修复封面

py/tests/test_玩偶哥哥.py

@@ -74,6 +74,45 @@ class TestWanOuGeGeSpider(unittest.TestCase):
             ],
         )
 
+    def test_parse_cards_ignores_module_items_container_and_uses_first_card_cover(self):
+        html = """
+        <div id="main">
+          <div class="module-items">
+            <div class="module-item">
+              <div class="module-item-pic">
+                <a href="/voddetail/123.html"></a>
+                <img data-src="/poster-a.jpg" alt="示例影片A" />
+              </div>
+              <div class="module-item-text">HD</div>
+            </div>
+            <div class="module-item">
+              <div class="module-item-pic">
+                <a href="/voddetail/456.html"></a>
+                <img data-src="/poster-b.jpg" alt="示例影片B" />
+              </div>
+              <div class="module-item-text">更新至10集</div>
+            </div>
+          </div>
+        </div>
+        """
+        self.assertEqual(
+            self.spider._parse_cards(html),
+            [
+                {
+                    "vod_id": "/voddetail/123.html",
+                    "vod_name": "示例影片A",
+                    "vod_pic": "http://wogg.xxooo.cf/poster-a.jpg",
+                    "vod_remarks": "HD",
+                },
+                {
+                    "vod_id": "/voddetail/456.html",
+                    "vod_name": "示例影片B",
+                    "vod_pic": "http://wogg.xxooo.cf/poster-b.jpg",
+                    "vod_remarks": "更新至10集",
+                },
+            ],
+        )
+
     @patch.object(Spider, "_request_html")
     def test_category_content_builds_reference_url_and_returns_page_payload(self, mock_request_html):
         mock_request_html.return_value = """

py/tests/test_至臻.py

@@ -68,6 +68,49 @@ class TestZhiZhenSpider(unittest.TestCase):
             ],
         )
 
+    def test_parse_cards_ignores_module_items_container_and_uses_first_card_cover(self):
+        html = """
+        <div id="main">
+          <div class="module-items">
+            <div class="module-item">
+              <div class="module-item-pic">
+                <a href="/index.php/vod/detail/id/123.html"></a>
+                <img data-src="/poster-a.jpg" alt="示例影片A" />
+              </div>
+              <div class="module-item-text">HD</div>
+              <div class="module-item-caption"><span>2025</span></div>
+            </div>
+            <div class="module-item">
+              <div class="module-item-pic">
+                <a href="/index.php/vod/detail/id/456.html"></a>
+                <img data-src="/poster-b.jpg" alt="示例影片B" />
+              </div>
+              <div class="module-item-text">更新至10集</div>
+              <div class="module-item-caption"><span>2024</span></div>
+            </div>
+          </div>
+        </div>
+        """
+        self.assertEqual(
+            self.spider._parse_cards(html),
+            [
+                {
+                    "vod_id": "/index.php/vod/detail/id/123.html",
+                    "vod_name": "示例影片A",
+                    "vod_pic": "http://www.miqk.cc/poster-a.jpg",
+                    "vod_remarks": "HD",
+                    "vod_year": "2025",
+                },
+                {
+                    "vod_id": "/index.php/vod/detail/id/456.html",
+                    "vod_name": "示例影片B",
+                    "vod_pic": "http://www.miqk.cc/poster-b.jpg",
+                    "vod_remarks": "更新至10集",
+                    "vod_year": "2024",
+                },
+            ],
+        )
+
     @patch.object(Spider, "_request_html")
     def test_category_content_builds_reference_url_and_returns_page_payload(self, mock_request_html):
         mock_request_html.return_value = """

py/tests/test_闪电.py

@@ -66,6 +66,49 @@ class TestShanDianSpider(unittest.TestCase):
             ],
         )
 
+    def test_parse_cards_ignores_module_items_container_and_uses_first_card_cover(self):
+        html = """
+        <div id="main">
+          <div class="module-items">
+            <div class="module-item">
+              <div class="module-item-pic">
+                <a href="/index.php/vod/detail/id/123.html"></a>
+                <img data-src="/poster-a.jpg" alt="示例影片A" />
+              </div>
+              <div class="module-item-text">HD</div>
+              <div class="module-item-caption"><span>2025</span></div>
+            </div>
+            <div class="module-item">
+              <div class="module-item-pic">
+                <a href="/index.php/vod/detail/id/456.html"></a>
+                <img data-src="/poster-b.jpg" alt="示例影片B" />
+              </div>
+              <div class="module-item-text">更新至10集</div>
+              <div class="module-item-caption"><span>2024</span></div>
+            </div>
+          </div>
+        </div>
+        """
+        self.assertEqual(
+            self.spider._parse_cards(html),
+            [
+                {
+                    "vod_id": "/index.php/vod/detail/id/123.html",
+                    "vod_name": "示例影片A",
+                    "vod_pic": "https://sd.sduc.site/poster-a.jpg",
+                    "vod_remarks": "HD",
+                    "vod_year": "2025",
+                },
+                {
+                    "vod_id": "/index.php/vod/detail/id/456.html",
+                    "vod_name": "示例影片B",
+                    "vod_pic": "https://sd.sduc.site/poster-b.jpg",
+                    "vod_remarks": "更新至10集",
+                    "vod_year": "2024",
+                },
+            ],
+        )
+
     @patch.object(Spider, "_request_html")
     def test_category_content_builds_reference_url_and_returns_page_payload(self, mock_request_html):
         mock_request_html.return_value = """

