15 +09:00
"_id": title,
"va": link,
"_vi": _vi,
"content_code": code,
}
)
# 정렬 여부 체크
# logger.debug(P.ModelSetting.get("ohli24_order_desc"))
# if P.ModelSetting.get("ohli24_order_desc") == "False":
# print("Here....")
# episodes.reverse()
# logger.info("des_items length:: %s", len(des_items))
2022-02-10 00:34:14 +09:00
for idx, item in enumerate(des_items):
2022-03-27 18:26:18 +09:00
# key = des_key[idx]
2022-04-06 23:45:15 +09:00
span = item.xpath(".//span//text()")
2022-04-17 13:45:37 +09:00
# logger.info(span)
2022-03-27 18:26:18 +09:00
key = description_dict[span[0]]
2022-04-13 15:18:08 +09:00
try:
des[key] = item.xpath(".//span/text()")[1]
2022-04-13 15:19:20 +09:00
except IndexError:
2022-04-13 15:18:08 +09:00
des[key] = ""
2022-02-10 00:34:14 +09:00
2022-04-17 13:45:37 +09:00
# logger.info(f"des::>> {des}")
2022-04-06 23:45:15 +09:00
image = image.replace("..", P.ModelSetting.get("ohli24_url"))
2022-04-17 13:45:37 +09:00
# logger.info("images:: %s", image)
# logger.info("title:: %s", title)
2022-02-10 00:34:14 +09:00
2022-04-06 23:45:15 +09:00
ser_description = tree.xpath(
'//div[@class="view-stocon"]/div[@class="c"]/text()'
)
2022-02-10 00:34:14 +09:00
data = {
2022-04-06 23:45:15 +09:00
"title": title,
"image": image,
"date": "2022.01.11 00:30 (화)",
"ser_description": ser_description,
"des": des,
"episode": episodes,
2022-02-10 00:34:14 +09:00
}
if not P.ModelSetting.get_bool("ohli24_order_desc"):
2022-04-06 23:45:15 +09:00
data["episode"] = list(reversed(data["episode"]))
data["list_order"] = "desc"
2022-03-27 18:26:18 +09:00
2022-02-10 00:34:14 +09:00
return data
# logger.info(response_text)
except Exception as e:
2022-04-06 23:45:15 +09:00
P.logger.error("Exception:%s", e)
2022-02-10 00:34:14 +09:00
P.logger.error(traceback.format_exc())
2022-04-06 23:45:15 +09:00
return {"ret": "exception", "log": str(e)}
def get_anime_info(self, cate, page):
try:
if cate == "ing":
url = (
P.ModelSetting.get("ohli24_url")
+ "/bbs/board.php?bo_table="
+ cate
+ "&page="
+ page
)
elif cate == "movie":
url = (
P.ModelSetting.get("ohli24_url")
+ "/bbs/board.php?bo_table="
+ cate
+ "&page="
+ page
)
else:
url = (
P.ModelSetting.get("ohli24_url")
+ "/bbs/board.php?bo_table="
+ cate
+ "&page="
+ page
)
# cate == "complete":
# logger.info("url:::> %s", url)
2022-04-06 23:45:15 +09:00
data = {}
response_data = LogicOhli24.get_html(url, timeout=10)
2023-01-13 20:14:11 +09:00
# response_data = asyncio.run(
# LogicOhli24.get_html_playwright(
# url,
# headless=False,
# # referer=referer_url,
# engine="chrome",
# # stealth=True,
# )
# )
# print(response_data)
2022-04-06 23:45:15 +09:00
tree = html.fromstring(response_data)
2023-01-15 16:46:48 +09:00
tmp_items = tree.xpath('//div[@class="list-row"]')
2022-04-06 23:45:15 +09:00
data["anime_count"] = len(tmp_items)
data["anime_list"] = []
for item in tmp_items:
entity = {}
entity["link"] = item.xpath(".//a/@href")[0]
entity["code"] = entity["link"].split("/")[-1]
entity["title"] = item.xpath(".//div[@class='post-title']/text()")[
0
].strip()
# logger.debug(item.xpath(".//div[@class='img-item']/img/@src")[0])
# logger.debug(item.xpath(".//div[@class='img-item']/img/@data-ezsrc")[0])
# entity["image_link"] = item.xpath(".//div[@class='img-item']/img/@src")[
# 0
# ].replace("..", P.ModelSetting.get("ohli24_url"))
if len(item.xpath(".//div[@class='img-item']/img/@src")) > 0:
