feat: add sjmusic detail parsing

2026-04-24 20:51:52 +08:00
parent f3f7027092
commit 3cb2b9e9fc
2 changed files with 178 additions and 0 deletions
@@ -74,6 +74,54 @@ SEARCH_HTML = """
 </body></html>
 """

+RANK_HTML = """
+<html><body>
+  <ul class="play_list">
+    <li><div class="name"><a href="/mp3/321.html">搁浅</a></div></li>
+    <li><div class="name"><a href="/mp3/322.html">简单爱</a></div></li>
+  </ul>
+</body></html>
+"""
+
+SONG_HTML = """
+<html><head><title>夜曲_世纪音乐</title></head><body>
+  <h1>夜曲</h1>
+  <div class="play_singer"><div class="name"><a>周杰伦</a></div></div>
+  <div class="playhimg"><img src="/img/song_detail.jpg"></div>
+</body></html>
+"""
+
+MV_DETAIL_HTML = """
+<html><head><title>晴天MV_世纪音乐</title></head><body>
+  <h1>晴天MV</h1>
+  <div class="play_singer"><div class="name"><a>周杰伦</a></div></div>
+  <div class="playhimg"><img src="/img/mv_detail.jpg"></div>
+</body></html>
+"""
+
+PLAYLIST_DETAIL_HTML = """
+<html><body>
+  <h1>周董歌单</h1>
+  <div class="pic"><img src="/img/playlist.jpg"></div>
+  <ul class="play_list">
+    <li><div class="name"><a href="/mp3/401.html">安静</a></div></li>
+    <li><div class="name"><a href="/mp3/402.html">晴天</a></div></li>
+  </ul>
+</body></html>
+"""
+
+SINGER_DETAIL_HTML = """
+<html><body>
+  <h1>周杰伦</h1>
+  <div class="singer_info"><div class="info"><p>华语男歌手</p></div></div>
+  <div class="pic"><img src="/img/singer_detail.jpg"></div>
+  <ul class="play_list">
+    <li><div class="name"><a href="/mp3/501.html">青花瓷</a></div></li>
+    <li><div class="name"><a href="/mp3/502.html">稻香</a></div></li>
+  </ul>
+</body></html>
+"""
+

 class TestSJMusicSpider(unittest.TestCase):
    def setUp(self):
@@ -145,6 +193,26 @@ class TestSJMusicSpider(unittest.TestCase):
            {"page": 1, "limit": 0, "total": 0, "list": []},
        )

+    @patch.object(Spider, "fetch")
+    def test_detail_content_builds_rank_song_mv_playlist_and_singer(self, mock_fetch):
+        mock_fetch.side_effect = [
+            SimpleNamespace(status_code=200, text=RANK_HTML),
+            SimpleNamespace(status_code=200, text=SONG_HTML),
+            SimpleNamespace(status_code=200, text=MV_DETAIL_HTML),
+            SimpleNamespace(status_code=200, text=PLAYLIST_DETAIL_HTML),
+            SimpleNamespace(status_code=200, text=SINGER_DETAIL_HTML),
+        ]
+        rank_vod = self.spider.detailContent(["rank:rise"])["list"][0]
+        song_vod = self.spider.detailContent(["song:123"])["list"][0]
+        mv_vod = self.spider.detailContent(["mv:456"])["list"][0]
+        playlist_vod = self.spider.detailContent(["playlist:top100"])["list"][0]
+        singer_vod = self.spider.detailContent(["singer:jay"])["list"][0]
+        self.assertEqual(rank_vod["vod_play_url"], "搁浅$music:321#简单爱$music:322")
+        self.assertEqual(song_vod["vod_play_url"], "周杰伦 - 夜曲$music:123")
+        self.assertEqual(mv_vod["vod_play_url"], "晴天MV$vplay:456:1080")
+        self.assertEqual(playlist_vod["vod_play_url"], "安静$music:401#晴天$music:402")
+        self.assertEqual(singer_vod["vod_play_url"], "青花瓷$music:501#稻香$music:502")
+

 if __name__ == "__main__":
    unittest.main()
@@ -101,6 +101,30 @@ class Spider(BaseSpider):
        page = int(pg)
        return {"page": page, "limit": len(items), "total": len(items), "list": items}

