blacktoon_v3.hds

"""
이 스크립트는 더 이상 기능하지 않습니다.
https://github.com/STR-HK/hdl-stubs/ 에서 최신 버전의 스크립트를 다운로드하세요.

This script is no longer functional.
Please download the latest version of the script from https://github.com/STR-HK/hdl-stubs/

このスクリプトはもう機能しません。
最新バージョンのスクリプトを https://github.com/STR-HK/hdl-stubs/ からダウンロードしてください。

此脚本已不再可用。
请从 https://github.com/STR-HK/hdl-stubs/ 下载最新版本的脚本。

Este script ya no funciona.
Por favor, descarga la última versión del script desde https://github.com/STR-HK/hdl-stubs/.

Ce script n'est plus fonctionnel.
Veuillez télécharger la dernière version du script depuis https://github.com/STR-HK/hdl-stubs/.

Этот скрипт больше не работает.
Пожалуйста, скачайте последнюю версию скрипта с https://github.com/STR-HK/hdl-stubs/.
"""

#coding: utf8
#title: Add Blacktoon.com
#author: STR.HK
#comment: Updated at 2021/06/12

import re
from utils import Soup, LazyUrl, Downloader, Session, clean_title
import clf2
import json

class Image(object):
    def __init__(self, src, title, p):
        ext = '.{}'.format(src.split('.')[-1])
        if ext.lower()[1:] not in ['jpg', 'jpeg', 'bmp', 'png', 'gif', 'webm', 'webp']:
            ext = '.jpg'
        self.filename = '{}/{:04}{}'.format(title, p, ext)
        self.url = LazyUrl(src, lambda _: src, self)

def logg(anything):
    log('​'.join(list(str(anything))))

@Downloader.register
class Downloader_Blacktoon(Downloader):
    type = 'blacktoon'
    URLS = [r'regex:blacktoon[0-9]*\.com']
    icon = 'https://blacktoon.net/favicon-red.ico'

    def read(self):
        siteMainURL = 'https://{}'.format(self.url.split('//')[-1].split('/')[0])
        toonNumber = self.url.split('/')[-1].split('.')[0]

        self.title = '{} - Loading Webtoon List...'.format(self.url)
        session = Session()
        res = clf2.solve(self.url, session=session)
        soup = Soup(res['html'], apply_css=True)

        scriptURL = siteMainURL + soup.find_all('script')[21]['src']
        self.title = '{} - Reading Webtoon List...'.format(self.url)
        get = get_list(scriptURL, session)
        ids = get['ids']
        titles = get['titles']

        for d in range(len(ids)):
            self.title = '[{}] {} / {} ( {} / {} ) - Reading...'.format(get_artist(soup), get_title(soup), titles[d], d+1, len(ids))
            for img in get_page_imgs(siteMainURL, toonNumber, d, ids, '[{}] {}'.format(get_artist(soup), titles[d])):
                self.urls.append(img.url)

        self.title = '[{}] {}'.format(get_artist(soup), get_title(soup))
        self.artist = get_artist(soup)

        # 이것으로 폴더 이름이 정해지기 떄문에 반드시 clean_title 해주어야 함
        self.title = clean_title(self.title)
        log('Blacktoon_Downloader: Successfully Downloaded {}'.format(self.title))

def get_list(scriptURL, session):
    res = clf2.solve(scriptURL, session=session)
    absolute = Soup(res['html']).get_text().replace('var clist = ','').replace(';','')
    ids = json.loads(absolute)
    for i, d in enumerate(ids):
        ids[i] = d['id']
    titles = json.loads(absolute)
    for t, i in enumerate(titles):
        titles[t] = i['t']
    return {'ids':ids, 'titles':titles}

def get_title(soup):
    content = soup.find('h3', class_='mt-2')
    title = content.find('b').text.strip()
    return(title)

def get_artist(soup):
    content = soup.find('p', class_='mt-2')
    artist = content.text.strip().split(':')[-1].replace(' ','')
    return(artist)

@try_n(8)
def get_page_imgs(siteMainURL, toonNumber, number, ids, title):
    page = clf2.solve('{}/webtoons/{}/{}.html'.format(siteMainURL, toonNumber, ids[number]))
    page = Soup(page['html'])
    src = page.find('div', {'id':'toon_content_imgs'}).find_all('img')
    imgs = []
    for s, r in enumerate(src):
        try:
            src[s] = r['src']
        except:
            src[s] = 'https://img.blacktoonimg.com/' + r['o_src']
    title = clean_title(title)
    
    for v, w in enumerate(src):
        img = Image(w, title, v+1)
        imgs.append(img)
    return(imgs)

log(u'{}: blacktoon'.format(tr_(u'Site Added')))