entity["image_link"] = item.xpath(
".//div[@class='img-item']/img/@src"
)[0].replace("..", P.ModelSetting.get("ohli24_url"))
else:
entity["image_link"] = item.xpath(
".//div[@class='img-item']/img/@data-ezsrc"
)[0]
2022-04-06 23:45:15 +09:00
data["ret"] = "success"
data["anime_list"].append(entity)
return data
except Exception as e:
P.logger.error("Exception:%s", e)
P.logger.error(traceback.format_exc())
return {"ret": "exception", "log": str(e)}
2022-06-26 21:46:16 +09:00
def get_auto_anime_info(self, url: str = ""):
try:
logger.info("url:::> %s", url)
data = {}
response_data = LogicOhli24.get_html(url, timeout=10)
tree = html.fromstring(response_data)
tmp_items = tree.xpath('//div[@class="list-row"]')
data["anime_count"] = len(tmp_items)
data["anime_list"] = []
for item in tmp_items:
entity = {}
entity["link"] = item.xpath(".//a/@href")[0]
entity["code"] = entity["link"].split("/")[-1]
entity["title"] = item.xpath(".//div[@class='post-title']/text()")[
0
].strip()
entity["image_link"] = item.xpath(".//div[@class='img-item']/img/@src")[
0
].replace("..", P.ModelSetting.get("ohli24_url"))
data["ret"] = "success"
data["anime_list"].append(entity)
return data
except Exception as e:
P.logger.error("Exception:%s", e)
P.logger.error(traceback.format_exc())
return {"ret": "exception", "log": str(e)}
# @staticmethod
2022-04-17 18:00:43 +09:00
def get_search_result(self, query, page, cate):
try:
_query = urllib.parse.quote(query)
url = (
P.ModelSetting.get("ohli24_url")
+ "/bbs/search.php?srows=24&gr_id=&sfl=wr_subject&stx="
+ _query
2022-04-17 18:00:43 +09:00
+ "&page="
+ page
)
2022-04-17 14:07:00 +09:00
logger.info("get_search_result()::url> %s", url)
data = {}
response_data = LogicOhli24.get_html(url, timeout=10)
tree = html.fromstring(response_data)
tmp_items = tree.xpath('//div[@class="list-row"]')
data["anime_count"] = len(tmp_items)
data["anime_list"] = []
for item in tmp_items:
entity = {}
entity["link"] = item.xpath(".//a/@href")[0]
# entity["code"] = entity["link"].split("/")[-1]
entity["wr_id"] = entity["link"].split("=")[-1]
# logger.debug(item.xpath(".//div[@class='post-title']/text()").join())
entity["title"] = "".join(
item.xpath(".//div[@class='post-title']/text()")
).strip()
entity["image_link"] = item.xpath(".//div[@class='img-item']/img/@src")[
0
].replace("..", P.ModelSetting.get("ohli24_url"))
entity["code"] = item.xpath(".//div[@class='img-item']/img/@alt")[0]
data["ret"] = "success"
data["anime_list"].append(entity)
return data
except Exception as e:
P.logger.error("Exception:%s", e)
2022-04-06 23:45:15 +09:00
P.logger.error(traceback.format_exc())
return {"ret": "exception", "log": str(e)}
2022-02-10 00:34:14 +09:00
def check_for_new_post(self):
# Get the HTML content of the page
res = requests.get(
f'{P.ModelSetting.get("ohli24_url")}/bbs/board.php?bo_table=ing'
)
soup = BeautifulSoup(res.content, "html.parser")
# Find the latest post on the page
latest_post = soup.find("div", class_="post-title").text
latest_post_image = (
soup.find("div", class_="img-item")
.find("img", class_="wr-img")
.get("src")
.replace("..", P.ModelSetting.get("ohli24_url"))
)
logger.debug(f"latest_post:: {latest_post}")
logger.debug(f"self.last_post_title:: {self.last_post_title}")