+    def _decode_vod_id(self, vod_id):
+        raw = str(vod_id or "").strip()
+        if ":" not in raw:
+            return "", ""
+        prefix, value = raw.split(":", 1)
+        if prefix == "rank":
+            return prefix, f"/list/{value}.html"
+        if prefix == "song":
+            return prefix, f"/mp3/{value}.html"
+        if prefix == "mv":
+            return prefix, f"/mp4/{value}.html"
+        if prefix == "playlist":
+            return prefix, f"/playlist/{value}.html"
+        if prefix == "singer":
+            return prefix, f"/singer/{value}.html"
+        return "", ""
+
+    def _encode_play_id(self, kind, value):
+        if kind == "music":
+            return f"music:{value}"
+        if kind == "vplay":
+            return f"vplay:{value}:1080"
+        return ""
+
    def _parse_list_cards(self, html, expected_prefixes):
        root = self._load_html(html)
        items = []
@@ -126,6 +150,21 @@ class Spider(BaseSpider):
            )
        return items

+    def _build_episode_rows(self, html):
+        root = self._load_html(html)
+        rows = []
+        for node in root.xpath("//*[contains(@class,'play_list')]//li"):
+            href = "".join(node.xpath(".//a[1]/@href")).strip()
+            song_id = self._extract_site_id(href, "mp3")
+            if not song_id:
+                continue
+            rows.append(
+                self._clean_text("".join(node.xpath(".//a[1]//text()")))
+                + "$"
+                + self._encode_play_id("music", song_id)
+            )
+        return rows
+
    def homeContent(self, filter):
        items = self._parse_home_items(self._fetch_html("/"))
        return {"class": list(self.classes), "filters": self._build_filters(), "list": items}
@@ -175,3 +214,74 @@ class Spider(BaseSpider):
            ["song:", "mv:", "playlist:", "singer:"],
        )
        return self._page_result(items, pg)
+
+    def detailContent(self, ids):
+        vod_id = str((ids or [""])[0] or "").strip()
+        kind, path = self._decode_vod_id(vod_id)
+        if not path:
+            return {"list": []}
+        html = self._fetch_html(path)
+        root = self._load_html(html)
+        title = self._clean_text("".join(root.xpath("//h1[1]//text()")))
+        pic = self._build_url("".join(root.xpath("(//img[1]/@src)[1]")))
+        if kind == "rank":
+            return {
+                "list": [
+                    {
+                        "vod_id": vod_id,
+                        "vod_name": title or "排行榜",
+                        "vod_pic": pic,
+                        "vod_remarks": "",
+                        "vod_content": "",
+                        "vod_play_from": self.name,
+                        "vod_play_url": "#".join(self._build_episode_rows(html)),
+                    }
+                ]
+            }
+        if kind == "song":
+            singer = self._clean_text("".join(root.xpath("//*[contains(@class,'play_singer')]//a[1]//text()")))
+            display = f"{singer} - {title}" if singer else title
+            return {
+                "list": [
+                    {
+                        "vod_id": vod_id,
+                        "vod_name": title,
+                        "vod_pic": pic,
+                        "vod_remarks": "",
+                        "vod_content": "",
+                        "vod_actor": singer,
+                        "vod_play_from": self.name,
+                        "vod_play_url": display + "$" + self._encode_play_id("music", vod_id.split(":", 1)[1]),
+                    }
+                ]
+            }
+        if kind == "mv":
+            return {
+                "list": [
+                    {
+                        "vod_id": vod_id,
+                        "vod_name": title,
+                        "vod_pic": pic,
+                        "vod_remarks": "",
+                        "vod_content": "",
+                        "vod_play_from": self.name,
+                        "vod_play_url": title + "$" + self._encode_play_id("vplay", vod_id.split(":", 1)[1]),
+                    }
+                ]
+            }
+        if kind in ("playlist", "singer"):
+            content = self._clean_text("".join(root.xpath("//*[contains(@class,'info')]//p[1]//text()")))
+            return {
+                "list": [
+                    {
+                        "vod_id": vod_id,
+                        "vod_name": title,
+                        "vod_pic": pic,
+                        "vod_remarks": "",
+                        "vod_content": content,
+                        "vod_play_from": self.name,
+                        "vod_play_url": "#".join(self._build_episode_rows(html)),
+                    }
+                ]
+            }
+        return {"list": []}