#!/usr/bin/env python3
"""
youdao_share_fetch.py - fetch Youdao Note share content (text + images)

Usage:
  python3 youdao_share_fetch.py <share_url_or_noteId> [output_dir]

Examples:
  python3 youdao_share_fetch.py https://share.note.youdao.com/s/DeSF10So /tmp/out
  python3 youdao_share_fetch.py d18bf6b03b7b97656ca8cec07eb31442 /tmp/out
"""

import sys
import os
import re
import json
import html
import urllib.request
import urllib.parse

UA = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'}


def get_note_id(url):
    """Extract note id from share url (short link or full share url)."""
    m = re.search(r'[?&]id=([0-9a-fA-F]{32})', url)
    if m:
        return m.group(1)
    # short link -> follow redirect and re-extract
    req = urllib.request.Request(url, headers=UA)
    resp = urllib.request.urlopen(req, timeout=20)
    final = resp.geturl()
    m = re.search(r'[?&]id=([0-9a-fA-F]{32})', final)
    if m:
        return m.group(1)
    return None


def fetch_note(note_id, unlogin_id='anonymous'):
    """Fetch note JSON via the public read API."""
    url = ('https://note.youdao.com/yws/api/note/' + note_id +
           '?sev=j1&editorType=1&unloginId=' + unlogin_id +
           '&ignoreOwnPassword=true')
    req = urllib.request.Request(url, headers=UA)
    resp = urllib.request.urlopen(req, timeout=30)
    return json.loads(resp.read().decode('utf-8'))


def parse_content(xml_content):
    """Extract text nodes and image source urls from note XML."""
    texts = [html.unescape(t) for t in re.findall(r'<text>([^<]*)</text>', xml_content) if t.strip()]
    imgs = re.findall(r'<source>([^<]+)</source>', xml_content)
    return texts, imgs


def download(url, outpath):
    """Download a resource file to outpath, return byte count."""
    req = urllib.request.Request(url, headers=UA)
    data = urllib.request.urlopen(req, timeout=30).read()
    with open(outpath, 'wb') as f:
        f.write(data)
    return len(data)


def main():
    if len(sys.argv) < 2:
        print(__doc__)
        sys.exit(1)

    target = sys.argv[1]
    outdir = sys.argv[2] if len(sys.argv) > 2 else '.'

    if re.fullmatch(r'[0-9a-fA-F]{32}', target):
        note_id = target
    else:
        note_id = get_note_id(target)
        if not note_id:
            print('ERROR: cannot resolve note id from:', target)
            sys.exit(1)

    print('noteId:', note_id)
    os.makedirs(outdir, exist_ok=True)

    data = fetch_note(note_id)
    print('title:', data.get('tl'))

    texts, imgs = parse_content(data.get('content', ''))
    for t in texts:
        print('TEXT:', t)
    print('images:', len(imgs))

    img_paths = []
    for i, u in enumerate(imgs):
        ext = os.path.splitext(urllib.parse.urlparse(u).path)[1] or '.png'
        p = os.path.join(outdir, 'img_%02d%s' % (i, ext))
        try:
            n = download(u, p)
            img_paths.append(p)
            print('  saved', p, '(%d bytes)' % n)
        except Exception as e:
            print('  FAIL img %d: %s' % (i, e))

    meta = {'noteId': note_id, 'title': data.get('tl'),
            'texts': texts, 'images': img_paths}
    meta_path = os.path.join(outdir, 'meta.json')
    with open(meta_path, 'w', encoding='utf-8') as f:
        json.dump(meta, f, ensure_ascii=False, indent=2)
    print('done. meta ->', meta_path)


if __name__ == '__main__':
    main()