Tampermonkey
입니다
// ==UserScript==
// @name 69shuba 통합 타겟 크롤러
// @version 8.0
// @description 모든 69shuba 소설 페이지에서 타겟 화수 입력 후 순차 크롤링
// @author Gemini
// @match https://www.69shuba.com/book/*
// @match https://www.69shuba.com/txt/*
// @grant none
// ==/UserScript==
(function() {
'use strict';
// UI 생성
const panel = document.createElement('div');
panel.style.cssText = 'position:fixed; top:20px; right:20px; z-index:9999; background:#fff; border:2px solid #333; padding:15px; border-radius:8px; width:220px;';
panel.innerHTML = `
<h4 style="margin:0 0 10px 0;">소설 크롤러</h4>
<input id="chList" type="text" placeholder="예: 6, 7, 8 또는 6 7 8" style="width:100%; margin-bottom:5px;">
<input id="delay" type="number" value="3.0" step="0.5" style="width:50px;">초 간격<br>
<button id="btnStart" style="margin-top:10px; width:100%;">시작하기</button>
`;
document.body.appendChild(panel);
document.getElementById('btnStart').onclick = () => {
const raw = document.getElementById('chList').value;
const delay = parseFloat(document.getElementById('delay').value) * 1000;
// 쉼표나 공백으로 숫자 추출
const targetNumbers = raw.split(/[\s,]+/).filter(x => x !== "").map(Number);
if (targetNumbers.length === 0) return alert('화수를 입력하세요');
localStorage.setItem('target_chapters', JSON.stringify(targetNumbers));
localStorage.setItem('crawl_delay', delay);
localStorage.setItem('crawl_status', 'running');
localStorage.setItem('novel_data', '');
location.reload();
};
// 크롤링 로직
if (localStorage.getItem('crawl_status') === 'running') {
if (window.location.href.includes('/book/')) {
const queue = [];
const targetNumbers = JSON.parse(localStorage.getItem('target_chapters'));
document.querySelectorAll('#catalog ul li a').forEach(a => {
const match = a.innerText.match(/第(\d+)章/);
if (match && targetNumbers.includes(parseInt(match[1]))) queue.push(a.href);
});
localStorage.setItem('crawler_queue', JSON.stringify(queue));
localStorage.setItem('crawler_index', 0);
window.location.href = queue[0];
}
else if (window.location.href.includes('/txt/')) {
const delay = parseInt(localStorage.getItem('crawl_delay'));
setTimeout(() => {
const title = document.querySelector('h1')?.innerText || '제목없음';
const content = document.querySelector('.txtnav')?.innerText || '';
let data = localStorage.getItem('novel_data') || '';
localStorage.setItem('novel_data', data + `\n\n=== ${title} ===\n\n${content}`);
let queue = JSON.parse(localStorage.getItem('crawler_queue') || '[]');
let index = parseInt(localStorage.getItem('crawler_index') || 0);
if (index < queue.length - 1) {
localStorage.setItem('crawler_index', index + 1);
window.location.href = queue[index + 1];
} else {
const blob = new Blob([localStorage.getItem('novel_data')], {type:'text/plain'});
const a = document.createElement('a');
a.href = URL.createObjectURL(blob);
a.download = 'novel_export.txt';
a.click();
localStorage.clear();
alert('완료! 파일이 다운로드되었습니다.');
}
}, delay);
}
}
})();
검도 제일선 볼려는데 누락이 너무 많아서 다운받다가 꼴받아서 만듬;;
일단
6, 7, 8, 11, 19, 29, 31, 49, 93, 119, 123, 147, 156, 157, 208, 209, 210, 211, 260, 265, 266, 288, 289, 427, 502, 505, 517, 566, 568, 569, 570, 571, 572, 573, 574, 627, 630, 631, 632, 638, 639, 645, 699, 714, 767, 777, 811, 812, 839, 848, 905, 927, 928, 937, 938, 939, 940, 945, 968, 969, 984, 1030, 1032, 1033, 1034, 1035, 1036, 1037, 1038, 1039, 1088, 1091, 1092, 1093, 1096, 1139, 1173, 1174, 1175, 1192, 1193, 1194, 1195, 1196, 1213, 1251, 1252, 1255, 1311, 1361, 1363, 1368, 1398, 1419, 1441, 1469, 1476, 1477, 1485, 1518, 1538, 1558, 1567, 1629, 1630, 1840, 1841, 1887, 1888, 1905, 1906, 1907, 1913, 1942, 1943, 1944, 1960, 1999, 2000, 2001, 2002, 2003, 2032, 2033, 2074, 2125, 2195, 2211, 2222, 2223, 2316, 2405, 2430, 2463, 2470, 2475, 2544, 2641, 2751, 2810, 2843, 3046, 3053, 3082, 3137, 3176, 3205, 3237, 3247, 3282, 3316, 3370, 3388, 3549, 3672
화 누락파일 원본 받은거만 올려드림 필요하시면 각자 알아서 번역해서 보시면 될듯
aHR0cHM6Ly9raW8uYWMvYy9keDJTQWpmT1dkS0xuOVNwRGFVNVdi
1주/국룰
제([0-9]+(장|화).*) 형식 기준으로 텍스트 파일 두개 정렬해서 합치는 파이썬입니다
////
import tkinter as tk
from tkinter import ttk, filedialog, messagebox, scrolledtext
import re
import os
from collections import defaultdict
def read_file_with_detected_encoding(filepath):
"""파일 인코딩을 감지하여 텍스트를 읽어옵니다."""
