From 633e0c97cdd56a45b5d50c1b289ba89f8889e373 Mon Sep 17 00:00:00 2001 From: ucmao <294323976@qq.com> Date: Tue, 1 Sep 2026 21:47:39 +0800 Subject: [PATCH] =?UTF-8?q?=E6=B7=BB=E5=8A=A0=E7=BD=91=E6=98=93=E4=BA=91?= =?UTF-8?q?=E9=9F=B3=E4=B9=90=E5=B9=B3=E5=8F=B0=E8=A7=A3=E6=9E=90=E6=94=AF?= =?UTF-8?q?=E6=8C=81?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- README.md | 17 +- configs/business_config.json | 5 + docs/index.md | 5 +- docs/parsers/netease-music.md | 59 +++++ docs/testing.md | 6 +- src/parsers/netease_music_parser.py | 362 ++++++++++++++++++++++++++++ tests/live_parser_samples.json | 53 +++- tests/test_netease_music_parser.py | 172 +++++++++++++ tests/test_web_fetcher.py | 25 ++ utils/web_fetcher.py | 15 ++ 10 files changed, 704 insertions(+), 15 deletions(-) create mode 100644 docs/parsers/netease-music.md create mode 100644 src/parsers/netease_music_parser.py create mode 100644 tests/test_netease_music_parser.py diff --git a/README.md b/README.md index 1eb6945..611fad2 100644 --- a/README.md +++ b/README.md @@ -3,7 +3,7 @@ **基于 Python 的多平台媒体原生本地解析系统** -[![License](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE) [![Python Version](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/) [![Flask](https://img.shields.io/badge/Framework-Flask-000000?logo=flask&logoColor=white)](https://flask.palletsprojects.com/) [![Docker](https://img.shields.io/badge/Docker-Ready-2496ED?logo=docker&logoColor=white)](#-部署指南) [![Support](https://img.shields.io/badge/support-41%20Platforms-brightgreen.svg)](#-支持的平台矩阵) +[![License](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE) [![Python Version](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/) [![Flask](https://img.shields.io/badge/Framework-Flask-000000?logo=flask&logoColor=white)](https://flask.palletsprojects.com/) [![Docker](https://img.shields.io/badge/Docker-Ready-2496ED?logo=docker&logoColor=white)](#-部署指南) [![Support](https://img.shields.io/badge/support-42%20Platforms-brightgreen.svg)](#-支持的平台矩阵)

解析逻辑 • @@ -63,6 +63,7 @@ | **Soul** | ✓ | ✓ | ✓ | ✓ | ✓ | | | | | **汽水音乐** | ✓ | ✓ | ✓ | ✓ | | ✓ | ✓ | | | **QQ音乐** | ✓ | ✓ | ✓ | ✓ | | | | | +| **网易云音乐** | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | | **腾讯频道** | ✓ | ✓ | ✓ | ✓ | | | | | | **剪映 / CapCut** | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | | | | **快影** | ✓ | ✓ | ✓ | ✓ | | ✓ | | | @@ -94,7 +95,7 @@ ### Cookie 配置(Docker 与 Python 环境运行通用) -大多数平台无需登录态即可解析;如需按需增强部分特定功能(如抖音放映厅长片、豆包无水印视频、视频号等),请先复制环境变量示例文件: +大多数平台无需登录态即可解析;如需按需增强部分特定功能(如豆包无水印视频、微信视频号等),请先复制环境变量示例文件: ```bash cp .env.example .env @@ -104,7 +105,7 @@ cp .env.example .env 1. **抖音放映厅长视频 (`DOUYIN_COOKIE`)**: * 仅在解析放映厅/影视长片/演唱会大片等强风控内容时才需要配置。推荐精简 Cookie 配置 `s_v_web_id=xxx; __ac_nonce=xxx`,该字段**不是个人账号登录信息**,仅为字节安全 SDK 的人机风控通行证。日常 99% 的普通短视频、图文笔记、LivePhoto、原声音乐等**完全免 Cookie 匿名解析**。 -2. **豆包视频 (`DOUBAO_COOKIE`)**: +2. **豆包无水印视频 (`DOUBAO_COOKIE`)**: * 用于解密获取 1080P 原始纯净无水印视频。由于该字段包含豆包的个人账号登录会话凭证,**建议使用闲置小号**。推荐精简 Cookie 配置 `sessionid_ss=xxx`。未配置时仍可解析公开图片与带水印预览切片。 3. **微信视频号视频 (`YUANBAO_COOKIE`)**: * 通过腾讯元宝接口提取视频号原始流。由于该接口绑定了腾讯元宝的账号会话(属于个人账号登录凭证),**建议使用闲置小号**。推荐精简 Cookie 配置 `hy_user=xxx; hy_token=xxx`。未配置时仅可获取除视频外的其他信息。 @@ -153,17 +154,17 @@ media-parser/ │ ├── architecture.md # 系统分层架构与生命周期设计 │ ├── reverse-guide.md # 通用逆向方法论 (抓包/SSR/JS签名提取) │ ├── testing.md # 完整测试规范与回归手册 -│ └── parsers/ # 38 份逆向分析文档,覆盖 41 个平台 +│ └── parsers/ # 39 份逆向分析文档,覆盖 42 个平台 ├── src/ # 核心业务逻辑 │ ├── api/ # RESTful API 路由 (/api/parse, /api/health) │ ├── web/ # Demo 体验页与交互蓝图 -│ ├── parsers/ # 38 个解析器模块,支持 41 个平台 (核心解析逻辑) +│ ├── parsers/ # 39 个解析器模块,支持 42 个平台 (核心解析逻辑) │ └── parser_factory.py # 工厂分发器 (解析器动态发现与自动注册) ├── utils/ # 底层工具库与逆向支持 │ ├── signer/ # JS 签名沙箱引擎 (a_bogus, x_bogus 等算法执行) │ └── web_fetcher.py # 智能 URL 识别、重定向追踪与请求封装 ├── tests/ # 完备的双层测试体系 -│ ├── live_parser_samples.json # 41 平台真实多形态在线样本库 +│ ├── live_parser_samples.json # 42 平台真实多形态在线样本库 │ ├── manual_verify_parsers.py # 命令行交互式冒烟与健康检查工具 │ └── test_*_parser.py # 各平台 Mock 自动化单元测试 ├── static/ & templates/ # Web 演示页面前端静态资源 @@ -177,7 +178,7 @@ media-parser/ * 🏗️ **[系统架构与生命周期设计](docs/architecture.md)**:分层设计、302 追踪与 `ParserFactory` 动态发现机制。 * 🔍 **[通用逆向方法论](docs/reverse-guide.md)**:SSR 数据提取、H5 接口伪装、JS 签名沙箱及抓包 SOP。 * 🧪 **[测试体系与回归验证](docs/testing.md)**:Pytest 单元测试、Mock 与线上真实样例回归。 -* 📚 **[平台逆向指南索引](docs/index.md)**:包含抖音、快手、小红书、B站等全部 41 个平台的技术文档。 +* 📚 **[平台逆向指南索引](docs/index.md)**:包含抖音、快手、小红书、B站等全部 42 个平台的技术文档。 --- @@ -186,7 +187,7 @@ media-parser/ 本项目拥有完备的测试体系,包括基础单元测试与基于真实样本库的在线回归测试: ### 1. 真实样本交互式验证 -样例测试库见 [`tests/live_parser_samples.json`](tests/live_parser_samples.json),用于实时验证 41 个平台的解析有效性与多形态覆盖: +样例测试库见 [`tests/live_parser_samples.json`](tests/live_parser_samples.json),用于实时验证 42 个平台的解析有效性与多形态覆盖: ```bash # 快速冒烟测试(每个平台测 1 条最具代表性的链接,极速完成健康检查) diff --git a/configs/business_config.json b/configs/business_config.json index aac4b76..9084b5c 100755 --- a/configs/business_config.json +++ b/configs/business_config.json @@ -88,6 +88,11 @@ "i2.y.qq.com": "QQ音乐", "y.qq.com": "QQ音乐", "www.y.qq.com": "QQ音乐", + "163cn.tv": "网易云音乐", + "music.163.com": "网易云音乐", + "www.music.163.com": "网易云音乐", + "y.music.163.com": "网易云音乐", + "fn.music.163.com": "网易云音乐", "pd.qq.com": "腾讯频道", "lv.ulikecam.com": "剪映", "www.capcut.cn": "剪映", diff --git a/docs/index.md b/docs/index.md index 4b094a1..99c02a3 100644 --- a/docs/index.md +++ b/docs/index.md @@ -2,7 +2,7 @@ 欢迎查阅 **Media Parser** 开发者文档与逆向工程知识库。 -本项目是一个高性能、模块化、支持 **41 个主流媒体与 AI 内容平台** 的无水印音视频、图文及 LivePhoto 结构化解析引擎。 +本项目是一个高性能、模块化、支持 **42 个主流媒体与 AI 内容平台** 的无水印音视频、图文及 LivePhoto 结构化解析引擎。 --- @@ -16,7 +16,7 @@ * **图文与综合社区**:[小红书](parsers/xiaohongshu.md) | [微信公众号](parsers/wechat-mp.md) | [微博](parsers/weibo.md) | [知乎](parsers/zhihu.md) | [闲鱼](parsers/xianyu.md) | [Soul](parsers/soul.md) * **长视频与弹幕/创作**:[哔哩哔哩](parsers/bilibili.md) | [AcFun](parsers/acfun.md) | [新片场](parsers/xinpianchang.md) | [好看视频](parsers/haokan.md) | [西瓜视频](parsers/xigua.md) | [剪映](parsers/jianying.md) | [快影](parsers/kwaiying.md) * **AI 生成与大模型**:[豆包 AI](parsers/doubao.md) | [腾讯元宝](parsers/yuanbao.md) | [即梦 AI](parsers/jimeng.md) | [可灵 AI](parsers/kling.md) | [海螺 AI](parsers/hailuo.md) | [通义千问](parsers/qianwen.md) | [夸克 AI](parsers/quark-ai.md) | [小云雀 AI](parsers/xiaoyunque.md) - * **音频与垂直频道**:[汽水音乐](parsers/qsmusic.md) | [QQ音乐](parsers/qqmusic.md) | [全民K歌](parsers/quanminkge.md) | [虎牙](parsers/huya.md) | [梨视频](parsers/lishipin.md) | [微信视频号](parsers/wechat-channels.md) | [腾讯频道](parsers/tencent-channel.md) + * **音频与垂直频道**:[汽水音乐](parsers/qsmusic.md) | [QQ音乐](parsers/qqmusic.md) | [网易云音乐](parsers/netease-music.md) | [全民K歌](parsers/quanminkge.md) | [虎牙](parsers/huya.md) | [梨视频](parsers/lishipin.md) | [微信视频号](parsers/wechat-channels.md) | [腾讯频道](parsers/tencent-channel.md) --- @@ -70,6 +70,7 @@ | 39 | **红果短剧** | 短剧视频 | ✅ 支持 | 🟢 免配置 | H5 推广页 HTML 提取 | [查看指南](parsers/fanqie.md) | | 40 | **红果漫剧** | 漫剧/短剧视频 | ✅ 支持 | 🟢 免配置 | H5 推广页 HTML 提取 | [查看指南](parsers/fanqie.md) | | 41 | **QQ音乐** | MV / 分享视频 / 多档 MP4 | ✅ 支持 | 🟢 免配置 | SSR 元数据 + MusicU 播放接口 | [查看指南](parsers/qqmusic.md) | +| 42 | **网易云音乐** | MV / Mlog / 歌曲 / 动态图集与 LivePhoto | ✅ 支持 | 🟢 公开内容免配置 | SSR / Event 数据 + 公开播放接口 | [查看指南](parsers/netease-music.md) | --- diff --git a/docs/parsers/netease-music.md b/docs/parsers/netease-music.md new file mode 100644 index 0000000..41efc60 --- /dev/null +++ b/docs/parsers/netease-music.md @@ -0,0 +1,59 @@ +# 网易云音乐解析指南 + +## 支持范围 + +- `163cn.tv` 分享短链 +- `fn.music.163.com` 的 MV 与 Mlog 分享页 +- `music.163.com/mv?id=...` 与 `music.163.com/song?id=...` +- `music.163.com/event?id=...` 和 `y.music.163.com/m/event?id=...` +- MV / 动态视频多清晰度、免费歌曲完整音频、歌词、图集与 LivePhoto + +## 分类解析 + +### MV + +通过公开的 MV 详情接口获取标题、封面、歌手及带时效签名的 `brs` 播放地址,按 1080P、720P、480P 等清晰度降序输出。 + +### Mlog 动态视频 + +读取分享页的 `window.__INITIAL_PROPS__`,从 `mlogInfo.resource.content.video.urlInfos` 获取多档签名视频,并提取发布者、封面和正文。 + +### Event 动态 + +旧版 Event 分享需要访问桌面落地页并解析 `event-data`: + +- `pics[].originUrl` 作为原图; +- `videoOriginalUrl` / `videoUrl` 作为 LivePhoto 动态部分; +- 关联免费歌曲继续请求完整音频与 LRC 歌词; +- Event 内的视频资源进入 `video_url` / `video_list`。 + +### 普通歌曲 + +歌曲详情通过公开接口获取;只有接口明确返回完整播放 URL 时才填写 `audio_url`。会员、付费、下架或区域受限歌曲不会把试听片段伪装成完整音频。 + +## 返回字段 + +| 字段 | 内容 | +| --- | --- | +| `video_id` | MV、Mlog、Event 或歌曲 ID | +| `title` | MV 名、动态标题或歌曲名 | +| `author` | 歌手或动态发布者 | +| `cover_url` | MV 封面、视频帧、专辑图或动态首图 | +| `video_url` | 最高可用清晰度视频 | +| `video_list` | 多档视频地址 | +| `audio_url` | 可公开播放的完整歌曲音频 | +| `subtitles` | LRC 转换后的时间轴歌词 | +| `image_list` | 动态原图及可选 `live_photo_url` | + +## 限制 + +- 音频和视频 URL 带短期签名,应在解析后及时使用。 +- 会员、付费、下架、私密或区域受限内容可能仅返回元数据。 +- 已删除的旧 Event 无法恢复其媒体内容。 + +## 验证 + +```bash +python3 -m unittest tests.test_netease_music_parser +python3 tests/manual_verify_parsers.py --platform "网易云音乐" +``` diff --git a/docs/testing.md b/docs/testing.md index 8b59aff..cb2772b 100644 --- a/docs/testing.md +++ b/docs/testing.md @@ -13,7 +13,7 @@ tests/ ├── test_parser_factory.py # 解析器自动注册与工厂路由测试 ├── test_web_fetcher.py # 302跳转与URL正则提取测试 ├── test_*_parser.py # 各平台专属的单元测试 -├── live_parser_samples.json # 真实线上验证样本库 (41+ 平台活跃样例) +├── live_parser_samples.json # 真实线上验证样本库 (42+ 平台活跃样例) ├── test_live_parser_samples.py # 自动化执行样本库回归测试 └── manual_verify_parsers.py # 命令行交互式/全量人工排查脚本 ``` @@ -48,10 +48,10 @@ pytest tests/test_live_parser_samples.py -s ``` ### 4. 运行交互式真实样本回归验证工具 -[tests/manual_verify_parsers.py](file:///Users/leo/Projects/media-parser/tests/manual_verify_parsers.py) 支持对 41+ 个平台的多种形态(短链、长链、视频、图集等)发起真实网络请求与字段契约校验: +[tests/manual_verify_parsers.py](file:///Users/leo/Projects/media-parser/tests/manual_verify_parsers.py) 支持对 42+ 个平台的多种形态(短链、长链、视频、图集等)发起真实网络请求与字段契约校验: ```bash -# 1. 快速冒烟测试 (每个平台只测 1 条最具代表性的链接,极速完成 41 平台基准健康检查) +# 1. 快速冒烟测试 (每个平台只测 1 条最具代表性的链接,极速完成 42 平台基准健康检查) python3 tests/manual_verify_parsers.py --limit 1 # 2. 验证指定平台的多形态覆盖 (支持重复传入多个 --platform 参数) diff --git a/src/parsers/netease_music_parser.py b/src/parsers/netease_music_parser.py new file mode 100644 index 0000000..7c99481 --- /dev/null +++ b/src/parsers/netease_music_parser.py @@ -0,0 +1,362 @@ +"""网易云音乐歌曲、MV、Mlog 与动态分享解析器。""" + +import html +import json +import re +from urllib.parse import parse_qs, urlencode, urlparse + +from configs.logging_config import get_logger +from src.parser_factory import register_parser +from src.parsers.base_parser import BaseParser + + +logger = get_logger(__name__) + + +@register_parser("网易云音乐") +class NeteaseMusicParser(BaseParser): + MOBILE_UA = ( + "Mozilla/5.0 (iPhone; CPU iPhone OS 18_0 like Mac OS X) " + "AppleWebKit/605.1.15 (KHTML, like Gecko) Version/18.0 Mobile/15E148 Safari/604.1" + ) + DESKTOP_UA = ( + "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) " + "AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0 Safari/537.36" + ) + + def __init__(self, real_url): + super().__init__(real_url) + self.headers = {"User-Agent": self.MOBILE_UA, "Referer": "https://music.163.com/"} + self.title = "" + self.cover_url = None + self.video_list = [] + self.audio_url = None + self.image_list = [] + self.subtitles = None + self.author = {"nickname": "", "author_id": "", "avatar": ""} + self.media_type, self.media_id = self._detect_media(real_url) + self._parse() + + @staticmethod + def _detect_media(url): + parsed = urlparse(url or "") + params = parse_qs(parsed.query) + path = parsed.path.lower() + media_id = (params.get("id") or [None])[0] + if "/landing/mlog" in path: + return "mlog", media_id + if "/landing/mv" in path or re.search(r"/(?:mv|mvdetail)(?:/|$)", path): + return "mv", media_id or parsed.path.rstrip("/").split("/")[-1] + if "/event" in path: + return "event", media_id + if "/song" in path: + return "song", media_id + return None, media_id + + def _parse(self): + if self.media_type == "mv": + self._parse_mv() + elif self.media_type == "mlog": + self._parse_mlog() + elif self.media_type == "event": + self._parse_event() + elif self.media_type == "song": + self._parse_song(self.media_id) + + def _request_json(self, url, params=None): + try: + response = self.session.get(url, params=params, headers=self.headers, timeout=10) + response.raise_for_status() + payload = response.json() + return payload if isinstance(payload, dict) else {} + except Exception as exc: + logger.warning("Failed to fetch NetEase Music API %s: %s", url, exc) + return {} + + def _parse_mv(self): + if not self.media_id: + return + payload = self._request_json( + "https://music.163.com/api/mv/detail", + {"id": self.media_id}, + ) + data = payload.get("data") or {} + self.title = data.get("name") or "" + self.cover_url = data.get("cover") + artists = data.get("artists") or [] + if artists and isinstance(artists[0], dict): + artist = artists[0] + self.author = { + "nickname": artist.get("name") or data.get("artistName") or "", + "author_id": str(artist.get("id") or data.get("artistId") or ""), + "avatar": artist.get("img1v1Url") or "", + } + elif data.get("artistName"): + self.author["nickname"] = data["artistName"] + self.author["author_id"] = str(data.get("artistId") or "") + + streams = [] + for quality, url in (data.get("brs") or {}).items(): + if self._valid_url(url): + try: + rank = int(quality) + except (TypeError, ValueError): + rank = 0 + streams.append((rank, url)) + streams.sort(key=lambda item: item[0], reverse=True) + self.video_list = self._unique(url for _, url in streams) + + def _parse_mlog(self): + payload = self._fetch_initial_props(self.real_url, self.MOBILE_UA) + info = payload.get("mlogInfo") or {} + resource = info.get("resource") or {} + content = resource.get("content") or {} + profile = resource.get("profile") or {} + video = content.get("video") or {} + + self._set_author(profile) + self.title = ( + content.get("title") + or content.get("text") + or (f"{self.author['nickname']}的音乐动态" if self.author["nickname"] else "网易云音乐动态") + ) + self.cover_url = ( + video.get("coverUrl") + or video.get("frameUrl") + or ((video.get("frameImage") or {}).get("imageUrl")) + ) + self.video_list = self._ranked_urls(video.get("urlInfos") or []) + if not self.video_list: + fallback = ((video.get("urlInfo") or {}).get("url")) + self.video_list = [fallback] if self._valid_url(fallback) else [] + self.image_list = self._extract_images(content.get("image") or []) + + song = content.get("song") or resource.get("song") or {} + if song.get("id") and not self.video_list: + self._parse_song(song["id"], fallback=song) + + def _parse_event(self): + if not self.media_id: + return + parsed = urlparse(self.real_url) + params = parse_qs(parsed.query) + query = {"id": self.media_id} + if uid := (params.get("uid") or params.get("userid") or [None])[0]: + query["uid"] = uid + url = f"https://music.163.com/event?{urlencode(query)}" + payload = self._fetch_event_data(url) + if not payload: + return + + user = payload.get("user") or {} + self._set_author(user) + try: + content = json.loads(payload.get("json") or "{}") + except json.JSONDecodeError: + content = {} + + song = content.get("song") or {} + self.title = content.get("title") or content.get("msg") or song.get("name") or "" + self.image_list = self._extract_event_images(payload.get("pics") or []) + if self.image_list: + first = self.image_list[0] + self.cover_url = first.get("url") if isinstance(first, dict) else first + + video_data = content.get("videoData") or {} + self.video_list = self._extract_nested_video_urls(video_data) + if song.get("id"): + self._parse_song(song["id"], fallback=song, preserve_title=True) + + def _parse_song(self, song_id, fallback=None, preserve_title=False): + if not song_id: + return + try: + numeric_id = int(song_id) + except (TypeError, ValueError): + return + detail = self._request_json( + "https://music.163.com/api/song/detail/", + {"id": numeric_id, "ids": json.dumps([numeric_id])}, + ) + songs = detail.get("songs") or [] + song = songs[0] if songs and isinstance(songs[0], dict) else (fallback or {}) + if not preserve_title or not self.title: + self.title = song.get("name") or self.title + album = song.get("album") or {} + self.cover_url = self.cover_url or album.get("picUrl") or album.get("blurPicUrl") + artists = song.get("artists") or [] + if artists and isinstance(artists[0], dict) and not self.author["nickname"]: + artist = artists[0] + self.author = { + "nickname": artist.get("name") or "", + "author_id": str(artist.get("id") or ""), + "avatar": artist.get("img1v1Url") or artist.get("picUrl") or "", + } + + player = self._request_json( + "https://music.163.com/api/song/enhance/player/url", + {"id": numeric_id, "ids": json.dumps([numeric_id]), "br": 320000}, + ) + entries = player.get("data") or [] + if entries and isinstance(entries[0], dict) and self._valid_url(entries[0].get("url")): + self.audio_url = entries[0]["url"] + self._parse_lyrics(numeric_id) + + def _parse_lyrics(self, song_id): + payload = self._request_json( + "https://music.163.com/api/song/lyric", + {"id": song_id, "lv": 1, "kv": 1, "tv": -1}, + ) + lyric = ((payload.get("lrc") or {}).get("lyric")) + if not isinstance(lyric, str): + return + subtitles = [] + for line in lyric.splitlines(): + match = re.match(r"\[(\d+):(\d+(?:\.\d+)?)\](.*)", line.strip()) + if match and match.group(3).strip(): + start = int(match.group(1)) * 60 + float(match.group(2)) + subtitles.append({"start": round(start, 3), "text": match.group(3).strip()}) + self.subtitles = subtitles or None + + def _fetch_initial_props(self, url, user_agent): + try: + response = self.session.get( + url, + headers={"User-Agent": user_agent, "Referer": "https://music.163.com/"}, + allow_redirects=True, + timeout=10, + ) + response.raise_for_status() + self.html_content = response.text + except Exception as exc: + logger.warning("Failed to fetch NetEase Music share page: %s", exc) + return {} + match = re.search( + r"window\.__INITIAL_PROPS__\s*=\s*(\{.*?\})\s*", + self.html_content or "", + re.DOTALL, + ) + if not match: + return {} + try: + return json.loads(match.group(1)) + except json.JSONDecodeError as exc: + logger.warning("Failed to parse NetEase Music initial props: %s", exc) + return {} + + def _fetch_event_data(self, url): + try: + response = self.session.get( + url, + headers={"User-Agent": self.DESKTOP_UA, "Referer": "https://music.163.com/"}, + timeout=10, + ) + response.raise_for_status() + except Exception as exc: + logger.warning("Failed to fetch NetEase Music event: %s", exc) + return {} + match = re.search( + r']+id="event-data"[^>]*>\s*(.*?)\s*', + response.text or "", + re.DOTALL, + ) + if not match: + return {} + try: + return json.loads(html.unescape(match.group(1))) + except json.JSONDecodeError as exc: + logger.warning("Failed to parse NetEase Music event data: %s", exc) + return {} + + def _set_author(self, profile): + if not isinstance(profile, dict): + return + self.author = { + "nickname": profile.get("nickname") or profile.get("name") or "", + "author_id": str(profile.get("userId") or profile.get("id") or ""), + "avatar": profile.get("avatarUrl") or profile.get("avatar") or "", + } + + @classmethod + def _ranked_urls(cls, entries): + ranked = [] + for entry in entries: + if not isinstance(entry, dict) or not cls._valid_url(entry.get("url")): + continue + quality = entry.get("resolution") or entry.get("r") or 0 + ranked.append((quality if isinstance(quality, (int, float)) else 0, entry["url"])) + ranked.sort(key=lambda item: item[0], reverse=True) + return cls._unique(url for _, url in ranked) + + @classmethod + def _extract_images(cls, entries): + images = [] + for entry in entries: + if isinstance(entry, str) and cls._valid_url(entry): + images.append(entry) + elif