From 742de4d9e824e2ec6b4621eb1641fc5b7a6fac2b Mon Sep 17 00:00:00 2001
From: Harold <8866033@gmail.com>
Date: Sat, 18 Apr 2026 11:58:08 +0800
Subject: [PATCH] feat: scaffold dbku spider parsing

---
 py/tests/test_dbku.py | 43 ++++++++++++++++++++
 py/独播库.py          | 91 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 134 insertions(+)
 create mode 100644 py/tests/test_dbku.py
 create mode 100644 py/独播库.py

diff --git a/py/tests/test_dbku.py b/py/tests/test_dbku.py
new file mode 100644
index 0000000..7512f8b
--- /dev/null
+++ b/py/tests/test_dbku.py
@@ -0,0 +1,43 @@
+import unittest
+from importlib.machinery import SourceFileLoader
+from pathlib import Path
+
+
+ROOT = Path(__file__).resolve().parents[1]
+MODULE = SourceFileLoader("dbku_spider", str(ROOT / "独播库.py")).load_module()
+Spider = MODULE.Spider
+
+
+class TestDBKUSpider(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, ["index", "movie", "variety", "anime", "hk", "luju"])
+
+    def test_parse_list_cards_extracts_detail_url_title_cover_and_description(self):
+        html = """
+        <div class="myui-vodlist__box">
+          <a class="thumb" href="/voddetail/123.html" title="示例影片" data-original="https://img.example/dbku.jpg"></a>
+          <span class="pic-text">更新至10集</span>
+        </div>
+        """
+        cards = self.spider._parse_list_cards(html)
+        self.assertEqual(
+            cards,
+            [
+                {
+                    "vod_id": "https://www.dbku.tv/voddetail/123.html",
+                    "vod_name": "示例影片",
+                    "vod_pic": "https://img.example/dbku.jpg",
+                    "vod_remarks": "更新至10集",
+                }
+            ],
+        )
+
+
+if __name__ == "__main__":
+    unittest.main()
diff --git a/py/独播库.py b/py/独播库.py
new file mode 100644
index 0000000..5223e36
--- /dev/null
+++ b/py/独播库.py
@@ -0,0 +1,91 @@
+# coding=utf-8
+import sys
+
+from base.spider import Spider as BaseSpider
+
+sys.path.append("..")
+
+
+class Spider(BaseSpider):
+    def __init__(self):
+        self.name = "独播库"
+        self.host = "https://www.dbku.tv"
+        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": "连续剧", "type_id": "index"},
+            {"type_name": "电影", "type_id": "movie"},
+            {"type_name": "综艺", "type_id": "variety"},
+            {"type_name": "动漫", "type_id": "anime"},
+            {"type_name": "港剧", "type_id": "hk"},
+            {"type_name": "陆剧", "type_id": "luju"},
+        ]
+
+    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 _build_url(self, href):
+        raw = str(href or "").strip()
+        if not raw:
+            return ""
+        if raw.startswith(("http://", "https://")):
+            return raw
+        if raw.startswith("//"):
+            return "https:" + raw
+        if raw.startswith("/"):
+            return self.host + raw
+        return self.host + "/" + raw
+
+    def _parse_list_cards(self, html):
+        root = self.html(html)
+        results = []
+        if root is None:
+            return results
+
+        cards = root.xpath("//*[contains(@class,'myui-vodlist__box')]")
+        seen = set()
+        for card in cards:
+            href = ""
+            title = ""
+            pic = ""
+            for anchor in card.xpath(".//a[@href]"):
+                raw_href = (anchor.xpath("./@href") or [""])[0].strip()
+                if "/voddetail/" in raw_href:
+                    href = self._build_url(raw_href)
+                    title = (
+                        (anchor.xpath("./@title") or [""])[0].strip()
+                        or "".join(anchor.xpath(".//text()")).strip()
+                    )
+                    pic = (
+                        (anchor.xpath("./@data-original") or [""])[0].strip()
+                        or (anchor.xpath("./@src") or [""])[0].strip()
+                    )
+                    break
+            if not href or href in seen or not title:
+                continue
+
+            remarks = "".join(card.xpath(".//*[contains(@class,'pic-text')][1]//text()")).strip()
+            seen.add(href)
+            results.append(
+                {
+                    "vod_id": href,
+                    "vod_name": title,
+                    "vod_pic": self._build_url(pic),
+                    "vod_remarks": remarks,
+                }
+            )
+        return results