From 4b40851bab4c161b7c86e94c6108895e2bbba437 Mon Sep 17 00:00:00 2001
From: Harold <8866033@gmail.com>
Date: Sat, 18 Apr 2026 11:16:07 +0800
Subject: [PATCH] feat: scaffold czzy spider parsing

---
 py/tests/test_czzy.py | 48 ++++++++++++++++++++++
 py/厂长资源.py        | 96 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 144 insertions(+)
 create mode 100644 py/tests/test_czzy.py
 create mode 100644 py/厂长资源.py

diff --git a/py/tests/test_czzy.py b/py/tests/test_czzy.py
new file mode 100644
index 0000000..6752c64
--- /dev/null
+++ b/py/tests/test_czzy.py
@@ -0,0 +1,48 @@
+import unittest
+from importlib.machinery import SourceFileLoader
+from pathlib import Path
+
+
+ROOT = Path(__file__).resolve().parents[1]
+MODULE = SourceFileLoader("czzy_spider", str(ROOT / "厂长资源.py")).load_module()
+Spider = MODULE.Spider
+
+
+class TestCZZYSpider(unittest.TestCase):
+    def setUp(self):
+        self.spider = Spider()
+        self.spider.init()
+
+    def test_home_content_exposes_expected_categories(self):
+        content = self.spider.homeContent(False)
+        class_ids = [item["type_id"] for item in content["class"]]
+        self.assertEqual(class_ids[:3], ["movie", "tv", "anime"])
+        self.assertIn("cn_drama", class_ids)
+
+    def test_parse_media_cards_extracts_basic_fields(self):
+        html = """
+        <ul class="mi_ne_kd">
+          <li>
+            <a href="/movie/abc.html" title="链接标题">
+              <img data-original="https://img.example/cover.jpg" alt="测试影片" />
+            </a>
+            <span class="jidi">更新至10集</span>
+          </li>
+        </ul>
+        """
+        cards = self.spider._parse_media_cards(html, "https://www.cz01.org")
+        self.assertEqual(
+            cards,
+            [
+                {
+                    "vod_id": "/movie/abc.html",
+                    "vod_name": "测试影片",
+                    "vod_pic": "https://img.example/cover.jpg",
+                    "vod_remarks": "更新至10集",
+                }
+            ],
+        )
+
+
+if __name__ == "__main__":
+    unittest.main()
diff --git a/py/厂长资源.py b/py/厂长资源.py
new file mode 100644
index 0000000..3a2c81a
--- /dev/null
+++ b/py/厂长资源.py
@@ -0,0 +1,96 @@
+# coding=utf-8
+import sys
+from urllib.parse import urljoin
+
+from base.spider import Spider as BaseSpider
+
+sys.path.append("..")
+
+
+class Spider(BaseSpider):
+    def __init__(self):
+        self.name = "厂长资源"
+        self.hosts = [
+            "https://www.cz01.org",
+            "https://www.czzy89.com",
+        ]
+        self.current_host = self.hosts[0]
+        self.headers = {
+            "User-Agent": (
+                "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
+                "AppleWebKit/537.36 (KHTML, like Gecko) "
+                "Chrome/124.0.0.0 Safari/537.36"
+            )
+        }
+        self.categories = [
+            {"type_name": "电影", "type_id": "movie"},
+            {"type_name": "电视剧", "type_id": "tv"},
+            {"type_name": "动漫", "type_id": "anime"},
+            {"type_name": "华语电影", "type_id": "cn_movie"},
+            {"type_name": "印度电影", "type_id": "in_movie"},
+            {"type_name": "俄罗斯电影", "type_id": "ru_movie"},
+            {"type_name": "加拿大电影", "type_id": "ca_movie"},
+            {"type_name": "日本电影", "type_id": "jp_movie"},
+            {"type_name": "韩国电影", "type_id": "kr_movie"},
+            {"type_name": "欧美电影", "type_id": "western_movie"},
+            {"type_name": "国产剧", "type_id": "cn_drama"},
+            {"type_name": "日剧", "type_id": "jp_drama"},
+            {"type_name": "美剧", "type_id": "us_drama"},
+            {"type_name": "韩剧", "type_id": "kr_drama"},
+            {"type_name": "海外剧", "type_id": "intl_drama"},
+        ]
+
+    def init(self, extend=""):
+        return None
+
+    def getName(self):
+        return self.name
+
+    def homeContent(self, filter):
+        return {"class": self.categories}
+
+    def homeVideoContent(self):
+        return {"list": []}
+
+    def _parse_media_cards(self, html, host):
+        root = self.html(html)
+        results = []
+        if root is None:
+            return results
+
+        for item in root.xpath("//li[.//a[@href]]"):
+            href = (item.xpath(".//a[@href][1]/@href") or [""])[0].strip()
+            if not href:
+                continue
+
+            title = (
+                (item.xpath(".//img[@alt][1]/@alt") or [""])[0].strip()
+                or (item.xpath(".//a[@title][1]/@title") or [""])[0].strip()
+                or "".join(item.xpath(".//a[1]//text()")).strip()
+            )
+
+            pic = ""
+            for expr in [
+                ".//img[@data-original][1]/@data-original",
+                ".//img[@data-src][1]/@data-src",
+                ".//img[@src][1]/@src",
+            ]:
+                pic = (item.xpath(expr) or [""])[0].strip()
+                if pic:
+                    break
+
+            remarks = (
+                (item.xpath(".//*[contains(@class,'jidi')][1]/text()") or [""])[0].strip()
+                or (item.xpath(".//*[contains(@class,'hdinfo')][1]/text()") or [""])[0].strip()
+            )
+
+            results.append(
+                {
+                    "vod_id": href,
+                    "vod_name": title or "未命名",
+                    "vod_pic": urljoin(host, pic) if pic.startswith("/") else pic,
+                    "vod_remarks": remarks,
+                }
+            )
+
+        return results