logger.debug(f"latest_post_image:: {latest_post_image}")
# Compare the latest post with the last recorded post
if latest_post != self.last_post_title:
# If there is a new post, update the last recorded post
self.last_post_title = latest_post
# Send a notification to Discord channel
# discord_client = discord.Client()
# discord_client.run(self.DISCORD_BOT_TOKEN)
#
# async def on_ready():
# channel = discord_client.get_channel(self.DISCORD_CHANNEL_ID)
# await channel.send(f"A new post has been added: {latest_post}")
#
# discord_client.close()
webhook = DiscordWebhook(url=self.discord_webhook_url)
embed = DiscordEmbed(title=self.discord_title, color=self.discord_color)
embed.set_timestamp()
path = self.last_post_title
embed.set_image(url=latest_post_image)
embed.add_embed_field(name="", value=path, inline=True)
embed.set_timestamp()
webhook.add_embed(embed)
response = webhook.execute()
return self.last_post_title
return self.last_post_title
def send_notify(self):
logger.debug("send_notify() routine")
while True:
self.last_post_title = self.check_for_new_post()
logger.debug(self.last_post_title)
time.sleep(600)
2022-03-27 18:26:18 +09:00
# @staticmethod
def plugin_load(self):
2022-02-08 23:17:30 +09:00
try:
2022-04-06 23:45:15 +09:00
logger.debug("%s plugin_load", P.package_name)
self.queue = FfmpegQueue(
P, P.ModelSetting.get_int("ohli24_max_ffmpeg_process_count")
)
2022-03-27 18:26:18 +09:00
self.current_data = None
self.queue.queue_start()
2022-02-08 23:17:30 +09:00
logger.debug(P.ModelSetting.get_bool("ohli24_discord_notify"))
if P.ModelSetting.get_bool("ohli24_discord_notify"):
self.send_notify()
2022-02-08 23:17:30 +09:00
except Exception as e:
2022-04-06 23:45:15 +09:00
logger.error("Exception:%s", e)
2022-02-08 23:17:30 +09:00
logger.error(traceback.format_exc())
@staticmethod
def plugin_unload():
try:
2022-04-06 23:45:15 +09:00
logger.debug("%s plugin_unload", P.package_name)
scheduler.remove_job("%s_recent" % P.package_name)
2022-02-08 23:17:30 +09:00
except Exception as e:
2022-04-06 23:45:15 +09:00
logger.error("Exception:%s", e)
2022-02-08 23:17:30 +09:00
logger.error(traceback.format_exc())
@staticmethod
def reset_db() -> bool:
db.session.query(ModelOhli24Item).delete()
db.session.commit()
return True
2022-02-10 00:34:14 +09:00
@staticmethod
@yommi_timeit
2023-01-13 20:14:11 +09:00
def get_html(
url, headers=None, referer=None, stream=False, timeout=10, stealth=False
2023-01-13 20:14:11 +09:00
):
2023-01-15 17:10:34 +09:00
# global response_data
2022-04-06 23:45:15 +09:00
data = ""
2023-01-15 17:10:34 +09:00
# response_date = ""
logger.debug(f"url: {url}")
2022-02-10 00:34:14 +09:00
try:
2022-03-27 18:26:18 +09:00
2023-01-13 20:14:11 +09:00
print("cloudflare protection bypass ==================P")
2023-01-15 17:10:34 +09:00
response_date = ""
2023-01-13 20:14:11 +09:00
if headers is not None:
LogicOhli24.headers = headers
# logger.debug(f"headers: {LogicOhli24.headers}")
2023-01-15 17:02:14 +09:00
# response_data = asyncio.run(
# LogicOhli24.get_html_playwright(
# url,
# headless=True,
# # referer=referer_url,
# engine="chrome",
# # stealth=True,
# )
# )
# # print(response_data)
#
# logger.debug(len(response_data))
2023-01-13 20:14:11 +09:00
2023-01-15 17:02:14 +09:00
# return response_data
2023-01-13 20:14:11 +09:00
2023-01-15 17:02:14 +09:00
if LogicOhli24.session is None:
