#!/usr/bin/env python3
"""爬取 jiaoling.gov.cn - 建设项目环境影响评价"""
import requests
from bs4 import BeautifulSoup
import sqlite3
import os
import re
import sys
from datetime import datetime

BASE_URL = "https://www.jiaoling.gov.cn"
LIST_URL = "https://www.jiaoling.gov.cn/xxgk/hjbh/jsxmhjyxpj/index.html"
SITE_NAME = "jiaoling.gov.cn-建设项目环境影响评价"
CUTOFF_DATE = "2023-06-16"
DB_PATH = os.getenv("SEARCH_DB", "/root/search.db")

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",
    "Referer": "https://www.jiaoling.gov.cn/",
}

def get_last_page():
    """获取总页数"""
    resp = requests.get(LIST_URL, headers=HEADERS, timeout=30)
    resp.encoding = "utf-8"
    soup = BeautifulSoup(resp.text, "html.parser")
    last = soup.select_one("a.last")
    if last and last.get("href"):
        m = re.search(r'index_(\d+)\.html', last["href"])
        if m:
            return int(m.group(1))
    return 1

def get_list_page(page):
    """获取某一页的标题/链接/时间"""
    if page == 1:
        url = LIST_URL
    else:
        url = f"https://www.jiaoling.gov.cn/xxgk/hjbh/jsxmhjyxpj/index_{page}.html"
    resp = requests.get(url, headers=HEADERS, timeout=30)
    resp.encoding = "utf-8"
    soup = BeautifulSoup(resp.text, "html.parser")
    items = []
    for li in soup.select("ul.list li"):
        a = li.find("a")
        span = li.find("span", class_="date")
        if not a or not span:
            continue
        title = a.get("title") or a.get_text(strip=True)
        href = a.get("href", "")
        if href and not href.startswith("http"):
            href = BASE_URL + href
        pub_date = span.get_text(strip=True)
        items.append({"title": title, "url": href, "publish_date": pub_date, "page": page})
    return items

def get_detail(url):
    """获取详情页的正文HTML + 附件"""
    resp = requests.get(url, headers=HEADERS, timeout=30)
    resp.encoding = "utf-8"
    soup = BeautifulSoup(resp.text, "html.parser")
    
    # 正文
    content_parts = []
    show_con = soup.select_one("div.show_con")
    if show_con:
        content_parts.append(str(show_con))
    
    # 附件
    show_fj = soup.select_one("div.show_fj")
    if show_fj:
        content_parts.append(str(show_fj))
    
    if content_parts:
        return "".join(content_parts)
    return ""

def crawl():
    conn = sqlite3.connect(DB_PATH, timeout=60)
    c = conn.cursor()
    
    c.execute("""
        CREATE TABLE IF NOT EXISTS gov_raw (
            id INTEGER PRIMARY KEY AUTOINCREMENT,
            title TEXT,
            page_url TEXT UNIQUE,
            content TEXT,
            publish_date TEXT,
            site_name TEXT DEFAULT '',
            crawl_time TEXT DEFAULT (datetime('now', '+8 hours')),
            similar TEXT
        )
    """)
    conn.commit()
    
    total_pages = get_last_page()
    print(f"总页数: {total_pages}")
    
    total_added = 0
    total_skipped = 0
    cutoff_reached = False
    
    for page in range(1, total_pages + 1):
        if cutoff_reached:
            break
        print(f"  第{page}页...")
        items = get_list_page(page)
        for item in items:
            pub = item["publish_date"]
            if pub and pub < CUTOFF_DATE:
                cutoff_reached = True
                print(f"    截止日期 {CUTOFF_DATE} (当前 {pub})，跳过后续")
                break
            
            c.execute("SELECT id FROM gov_raw WHERE page_url = ?", (item["url"],))
            if c.fetchone():
                total_skipped += 1
                continue
            
            content = get_detail(item["url"])
            if not content:
                print(f"    警告: 空正文 {item['title'][:30]}")
                total_skipped += 1
                continue
            
            c.execute(
                "INSERT OR IGNORE INTO gov_raw (title, page_url, content, publish_date, site_name) VALUES (?, ?, ?, ?, ?)",
                (item["title"], item["url"], content, pub, SITE_NAME)
            )
            if c.rowcount > 0:
                total_added += 1
            conn.commit()
        
        if cutoff_reached:
            break
    
    conn.close()
    print(f"完成: 新增 {total_added} 条, 跳过 {total_skipped} 条")

if __name__ == "__main__":
    crawl()