py/玩偶哥哥.py

@@ -106,14 +106,16 @@ class Spider(BaseSpider):
 
         items = []
         seen = set()
-        for node in root.xpath("//*[@id='main']//*[contains(@class,'module-item')]"):
-            href = "".join(node.xpath(".//*[contains(@class,'module-item-pic')]//a[1]/@href")).strip()
-            title = "".join(node.xpath(".//*[contains(@class,'module-item-pic')]//img[1]/@alt")).strip()
+        for node in root.xpath(
+            "//*[@id='main']//*[contains(concat(' ', normalize-space(@class), ' '), ' module-item ')]"
+        ):
+            href = ((node.xpath("(.//*[contains(@class,'module-item-pic')]//a[@href])[1]/@href") or [""])[0]).strip()
+            title = ((node.xpath("(.//*[contains(@class,'module-item-pic')]//img[@alt])[1]/@alt") or [""])[0]).strip()
             pic = (
-                "".join(node.xpath(".//*[contains(@class,'module-item-pic')]//img[1]/@data-src")).strip()
-                or "".join(node.xpath(".//*[contains(@class,'module-item-pic')]//img[1]/@src")).strip()
+                ((node.xpath("(.//*[contains(@class,'module-item-pic')]//img[@data-src])[1]/@data-src") or [""])[0]).strip()
+                or ((node.xpath("(.//*[contains(@class,'module-item-pic')]//img[@src])[1]/@src") or [""])[0]).strip()
             )
-            remarks = self._clean_text("".join(node.xpath(".//*[contains(@class,'module-item-text')][1]//text()")))
+            remarks = self._clean_text("".join(node.xpath("(.//*[contains(@class,'module-item-text')])[1]//text()")))
             if not href or not title or href in seen:
                 continue
             seen.add(href)
@@ -147,8 +149,8 @@ class Spider(BaseSpider):
             href = "".join(node.xpath(".//*[contains(@class,'video-serial')][1]/@href")).strip()
             title = "".join(node.xpath(".//*[contains(@class,'video-serial')][1]/@title")).strip()
             pic = (
-                "".join(node.xpath(".//*[contains(@class,'module-item-pic')]//img[1]/@data-src")).strip()
-                or "".join(node.xpath(".//*[contains(@class,'module-item-pic')]//img[1]/@src")).strip()
+                ((node.xpath("(.//*[contains(@class,'module-item-pic')]//img[@data-src])[1]/@data-src") or [""])[0]).strip()
+                or ((node.xpath("(.//*[contains(@class,'module-item-pic')]//img[@src])[1]/@src") or [""])[0]).strip()
             )
             remarks = self._clean_text(
                 "".join(node.xpath(".//*[contains(@class,'video-serial')][1]//text()"))

py/至臻.py

@@ -95,15 +95,17 @@ class Spider(BaseSpider):
 