LogicOhli24.session = requests.session()
2023-01-13 20:14:11 +09:00
LogicOhli24.session.verify = False
2023-01-15 17:02:14 +09:00
# logger.debug('get_html :%s', url)
2023-01-15 17:43:12 +09:00
# LogicOhli24.headers["Referer"] = "" if referer is None else referer
# logger.debug(f"referer:: {referer}")
2023-01-15 17:43:12 +09:00
if referer:
LogicOhli24.headers["Referer"] = referer
2023-01-15 17:02:14 +09:00
2023-01-15 17:43:12 +09:00
# logger.info(headers)
# logger.debug(f"LogicOhli24.headers:: {LogicOhli24.headers}")
proxies = {
"http": "http://192.168.0.2:3138",
"https": "http://192.168.0.2:3138",
}
2023-01-15 17:02:14 +09:00
page_content = LogicOhli24.session.get(
url, headers=LogicOhli24.headers, timeout=timeout, proxies=proxies
2023-01-15 17:02:14 +09:00
)
response_data = page_content.text
2023-01-15 17:43:12 +09:00
# logger.debug(response_data)
2023-01-15 17:05:52 +09:00
return response_data
2022-02-10 00:34:14 +09:00
except Exception as e:
2022-04-06 23:45:15 +09:00
logger.error("Exception:%s", e)
2022-02-10 00:34:14 +09:00
logger.error(traceback.format_exc())
2023-01-15 17:10:34 +09:00
# return response_data
2022-02-10 00:34:14 +09:00
2022-03-27 18:26:18 +09:00
#########################################################
def add(self, episode_info):
if self.is_exist(episode_info):
2022-04-06 23:45:15 +09:00
return "queue_exist"
2022-03-27 18:26:18 +09:00
else:
2022-04-06 23:45:15 +09:00
db_entity = ModelOhli24Item.get_by_ohli24_id(episode_info["_id"])
# logger.debug("db_entity:::> %s", db_entity)
2022-03-27 18:26:18 +09:00
if db_entity is None:
entity = Ohli24QueueEntity(P, self, episode_info)
# logger.debug("entity:::> %s", entity.as_dict())
2022-03-27 18:26:18 +09:00
ModelOhli24Item.append(entity.as_dict())
# logger.debug("entity:: type >> %s", type(entity))
2022-03-27 18:26:18 +09:00
self.queue.add_queue(entity)
2022-04-06 23:45:15 +09:00
return "enqueue_db_append"
elif db_entity.status != "completed":
2022-03-27 18:26:18 +09:00
entity = Ohli24QueueEntity(P, self, episode_info)
self.queue.add_queue(entity)
2022-04-06 23:45:15 +09:00
return "enqueue_db_exist"
2022-03-27 18:26:18 +09:00
else:
2022-04-06 23:45:15 +09:00
return "db_completed"
2022-03-27 18:26:18 +09:00
def is_exist(self, info):
for e in self.queue.entity_list:
2022-04-06 23:45:15 +09:00
if e.info["_id"] == info["_id"]:
2022-03-27 18:26:18 +09:00
return True
return False
2022-02-08 23:17:30 +09:00
class Ohli24QueueEntity(FfmpegQueueEntity):
def __init__(self, P, module_logic, info):
super(Ohli24QueueEntity, self).__init__(P, module_logic, info)
2022-03-27 18:26:18 +09:00
self._vi = None
self.url = None
self.epi_queue = None
self.filepath = None
self.savepath = None
self.quality = None
self.filename = None
2022-02-08 23:17:30 +09:00
self.vtt = None
self.season = 1
self.content_title = None
2022-03-27 18:26:18 +09:00
self.srt_url = None
self.headers = None
# Todo::: 임시 주석 처리
self.make_episode_info()
def refresh_status(self):
2022-04-06 23:45:15 +09:00
self.module_logic.socketio_callback("status", self.as_dict())
2022-03-27 18:26:18 +09:00
def info_dict(self, tmp):
# logger.debug('self.info::> %s', self.info)
for key, value in self.info.items():
tmp[key] = value
2022-04-06 23:45:15 +09:00
tmp["vtt"] = self.vtt
tmp["season"] = self.season
tmp["content_title"] = self.content_title
