ai-contract-platform/scripts/test-post-search-api.py

#!/usr/bin/env python3
"""
使用POST搜索API获取法律列表和bbbs ID

根据API文档，POST /law-search/search/list 可能可以获取完整的法律列表包含bbbs
"""

import json
import time
import urllib.parse
import urllib.request
import ssl
from datetime import datetime

ssl_context = ssl.create_default_context()
ssl_context.check_hostname = False
ssl_context.verify_mode = ssl.CERT_NONE

API_BASE = "https://flk.npc.gov.cn/law-search"

def post_search_laws(title: str = "", page: int = 1, size: int = 20, category_id: int = None):
    """使用POST API搜索法律"""
    url = f"{API_BASE}/search/list"

    # 构建请求体
    body = {
        "title": title,
        "page": page,
        "size": size
    }
    if category_id:
        body["flflId"] = category_id  # 分类ID

    data = json.dumps(body).encode('utf-8')

    req = urllib.request.Request(
        url,
        data=data,
        headers={
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36',
            'Accept': 'application/json',
            'Content-Type': 'application/json;charset=UTF-8',
            'Referer': 'https://flk.npc.gov.cn/'
        },
        method='POST'
    )

    try:
        with urllib.request.urlopen(req, context=ssl_context, timeout=30) as response:
            return json.loads(response.read().decode('utf-8'))
    except Exception as e:
        print(f"POST request failed: {e}")
        return None


def search_by_category(category_id: int, category_name: str, max_pages: int = 20):
    """按分类搜索获取所有法律"""
    print(f"\nSearching category: {category_name} (id={category_id})")

    all_laws = []
    for page in range(1, max_pages + 1):
        print(f"  Page {page}...")
        result = post_search_laws(category_id=category_id, page=page, size=100)
        if not result or result.get('code') != 200:
            print(f"  Failed at page {page}")
            break

        data = result.get('data', {})
        items = data.get('rows', [])
        if not items:
            print(f"  No more items")
            break

        for item in items:
            all_laws.append({
                'bbbs': item.get('bbbs'),
                'title': item.get('title'),
                'type': item.get('flxz'),
                'authority': item.get('zdjgName'),
                'publish_date': item.get('gbrq'),
                'effective_date': item.get('sxrq')
            })

        total = data.get('total', 0)
        print(f"  Found {len(items)} items, total={total}")
        if len(all_laws) >= total:
            break

        time.sleep(0.5)

    return all_laws


def search_specific_law(title: str):
    """搜索特定法律并获取bbbs"""
    print(f"\nSearching: {title}")
    result = post_search_laws(title=title, page=1, size=10)

    if not result or result.get('code') != 200:
        print(f"  Search failed")
        return None

    data = result.get('data', {})
    items = data.get('rows', [])

    # 精确匹配
    for item in items:
        if item.get('title') == title:
            print(f"  Found exact match: bbbs={item.get('bbbs')}")
            return {
                'bbbs': item.get('bbbs'),
                'title': item.get('title'),
                'type': item.get('flxz'),
                'authority': item.get('zdjgName'),
                'publish_date': item.get('gbrq'),
                'effective_date': item.get('sxrq')
            }

    # 返回最接近的匹配
    if items:
        print(f"  No exact match, closest: {items[0].get('title')}")
        return None

    return None


def main():
    print("=" * 60)
    print("Testing POST search API for bbbs ID")
    print("=" * 60)

    # 测试POST搜索API
    # 先尝试搜索特定法律
    test_titles = [
        "中华人民共和国社会保险法",
        "中华人民共和国建筑法",
        "中华人民共和国合伙企业法",
        "工伤保险条例",
    ]

    results = []

    for title in test_titles:
        law = search_specific_law(title)
        if law:
            results.append(law)
        time.sleep(0.5)

    # 输出结果
    output = {
        "search_date": datetime.now().isoformat(),
        "method": "POST_search_api",
        "results": results
    }

    with open('project-docs/phase14-legal-fulltext-library/bbbs-lookup-test.json', 'w', encoding='utf-8') as f:
        json.dump(output, f, ensure_ascii=False, indent=2)

    print(f"\n\nResults saved to: project-docs/phase14-legal-fulltext-library/bbbs-lookup-test.json")
    print(f"Found {len(results)} laws with bbbs")

    return results


if __name__ == '__main__':
    main()