feat: add dbku detail parsing

py/tests/test_dbku.py

@@ -95,6 +95,39 @@ class TestDBKUSpider(unittest.TestCase):
         self.assertEqual(result["list"][0]["vod_id"], "https://www.dbku.tv/voddetail/321.html")
         self.assertEqual(result["list"][0]["vod_name"], "搜索影片")
 
+    def test_parse_detail_page_extracts_meta_and_episodes(self):
+        html = """
+        <div class="myui-content__thumb">
+          <img data-original="/poster.jpg" />
+        </div>
+        <div class="myui-content__detail">
+          <h1 class="title">独播剧</h1>
+          <p>年份：2025</p>
+          <p>地区：大陆</p>
+          <p>导演：张三</p>
+          <p>主演：李四</p>
+        </div>
+        <span class="data">一段剧情简介</span>
+        <a href="/vodplay/100-1-1.html">第1集</a>
+        <a href="/vodplay/100-1-2.html">第2集</a>
+        """
+        result = self.spider._parse_detail_page(html, "https://www.dbku.tv/voddetail/100.html")
+        vod = result["list"][0]
+        self.assertEqual(vod["vod_name"], "独播剧")
+        self.assertEqual(vod["vod_year"], "2025")
+        self.assertEqual(vod["vod_play_from"], "独播库")
+        self.assertIn("第1集$https://www.dbku.tv/vodplay/100-1-1.html", vod["vod_play_url"])
+
+    @patch.object(Spider, "_request_html")
+    def test_detail_content_reads_from_vod_id_url(self, mock_request_html):
+        mock_request_html.return_value = """
+        <h1 class="title">详情影片</h1>
+        <a href="/vodplay/200-1-1.html">第1集</a>
+        """
+        result = self.spider.detailContent(["https://www.dbku.tv/voddetail/200.html"])
+        self.assertEqual(result["list"][0]["vod_id"], "https://www.dbku.tv/voddetail/200.html")
+        self.assertEqual(result["list"][0]["vod_name"], "详情影片")
+
 
 if __name__ == "__main__":
     unittest.main()

py/独播库.py

@@ -1,4 +1,5 @@
 # coding=utf-8
+import re
 import sys
 from urllib.parse import quote
 
@@ -160,3 +161,54 @@ class Spider(BaseSpider):
         path = "/vodsearch/-------------.html?wd={0}&submit=".format(quote(key))
         html = self._request_html(path, expect_xpath="//*[@id='searchList']|//*[contains(@class,'myui-vodlist__box')]")
         return self._page_result(self._parse_search_cards(html), pg)
+
+    def _extract_text_by_prefix(self, html, prefixes):
+        texts = re.findall(r">([^<>]+)<", html)
+        for text in texts:
+            clean = text.strip()
+            for prefix in prefixes:
+                if clean.startswith(prefix):
+                    return clean.split("：", 1)[-1].strip()
+        return ""
+
+    def _parse_detail_page(self, html, vod_id):
+        root = self.html(html)
+        title = ((root.xpath("//*[contains(@class,'title')][1]//text()") or [""])[0]).strip()
+        pic = (
+            (root.xpath("//*[contains(@class,'myui-content__thumb')]//img/@data-original") or [""])[0].strip()
+            or (root.xpath("//*[contains(@class,'myui-content__thumb')]//img/@src") or [""])[0].strip()
+        )
+        content = "".join(root.xpath("//*[contains(@class,'data')][1]//text()")).strip()
+
+        episodes = []
+        seen = set()
+        for href, label in re.findall(
+            r'<a[^>]+href=["\']([^"\']*/vodplay/\d+-\d+-\d+\.html[^"\']*)["\'][^>]*>([\s\S]*?)</a>',
+            html,
+            re.I,
+        ):
+            url = self._build_url(href)
+            name = re.sub(r"<[^>]*>", "", label).strip()
+            if not url or not name or "立即播放" in name or url in seen:
+                continue
+            seen.add(url)
+            episodes.append(f"{name}${url}")
+
+        vod = {
+            "vod_id": vod_id,
+            "vod_name": title,
+            "vod_pic": self._build_url(pic),
+            "vod_year": self._extract_text_by_prefix(html, ["年份："]),
+            "vod_area": self._extract_text_by_prefix(html, ["地区："]),
+            "vod_actor": self._extract_text_by_prefix(html, ["主演："]),
+            "vod_director": self._extract_text_by_prefix(html, ["导演："]),
+            "vod_content": content,
+            "vod_play_from": "独播库",
+            "vod_play_url": "#".join(episodes),
+        }
+        return {"list": [vod]}
+
+    def detailContent(self, ids):
+        vod_id = ids[0]
+        html = self._request_html(vod_id, expect_xpath="//*[contains(@class,'title')]|//a[contains(@href,'/vodplay/')]")
+        return self._parse_detail_page(html, vod_id)