tmp["ohli24_info"] = self.info
tmp["epi_queue"] = self.epi_queue
2022-03-27 18:26:18 +09:00
return tmp
def donwload_completed(self):
2022-04-06 23:45:15 +09:00
db_entity = ModelOhli24Item.get_by_ohli24_id(self.info["_id"])
2022-03-27 18:26:18 +09:00
if db_entity is not None:
2022-04-06 23:45:15 +09:00
db_entity.status = "completed"
2022-03-27 18:26:18 +09:00
db_entity.complated_time = datetime.now()
db_entity.save()
# Get episode info from OHLI24 site
2022-06-26 21:46:16 +09:00
def make_episode_info(self):
try:
base_url = "https://a18.ohli24.com"
base_url = P.ModelSetting.get("ohli24_url")
2022-06-26 21:46:16 +09:00
iframe_url = ""
2023-01-15 16:46:48 +09:00
# https://ohli24.org/e/%EB%85%B9%EC%9D%84%20%EB%A8%B9%EB%8A%94%20%EB%B9%84%EC%8A%A4%EC%BD%94%206%ED%99%94
2022-06-26 21:46:16 +09:00
url = self.info["va"]
ourls = parse.urlparse(url)
headers = {
2023-01-15 17:43:12 +09:00
"Referer": f"{ourls.scheme}://{ourls.netloc}",
2023-01-15 16:46:48 +09:00
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) "
"Chrome/96.0.4664.110 Whale/3.12.129.46 Safari/537.36",
2022-06-26 21:46:16 +09:00
}
2023-01-15 17:43:12 +09:00
logger.debug(headers)
2022-06-26 21:46:16 +09:00
logger.debug("make_episode_info()::url==> %s", url)
logger.info(f"self.info:::> {self.info}")
2023-01-13 20:14:11 +09:00
# text = requests.get(url, headers=headers).text
2023-01-15 17:43:12 +09:00
text = LogicOhli24.get_html(
url, headers=headers, referer=f"{ourls.scheme}://{ourls.netloc}"
)
2022-06-26 21:46:16 +09:00
# logger.debug(text)
soup1 = BeautifulSoup(text, "lxml")
pattern = re.compile(r"url : \"\.\.(.*)\"")
script = soup1.find("script", text=pattern)
if script:
match = pattern.search(script.text)
if match:
iframe_url = match.group(1)
logger.info("iframe_url::> %s", iframe_url)
# try:
# iframe_url = soup1.find("iframe")["src"]
# except:
#
# pattern = r"\.\.\/(.*stream.php.*)"
#
# match = re.search(pattern, text, re.MULTILINE)
# if match:
# print(match)
# matched_line = match.group(0)
# print(matched_line)
# iframe_url = "https://ohli24.org/"
iframe_src = f'{P.ModelSetting.get("ohli24_url")}{iframe_url}'
iframe_html = LogicOhli24.get_html(iframe_src, headers=headers, timeout=600)
# print(iframe_html)
pattern = r"<iframe src=\"(.*?)\" allowfullscreen>"
match = re.search(pattern, iframe_html)
if match:
iframe_src = match.group(1)
print(iframe_src)
2022-06-26 21:46:16 +09:00
logger.debug(f"iframe_src:::> {iframe_src}")
2022-06-26 21:46:16 +09:00
2023-01-13 20:14:11 +09:00
# resp1 = requests.get(iframe_src, headers=headers, timeout=600).text
resp1 = LogicOhli24.get_html(iframe_src, headers=headers, timeout=600)
# logger.info("resp1::>> %s", resp1)
2022-06-26 21:46:16 +09:00
soup3 = BeautifulSoup(resp1, "lxml")
# packed_pattern = re.compile(r'\\{*(eval.+)*\\}', re.MULTILINE | re.DOTALL)
s_pattern = re.compile(r"(eval.+)", re.MULTILINE | re.DOTALL)
packed_pattern = re.compile(
r"if?.([^{}]+)\{.*(eval.+)\}.+else?.{.(eval.+)\}", re.DOTALL
)
packed_script = soup3.find("script", text=s_pattern)
# packed_script = soup3.find('script')
2022-10-30 00:14:17 +09:00
# logger.info("packed_script>>> %s", packed_script.text)
2022-06-26 21:46:16 +09:00
unpack_script = None
if packed_script is not None:
# logger.debug('zzzzzzzzzzzz')
match = packed_pattern.search(packed_script.text)
