feat: add tengxun category and batch helper

py/tests/test_腾讯视频.py

@@ -21,6 +21,13 @@ HOME_HTML = """
 </div>
 """
 
+CATEGORY_HTML = """
+<div class="list_item">
+  <a data-float="/x/cover/cid001/vid001.html"><img alt="三体" src="https://img.test/c.jpg"></a>
+  <a>更新至30集</a>
+</div>
+"""
+
 
 class TestTencentSpider(unittest.TestCase):
     def setUp(self):
@@ -71,6 +78,48 @@ class TestTencentSpider(unittest.TestCase):
             },
         )
 
+    @patch.object(Spider, "fetch")
+    def test_category_content_maps_filters_and_prefixes_channel(self, mock_fetch):
+        mock_fetch.return_value = SimpleNamespace(text=CATEGORY_HTML)
+        result = self.spider.categoryContent(
+            "tv",
+            "2",
+            False,
+            {
+                "sort": "18",
+                "iyear": "2024",
+                "year": "2024",
+                "type": "17",
+                "feature": "4",
+                "area": "2",
+                "itrailer": "1",
+                "sex": "1",
+            },
+        )
+        request_url = mock_fetch.call_args.args[0]
+        self.assertIn("channel=tv", request_url)
+        self.assertIn("offset=21", request_url)
+        self.assertIn("sort=18", request_url)
+        self.assertIn("iyear=2024", request_url)
+        self.assertIn("year=2024", request_url)
+        self.assertIn("itype=17", request_url)
+        self.assertIn("ifeature=4", request_url)
+        self.assertIn("iarea=2", request_url)
+        self.assertIn("itrailer=1", request_url)
+        self.assertIn("gender=1", request_url)
+        self.assertEqual(result["list"][0]["vod_id"], "tv$/x/cover/cid001/vid001.html")
+        self.assertEqual(result["page"], 2)
+        self.assertEqual(result["limit"], 21)
+        self.assertEqual(result["pagecount"], 9999)
+
+    @patch.object(Spider, "fetch")
+    def test_get_batch_video_info_parses_qzoutputjson_payload(self, mock_fetch):
+        mock_fetch.return_value = SimpleNamespace(
+            text='QZOutputJson={"results":[{"fields":{"vid":"vid001","title":"第1集","category_map":["0","正片"]}}]};'
+        )
+        result = self.spider._get_batch_video_info(["vid001"])
+        self.assertEqual(result, [{"vid": "vid001", "title": "第1集", "type": "正片"}])
+
 
 if __name__ == "__main__":
     unittest.main()

py/腾讯视频.py

@@ -1,4 +1,5 @@
 # coding=utf-8
+import json
 import re
 import sys
 
@@ -74,3 +75,74 @@ class Spider(BaseSpider):
 
     def playerContent(self, flag, id, vipFlags):
         return {"parse": 1, "jx": 1, "url": id, "header": self._headers()}
+
+    def _safe_json(self, text, strip_prefix="", strip_suffix=""):
+        raw = str(text or "")
+        if strip_prefix and raw.startswith(strip_prefix):
+            raw = raw[len(strip_prefix):]
+        if strip_suffix and raw.endswith(strip_suffix):
+            raw = raw[: -len(strip_suffix)]
+        return json.loads(raw) if raw else {}
+
+    def _get_batch_video_info(self, vids):
+        results = []
+        for start in range(0, len(vids or []), 30):
+            batch = vids[start:start + 30]
+            if not batch:
+                continue
+            url = (
+                "https://union.video.qq.com/fcgi-bin/data?otype=json&tid=1804&appid=20001238"
+                "&appkey=6c03bbe9658448a4&union_platform=1&idlist=" + ",".join(batch)
+            )
+            response = self.fetch(url, headers=self._headers())
+            payload = self._safe_json(getattr(response, "text", ""), strip_prefix="QZOutputJson=", strip_suffix=";")
+            for item in payload.get("results", []):
+                fields = item.get("fields", {})
+                category_map = fields.get("category_map", [])
+                results.append(
+                    {
+                        "vid": fields.get("vid", ""),
+                        "title": fields.get("title", ""),
+                        "type": category_map[1] if len(category_map) > 1 else "",
+                    }
+                )
+        return results
+
+    def categoryContent(self, tid, pg, filter, extend):
+        page = int(pg)
+        offset = (page - 1) * 21
+        params = [
+            "_all=1",
+            "append=1",
+            f"channel={tid}",
+            "listpage=1",
+            f"offset={offset}",
+            "pagesize=21",
+            "iarea=-1",
+        ]
+        options = dict(extend or {})
+        if options.get("sort"):
+            params.append(f"sort={options['sort']}")
+        if options.get("iyear"):
+            params.append(f"iyear={options['iyear']}")
+        if options.get("year"):
+            params.append(f"year={options['year']}")
+        if options.get("type"):
+            params.append(f"itype={options['type']}")
+        if options.get("feature"):
+            params.append(f"ifeature={options['feature']}")
+        if options.get("area"):
+            params.append(f"iarea={options['area']}")
+        if options.get("itrailer"):
+            params.append(f"itrailer={options['itrailer']}")
+        if options.get("sex"):
+            params.append(f"gender={options['sex']}")
+        url = f"{self.base_host}/x/bu/pagesheet/list?" + "&".join(params)
+        response = self.fetch(url, headers=self._headers())
+        return {
+            "list": self._parse_list_items(getattr(response, "text", ""), with_channel=True, channel_id=str(tid)),
+            "page": page,
+            "pagecount": 9999,
+            "limit": 21,
+            "total": 999999,
+        }