#!/usr/bin/env python3
"""crawl_dmlhq.py - 达尔罕茂明安联合旗-生态环境"""
import sys, os, requests, re
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 = '达茂联合旗-生态环境'
BASE = 'http://dmlhq.gov.cn/zwgk/zfxxgk/xxgk_fdzdgknr/fd_zdlyxxgk/zdly_sthj'

def fetch_urls_from_page(page_num):
    if page_num == 0:
        url = BASE + '/'
    else:
        url = f'{BASE}/index_{page_num}.html'
    try:
        r = requests.get(url, timeout=20)
        r.encoding = 'utf-8'
    except:
        return []
    m = re.search(r'<ul class="module_list">(.*?)</ul>', r.text, re.DOTALL)
    if not m:
        return []
    items = re.findall(
        r'<a href="([^"]+)"[^>]*>\s*<span>\s*(.*?)\s*</span>\s*<span>\s*(\d{4}-\d{2}-\d{2})\s*</span>',
        m.group(1), re.DOTALL
    )
    results = []
    for href, title_html, pub_date in items:
        if href.startswith('./'):
            full_url = BASE + href[1:]
        else:
            full_url = BASE + '/' + href
        results.append({'url': full_url, 'pub_date': pub_date})
    return results

def fetch_detail(url):
    try:
        r = requests.get(url, timeout=20)
        r.encoding = 'utf-8'
    except:
        return '', ''
    
    # Title: text between <div class="title"> and next <div
    title = ''
    m = re.search(r'<div class="title">(.*?)<div class="other">', r.text, re.DOTALL)
    if m:
        title = re.sub(r'<[^>]+>', '', m.group(1))
        title = re.sub(r'\s+', ' ', title).strip()
    
    # Content from TRS_UEDITOR
    content = ''
    m = re.search(
        r'<div class="trs_editor_view TRS_UEDITOR[^"]*"[^>]*>(.*?)</div>\s*</div>',
        r.text, re.DOTALL
    )
    if m:
        content = m.group(1).strip()
    
    return title, content

def run(incremental=False):
    records = []
    seen_urls = set()
    for pg in range(4):
        items = fetch_urls_from_page(pg)
        if not items:
            break
        print(f"  Page {pg+1}: {len(items)} items")
        for item in items:
            if item['pub_date'] < CUTOFF:
                continue
            if item['url'] in seen_urls:
                continue
            seen_urls.add(item['url'])
            title, content = fetch_detail(item['url'])
            if not title:
                print(f"    Skip (no title): {item['url']}")
                continue
            print(f"    [{len(content):5d}] {title[:60]}")
            records.append({
                'title': title,
                'url': item['url'],
                'pub_date': item['pub_date'],
                'site_name': SITE_NAME,
                'content': content,
                'summary': '',
            })
        if incremental:
            break
    print(f"  Total: {len(records)} items")
    valid = [r for r in records if r['content'].strip()]
    if valid:
        push_to_searchdb(valid, "dmlhq_sthj")
    return len(valid)

if __name__ == '__main__':
    inc = '--incremental' in sys.argv
    cnt = run(incremental=inc)
    print(f"Done: {cnt} records")