feat: add rrdy category parsing

py/tests/test_人人电影.py

@@ -1,6 +1,7 @@
 import unittest
 from importlib.machinery import SourceFileLoader
 from pathlib import Path
+from unittest.mock import patch
 
 
 ROOT = Path(__file__).resolve().parents[1]
@@ -47,3 +48,48 @@ class TestRenRenDianYingSpider(unittest.TestCase):
         self.assertEqual(self.spider._normalize_title("《繁花》"), "繁花")
         self.assertEqual(self.spider._normalize_title("「诛仙」特别篇"), "诛仙")
         self.assertEqual(self.spider._normalize_title("普通标题"), "普通标题")
+
+    def test_parse_cards_extracts_expected_fields(self):
+        html = """
+        <ul id="movielist">
+          <li>
+            <div class="pure-img"><img class="pure-img" data-original="/poster.jpg" /></div>
+            <div class="intro">
+              <h2><a href="/movie/123.html" title="《示例电影》">《示例电影》</a></h2>
+            </div>
+            <div class="dou"><b>8.8</b></div>
+          </li>
+        </ul>
+        """
+        self.assertEqual(
+            self.spider._parse_cards(html),
+            [
+                {
+                    "vod_id": "/movie/123.html",
+                    "vod_name": "示例电影",
+                    "vod_pic": "https://www.rrdynb.com/poster.jpg",
+                    "vod_remarks": "8.8",
+                }
+            ],
+        )
+
+    @patch.object(Spider, "_request_html")
+    def test_category_content_builds_reference_url_and_page_payload(self, mock_request_html):
+        mock_request_html.return_value = """
+        <ul id="movielist">
+          <li>
+            <img class="pure-img" data-original="/cate.jpg" />
+            <div class="intro"><h2><a href="/movie/456.html" title="分类影片">分类影片</a></h2></div>
+            <div class="dou"><b>更新中</b></div>
+          </li>
+        </ul>
+        """
+        result = self.spider.categoryContent("movie/list_2", "3", False, {})
+        self.assertEqual(
+            mock_request_html.call_args.args[0],
+            "https://www.rrdynb.com/movie/list_2_3.html",
+        )
+        self.assertEqual(result["page"], 3)
+        self.assertEqual(result["limit"], 1)
+        self.assertEqual(result["list"][0]["vod_name"], "分类影片")
+        self.assertNotIn("pagecount", result)

py/人人电影.py

@@ -78,3 +78,53 @@ class Spider(BaseSpider):
         if any(re.search(pattern, raw, re.I) for pattern in self.excluded_pan_patterns):
             return False
         return any(re.search(pattern, raw, re.I) for pattern in self.supported_pan_patterns)
+
+    def _request_html(self, path_or_url):
+        target = path_or_url if str(path_or_url).startswith("http") else self._build_url(path_or_url)
+        response = self.fetch(target, headers=dict(self.headers), timeout=10)
+        if response.status_code != 200:
+            return ""
+        return response.text or ""
+
+    def _clean_text(self, text):
+        return re.sub(r"\s+", " ", str(text or "").replace("\xa0", " ")).strip()
+
+    def _parse_cards(self, html):
+        root = self.html(html)
+        if root is None:
+            return []
+
+        items = []
+        seen = set()
+        for node in root.xpath("//*[@id='movielist']//li"):
+            href = "".join(node.xpath(".//*[contains(@class,'intro')]//h2//a[1]/@href")).strip()
+            title = (
+                "".join(node.xpath(".//*[contains(@class,'intro')]//h2//a[1]/@title")).strip()
+                or "".join(node.xpath(".//*[contains(@class,'intro')]//h2//a[1]//text()")).strip()
+            )
+            pic = (
+                "".join(node.xpath(".//*[contains(@class,'pure-img')][1]/@data-original")).strip()
+                or "".join(node.xpath(".//*[contains(@class,'pure-img')][1]/@src")).strip()
+                or "".join(node.xpath(".//*[contains(@class,'pure-img')]//img[1]/@data-original")).strip()
+                or "".join(node.xpath(".//*[contains(@class,'pure-img')]//img[1]/@src")).strip()
+            )
+            remarks = self._clean_text("".join(node.xpath(".//*[contains(@class,'dou')][1]//text()")))
+            if not href or not title or href in seen:
+                continue
+            seen.add(href)
+            items.append(
+                {
+                    "vod_id": href,
+                    "vod_name": self._normalize_title(title),
+                    "vod_pic": self._build_url(pic),
+                    "vod_remarks": remarks,
+                }
+            )
+        return items
+
+    def categoryContent(self, tid, pg, filter, extend):
+        page = int(pg)
+        class_path = str(tid or "").lstrip("/")
+        url = self._build_url(f"{class_path}_{page}.html")
+        items = self._parse_cards(self._request_html(url))
+        return {"page": page, "limit": len(items), "total": page * 20 + len(items), "list": items}