#!/usr/bin/env python3
"""crawl_binhai_hjbh.py - 滨海县人民政府-生态环境 (TRS col recordset)"""
import sys, os, requests, re, argparse
from datetime import datetime, timedelta

sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
from crawler_lib import push_to_searchdb

CUTOFF = (datetime.now() - timedelta(days=365*3)).strftime('%Y-%m-%d')
SITE_NAME = '滨海县-生态环境'
HEADERS = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) Chrome/120.0'}
LIST_URL = 'https://www.binhai.gov.cn/col/col25884/index.html?number=H00015H0005'

def fetch_urls_from_page(page_num):
    if page_num > 0:
        return []  # 首页 recordset 一次含全部 45 条
    try:
        r = requests.get(LIST_URL, timeout=(5, 15), headers=HEADERS, verify=False)
        r.encoding = 'utf-8'
    except:
        return []
    # recordset CDATA: <li><a href="/art/...">标题</a><span>2026- 08- 06</span></li>
    items = re.findall(
        r'<li><a href="(/art/[^"]+)"[^>]*>\s*(.*?)\s*</a><span>\s*(\d{4})-\s*(\d{2})-\s*(\d{2})\s*</span></li>',
        r.text, re.DOTALL
    )
    results = []
    for href, title_html, y, m, d in items:
        title = re.sub(r'<[^>]+>', '', title_html).strip()
        title = re.sub(r'\s+', '', title)
        if len(title) < 4:
            continue
        full_url = 'https://www.binhai.gov.cn' + href
        results.append({'url': full_url, 'pub_date': f'{y}-{m}-{d}', 'title': title})
    return results

def fetch_detail(url):
    for _attempt in range(2):
        try:
            r = requests.get(url, timeout=(5, 15), headers=HEADERS, verify=False)
            r.encoding = 'utf-8'
            break
        except:
            r = None
    if r is None:
        return '', ''
    title = ''
    # <title>: "滨海县人民政府 生态环境 标题"
    m = re.search(r'<title>([^<]*)</title>', r.text, re.DOTALL)
    if m:
        title = re.sub(r'<[^>]+>', '', m.group(1)).strip()
        title = re.sub(r'^\s*滨海县人民政府\s+生态环境\s+', '', title)
        title = re.sub(r'\s*[-_|]\s*滨海县人民政府\s*$', '', title)
    content = ''
    m = re.search(r'class="content bt-box-1200"(.*?)</div>\s*</div>', r.text, re.DOTALL)
    if m:
        content = m.group(1).strip()
    else:
        m = re.search(r'class="content bt-box-1200"(.*)', r.text, re.DOTALL)
        if m:
            content = m.group(1).strip()
    return title, content

def run(max_pages=1):
    records = []
    seen = set()
    for pg in range(max_pages):
        items = fetch_urls_from_page(pg)
        if not items:
            break
        print(f"  Page {pg+1}: {len(items)} items")
        for it in items:
            if it['pub_date'] and it['pub_date'] < CUTOFF:
                continue
            if it['url'] in seen:
                continue
            seen.add(it['url'])
            title, content = fetch_detail(it['url'])
            if not title:
                title = it['title']
            if not content.strip():
                continue
            records.append({
                'title': title, 'url': it['url'], 'pub_date': it['pub_date'],
                'site_name': SITE_NAME, 'content': content, 'summary': '',
            })
    print(f"  Total: {len(records)} items")
    valid = [r for r in records if r['content'].strip()]
    if valid:
        push_to_searchdb(valid, "binhai_hjbh")
    return len(valid)

if __name__ == '__main__':
    ap = argparse.ArgumentParser()
    ap.add_argument('--pages', type=int, default=1)
    args = ap.parse_args()
    cnt = run(max_pages=args.pages)
    print(f"Done: {cnt} records")