isinstance(entry, dict): + url = entry.get("originUrl") or entry.get("url") or entry.get("imageUrl") or entry.get("picUrl") + if cls._valid_url(url): + images.append(url) + return cls._unique(images) + + @classmethod + def _extract_event_images(cls, entries): + images = [] + for entry in entries: + if not isinstance(entry, dict): + continue + url = entry.get("originUrl") or entry.get("pcRectangleUrl") or entry.get("rectangleUrl") + if not cls._valid_url(url): + continue + live_url = entry.get("videoOriginalUrl") or entry.get("videoUrl") + images.append( + {"url": url, "live_photo_url": live_url if cls._valid_url(live_url) else None} + ) + return images + + @classmethod + def _extract_nested_video_urls(cls, value): + found = [] + if isinstance(value, dict): + for key, child in value.items(): + if "url" in key.lower() and cls._valid_url(child) and child.lower().split("?", 1)[0].endswith((".mp4", ".mov", ".m3u8")): + found.append(child) + else: + found.extend(cls._extract_nested_video_urls(child)) + elif isinstance(value, list): + for child in value: + found.extend(cls._extract_nested_video_urls(child)) + return cls._unique(found) + + @staticmethod + def _valid_url(value): + return isinstance(value, str) and value.startswith(("http://", "https://")) + + @staticmethod + def _unique(values): + return list(dict.fromkeys(value for value in values if value)) + + def get_real_video_url(self): + return self.video_list[0] if self.video_list else None + + def get_video_list(self): + return self.video_list + + def get_audio_url(self): + return self.audio_url + + def get_title_content(self): + return self.title + + def get_cover_photo_url(self): + return self.cover_url + + def get_author_info(self): + return self.author + + def get_image_list(self): + return self.image_list + + def get_subtitles(self): + return self.subtitles diff --git a/tests/live_parser_samples.json b/tests/live_parser_samples.json index e3896ca..d62bf80 100644 --- a/tests/live_parser_samples.json +++ b/tests/live_parser_samples.json @@ -1,8 +1,57 @@ { "schema_version": 2, - "description": "41 平台多形态全景自动化回归测试用例库 (涵盖短链/长链/图集/单视频/AI生成等)", - "total_cases": 290, + "description": "42 平台多形态全景自动化回归测试用例库 (涵盖短链/长链/图集/单视频/AI生成等)", + "total_cases": 293, "cases": [ + { + "platform": "网易云音乐", + "url": "https://163cn.tv/beBkdACV", + "media_types": [ + "audio", + "images", + "live_media" + ], + "expected_fields": [ + "audio", + "images", + "live_media", + "cover", + "title", + "author" + ], + "note": "2026-09-01 已验证: 网易云短链 Event,包含歌曲、图集、LivePhoto 与歌词", + "pattern": "Event 音乐图文与实况" + }, + { + "platform": "网易云音乐", + "url": "https://163cn.tv/ba6qK0Lv", + "media_types": [ + "video" + ], + "expected_fields": [ + "video", + "cover", + "title", + "author" + ], + "note": "2026-09-01 已验证: 网易云 Mlog 分享短链,多档签名视频", + "pattern": "Mlog 动态视频" + }, + { + "platform": "网易云音乐", + "url": "https://fn.music.163.com/g/mlog/mlog-mobile/landing/mv?id=34781314&userid=12112389178", + "media_types": [ + "video" + ], + "expected_fields": [ + "video", + "cover", + "title", + "author" + ], + "note": "2026-09-01 已验证: 网易云 MV 分享,可提取 1080P 至 240P 多档 MP4", + "pattern": "MV 多清晰度" + }, { "platform": "QQ音乐", "url": "https://c6.y.qq.com/base/fcgi-bin/u?__=eZmYFaYs9yHY", diff --git a/tests/test_netease_music_parser.py b/tests/test_netease_music_parser.py new file mode 100644 index 0000000..070e918 --- /dev/null +++ b/tests/test_netease_music_parser.py @@ -0,0 +1,172 @@ +import html +import json +import unittest +from unittest.mock import Mock, patch + +from src.parsers.netease_music_parser import NeteaseMusicParser + + +class NeteaseMusicParserTest(unittest.TestCase): + @staticmethod + def response(*, text="", payload=None, url="https://music.163.com/"): + response = Mock() + response.text = text + response.url = url + response.json.return_value = payload or {} + response.raise_for_status.return_value = None + return response + + @staticmethod + def initial_html(key, value): + payload = {key: value, "isServerError": False} + return f"" + + @patch("src.parsers.base_parser.requests.Session.get") + def test_parses_mv_with_highest_quality_first(self, get): + get.return_value = self.response( + payload={ + "code": 200, + "data": { + "id": 34781314, + "name": "透明爱人", + "cover": "http://p1.music.126.net/cover.jpg", + "artistName": "白鹿", + "artistId": 12603258, + "artists": [{"id": 12603258, "name": "白鹿"}], + "brs": { + "480": "http://vod.126.net/480.mp4", + "1080": "http://vod.126.net/1080.mp4", + "720": "http://vod.126.net/720.mp4", + }, + }, + } + ) + parser = NeteaseMusicParser( + "https://fn.music.163.com/g/mlog/mlog-mobile/landing/mv?id=34781314" + ) + self.assertEqual(parser.get_title_content(), "透明爱人") + self.assertEqual(parser.get_author_info()["nickname"], "白鹿") + self.assertEqual(parser.get_real_video_url(), "http://vod.126.net/1080.mp4") + self.assertEqual(len(parser.get_video_list()), 3) + + @patch("src.parsers.base_parser.requests.Session.get") + def test_parses_mlog_signed_video_and_profile(self, get): + mlog = { + "resource": { + "content": { + "title": "动态视频", + "image": [], + "video": { + "coverUrl": "http://p1.music.126.net/mlog-cover.jpg", + "urlInfos": [ + {"resolution": 360, "url": "http://vod.126.net/360.mp4"}, + {"resolution": 1080, "url": "http://vod.126.net/1080.mp4"}, + ], + }, + }, + "profile": { + "userId": 123, + "nickname": "云村用户", + "avatarUrl": "http://p1.music.126.net/avatar.jpg", + }, + } + } + get.return_value = self.response(text=self.initial_html("mlogInfo", mlog)) + parser = NeteaseMusicParser( + "https://fn.music.163.com/g/mlog/mlog-mobile/landing/mlog?id=a123&type=2" + ) + self.assertEqual(parser.get_title_content(), "动态视频") + self.assertEqual(parser.get_author_info()["author_id"], "123") + self.assertEqual(parser.get_real_video_url(), "http://vod.126.net/1080.mp4") + + @patch("src.parsers.base_parser.requests.Session.get") + def test_parses_event_images_livephotos_and_free_song(self, get): + event = { + "user": { + "userId": 456, + "nickname": "动态作者", + "avatarUrl": "http://p1.music.126.net/event-avatar.jpg", + }, + "json": json.dumps( + { + "title": "动态标题", + "msg": "动态正文", + "song": {"id": 3383347615, "name": "念张师"}, + "videoData": None, + }, + ensure_ascii=False, + ), + "pics": [ + { + "originUrl": "http://p1.music.126.net/photo.jpg", + "videoOriginalUrl": "http://vod.126.net/live.mov", + } + ], + } + event_html = ( + '" + ) + + def side_effect(url, **kwargs): + if "/event" in url: + return self.response(text=event_html) + if "/song/detail/" in url: + return self.response( + payload={ + "songs": [ + { + "id": 3383347615, + "name": "念张师", + "album": {"picUrl": "http://p1.music.126.net/album.jpg"}, + "artists": [{"id": 1, "name": "歌手"}], + } + ] + } + ) + if "/player/url" in url: + return self.response(payload={"data": [{"url": "http://m801.music.126.net/song.mp3"}]}) + return self.response(payload={"lrc": {"lyric": "[00:01.50]第一句\n[00:03.00]第二句"}}) + + get.side_effect = side_effect + parser = NeteaseMusicParser( + "https://music.163.com/event?id=37613855054&uid=13685426555" + ) + self.assertEqual(parser.get_title_content(), "动态标题") + self.assertEqual(parser.get_audio_url(), "http://m801.music.126.net/song.mp3") + self.assertEqual(parser.get_image_list()[0]["live_photo_url"], "http://vod.126.net/live.mov") + self.assertEqual(parser.get_subtitles()[0], {"start": 1.5, "text": "第一句"}) + + @patch("src.parsers.base_parser.requests.Session.get") + def test_paid_song_does_not_return_fake_audio(self, get): + def side_effect(url, **kwargs): + if "/song/detail/" in url: + return self.response( + payload={ + "songs": [ + { + "id": 472137906, + "name": "时差", + "album": {"picUrl": "http://p1.music.126.net/album.jpg"}, + "artists": [{"id": 1, "name": "鹿晗"}], + } + ] + } + ) + return self.response(payload={"data": [{"url": None}], "lrc": {}}) + + get.side_effect = side_effect + parser = NeteaseMusicParser("https://music.163.com/song?id=472137906") + self.assertEqual(parser.get_title_content(), "时差") + self.assertIsNone(parser.get_audio_url()) + + @patch("src.parsers.base_parser.requests.Session.get") + def test_invalid_song_id_fails_cleanly(self, get): + parser = NeteaseMusicParser("https://music.163.com/song?id=invalid") + get.assert_not_called() + self.assertIsNone(parser.get_audio_url()) + + +if __name__ == "__main__": + unittest.main() diff --git a/tests/test_web_fetcher.py b/tests/test_web_fetcher.py index a09ce35..5c9d604 100644 --- a/tests/test_web_fetcher.py +++ b/tests/test_web_fetcher.py @@ -43,6 +43,14 @@ class UrlParserTest(unittest.TestCase): "https://i2.y.qq.com/n3/other/pages/details/mv.html?vid=012XViNT0znYUR&noise=x", "https://i2.y.qq.com/n3/other/pages/details/mv.html?vid=012XViNT0znYUR", ), + ( + "https://fn.music.163.com/g/mlog/mlog-mobile/landing/mlog?id=a123&type=2&userid=456&noise=x", + "https://fn.music.163.com/g/mlog/mlog-mobile/landing/mlog?id=a123&userid=456&type=2", + ), + ( + "https://music.163.com/#/song?id=3383347615&noise=x", + "https://music.163.com/song?id=3383347615", + ), ("https://pd.qq.com/s/code?b=2&noise=x", "https://pd.qq.com/s/code?b=2"), ("https://video.weibo.com/show?fid=1034:123&noise=x", "https://video.weibo.com/show?fid=1034%3A123"), ( @@ -177,6 +185,11 @@ class UrlParserTest(unittest.TestCase): self.assertEqual(UrlParser.get_platform("https://i2.y.qq.com/n3/other/pages/details/mv.html?vid=abc"), "QQ音乐") self.assertEqual(UrlParser.get_platform("https://y.qq.com/n/ryqq/mv/abc"), "QQ音乐") + def test_recognizes_netease_music_domains(self): + self.assertEqual(UrlParser.get_platform("https://163cn.tv/abc123"), "网易云音乐") + self.assertEqual(UrlParser.get_platform("https://music.163.com/song?id=1"), "网易云音乐") + self.assertEqual(UrlParser.get_platform("https://fn.music.163.com/g/mlog/x"), "网易云音乐") + def test_recognizes_xigua_video_on_iesdouyin_domain(self): self.assertEqual( UrlParser.get_platform("https://www.iesdouyin.com/xg/video/7676450021063735414/"), @@ -282,6 +295,18 @@ class WebFetcherTest(unittest.TestCase): "https://i2.y.qq.com/n3/other/pages/details/mv.html?vid=012XViNT0znYUR", ) + def test_follows_netease_short_link_and_preserves_event_id(self): + redirect_url = "https://y.music.163.com/m/event?id=37826361829&uid=5153433584&dlt=0846" + with patch( + "utils.web_fetcher.requests.get", + return_value=self.response(redirect_url), + ): + result = WebFetcher.fetch_redirect_url("https://163cn.tv/beBkdACV") + self.assertEqual( + result, + "https://y.music.163.com/m/event?id=37826361829&uid=5153433584", + ) + def test_stops_before_login_or_verification_page(self): for blocked_path in ("/login", "/404", "/captcha", "/verify", "/error"): with self.subTest(blocked_path=blocked_path): diff --git a/utils/web_fetcher.py b/utils/web_fetcher.py index 0a1ad79..bc1d341 100755 --- a/utils/web_fetcher.py +++ b/utils/web_fetcher.py @@ -221,6 +221,21 @@ class UrlParser: preserved_params.append((key, value)) if preserved_params: address = f"{address}?{urlencode(preserved_params)}" + elif platform == "网易云音乐": + query_params = parse_qs(parsed_url.query) + fragment = parsed_url.fragment.lstrip("/") + if "?" in fragment: + fragment_path, fragment_query = fragment.split("?", 1) + if fragment_path in {"song", "mv", "event"}: + address = f"{parsed_url.scheme}://{domain}/{fragment_path}" + query_params = parse_qs(fragment_query) + preserved_params = [] + for key in ("id", "uid", "userid", "type", "eventId", "songId"): + value = query_params.get(key, [None])[0] + if value is not None and value != "null": + preserved_params.append((key, value)) + if preserved_params: + address = f"{address}?{urlencode(preserved_params)}" elif platform == "腾讯频道": query_params = parse_qs(parsed_url.query) if value := query_params.get("b", [None])[0]: