feat: complete shuangxing spider

2026-04-29 15:35:32 +08:00
parent 39cdce34c9
commit ce784ea9c2
2 changed files with 130 additions and 1 deletions
@@ -109,6 +109,63 @@ class TestShuangXingSpider(unittest.TestCase):
    def test_search_content_short_circuits_blank_keyword(self):
        self.assertEqual(self.spider.searchContent("", False, "1"), {"page": 1, "total": 0, "list": []})

+    @patch.object(Spider, "_get_html")
+    def test_detail_content_extracts_title_and_sorted_deduplicated_pan_lines(self, mock_get_html):
+        mock_get_html.return_value = """
+        <body>
+          <div>
+            <div class="s20erx erx-m-bot erx-content">
+              <main><article><h1>双星示例</h1></article></main>
+            </div>
+          </div>
+          <div id="maximg">
+            <div class="dlipp-cont-wp"><div><div class="dlipp-cont-bd">
+              <a href="https://pan.baidu.com/s/b-demo"></a>
+              <a href="https://pan.quark.cn/s/q-demo"></a>
+              <a href="https://pan.baidu.com/s/b-demo"></a>
+              <a href="https://example.com/ignored"></a>
+            </div></div></div>
+          </div>
+        </body>
+        """
+        result = self.spider.detailContent(["/post/demo"])
+        self.assertEqual(mock_get_html.call_args.args[0], "https://1.star2.cn/post/demo")
+        self.assertEqual(
+            result,
+            {
+                "list": [
+                    {
+                        "vod_id": "/post/demo",
+                        "vod_name": "双星示例",
+                        "vod_pic": "",
+                        "vod_remarks": "",
+                        "vod_content": "",
+                        "vod_director": "",
+                        "vod_actor": "",
+                        "vod_play_from": "quark$$$baidu",
+                        "vod_play_url": "夸克资源$https://pan.quark.cn/s/q-demo$$$百度资源$https://pan.baidu.com/s/b-demo",
+                    }
+                ]
+            },
+        )
+
+    @patch.object(Spider, "_get_html")
+    def test_detail_content_returns_empty_list_for_blank_html(self, mock_get_html):
+        mock_get_html.return_value = ""
+        self.assertEqual(self.spider.detailContent(["/post/missing"]), {"list": []})
+
+    def test_player_content_passthroughs_supported_pan_links(self):
+        self.assertEqual(
+            self.spider.playerContent("quark", "https://pan.quark.cn/s/demo", {}),
+            {"parse": 0, "playUrl": "", "url": "https://pan.quark.cn/s/demo"},
+        )
+
+    def test_player_content_rejects_unknown_links(self):
+        self.assertEqual(
+            self.spider.playerContent("site", "https://example.com/video", {}),
+            {"parse": 0, "playUrl": "", "url": ""},
+        )
+

 if __name__ == "__main__":
    unittest.main()
@@ -1,7 +1,7 @@
 # coding=utf-8
 import re
 import sys
-from urllib.parse import quote
+from urllib.parse import quote, urljoin

 from base.spider import Spider as BaseSpider

@@ -24,6 +24,18 @@ class Spider(BaseSpider):
        ("wj", "外剧"),
        ("dm", "动漫"),
    ]
+    PAN_TITLES = {
+        "quark": "夸克资源",
+        "ali": "阿里资源",
+        "115": "115资源",
+        "tianyi": "天翼资源",
+        "uc": "UC资源",
+        "baidu": "百度资源",
+        "xunlei": "迅雷资源",
+        "123pan": "123资源",
+        "yd": "移动云盘资源",
+    }
+    PAN_ORDER = ["quark", "ali", "115", "tianyi", "uc", "baidu", "xunlei", "123pan", "yd"]

    def __init__(self):
        self.name = "双星"
@@ -112,3 +124,63 @@ class Spider(BaseSpider):
            return {"page": page, "total": 0, "list": []}
        items = self._parse_cards(self._get_html(f"{self.BASE_URL}/search/?keyword={quote(keyword)}&page={page}"))
        return {"page": page, "total": len(items), "list": items}
+
+    def _build_pan_lines(self, share_links):
+        groups = {}
+        seen = set()
+        for link in share_links:
+            raw = str(link or "").strip()
+            pan_type = self._detect_pan_type(raw)
+            if not raw or not pan_type or raw in seen:
+                continue
+            seen.add(raw)
+            groups.setdefault(pan_type, []).append(f"{self.PAN_TITLES[pan_type]}${raw}")
+        if not groups:
+            return {"vod_play_from": "", "vod_play_url": ""}
+        names = [name for name in self.PAN_ORDER if name in groups]
+        return {
+            "vod_play_from": "$$$".join(names),
+            "vod_play_url": "$$$".join("#".join(groups[name]) for name in names),
+        }
+
+    def detailContent(self, ids):
+        vod_id = str((ids or [""])[0] or "").strip()
+        if not vod_id:
+            return {"list": []}
+        html = self._get_html(urljoin(self.BASE_URL, vod_id))
+        root = self.html(html)
+        if root is None:
+            return {"list": []}
+        title = self._clean_text(
+            "".join(
+                root.xpath(
+                    "/html/body/div/div[contains(@class,'s20erx') and contains(@class,'erx-content')]/main/article/h1//text()"
+                )
+            )
+        )
+        share_links = [
+            str(value).strip()
+            for value in root.xpath("//*[@id='maximg']//div[contains(@class,'dlipp-cont-bd')]//a[@href]/@href")
+        ]
+        play = self._build_pan_lines(share_links)
+        return {
+            "list": [
+                {
+                    "vod_id": vod_id,
+                    "vod_name": title,
+                    "vod_pic": "",
+                    "vod_remarks": "",
+                    "vod_content": "",
+                    "vod_director": "",
+                    "vod_actor": "",
+                    "vod_play_from": play["vod_play_from"],
+                    "vod_play_url": play["vod_play_url"],
+                }
+            ]
+        }
+
+    def playerContent(self, flag, id, vipFlags):
+        target = str(id or "").strip()
+        if self._detect_pan_type(target):
+            return {"parse": 0, "playUrl": "", "url": target}
+        return {"parse": 0, "playUrl": "", "url": ""}