# -*- coding: utf-8 -*-
"""批量抓取 README.md 中 Super Simple Songs 歌词，保存为 '序号+标题.md'。

- 歌词来源：页面 <select name="languages"> 的语言选项 data-lyrics，
  或侧栏 .lyric-wrapper 的 data-lyrics（英文无独立属性时用后者）。
- 支持断点续跑：已存在的文件直接跳过；失败记入 failed.txt。
"""
import html
import json
import os
import re
import sys
import time
from concurrent.futures import ThreadPoolExecutor, as_completed
from datetime import date

import requests

BASE = os.path.dirname(os.path.abspath(__file__))
OUT_DIR = os.path.join(BASE, "lyrics")
FAILED = os.path.join(BASE, "failed.txt")
UA = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 Chrome/126.0 Safari/537.36"

session = requests.Session()
session.headers["User-Agent"] = UA


def parse_readme(path):
    items = []
    pat = re.compile(r"^\s*(\d+)\.\s+(.+?)\s+(?:—|–|---|--)\s+(https?://\S+)\s*$")
    with open(path, encoding="utf-8") as f:
        for line in f:
            m = pat.match(line)
            if m:
                items.append({"num": int(m.group(1)), "title": m.group(2).strip(), "url": m.group(3)})
    return items


def sanitize_name(name):
    name = re.sub(r'[\\/:*?"<>|]', "-", name)
    return re.sub(r"\s+", " ", name).strip()


def to_plain(lyrics_html):
    s = html.unescape(lyrics_html)
    s = re.sub(r"<br\s*/?>", "\n", s, flags=re.I)
    s = re.sub(r"</p>", "\n\n", s, flags=re.I)
    s = re.sub(r"<[^>]+>", "", s)
    s = re.sub(r"[ \t]+\n", "\n", s)
    s = re.sub(r"\n{3,}", "\n\n", s).strip()
    return s


def extract_lyrics(text):
    """返回 (lyrics_html, source)；找不到返回 (None, None)。"""
    fallback = None
    m = re.search(r'<div[^>]*class="lyric-wrapper[^"]*"[^>]*data-lyrics="([^"]*)"', text)
    if m:
        fallback = m.group(1)
    sel = re.search(r'<select[^>]*name="languages"[^>]*>(.*?)</select>', text, re.S | re.I)
    if sel:
        options = re.findall(r"<option[^>]*>", sel.group(1))
        en = next((o for o in options if re.search(r'value="English"', o)), None)
        chosen = en or next((o for o in options if "selected" in o), options[0] if options else None)
        if chosen:
            dm = re.search(r'data-lyrics="([^"]*)"', chosen)
            if dm:
                return dm.group(1), "select"
            if chosen is en:
                return fallback, "fallback-div"
    if fallback:
        return fallback, "fallback-div"
    return None, None


def fetch_once(url):
    r = session.get(url, timeout=20, headers={"Accept-Language": "en-US,en;q=0.9"})
    r.raise_for_status()
    return r.text


def process(item):
    num, title, url = item["num"], item["title"], item["url"]
    fname = f"{num:03d}-{sanitize_name(title)}.md"
    out_path = os.path.join(OUT_DIR, fname)
    if os.path.exists(out_path) and os.path.getsize(out_path) > 0:
        return num, fname, "skip"
    last_err = None
    for attempt in range(3):
        try:
            text = fetch_once(url)
            break
        except Exception as e:
            last_err = str(e)
            time.sleep(2 + attempt * 2)
    else:
        return num, fname, f"fetch-error: {last_err}"
    lyrics_html, source = extract_lyrics(text)
    if not lyrics_html:
        return num, fname, "no-lyrics"
    lyrics = to_plain(lyrics_html)
    if not lyrics:
        return num, fname, "empty-lyrics"
    body = f"# {num}. {title}\n\n- 来源: {url}\n- 抓取日期: {date.today()}\n\n## 歌词\n\n{lyrics}\n"
    tmp = out_path + ".tmp"
    with open(tmp, "w", encoding="utf-8") as f:
        f.write(body)
    os.replace(tmp, out_path)
    return num, fname, f"ok({len(lyrics)})"


def main():
    items = parse_readme(os.path.join(BASE, "README.md"))
    print(f"共 {len(items)} 首歌")
    os.makedirs(OUT_DIR, exist_ok=True)
    results = []
    with open(FAILED, "w", encoding="utf-8") as fail_f:
        with ThreadPoolExecutor(max_workers=8) as pool:
            futures = {pool.submit(process, it): it for it in items}
            done = 0
            for fut in as_completed(futures):
                num, fname, status = fut.result()
                done += 1
                results.append((num, status))
                if status == "skip":
                    tag = "已存在"
                elif status.startswith("ok"):
                    tag = f"成功 {status}"
                else:
                    tag = f"失败 {status}"
                    fail_f.write(f"{num}\t{fname}\t{status}\n")
                    fail_f.flush()
                print(f"[{done}/{len(items)}] {num:>3} {tag}", flush=True)
    ok = sum(1 for _, s in results if s.startswith("ok"))
    skip = sum(1 for _, s in results if s == "skip")
    bad = [n for n, s in results if s not in ("skip",) and not s.startswith("ok")]
    print(f"\n完成: 新增 {ok}, 已存在 {skip}, 失败 {len(bad)}")
    if bad:
        print("失败序号:", bad)


if __name__ == "__main__":
    main()