# match = re.search(packed_pattern, packed_script.text)
# logger.debug("match::: %s", match.group())
2022-10-30 00:14:17 +09:00
# unpack_script = jsbeautifier.beautify(match.group(3))
logger.debug(type(packed_script))
unpack_script = jsbeautifier.beautify(str(packed_script))
2022-06-26 21:46:16 +09:00
p1 = re.compile(r"(\"tracks\".*\])\,\"captions\"", re.MULTILINE | re.DOTALL)
m2 = re.search(
r"(\"tracks\".*\]).*\"captions\"",
unpack_script,
flags=re.MULTILINE | re.DOTALL,
)
# print(m2.group(1))
dict_string = "{" + m2.group(1) + "}"
2023-01-29 21:21:50 +09:00
# logger.info(f"dict_string::> {dict_string}")
2022-06-26 21:46:16 +09:00
tracks = json.loads(dict_string)
self.srt_url = tracks["tracks"][0]["file"]
logger.debug(f'srt_url::: {tracks["tracks"][0]["file"]}')
video_hash = iframe_src.split("/")
video_hashcode = re.sub(r"index\.php\?data=", "", video_hash[-1])
self._vi = video_hashcode
video_info_url = f"{video_hash[0]}//{video_hash[2]}/player/index.php?data={video_hashcode}&do=getVideo"
# print('hash:::', video_hash)
logger.debug(f"video_info_url::: {video_info_url}")
headers = {
"referer": f"{iframe_src}",
"user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) "
"Chrome/96.0.4664.110 Whale/3.12.129.46 Safari/537.36"
"Mozilla/5.0 (Macintosh; Intel "
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) "
"Chrome/116.0.0.0 Safari/537.36"
2022-06-26 21:46:16 +09:00
"Whale/3.12.129.46 Safari/537.36",
"X-Requested-With": "XMLHttpRequest",
"Cookie": "PHPSESSID=b6hnl2crfvtg36sm6rjjkso4p0; 2a0d2363701f23f8a75028924a3af643=MTgwLjY2LjIyMi4xODk%3D; _ga=GA1.1.586565509.1695135593; __gads=ID=60e47defb3337e02-227f0fc9e3e3009a:T=1695135593:RT=1695135593:S=ALNI_MagY46XGCbx9E4Et2DRzfUHdTAKsg; __gpi=UID=00000c4bb3d077c8:T=1695135593:RT=1695135593:S=ALNI_MYvj_8OjdhtGPEGoXhPsQWq1qye8Q; _ga_MWWDFMDJR0=GS1.1.1695135593.1.1.1695135599.0.0.0",
2022-06-26 21:46:16 +09:00
}
2022-12-21 21:25:56 +09:00
2022-06-26 21:46:16 +09:00
payload = {
"hash": video_hash[-1],
}
resp2 = requests.post(
video_info_url, headers=headers, data=payload, timeout=20
).json()
logger.debug("resp2::> %s", resp2)
hls_url = resp2["videoSource"]
logger.debug(f"video_url::> {hls_url}")
resp3 = requests.get(hls_url, headers=headers).text
# logger.debug(resp3)
# stream_url = hls_url.split('\n')[-1].strip()
stream_info = resp3.split("\n")[-2:]
# logger.debug('stream_url:: %s', stream_url)
logger.debug(f"stream_info:: {stream_info}")
self.headers = {
"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
"Chrome/71.0.3554.0 Safari/537.36Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
"AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3554.0 Safari/537.36",
"Referer": "https://ndoodle.xyz/video/03a3655fff3e9bdea48de9f49e938e32",
}
self.url = stream_info[1].strip()
logger.info(self.url)
if "anibeast.com" in self.url:
self.headers["Referer"] = iframe_src
if "crazypatutu.com" in self.url:
self.headers["Referer"] = iframe_src
2022-06-26 21:46:16 +09:00
match = re.compile(r'NAME="(?P<quality>.*?)"').search(stream_info[0])
self.quality = "720P"
if match is not None:
self.quality = match.group("quality")
logger.info(self.quality)
match = re.compile(
r"(?P<title>.*?)\s*((?P<season>\d+)%s)?\s*((?P<epi_no>\d+)%s)"
% ("", "")
).search(self.info["title"])
# epi_no 초기값
epi_no = 1
if match:
self.content_title = match.group("title").strip()
