#!/usr/bin/env python3
"""太和区-民意征集 爬虫 (VSB9 CMS)"""
import re, sys, os, time, hashlib
import requests
from bs4 import BeautifulSoup
from datetime import datetime, timedelta

BASE_URL = "http://www.jzth.gov.cn"
LIST_URL = "http://www.jzth.gov.cn/collect_list.jsp?urltype=tree.TreeTempUrl&wbtreeid=1366"
DB_PATH = "/root/search.db"
SITE_NAME = "太和区-民意征集"
TABLE_NAME = "gov_raw"

HEADERS = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
    "Accept-Language": "zh-CN,zh;q=0.9",
}

# 3年内的日期
THREE_YEARS_AGO = (datetime.now() - timedelta(days=3*365)).strftime("%Y-%m-%d")


def get_list():
    """获取列表页HTML"""
    try:
        r = requests.get(LIST_URL, headers=HEADERS, timeout=30, verify=False)
        if r.status_code == 200:
            return r.text
    except Exception as e:
        print(f"  [!] 获取列表失败: {e}", flush=True)
    return None


def parse_list(html):
    """解析列表，返回 [(title, url, date_str), ...]"""
    soup = BeautifulSoup(html, "html.parser")
    items = []
    for li in soup.select("ul.newsList li"):
        a = li.select_one("a")
        if not a:
            continue
        href = a.get("href", "").strip()
        title_span = a.select_one("span span")
        title = title_span.get_text(strip=True) if title_span else a.get_text(strip=True)
        label = li.select_one("label")
        date_str = label.get_text(strip=True) if label else ""

        if href and title:
            if href.startswith("http"):
                full_url = href
            else:
                full_url = BASE_URL + "/" + href.lstrip("/")
            items.append((title, full_url, date_str))
    return items


def fetch_detail(url):
    """获取详情页，返回 (title, pub_date, content_html)"""
    try:
        r = requests.get(url, headers=HEADERS, timeout=30, verify=False)
        if r.status_code != 200:
            return None, None, None
    except:
        return None, None, None

    soup = BeautifulSoup(r.text, "html.parser")

    # 标题
    title_el = soup.select_one("div.nr1")
    title = title_el.get_text(strip=True) if title_el else ""

    # 日期 - 从nr2中提取
    pub_date = ""
    nr2 = soup.select_one("div.nr2")
    if nr2:
        txt = nr2.get_text()
        m = re.search(r'(\d{4}-\d{2}-\d{2})', txt)
        if m:
            pub_date = m.group(1)

    # 正文内容
    content_el = soup.select_one("div.nr3")
    content = ""
    if content_el:
        content = str(content_el)

    return title, pub_date, content


def main():
    requests.packages.urllib3.disable_warnings()

    import sqlite3
    conn = sqlite3.connect(DB_PATH)
    cur = conn.cursor()

    # 已存在的URL
    cur.execute(f"SELECT page_url FROM {TABLE_NAME}")
    existing_urls = set(row[0] for row in cur.fetchall())

    print("[*] 正在获取列表...", flush=True)
    html = get_list()
    if not html:
        print("[!] 列表为空", flush=True)
        conn.close()
        return

    items = parse_list(html)
    print(f"[*] 列表共 {len(items)} 条", flush=True)

    # 过滤3年内
    filtered = [(t, u, d) for t, u, d in items if d >= THREE_YEARS_AGO]
    print(f"[*] 3年内: {len(filtered)} 条", flush=True)

    if not filtered:
        print("[✓] 无3年内数据", flush=True)
        conn.close()
        return

    new_items = [(t, u, d) for t, u, d in filtered if u not in existing_urls]
    print(f"[*] 排除已存在后，新增 {len(new_items)} 条", flush=True)

    if not new_items:
        print("[✓] 无新数据需要爬取", flush=True)
        conn.close()
        return

    inserted = 0
    for i, (title, url, date_str) in enumerate(new_items, 1):
        print(f"  [{i}/{len(new_items)}] {title[:40]}...", flush=True)
        det_title, det_date, content = fetch_detail(url)

        final_title = det_title or title
        final_date = det_date or date_str

        if not content or len(content.strip()) < 50:
            print(f"    [!] 内容为空或过短，跳过", flush=True)
            continue

        text_only = BeautifulSoup(content, "html.parser").get_text(strip=True)
        summary = text_only[:200] if text_only else ""

        try:
            cur.execute(
                f"INSERT OR IGNORE INTO {TABLE_NAME} (title, page_url, content, summary, publish_date, site_name) VALUES (?, ?, ?, ?, ?, ?)",
                (final_title, url, content, summary, final_date, SITE_NAME)
            )
            if cur.rowcount > 0:
                inserted += 1
                conn.commit()
        except Exception as e:
            print(f"    [!] 入库失败: {e}", flush=True)

        time.sleep(0.3)

    conn.close()
    print(f"\n[✓] 完成！入库 {inserted} 条新数据", flush=True)


if __name__ == "__main__":
    main()