"""
智联招聘 小程序爬虫入口

功能:
    1. 从后端获取关键词（优先断点续爬 > 失败重试 > 全新）
    2. 调用 SearchPositions 分页爬取职位列表
    3. 每页实时上传数据 + 汇报进度
    4. 支持从断点页码恢复
    5. 可选：搜索 job 时顺带抓取公司详情

启动:
    python -m spiderJobs.platforms.zhilian.main

环境变量:
    API_BASE_URL       后端地址 (默认 http://124.222.106.226:9999)
    MAX_PAGES          每个关键词最大翻页数 (默认 3)
    SLEEP_MIN_SECONDS  最小延迟秒数 (默认 10)
    SLEEP_MAX_SECONDS  最大延迟秒数 (默认 20)
    INLINE_COMPANY     是否内联抓公司 (默认 1，设 0 关闭)
"""

from __future__ import annotations

import os
import sys
from typing import Optional

_project_root = os.path.abspath(os.path.join(os.path.dirname(__file__), "..", "..", ".."))
if _project_root not in sys.path:
    sys.path.insert(0, _project_root)

from crawler_core.base import BaseFetcher, BaseSearcher
from spiderJobs.platforms.zhilian.api import GetCompanyDetail, SearchPositions
from spiderJobs.platforms.zhilian.client import ZhilianClient, create_cgate_client
from spiderJobs.runner.loop import run_crawl_loop


# 智联城市代码映射
CITY_CODE_MAP = {
    "全国": "",
    "北京": 530,
    "上海": 538,
    "广州": 763,
    "深圳": 765,
    "杭州": 653,
    "成都": 801,
    "南京": 635,
    "武汉": 736,
    "西安": 854,
    "长沙": 749,
    "重庆": 551,
    "苏州": 639,
    "天津": 531,
    "厦门": 682,
    "郑州": 719,
    "合肥": 664,
    "济南": 703,
    "青岛": 704,
    "大连": 600,
    "东莞": 769,
    "佛山": 766,
    "珠海": 768,
    "无锡": 636,
    "宁波": 654,
}


def create_searcher(keyword: dict, http_client: ZhilianClient) -> BaseSearcher:
    """根据关键词创建智联搜索器"""
    city = keyword.get("city", "")
    job = keyword.get("job", "")
    city_code = CITY_CODE_MAP.get(city, 538)

    return SearchPositions(
        keyword=job,
        city_code=city_code,
        client=http_client,
    )


def extract_company_id(job: dict) -> Optional[str]:
    """从智联 job dict 中提取公司 ID (companyNumber)"""
    company_number = job.get("companyNumber") or job.get("company", {}).get("number")
    return str(company_number) if company_number else None


def create_company_fetcher(company_id: str, http_client: ZhilianClient) -> BaseFetcher:
    """创建智联公司详情 fetcher"""
    return GetCompanyDetail(number=company_id, client=http_client)


def main():
    client_kwargs = {}

    proxy = os.environ.get("PROXY_URL", "")
    if proxy:
        client_kwargs["proxy"] = proxy

    run_crawl_loop(
        platform="zhilian",
        create_searcher=create_searcher,
        create_client_fn=create_cgate_client,
        max_pages=3,
        data_type="job",
        client_kwargs=client_kwargs,
        extract_company_id=extract_company_id,
        create_company_fetcher=create_company_fetcher,
    )


if __name__ == "__main__":
    main()