#!/usr/bin/env python3
"""
全南县 - 重点民生项目 (quannan.gov.cn)
https://www.quannan.gov.cn/qnxxxgk/zdmsxm25v/xxgk_list.shtml
UCAP CMS, 详情: /qnxxxgk/zdms25n1/202606/uuid.shtml or /qnxxxgk/zdmsxm25v/...
正文: UCAPCONTENT, 标题: UCAPTITLE
"""
import sys, os, re, time
from datetime import datetime, timezone, timedelta
import requests, urllib3
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
from crawler_lib import push_to_searchdb
urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)

SITE_NAME = "全南县重点民生项目"
BASE_URL = "https://www.quannan.gov.cn"
THREE_YEARS_AGO = (datetime.now(timezone.utc) - timedelta(days=365*3)).strftime("%Y-%m-%d")
MAX_PAGES = 5
HEADERS = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"}

def fetch(url):
    try:
        r = requests.get(url, headers=HEADERS, timeout=20, verify=False)
        r.encoding = 'utf-8'
        return r.text
    except Exception as e:
        print(f"❌ {e}")
        return None

def parse_list(html):
    items = []
    # 列表页条目: <a href="/qnxxxgk/zdms25n1/202606/xxx.shtml">标题</a>
    pattern = r'<a[^>]*href="(/qnxxxgk/[^/]+/\d{6}/[a-f0-9]+\.shtml)"[^>]*>(.*?)</a>'
    for m in re.finditer(pattern, html, re.DOTALL):
        href = m.group(1)
        title = re.sub(r'<[^>]+>', '', m.group(2)).strip()
        if not title or len(title) < 5:
            continue
        if 'xxgk_list' in href or 'javascript' in href:
            continue
        items.append((title, BASE_URL + href))
    return items

def extract_nested(html, tag_start, tag='div'):
    """找到匹配的闭合标签，支持嵌套div"""
    close_tag = f'</{tag}>'
    open_tag = f'<{tag}'
    depth = 0
    i = tag_start
    n = len(html)
    while i < n:
        if html[i:i+4] == '<!--':
            end = html.find('-->', i+4)
            if end > i:
                i = end + 3
            else:
                i += 1
            continue
        if html[i:i+len(close_tag)] == close_tag:
            if depth == 0:
                return html[tag_start:i]
            depth -= 1
            i += len(close_tag)
            continue
        if html[i:i+len(open_tag)] == open_tag and html[i+len(open_tag)] in (' ', '>', '\n', '\t', '\r'):
            depth += 1
            i += len(open_tag)
            continue
        i += 1
    return html[tag_start:]

def fetch_detail(url):
    html = fetch(url)
    if not html:
        return None, None, None
    result = {}
    # 标题: UCAPTITLE
    m = re.search(r'<UCAPTITLE>(.*?)</UCAPTITLE>', html, re.DOTALL)
    if m:
        result["title"] = m.group(1).strip()
    if not result.get("title"):
        m = re.search(r'<h1[^>]*class="article-title"[^>]*>(.*?)</h1>', html, re.DOTALL)
        if m:
            result["title"] = re.sub(r"<[^>]+>", "", m.group(1)).strip()
    if not result.get("title"):
        m = re.search(r'<meta[^>]*name="ArticleTitle"[^>]*content="([^"]+)"', html)
        if m:
            result["title"] = m.group(1)

    # 日期: meta PubDate
    m = re.search(r'<meta[^>]*name="PubDate"[^>]*content="(\d{4}-\d{1,2}-\d{1,2})', html)
    if m:
        result["publish_date"] = m.group(1)

    # 正文: UCAPCONTENT
    m = re.search(r'<UCAPCONTENT>(.*?)</UCAPCONTENT>', html, re.DOTALL)
    if m:
        content = m.group(1).strip()
        if len(content) > 50:
            result["content"] = content

    if not result.get("content"):
        # 兜底: article-content div
        m = re.search(r'class="article-content[^"]*"[^>]*id="zoomcon"[^>]*>', html)
        if m:
            content = extract_nested(html, m.end()).strip()
            content = re.sub(r"<script[^>]*>.*?</script>", "", content, flags=re.DOTALL|re.I)
            content = re.sub(r"<style[^>]*>.*?</style>", "", content, flags=re.DOTALL|re.I)
            if len(content) > 50:
                result["content"] = content

    return result.get("title"), result.get("content"), result.get("publish_date")

def main():
    print(f"\n{'='*50}\n🏠 {SITE_NAME}\n{'='*50}")
    all_list = []
    for page in range(1, MAX_PAGES + 1):
        if page == 1:
            url = "https://www.quannan.gov.cn/qnxxxgk/zdmsxm25v/xxgk_list.shtml"
        else:
            url = f"https://www.quannan.gov.cn/qnxxxgk/zdmsxm25v/xxgk_list_{page}.shtml"
        print(f"\n📄 第 {page} 页...", end=" ", flush=True)
        html = fetch(url)
        if not html:
            print("❌ 请求失败")
            break
        items = parse_list(html)
        if not items:
            print("0 条，结束")
            break
        print(f"✅ {len(items)} 条")
        all_list.extend(items)

    print(f"\n📊 列表总计: {len(all_list)} 条")

    # 去重，只保留含"项目"或"环境影响"的条目
    all_items, seen = [], set()
    for i, (title, url) in enumerate(all_list):
        if "项目" not in title and "环境影响" not in title and "环评" not in title:
            continue
        if url in seen:
            continue
        seen.add(url)
        print(f"  [{i+1}/{len(all_list)}] {title[:60]}...", end=" ", flush=True)
        dt, content, date = fetch_detail(url)
        if dt:
            title = dt
        summary = re.sub(r"<[^>]+>", " ", content or "").strip()[:300]
        summary = re.sub(r"\s+", " ", summary)
        all_items.append({
            "site_name": SITE_NAME,
            "title": title,
            "url": url,
            "content": content or "",
            "pub_date": date or "",
            "summary": summary,
            "tags": SITE_NAME,
        })
        print("✅")
        time.sleep(0.3)

    if all_items:
        push_to_searchdb(all_items, "quannan_zdmsxm")
    print(f"\n✅ 完成! 共 {len(all_items)} 条")

if __name__ == "__main__":
    t0 = time.time()
    main()
    print(f"⏱ 耗时: {time.time() - t0:.1f}s")