#!/usr/bin/env python3
"""
沾益区 - 环评管理 (zhanyi.gov.cn)
https://www.zhanyi.gov.cn/index.php/pub/special/378.html
PHP站点, 分页: ?cate=378&page=N, 详情: /index.php/news/1hpgl/XXXXX.html
正文容器: div.web_con
"""
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 = "沾益区环评管理"
BASE_URL = "https://www.zhanyi.gov.cn"
LIST_URL = "https://www.zhanyi.gov.cn/index.php/pub/special/378.html"
THREE_YEARS_AGO = (datetime.now(timezone.utc) - timedelta(days=365*3)).strftime("%Y-%m-%d")
MAX_PAGES = 5
HEADERS = {"User-Agent": "Mozilla/5.0"}

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

def parse_list(html):
    items = []
    pattern = r'href="(https?://www\.zhanyi\.gov\.cn/index\.php/news/[^"]+\.html)"[^>]*>(.*?)</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
        items.append((title, href))
    return items

def extract_nested(html, tag_start):
    """找到匹配的闭合标签，支持嵌套div/section"""
    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+6] == '</div>' or html[i:i+8] == '</section>':
            if depth == 0:
                return html[tag_start:i]
            depth -= 1
            i += 6 if html[i:i+6] == '</div>' else 8
            continue
        if html[i:i+4] == '<div' and html[i+4] in (' ', '>', '\n', '\t', '\r'):
            depth += 1
            i += 4
            continue
        if html[i:i+8] == '<section' and html[i+8] in (' ', '>', '\n', '\t', '\r'):
            depth += 1
            i += 8
            continue
        i += 1
    return html[tag_start:]

def fetch_detail(url):
    html = fetch(url)
    if not html: return None, None, None
    result = {}
    # 标题: <h5>xxx</h5>
    m = re.search(r'<h5[^>]*>(.*?)</h5>', html, re.DOTALL)
    if m: result["title"] = re.sub(r"<[^>]+>", "", m.group(1)).strip()
    # 日期: 发布时间：2026-02-05
    m = re.search(r'发布时间：(\d{4}-\d{1,2}-\d{1,2})', html)
    if m: result["publish_date"] = m.group(1)
    # 正文: div.web_con (嵌套感知)
    m = re.search(r'class="web_con[^"]*"[^>]*>', 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) > 100:
            result["content"] = content
    # 兜底: single_web
    if not result.get("content"):
        m = re.search(r'<(div|section)[^>]*class="single_web[^"]*"[^>]*>', 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) > 100:
                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):
        url = LIST_URL if page == 1 else f"{LIST_URL}?cate=378&page={page}"
        print(f"\n📄 第 {page} 页...", end=" ", flush=True)
        html = fetch(url)
        if not html: print("❌"); break
        items = parse_list(html)
        if not items: print("0 条"); break
        print(f"✅ {len(items)} 条")
        all_list.extend(items)
    print(f"\n📊 列表总计: {len(all_list)} 条")
    all_items, seen = [], set()
    for i, (title, url) in enumerate(all_list):
        if "项目" not in title: continue
        if url in seen: continue
        seen.add(url)
        print(f"  [{i+1}/{len(all_list)}] {title[:50]}...", 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, "zhanyi_hpgl")
    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")