优化酷狗音乐分享链解析与URL重定向拦截逻辑

This commit is contained in:
ucmao
2026-09-16 16:43:47 +08:00
parent c24c120b5b
commit 1da33baebb
7 changed files with 108 additions and 41 deletions
+6 -3
View File
@@ -3,15 +3,18 @@
## 支持范围
- 移动端 MV 分享链接:`m.kugou.com/mv/?hash=...`、`m3ws.kugou.com/mv/?hash=...` 与 `t1.kugou.com` 短链。
- 歌曲分享页:可返回公开、免费的音频;付费歌曲和试听片段只返回元数据,不会误报为完整音频。
- 歌曲分享页与短链:`m.kugou.com/share/song.html?chain=...`、`m.kugou.com/share/default.html?chain=...` 与 PC 端重定向分享页 `kugou.com/share/<chain>.html`。
- 歌曲音频:可返回公开、免费的高品质音频直链;付费歌曲和试听片段只返回元数据,不会误报为完整音频。
## 提取字段
MV 可提取标题、歌手、封面与所有公开 MP4 清晰度;免费歌曲可提取标题、歌手、封面及音频地址。
MV 可提取标题、歌手、封面与所有公开 MP4 清晰度;免费歌曲可提取标题、歌手、封面及音频直链地址。
## 实现说明
MV 播放信息来自酷狗移动端公开接口。解析器按官方网页的参数排序与 MD5 方式生成临时签名,再优先返回 SQ、RQ、LE、SD 清晰度。地址带有效期,应在取得后尽快使用。
- **MV 解析**:播放信息来自酷狗移动端公开接口。解析器按官方网页的参数排序与 MD5 方式生成临时签名,再优先返回 SQ、RQ、LE、SD 清晰度。
- **歌曲解析**:通过提取分享链标识(`chain`)获取歌曲详细信息(`songName`、歌手信息、专辑封面、高品质 MP3 播放直链),并兼容 PC 端与移动端不同重定向形态。
- **链接有效期**:返回的直链地址带有官方时效性签名,应在取得后尽快播放或下载。
## 限制
+6 -1
View File
@@ -77,10 +77,15 @@ def _execute_parse(text, access):
if not share_url:
response, status = make_response(400, '未找到有效的分享链接', None, False, 'URL_NOT_FOUND'), 400
return response, status
# 1. 解析基础信息
redirect_url = WebFetcher.fetch_redirect_url(share_url)
if not redirect_url:
if not WebFetcher._is_allowed_target(share_url):
logger.error(f'This link is not supported for extraction: {share_url}')
response, status = make_response(400, '该链接尚未支持提取', None, False, 'PLATFORM_NOT_SUPPORTED'), 400
return response, status
platform = UrlParser.get_platform(share_url)
response, status = make_response(400, '无法访问或识别该分享链接', None, False, 'REDIRECT_FAILED'), 400
return response, status
+68 -34
View File
@@ -41,14 +41,21 @@ class KugouMusicParser(BaseParser):
def _detect_media(url):
parsed = urlparse(url or "")
params = parse_qs(parsed.query)
path = parsed.path.lower()
desktop_mv = re.search(r"/mvweb/html/mv_([0-9a-f]{32})\.html", path)
path = parsed.path
path_lower = path.lower()
desktop_mv = re.search(r"/mvweb/html/mv_([0-9a-f]{32})\.html", path, re.I)
if desktop_mv:
return "mv", desktop_mv.group(1)
if "/mv" in path or "/mv/" in path:
if "/mv" in path_lower or "/mv/" in path_lower:
return "mv", (params.get("hash") or [None])[0]
if "/share/song" in path or "/song" in path:
return "song", (params.get("chain") or [None])[0]
chain_path_match = re.search(r"/share/([a-zA-Z0-9_-]+)\.html", path)
if chain_path_match and chain_path_match.group(1).lower() not in ("song", "default", "index"):
return "song", chain_path_match.group(1)
chain = (params.get("chain") or [None])[0]
if chain:
return "song", chain
if "/share/song" in path_lower or "/song" in path_lower or "/share/default" in path_lower:
return "song", chain
return None, None
def _parse(self):
@@ -99,41 +106,68 @@ class KugouMusicParser(BaseParser):
self.video_list = self._extract_mv_streams(payload.get("mvdata") or {})
def _parse_song_page(self):
target_url = self.real_url
if self.content_id:
target_url = f"https://m.kugou.com/share/song.html?chain={self.content_id}"
try:
response = self.session.get(self.real_url, headers=self.headers, timeout=10)
response = self.session.get(target_url, headers=self.headers, timeout=10)
response.raise_for_status()
self.html_content = response.text
except Exception as exc:
logger.warning("Failed to fetch Kugou song page: %s", exc)
return
match = re.search(r"var\s+phpParam\s*=\s*(\{.*?\});", self.html_content, re.DOTALL)