if "season" in match.groupdict() and match.group("season") is not None:
self.season = int(match.group("season"))
# epi_no = 1
epi_no = int(match.group("epi_no"))
ret = "%s.S%sE%s.%s-OHNI24.mp4" % (
self.content_title,
"0%s" % self.season if self.season < 10 else self.season,
"0%s" % epi_no if epi_no < 10 else epi_no,
self.quality,
)
else:
self.content_title = self.info["title"]
P.logger.debug("NOT MATCH")
ret = "%s.720p-OHNI24.mp4" % self.info["title"]
# logger.info('self.content_title:: %s', self.content_title)
self.epi_queue = epi_no
self.filename = Util.change_text_for_use_filename(ret)
logger.info(f"self.filename::> {self.filename}")
self.savepath = P.ModelSetting.get("ohli24_download_path")
logger.info(f"self.savepath::> {self.savepath}")
# TODO: 완결 처리
if P.ModelSetting.get_bool("ohli24_auto_make_folder"):
if self.info["day"].find("완결") != -1:
folder_name = "%s %s" % (
P.ModelSetting.get("ohli24_finished_insert"),
self.content_title,
)
else:
folder_name = self.content_title
folder_name = Util.change_text_for_use_filename(folder_name.strip())
self.savepath = os.path.join(self.savepath, folder_name)
if P.ModelSetting.get_bool("ohli24_auto_make_season_folder"):
self.savepath = os.path.join(
self.savepath, "Season %s" % int(self.season)
)
self.filepath = os.path.join(self.savepath, self.filename)
if not os.path.exists(self.savepath):
os.makedirs(self.savepath)
from framework.common.util import write_file, convert_vtt_to_srt
srt_filepath = os.path.join(
self.savepath, self.filename.replace(".mp4", ".ko.srt")
)
2023-01-29 21:21:50 +09:00
if (
self.srt_url is not None
and not os.path.exists(srt_filepath)
and not ("thumbnails.vtt" in self.srt_url)
):
2022-06-26 21:46:16 +09:00
srt_data = requests.get(self.srt_url, headers=headers).text
write_file(srt_data, srt_filepath)
except Exception as e:
P.logger.error("Exception:%s", e)
P.logger.error(traceback.format_exc())
2022-02-08 23:17:30 +09:00
class ModelOhli24Item(db.Model):
2022-04-06 23:45:15 +09:00
__tablename__ = "{package_name}_ohli24_item".format(package_name=P.package_name)
__table_args__ = {"mysql_collate": "utf8_general_ci"}
2022-02-08 23:17:30 +09:00
__bind_key__ = P.package_name
id = db.Column(db.Integer, primary_key=True)
created_time = db.Column(db.DateTime)
completed_time = db.Column(db.DateTime)
reserved = db.Column(db.JSON)
content_code = db.Column(db.String)
season = db.Column(db.Integer)
episode_no = db.Column(db.Integer)
title = db.Column(db.String)
episode_title = db.Column(db.String)
2022-03-27 18:26:18 +09:00
ohli24_va = db.Column(db.String)
ohli24_vi = db.Column(db.String)
ohli24_id = db.Column(db.String)
2022-02-08 23:17:30 +09:00
quality = db.Column(db.String)
filepath = db.Column(db.String)
filename = db.Column(db.String)
savepath = db.Column(db.String)
video_url = db.Column(db.String)
vtt_url = db.Column(db.String)
thumbnail = db.Column(db.String)
status = db.Column(db.String)
ohli24_info = db.Column(db.JSON)
def __init__(self):
self.created_time = datetime.now()
def __repr__(self):
return repr(self.as_dict())
def as_dict(self):
ret = {x.name: getattr(self, x.name) for x in self.__table__.columns}
2022-04-06 23:45:15 +09:00
ret["created_time"] = self.created_time.strftime("%Y-%m-%d %H:%M:%S")
ret["completed_time"] = (
self.completed_time.strftime("%Y-%m-%d %H:%M:%S")