         items = []
         seen = set()
-        for node in root.xpath("//*[@id='main']//*[contains(@class,'module-item')]"):
-            href = "".join(node.xpath(".//*[contains(@class,'module-item-pic')]//a[1]/@href")).strip()
-            title = "".join(node.xpath(".//*[contains(@class,'module-item-pic')]//img[1]/@alt")).strip()
+        for node in root.xpath(
+            "//*[@id='main']//*[contains(concat(' ', normalize-space(@class), ' '), ' module-item ')]"
+        ):
+            href = ((node.xpath("(.//*[contains(@class,'module-item-pic')]//a[@href])[1]/@href") or [""])[0]).strip()
+            title = ((node.xpath("(.//*[contains(@class,'module-item-pic')]//img[@alt])[1]/@alt") or [""])[0]).strip()
             pic = (
-                "".join(node.xpath(".//*[contains(@class,'module-item-pic')]//img[1]/@data-src")).strip()
-                or "".join(node.xpath(".//*[contains(@class,'module-item-pic')]//img[1]/@src")).strip()
+                ((node.xpath("(.//*[contains(@class,'module-item-pic')]//img[@data-src])[1]/@data-src") or [""])[0]).strip()
+                or ((node.xpath("(.//*[contains(@class,'module-item-pic')]//img[@src])[1]/@src") or [""])[0]).strip()
             )
-            remarks = self._clean_text("".join(node.xpath(".//*[contains(@class,'module-item-text')][1]//text()")))
-            year = self._clean_text("".join(node.xpath(".//*[contains(@class,'module-item-caption')][1]//span[1]//text()")))
+            remarks = self._clean_text("".join(node.xpath("(.//*[contains(@class,'module-item-text')])[1]//text()")))
+            year = self._clean_text("".join(node.xpath("(.//*[contains(@class,'module-item-caption')])[1]//span[1]//text()")))
             if not href or not title or href in seen:
                 continue
             seen.add(href)
@@ -138,8 +140,8 @@ class Spider(BaseSpider):
             href = "".join(node.xpath(".//*[contains(@class,'video-serial')][1]/@href")).strip()
             title = "".join(node.xpath(".//*[contains(@class,'video-serial')][1]/@title")).strip()
             pic = (
-                "".join(node.xpath(".//*[contains(@class,'module-item-pic')]//img[1]/@data-src")).strip()
-                or "".join(node.xpath(".//*[contains(@class,'module-item-pic')]//img[1]/@src")).strip()
+                ((node.xpath("(.//*[contains(@class,'module-item-pic')]//img[@data-src])[1]/@data-src") or [""])[0]).strip()
+                or ((node.xpath("(.//*[contains(@class,'module-item-pic')]//img[@src])[1]/@src") or [""])[0]).strip()
             )
             remarks = self._clean_text(
                 "".join(node.xpath(".//*[contains(@class,'video-serial')][1]//text()"))

py/闪电.py

@@ -93,15 +93,17 @@ class Spider(BaseSpider):
 
         items = []
         seen = set()
-        for node in root.xpath("//*[@id='main']//*[contains(@class,'module-item')]"):
-            href = "".join(node.xpath(".//*[contains(@class,'module-item-pic')]//a[1]/@href")).strip()
-            title = "".join(node.xpath(".//*[contains(@class,'module-item-pic')]//img[1]/@alt")).strip()
+        for node in root.xpath(
+            "//*[@id='main']//*[contains(concat(' ', normalize-space(@class), ' '), ' module-item ')]"
+        ):
+            href = ((node.xpath("(.//*[contains(@class,'module-item-pic')]//a[@href])[1]/@href") or [""])[0]).strip()
+            title = ((node.xpath("(.//*[contains(@class,'module-item-pic')]//img[@alt])[1]/@alt") or [""])[0]).strip()
             pic = (
-                "".join(node.xpath(".//*[contains(@class,'module-item-pic')]//img[1]/@data-src")).strip()
-                or "".join(node.xpath(".//*[contains(@class,'module-item-pic')]//img[1]/@src")).strip()
+                ((node.xpath("(.//*[contains(@class,'module-item-pic')]//img[@data-src])[1]/@data-src") or [""])[0]).strip()
+                or ((node.xpath("(.//*[contains(@class,'module-item-pic')]//img[@src])[1]/@src") or [""])[0]).strip()
             )
-            remarks = self._clean_text("".join(node.xpath(".//*[contains(@class,'module-item-text')][1]//text()")))
-            year = self._clean_text("".join(node.xpath(".//*[contains(@class,'module-item-caption')][1]//span[1]//text()")))
+            remarks = self._clean_text("".join(node.xpath("(.//*[contains(@class,'module-item-text')])[1]//text()")))
+            year = self._clean_text("".join(node.xpath("(.//*[contains(@class,'module-item-caption')])[1]//span[1]//text()")))
             if not href or not title or href in seen:
                 continue
             seen.add(href)
@@ -136,8 +138,8 @@ class Spider(BaseSpider):
             href = "".join(node.xpath(".//*[contains(@class,'video-serial')][1]/@href")).strip()
             title = "".join(node.xpath(".//*[contains(@class,'video-serial')][1]/@title")).strip()
             pic = (
-                "".join(node.xpath(".//*[contains(@class,'module-item-pic')]//img[1]/@data-src")).strip()
-                or "".join(node.xpath(".//*[contains(@class,'module-item-pic')]//img[1]/@src")).strip()
+                ((node.xpath("(.//*[contains(@class,'module-item-pic')]//img[@data-src])[1]/@data-src") or [""])[0]).strip()
+                or ((node.xpath("(.//*[contains(@class,'module-item-pic')]//img[@src])[1]/@src") or [""])[0]).strip()
             )
             remarks = self._clean_text(
                 "".join(node.xpath(".//*[contains(@class,'video-serial')][1]//text()"))