From 590a60d15ab633c983d2365c0b98d21ffdf493e2 Mon Sep 17 00:00:00 2001
From: Harold <8866033@gmail.com>
Date: Mon, 20 Apr 2026 15:44:18 +0800
Subject: [PATCH] feat: add rrdy detail pan parsing

---
 py/tests/test_人人电影.py | 42 ++++++++++++++++++++++++++++++++
 py/人人电影.py            | 50 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 92 insertions(+)

diff --git a/py/tests/test_人人电影.py b/py/tests/test_人人电影.py
index bb1887d..b17344b 100644
--- a/py/tests/test_人人电影.py
+++ b/py/tests/test_人人电影.py
@@ -124,3 +124,45 @@ class TestRenRenDianYingSpider(unittest.TestCase):
 
     def test_search_content_returns_empty_list_for_blank_keyword(self):
         self.assertEqual(self.spider.searchContent("", False, "1"), {"page": 1, "total": 0, "list": []})
+
+    def test_extract_pan_links_filters_xunlei_and_aliyun(self):
+        html = """
+        <div class="movie-txt">
+          <a href="https://pan.baidu.com/s/b1">百度网盘</a>
+          <a href="https://pan.quark.cn/s/q1">夸克资源</a>
+          <a href="https://pan.xunlei.com/s/x1">迅雷资源</a>
+          <a href="https://www.alipan.com/s/a1">阿里资源</a>
+        </div>
+        """
+        self.assertEqual(
+            self.spider._extract_pan_links(html),
+            [
+                ("百度网盘", "https://pan.baidu.com/s/b1"),
+                ("夸克资源", "https://pan.quark.cn/s/q1"),
+            ],
+        )
+
+    @patch.object(Spider, "_request_html")
+    def test_detail_content_extracts_meta_and_builds_single_pan_line(self, mock_request_html):
+        mock_request_html.return_value = """
+        <div class="movie-des"><h1>人人示例片</h1></div>
+        <div class="movie-img"><img src="/poster-detail.jpg" /></div>
+        <div class="movie-txt">
+          <p>一段简介</p>
+          <a href="https://pan.baidu.com/s/b1">百度网盘</a>
+          <a href="https://pan.quark.cn/s/q1">夸克资源</a>
+          <a href="https://pan.xunlei.com/s/x1">迅雷资源</a>
+        </div>
+        """
+        result = self.spider.detailContent(["/movie/123.html"])
+        self.assertEqual(mock_request_html.call_args.args[0], "https://www.rrdynb.com/movie/123.html")
+        vod = result["list"][0]
+        self.assertEqual(vod["vod_id"], "/movie/123.html")
+        self.assertEqual(vod["vod_name"], "人人示例片")
+        self.assertEqual(vod["vod_pic"], "https://www.rrdynb.com/poster-detail.jpg")
+        self.assertIn("一段简介", vod["vod_content"])
+        self.assertEqual(vod["vod_play_from"], "网盘")
+        self.assertEqual(
+            vod["vod_play_url"],
+            "百度网盘$https://pan.baidu.com/s/b1#夸克资源$https://pan.quark.cn/s/q1",
+        )
diff --git a/py/人人电影.py b/py/人人电影.py
index 7e9de60..a8c6320 100644
--- a/py/人人电影.py
+++ b/py/人人电影.py
@@ -143,3 +143,53 @@ class Spider(BaseSpider):
 
         items = self._parse_cards(self._request_html(url))
         return {"page": page, "total": len(items), "list": items}
+
+    def _extract_pan_links(self, html):
+        root = self.html(html)
+        if root is None:
+            return []
+
+        items = []
+        seen = set()
+        for node in root.xpath("//*[contains(@class,'movie-txt')]//a[@href]"):
+            href = "".join(node.xpath("./@href")).strip()
+            title = self._clean_text("".join(node.xpath(".//text()"))) or "网盘资源"
+            if not self._is_supported_pan_url(href) or href in seen:
+                continue
+            seen.add(href)
+            items.append((title, href))
+        return items
+
+    def _parse_detail(self, vod_id, html):
+        root = self.html(html)
+        if root is None:
+            return {
+                "vod_id": vod_id,
+                "vod_name": "",
+                "vod_pic": "",
+                "vod_content": "",
+                "vod_play_from": "",
+                "vod_play_url": "",
+            }
+
+        vod_name = self._clean_text("".join(root.xpath("//*[contains(@class,'movie-des')]//h1[1]//text()")))
+        vod_pic = self._build_url("".join(root.xpath("//*[contains(@class,'movie-img')]//img[1]/@src")).strip())
+        vod_content = self._clean_text("".join(root.xpath("//*[contains(@class,'movie-txt')][1]//text()")))
+        pan_links = self._extract_pan_links(html)
+        play_url = "#".join([f"{title}${url}" for title, url in pan_links])
+        return {
+            "vod_id": vod_id,
+            "vod_name": vod_name,
+            "vod_pic": vod_pic,
+            "vod_content": vod_content,
+            "vod_play_from": "网盘" if play_url else "",
+            "vod_play_url": play_url,
+        }
+
+    def detailContent(self, ids):
+        result = {"list": []}
+        for raw_id in ids:
+            vod_id = str(raw_id or "").strip()
+            detail = self._parse_detail(vod_id, self._request_html(self._build_url(vod_id)))
+            result["list"].append(detail)
+        return result