if self.completed_time is not None
else None
)
2022-02-08 23:17:30 +09:00
return ret
def save(self):
db.session.add(self)
db.session.commit()
@classmethod
2022-03-27 18:26:18 +09:00
def get_by_id(cls, idx):
return db.session.query(cls).filter_by(id=idx).first()
2022-02-08 23:17:30 +09:00
@classmethod
2022-03-27 18:26:18 +09:00
def get_by_ohli24_id(cls, ohli24_id):
return db.session.query(cls).filter_by(ohli24_id=ohli24_id).first()
2022-02-08 23:17:30 +09:00
@classmethod
2022-03-27 18:26:18 +09:00
def delete_by_id(cls, idx):
db.session.query(cls).filter_by(id=idx).delete()
2022-02-08 23:17:30 +09:00
db.session.commit()
return True
@classmethod
def web_list(cls, req):
ret = {}
2022-04-06 23:45:15 +09:00
page = int(req.form["page"]) if "page" in req.form else 1
2022-02-08 23:17:30 +09:00
page_size = 30
2022-04-06 23:45:15 +09:00
job_id = ""
search = req.form["search_word"] if "search_word" in req.form else ""
option = req.form["option"] if "option" in req.form else "all"
order = req.form["order"] if "order" in req.form else "desc"
2022-02-08 23:17:30 +09:00
query = cls.make_query(search=search, order=order, option=option)
count = query.count()
query = query.limit(page_size).offset((page - 1) * page_size)
lists = query.all()
2022-04-06 23:45:15 +09:00
ret["list"] = [item.as_dict() for item in lists]
ret["paging"] = Util.get_paging_info(count, page, page_size)
2022-02-08 23:17:30 +09:00
return ret
@classmethod
2022-04-06 23:45:15 +09:00
def make_query(cls, search="", order="desc", option="all"):
2022-02-08 23:17:30 +09:00
query = db.session.query(cls)
2022-04-06 23:45:15 +09:00
if search is not None and search != "":
if search.find("|") != -1:
tmp = search.split("|")
2022-02-08 23:17:30 +09:00
conditions = []
for tt in tmp:
2022-04-06 23:45:15 +09:00
if tt != "":
conditions.append(cls.filename.like("%" + tt.strip() + "%"))
2022-02-08 23:17:30 +09:00
query = query.filter(or_(*conditions))
2022-04-06 23:45:15 +09:00
elif search.find(",") != -1:
tmp = search.split(",")
2022-02-08 23:17:30 +09:00
for tt in tmp:
2022-04-06 23:45:15 +09:00
if tt != "":
query = query.filter(cls.filename.like("%" + tt.strip() + "%"))
2022-02-08 23:17:30 +09:00
else:
2022-04-06 23:45:15 +09:00
query = query.filter(cls.filename.like("%" + search + "%"))
if option == "completed":
query = query.filter(cls.status == "completed")
2022-02-08 23:17:30 +09:00
2022-04-06 23:45:15 +09:00
query = (
query.order_by(desc(cls.id)) if order == "desc" else query.order_by(cls.id)
)
2022-02-08 23:17:30 +09:00
return query
@classmethod
def get_list_uncompleted(cls):
2022-04-06 23:45:15 +09:00
return db.session.query(cls).filter(cls.status != "completed").all()
2022-02-08 23:17:30 +09:00
@classmethod
def append(cls, q):
item = ModelOhli24Item()
2022-04-06 23:45:15 +09:00
item.content_code = q["content_code"]
item.season = q["season"]
item.episode_no = q["epi_queue"]
item.title = q["content_title"]
item.episode_title = q["title"]
item.ohli24_va = q["va"]
item.ohli24_vi = q["_vi"]
item.ohli24_id = q["_id"]
item.quality = q["quality"]
item.filepath = q["filepath"]
item.filename = q["filename"]
item.savepath = q["savepath"]
item.video_url = q["url"]
item.vtt_url = q["vtt"]
item.thumbnail = q["thumbnail"]
item.status = "wait"
item.ohli24_info = q["ohli24_info"]
2022-02-08 23:17:30 +09:00
item.save()