#!/usr/bin/env python3
"""眉山市彭山区-环评公示 爬虫 (VSB9 CMS)"""
import re, sys, os, time
import requests
from bs4 import BeautifulSoup

BASE_URL = "https://www.scps.gov.cn"
LIST_URL = "https://www.scps.gov.cn/zfjg/yq/scpsjjkfq/xxgk/hpgs.htm"
DB_PATH = "/root/search.db"
SITE_NAME = "眉山市彭山区-环评公示"
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",
}


def get_list():
    try:
        r = requests.get(LIST_URL, headers=HEADERS, timeout=30, verify=False)
        r.encoding = "utf-8"
        if r.status_code == 200:
            return r.text
    except Exception as e:
        print(f"  [!] 请求失败: {e}", flush=True)
    return None


def parse_list(html):
    soup = BeautifulSoup(html, "html.parser")
    items = []
    tables = soup.select("table")
    for table in tables:
        rows = table.select("tr")
        for row in rows:
            tds = row.select("td")
            if len(tds) >= 3:
                a = tds[1].select_one("a")
                date_a = tds[2].select_one("a")
                if a and date_a:
                    href = a.get("href", "").strip()
                    title = a.get_text(strip=True)
                    date_str = date_a.get_text(strip=True)
                    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):
    try:
        r = requests.get(url, headers=HEADERS, timeout=30, verify=False)
        r.encoding = "utf-8"
        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.contit h3")
    title = title_el.get_text(strip=True) if title_el else ""

    # 日期
    pub_date = ""
    for li in soup.select("div.contit ul li"):
        txt = li.get_text()
        m = re.search(r'(\d{4}-\d{2}-\d{2})', txt)
        if m:
            pub_date = m.group(1)

    # 正文
    content_el = soup.select_one("div.contnj")
    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()

    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)

    new_items = [(t, u, d) for t, u, d in items 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()