try:
with open(filepath, 'rb') as f:
raw_data = f.read()
except Exception as e:
return None
if raw_data.startswith(b'\xff\xfe'): return raw_data[2:].decode('utf-16-le', errors='ignore')
if raw_data.startswith(b'\xfe\xff'): return raw_data[2:].decode('utf-16-be', errors='ignore')
if raw_data.startswith(b'\xef\xbb\xbf'): return raw_data[3:].decode('utf-8', errors='ignore')
for enc in ('utf-8', 'cp949', 'euc-kr', 'utf-16'):
try: return raw_data.decode(enc)
except UnicodeDecodeError: continue
return raw_data.decode('utf-8', errors='ignore')
def save_file_utf16_crlf(filepath, content):
"""결과를 UTF-16 LE BOM 형식으로 저장합니다."""
try:
fixed_content = content.replace('\r\n', '\n').replace('\r', '\n').replace('\n', '\r\n')
data = ('\ufeff' + fixed_content).encode('utf-16-le')
with open(filepath, 'wb') as f:
f.write(data)
return True, None
except Exception as e:
return False, str(e)
class ChapterMergerApp:
def __init__(self, root):
self.root = root
self.root.title("장 번호순 파일 병합기 (v1.2)")
self.root.geometry("600x550")
self.path_A = tk.StringVar()
self.path_B = tk.StringVar()
self.create_widgets()
def create_widgets(self):
main_frame = tk.Frame(self.root, padx=20, pady=20)
main_frame.pack(fill="both", expand=True)
tk.Label(main_frame, text="병합할 파일들을 선택하세요 (제n장 기준 정렬)", font=("Malgun Gothic", 12, "bold")).pack(pady=(0, 20))
f1 = tk.Frame(main_frame)
f1.pack(fill="x", pady=5)
tk.Label(f1, text="파일 1:").pack(side="left")
tk.Entry(f1, textvariable=self.path_A, width=50).pack(side="left", padx=5)
tk.Button(f1, text="찾기", command=lambda: self.path_A.set(filedialog.askopenfilename())).pack(side="left")
f2 = tk.Frame(main_frame)
f2.pack(fill="x", pady=5)
tk.Label(f2, text="파일 2:").pack(side="left")
tk.Entry(f2, textvariable=self.path_B, width=50).pack(side="left", padx=5)
tk.Button(f2, text="찾기", command=lambda: self.path_B.set(filedialog.askopenfilename())).pack(side="left")
tk.Button(main_frame, text="번호순 병합 실행", command=self.run_merge,
bg="#E0F7FA", font=("Malgun Gothic", 10, "bold"), height=2).pack(pady=20, fill="x")
self.log_area = scrolledtext.ScrolledText(main_frame, height=15, state="disabled", bg="#F8F8F8")
self.log_area.pack(fill="both", expand=True)
def log(self, msg):
self.log_area.config(state="normal")
self.log_area.insert(tk.END, msg + "\n")
self.log_area.see(tk.END)
self.log_area.config(state="disabled")
def parse_chapters(self, filepath):
content = read_file_with_detected_encoding(filepath)
if not content: return {}
# 줄바꿈 통일 (정규식 처리를 위해)
content = content.replace('\r\n', '\n').replace('\r', '\n')
# 제n장/화 패턴 분리
pattern = re.compile(r'(^제\s*\d+\s*(?:장|화|章|話).*)', re.MULTILINE)
parts = pattern.split(content)
chapter_dict = defaultdict(list)
# 서문 처리
if parts[0].strip():
chapter_dict[0].append(parts[0].strip() + "\n\n")
for i in range(1, len(parts), 2):
title = parts[i].strip()
body = parts[i+1].strip() if i+1 < len(parts) else ""
num_match = re.search(r'(\d+)', title)
num = int(num_match.group(1)) if num_match else 999999
# ★ 핵심 수정: 제목과 본문 사이에 빈 줄(\n\n) 삽입
formatted_chapter = f"{title}\n\n{body}"
chapter_dict[num].append(formatted_chapter)
return chapter_dict
def run_merge(self):
p1, p2 = self.path_A.get(), self.path_B.get()
if not p1 or not p2:
messagebox.showwarning("경고", "파일을 두 개 모두 선택해주세요.")
return
self.log(f"병합 시작...")
try:
data1 = self.parse_chapters(p1)
data2 = self.parse_chapters(p2)
all_numbers = sorted(list(set(data1.keys()) | set(data2.keys())))
final_content = []
for n in all_numbers:
segments = []
if n in data1: segments.extend(data1[n])
if n in data2: segments.extend(data2[n])
for s in segments:
text = s.strip()
if text:
# 각 장과 장 사이에도 빈 줄 추가
final_content.append(text + "\n\n")
save_path = os.path.splitext(p1)[0] + "_merged_ordered.txt"
success, err = save_file_utf16_crlf(save_path, "".join(final_content))
if success:
self.log(f"성공! 정렬된 파일 저장됨: {os.path.basename(save_path)}")
messagebox.showinfo("성공", f"병합 완료!\n저장위치: {save_path}")
else:
self.log(f"저장 실패: {err}")
except Exception as e:
self.log(f"오류: {e}")
messagebox.showerror("오류", str(e))
if __name__ == "__main__":
root = tk.Tk()
app = ChapterMergerApp(root)
root.mainloop()