if not match:
return
try:
payload = json.loads(match.group(1))
except json.JSONDecodeError:
return
data = ((payload.get("song_info") or {}).get("data") or {})
self.title = data.get("songName") or data.get("fileName") or ""
cover = data.get("album_img") or data.get("imgUrl")
self.cover_url = cover.replace("{size}", "400") if isinstance(cover, str) else cover
authors = data.get("authors") or []
if authors and isinstance(authors[0], dict):
author = authors[0]
self.author = {
"nickname": author.get("author_name") or author.get("name") or "",
"author_id": str(author.get("author_id") or author.get("id") or ""),
"avatar": (author.get("avatar") or "").replace("{size}", "400"),
}
elif data.get("singerName"):
self.author["nickname"] = data["singerName"]
if target_url != self.real_url:
try:
response = self.session.get(self.real_url, headers=self.headers, timeout=10)
response.raise_for_status()
self.html_content = response.text
except Exception:
return
else:
return
# 付费、试听或平台明确报错的地址不能作为完整音频返回。
if data.get("error") or data.get("pay_type") not in (None, 0, "0"):
return
url = data.get("url")
if self._valid_url(url):
self.audio_url = url
match = re.search(r"var\s+phpParam\s*=\s*(\{.*?\});", self.html_content or "", re.DOTALL)
if match:
try:
payload = json.loads(match.group(1))
data = ((payload.get("song_info") or {}).get("data") or {})
self.title = data.get("songName") or data.get("fileName") or ""
cover = data.get("album_img") or data.get("imgUrl")
self.cover_url = cover.replace("{size}", "400") if isinstance(cover, str) else cover
authors = data.get("authors") or []
if authors and isinstance(authors[0], dict):
author = authors[0]
self.author = {
"nickname": author.get("author_name") or author.get("name") or "",
"author_id": str(author.get("author_id") or author.get("id") or ""),
"avatar": (author.get("avatar") or "").replace("{size}", "400"),
}
elif data.get("singerName"):
self.author["nickname"] = data["singerName"]
# 付费、试听或平台明确报错的地址不能作为完整音频返回。
if not (data.get("error") or data.get("pay_type") not in (None, 0, "0")):
url = data.get("url")
if self._valid_url(url):
self.audio_url = url
return
except Exception as e:
logger.debug("Failed to parse phpParam: %s", e)
match_smarty = re.search(r"var\s+dataFromSmarty\s*=\s*(\[.*?\]);", self.html_content or "", re.DOTALL)
if match_smarty:
try:
smarty_list = json.loads(match_smarty.group(1))
if smarty_list and isinstance(smarty_list[0], dict):
item = smarty_list[0]
self.title = item.get("song_name") or item.get("audio_name") or ""
self.author = {
"nickname": item.get("author_name") or "",
"author_id": str(item.get("author_id") or ""),
"avatar": "",
}
except Exception as e:
logger.debug("Failed to parse dataFromSmarty: %s", e)
@staticmethod
def _extract_mv_streams(mvdata):
+5
View File
@@ -269,6 +269,11 @@
<td class="px-3.5 py-2.5"><code class="font-mono text-xs font-semibold text-slate-800 bg-slate-100/90 px-2 py-0.5 rounded border border-slate-200/60">URL_NOT_FOUND</code></td>
<td class="px-3.5 py-2.5 text-slate-600 leading-relaxed">文本中未提取到合法的 http/https 链接,请检查分享文本是否完整。</td>
</tr>
<tr>
<td class="px-3.5 py-2.5"><span class="inline-flex items-center px-1.5 py-0.5 rounded text-xs font-mono font-medium bg-rose-50 text-rose-700 border border-rose-200/60">400</span></td>
<td class="px-3.5 py-2.5"><code class="font-mono text-xs font-semibold text-slate-800 bg-slate-100/90 px-2 py-0.5 rounded border border-slate-200/60">REDIRECT_FAILED</code></td>
<td class="px-3.5 py-2.5 text-slate-600 leading-relaxed">短链接重定向解析失败或网络超时不可达,请检查原链接是否可正常打开。</td>
</tr>
<tr>
<td class="px-3.5 py-2.5"><span class="inline-flex items-center px-1.5 py-0.5 rounded text-xs font-mono font-medium bg-rose-50 text-rose-700 border border-rose-200/60">400</span></td>
<td class="px-3.5 py-2.5"><code class="font-mono text-xs font-semibold text-slate-800 bg-slate-100/90 px-2 py-0.5 rounded border border-slate-200/60">PLATFORM_NOT_SUPPORTED</code></td>
+2 -2
View File
@@ -98,11 +98,11 @@ class ApiContractTest(unittest.TestCase):
def test_rejects_unresolvable_redirect(self):
with patch("src.api.parse.WebFetcher.fetch_redirect_url", return_value=None):
response = self.client.post("/api/parse", json={"text": "https://example.com"})
response = self.client.post("/api/parse", json={"text": "https://v.douyin.com/abc1234/"})
self.assert_bad_request(response, "无法访问或识别该分享链接", "REDIRECT_FAILED")
def test_rejects_unsupported_domain(self):
response = self.post_with_parser(self.parser(), "https://unsupported.example/video/1")
response = self.client.post("/api/parse", json={"text": "https://unsupported.example/video/1"})
self.assert_bad_request(response, "该链接尚未支持提取", "PLATFORM_NOT_SUPPORTED")
def test_rejects_empty_media_with_platform_specific_message(self):
+11
View File
@@ -66,6 +66,17 @@ class KugouMusicParserTest(unittest.TestCase):
self.assertEqual(parser.media_type, "mv")
self.assertEqual(parser.content_id, "48da1fe5cbe4f8774f73160042377b1e")
@patch("src.parsers.base_parser.requests.Session.get")
def test_supports_share_chain_html_redirect_path(self, get):
song = {"song_info": {"data": {"songName": "红红的太阳", "pay_type": 0, "url": "https://sharefs.kugou.com/full.mp3", "authors": [{"author_name": "张韶涵", "author_id": 123}]}}}
get.return_value = self.response(text=f"<script>var phpParam = {json.dumps(song, ensure_ascii=False)};</script>")
parser = KugouMusicParser("http://www.kugou.com/share/1ixUXa2G5V3.html")
self.assertEqual(parser.media_type, "song")
self.assertEqual(parser.content_id, "1ixUXa2G5V3")
self.assertEqual(parser.get_title_content(), "红红的太阳")
self.assertEqual(parser.get_author_info()["nickname"], "张韶涵")
self.assertEqual(parser.get_audio_url(), "https://sharefs.kugou.com/full.mp3")
if __name__ == "__main__":
unittest.main()
+10 -1
View File
@@ -101,7 +101,7 @@ class UrlParser:
def get_url(text):
if not isinstance(text, str):
return None
url_pattern = re.compile(r'\bhttps?:\/\/(?:www\.|[-a-zA-Z0-9.@:%_+~#=]{1,256}\.[a-zA-Z0-9()]{1,6})\b(?:[-a-zA-Z0-9()@:%_+.~#?&//=]*)?')
url_pattern = re.compile(r'https?:\/\/(?:www\.|[-a-zA-Z0-9.@:%_+~#=]{1,256}\.[a-zA-Z0-9()]{1,24})\b(?:[-a-zA-Z0-9()@:%_+.~#?&//=]*?)(?=(?:https?:\/\/|$|\s))')
match = url_pattern.search(text)
if match:
return match.group()
@@ -182,6 +182,15 @@ class UrlParser:
address = f"{address}?{urlencode(preserved_params)}"
elif platform == "快手":
address = address.replace('http://', 'https://')
elif platform == "酷狗音乐":
query_params = parse_qs(parsed_url.query)
preserved_params = []
for key in ('hash', 'sruserid', 'kgsscty1', 'chain'):
value = query_params.get(key, [None])[0]
if value is not None:
preserved_params.append((key, value))
if preserved_params:
address = f"{address}?{urlencode(preserved_params)}"
elif platform == "抖音":
query_params = parse_qs(parsed_url.query)
preserved_params = []