#!/usr/bin/env python3
"""
茂名市环境保护产业协会 — 信息公开 (mmhbxh.com)
==============================================
列表: /xxgk/zh-cn/index.html → index_N.html (N=1..7)
详情: /xxgk/xxx/zh-cn/content/post_数字.html
正文: <div class="body"> (含附件链接)
日期: 日期：YYYY-MM-DD text

旧 URL (/18.aspx) 已失效，新 URL 正常工作
"""
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, fetch_page, clean_html, parse_date, extract_date_from_html
urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)

SITE_NAME = "茂名市环境保护产业协会-信息公开"
BASE_URL = "http://www.mmhbxh.com"
LIST_MAIN = "http://www.mmhbxh.com/xxgk/zh-cn/index.html"
MAX_PAGES = 5   # 已知共7页，第8页404
CUTOFF = (datetime.now(timezone.utc) - timedelta(days=365*3)).strftime("%Y-%m-%d")

def fetch(url):
    try:
        r = requests.get(url, timeout=20, verify=False)
        r.encoding = 'utf-8'
        return r.text
    except:
        return None

def parse_list(html):
    """<li><a class="title" href="...">Title</a><span class="date">[YYYY-MM-DD]</span></li>"""
    items = []
    for m in re.finditer(
        r'<li[^>]*>\s*<a[^>]*class="title"[^>]*href="([^"]+)"[^>]*>(.*?)</a>\s*<span[^>]*class="date"[^>]*>\[?(\d{4}-\d{2}-\d{2})\]?</span>',
        html, re.DOTALL
    ):
        href = m.group(1).strip()
        title = re.sub(r'<[^>]+>', '', m.group(2)).strip()
        date = m.group(3).strip()
        if not href.startswith('http'):
            href = BASE_URL + href
        if title and date:
            items.append((title, href, date))
    return items

def fetch_detail(url):
    """提取详情页：h1标题, 日期, .body正文"""
    html = fetch(url)
    if not html:
        return "", "", ""

    # 标题 — h1
    title = ""
    m = re.search(r'<h1[^>]*>(.*?)</h1>', html, re.DOTALL)
    if m:
        title = re.sub(r'<[^>]+>', '', m.group(1)).strip()

    # 日期 — "日期：YYYY-MM-DD" 文本
    pub_date = ""
    m = re.search(r'日期[：:]\s*(\d{4}-\d{1,2}-\d{1,2})', html)
    if m:
        pub_date = m.group(1)
    if not pub_date:
        # fallback: 用通用提取
        pub_date = extract_date_from_html(html)

    # 正文 — <div class="body">
    content = ""
    m = re.search(r'<div[^>]*class="body"[^>]*>(.*?)</div>\s*</div>', html, re.DOTALL)
    if m:
        content = m.group(1).strip()
    if not content or len(content) < 50:
        # 尝试更宽松的匹配
        m = re.search(r'class="body"[^>]*>(.*?)</div>\s*<(?:/div|div|script)', html, re.DOTALL)
        if m:
            content = m.group(1).strip()

    if content:
        content = clean_html(content)
        # 清理多余空行
        content = re.sub(r'>\s+<', '><', content)
        content = re.sub(r'\n{3,}', '\n\n', content)

    return title, pub_date, content


def run(args=None):
    incremental = False
    if args and '1' in args:
        incremental = True
    print(f"爬取: {SITE_NAME}")
    results = []

    # 先爬第一页
    html = fetch(LIST_MAIN)
    if not html:
        print("  ❌ 无法获取列表页")
        return

    pages_to_crawl = 1 if incremental else MAX_PAGES
    for page in range(1, pages_to_crawl + 1):
        if page == 1:
            page_html = html
        else:
            page_url = f"http://www.mmhbxh.com/xxgk/zh-cn/index_{page}.html"
            page_html = fetch(page_url)
            if not page_html or len(page_html) < 500:
                print(f"  第{page}页: 无内容，停止翻页")
                break

        items = parse_list(page_html)
        if not items:
            print(f"  第{page}页: 0 条")
            if page > 1:
                break
            continue
        print(f"  第{page}页: {len(items)} 条")

        for i, (title, url, date) in enumerate(items):
            print(f"  [{i+1}/{len(items)}] {title[:35]}...", end=" ", flush=True)
            if date < CUTOFF:
                print("⏭ 超时范围")
                continue

            detail_title, pub_date, content = fetch_detail(url)
            if not content or len(content) < 50:
                print("⚠ 无正文")
                continue

            final_title = detail_title or title
            final_date = pub_date or date

            summary = re.sub(r'<[^>]+>', '', content)[:200].strip()
            results.append({
                "site_name": SITE_NAME,
                "title": final_title,
                "url": url,
                "content": content,
                "summary": summary,
                "pub_date": final_date,
                "category": "信息公开",
                "tags": "茂名环保,环评公示",
            })
            print(f"✅ ({len(content)}字)")
            time.sleep(0.3)

    if results:
        print(f"\n  入库 {len(results)} 条")
        push_to_searchdb(results, "mmhbxh_xxgk")
    else:
        print("  ⏭ 无新数据入库")
    print("完成")


if __name__ == "__main__":
    run(sys.argv[1] if len(sys.argv) > 1 else None)