feat: add AAZ音乐 search parsing

2026-04-25 09:00:37 +08:00
parent fc6cc24529
commit 000ec1c5de
2 changed files with 56 additions and 1 deletions
@@ -1,7 +1,7 @@
 # coding=utf-8
 import re
 import sys
-from urllib.parse import urljoin
+from urllib.parse import quote, urljoin

 from base.spider import Spider as BaseSpider

@@ -119,6 +119,26 @@ class Spider(BaseSpider):
            )
        return items

+    def _parse_search_cards(self, html):
+        root = self._load_html(html)
+        items = []
+        seen = set()
+        for node in root.xpath("//li"):
+            href = "".join(node.xpath(".//div[contains(@class,'name')]//a[1]/@href")).strip()
+            vod_id = self._encode_vod_id(href)
+            if not vod_id or vod_id in seen:
+                continue
+            seen.add(vod_id)
+            items.append(
+                {
+                    "vod_id": vod_id,
+                    "vod_name": self._clean_text("".join(node.xpath(".//div[contains(@class,'name')]//a[1]/@title"))),
+                    "vod_pic": self._build_url("".join(node.xpath(".//img[1]/@src"))),
+                    "vod_remarks": "",
+                }
+            )
+        return items
+
    def homeContent(self, filter):
        items = self._parse_song_cards(self._fetch_html(self.category_paths["new"]))
        return {"class": list(self.classes), "list": items}
@@ -141,3 +161,11 @@ class Spider(BaseSpider):
        else:
            items = self._parse_folder_cards(html, "mv")
        return {"page": int(pg), "limit": len(items), "total": len(items), "list": items}
+
+    def searchContent(self, key, quick, pg="1"):
+        keyword = self._clean_text(key)
+        if not keyword:
+            return self._empty_result(1)
+        html = self._fetch_html("/so/%s.html" % quote(keyword))
+        items = self._parse_search_cards(html)
+        return {"page": int(pg), "limit": len(items), "total": len(items), "list": items}
@@ -60,6 +60,18 @@ MV_HTML = """
 </body></html>
 """

+SEARCH_HTML = """
+<html><body>
+  <ul>
+    <li><div class="name"><a href="/m/2001.html" title="夜曲">夜曲</a></div></li>
+    <li><div class="name"><a href="/s/jay" title="周杰伦">周杰伦</a></div></li>
+    <li><div class="name"><a href="/p/jaybest" title="周董精选">周董精选</a></div></li>
+    <li><div class="name"><a href="/a/fantasy" title="范特西">范特西</a></div></li>
+    <li><div class="name"><a href="/v/nocturnemv" title="夜曲MV">夜曲MV</a></div></li>
+  </ul>
+</body></html>
+"""
+

 class TestAAZMusicSpider(unittest.TestCase):
    def setUp(self):
@@ -108,6 +120,21 @@ class TestAAZMusicSpider(unittest.TestCase):
            {"page": 1, "limit": 0, "total": 0, "list": []},
        )

+    @patch.object(Spider, "fetch")
+    def test_search_content_maps_mixed_result_types(self, mock_fetch):
+        mock_fetch.return_value = SimpleNamespace(status_code=200, text=SEARCH_HTML)
+        result = self.spider.searchContent("周杰伦", False, "1")
+        self.assertEqual(
+            [item["vod_id"] for item in result["list"]],
+            ["song:2001", "singer:jay", "playlist:jaybest", "album:fantasy", "mv:nocturnemv"],
+        )
+
+    def test_search_content_returns_empty_for_blank_keyword(self):
+        self.assertEqual(
+            self.spider.searchContent("", False, "1"),
+            {"page": 1, "limit": 0, "total": 0, "list": []},
+        )
+

 if __name__ == "__main__":
    unittest.main()