import os
import re

base_dir = os.path.dirname(os.path.abspath(__file__))

def parse_rss_feeds(filepath):
    """解析 rss_feeds.txt 格式：源名称|RSS地址"""
    entries = []
    with open(filepath, 'r', encoding='utf-8') as f:
        for line in f:
            line = line.strip()
            if not line or line.startswith('#'):
                continue
            if '|' in line:
                name, url = line.split('|', 1)
                entries.append((name.strip(), url.strip()))
    return entries

def parse_high_quality(filepath):
    """解析高质量列表格式：公众号名称\t公众号ID\tRSS订阅地址"""
    entries = []
    with open(filepath, 'r', encoding='utf-8') as f:
        for line in f:
            line = line.strip()
            if not line or line.startswith('#'):
                continue
            parts = line.split('\t')
            if len(parts) >= 3:
                name = parts[0].strip()
                url = parts[2].strip()
                if url:
                    entries.append((name, url))
    return entries

def main():
    feeds_path = os.path.join(base_dir, 'rss_feeds.txt')
    hq_path = os.path.join(base_dir, 'rss_feed_list_高质量 copy.txt')
    output_path = os.path.join(base_dir, 'rss_feeds_merged.txt')

    feeds_entries = parse_rss_feeds(feeds_path)
    hq_entries = parse_high_quality(hq_path)

    all_entries = feeds_entries + hq_entries

    seen_urls = set()
    unique_entries = []
    for name, url in all_entries:
        if url not in seen_urls:
            seen_urls.add(url)
            unique_entries.append((name, url))

    english_entries = []
    wechat_entries = []
    for name, url in unique_entries:
        if 'werss.yynnice.top' in url:
            wechat_entries.append((name, url))
        else:
            english_entries.append((name, url))

    wechat_entries.sort(key=lambda x: x[0].lower())
    english_entries.sort(key=lambda x: x[0].lower())

    with open(output_path, 'w', encoding='utf-8') as f:
        f.write('# 军事科技RSS订阅源列表（合并版）\n')
        f.write('# 格式：<源名称>|<RSS地址>\n')
        f.write('# 以#开头的行是注释，会自动忽略\n')
        f.write('# 空行也会自动跳过\n')
        f.write('# 合并时间: 2026-05-29\n')
        f.write('\n')

        if english_entries:
            f.write('# 英文军事源\n')
            for name, url in english_entries:
                f.write(f'{name}|{url}\n')
            f.write('\n')

        if wechat_entries:
            f.write('# 中文微信公众号源\n')
            for name, url in wechat_entries:
                f.write(f'{name}|{url}\n')

    print(f'英文源: {len(english_entries)} 个')
    print(f'中文微信公众号源: {len(wechat_entries)} 个')
    print(f'总计: {len(english_entries) + len(wechat_entries)} 个')
    print(f'已写入: {output_path}')

if __name__ == '__main__':
    main()