hs-m3u8 0.1.2__tar.gz → 0.1.4__tar.gz

{hs_m3u8-0.1.2 → hs_m3u8-0.1.4}/PKG-INFO

@@ -1,12 +1,12 @@
-Metadata-Version: 2.3
+Metadata-Version: 2.4
 Name: hs-m3u8
-Version: 0.1.2
+Version: 0.1.4
 Summary: m3u8 下载器
 Project-URL: homepage, https://github.com/x-haose/hs-m3u8
 Project-URL: repository, https://github.com/x-haose/hs-m3u8
 Project-URL: documentation, https://github.com/x-haose/hs-m3u8
 Author-email: 昊色居士 <xhrtxh@gmail.com>
-License: MIT
+License-Expression: MIT
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: MIT License
@@ -36,6 +36,13 @@ m3u8 视频下载工具。支持大部分的m3u8视频下载。后续增加UI界
 - 可选择保留ts文件
 - 内置Windows平台ffmpeg可执行文件（由于Linux及Mac下权限问题，需自行安装ffmpeg文件）
 
+## 计划
+
+- 增加cli功能，通过终端执行命令去下载
+- 增加支持curl参数功能。直接在curl里面读取请求头及cookie
+- 编写详细文档
+- 选择一个合适的技术栈，增加UI界面
+
 ## 安装
 
 ### pip包安装

{hs_m3u8-0.1.2 → hs_m3u8-0.1.4}/README.md

@@ -10,6 +10,13 @@ m3u8 视频下载工具。支持大部分的m3u8视频下载。后续增加UI界
 - 可选择保留ts文件
 - 内置Windows平台ffmpeg可执行文件（由于Linux及Mac下权限问题，需自行安装ffmpeg文件）
 
+## 计划
+
+- 增加cli功能，通过终端执行命令去下载
+- 增加支持curl参数功能。直接在curl里面读取请求头及cookie
+- 编写详细文档
+- 选择一个合适的技术栈，增加UI界面
+
 ## 安装
 
 ### pip包安装

{hs_m3u8-0.1.2 → hs_m3u8-0.1.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "hs-m3u8"
-version = "0.1.2"
+version = "0.1.4"
 description = "m3u8 下载器"
 authors = [
     { name = "昊色居士", email = "xhrtxh@gmail.com" }
@@ -42,6 +42,7 @@ build-backend = "hatchling.build"
 managed = true
 dev-dependencies = [
     "pre-commit>=4.0.1",
+    "twine>=6.0.1",
 ]
 include = [
     "src/hs_m3u8/"
@@ -136,8 +137,8 @@ unfixable = []
 
 
 [tool.rye.scripts]
-publish_testpypi = { cmd = "rye publish --repository testpypi --repository-url https://test.pypi.org/legacy/" }
-publish_pypi = { cmd = "rye publish" }
+publish_testpypi = { cmd = "rye run twine upload -r testpypi dist/*" }
+publish_pypi = { cmd = "rye run twine upload dist/*" }
 sb = { cmd = "rye build --clean" }
 spt = { chain = ["sb", "publish_testpypi"] }
 sp = { chain = ["sb", "publish_pypi"] }

{hs_m3u8-0.1.2 → hs_m3u8-0.1.4}/requirements-dev.lock

@@ -46,6 +46,8 @@ datarecorder==3.6.2
     # via downloadkit
 distlib==0.3.9
     # via virtualenv
+docutils==0.21.2
+    # via readme-renderer
 downloadkit==2.0.5
     # via drissionpage
 drissionpage==4.1.0.12
@@ -84,8 +86,16 @@ idna==3.10
     # via requests
     # via tldextract
     # via yarl
+jaraco-classes==3.4.0
+    # via keyring
+jaraco-context==6.0.1
+    # via keyring
+jaraco-functools==4.1.0
+    # via keyring
 jmespath==1.0.1
     # via parsel
+keyring==25.6.0
+    # via twine
 loguru==0.7.2
     # via hssp
 lxml==5.3.0
@@ -93,9 +103,18 @@ lxml==5.3.0
     # via parsel
 m3u8==6.0.0
     # via hs-m3u8
+markdown-it-py==3.0.0
+    # via rich
+mdurl==0.1.2
+    # via markdown-it-py
+more-itertools==10.6.0
+    # via jaraco-classes
+    # via jaraco-functools
 multidict==6.1.0
     # via aiohttp
     # via yarl
+nh3==0.2.20
+    # via readme-renderer
 nodeenv==1.9.1
     # via pre-commit
 openpyxl==3.1.5
@@ -104,8 +123,11 @@ orderedmultidict==1.0.1
     # via furl
 packaging==24.2
     # via parsel
+    # via twine
 parsel==1.9.1
     # via hssp
+pkginfo==1.12.0
+    # via twine
 platformdirs==4.3.6
     # via virtualenv
 pre-commit==4.0.1
@@ -124,6 +146,9 @@ pydantic-core==2.23.4
     # via pydantic
 pydantic-settings==2.6.1
     # via hssp
+pygments==2.19.1
+    # via readme-renderer
+    # via rich
 python-dotenv==1.0.1
     # via pydantic-settings
 pytz==2024.2
@@ -131,14 +156,24 @@ pytz==2024.2
 pyyaml==6.0.2
     # via pre-commit
     # via pydantic-settings
+readme-renderer==44.0
+    # via twine
 requests==2.32.3
     # via downloadkit
     # via drissionpage
     # via hssp
     # via requests-file
+    # via requests-toolbelt
     # via tldextract
+    # via twine
 requests-file==2.1.0
     # via tldextract
+requests-toolbelt==1.0.0
+    # via twine
+rfc3986==2.0.0
+    # via twine
+rich==13.9.4
+    # via twine
 six==1.16.0
     # via apscheduler
     # via furl
@@ -152,6 +187,7 @@ tldextract==5.1.3
     # via drissionpage
 tomli==2.1.0
     # via pydantic-settings
+twine==6.0.1
 typing-extensions==4.12.2
     # via curl-cffi
     # via pydantic
@@ -160,6 +196,7 @@ tzlocal==5.2
     # via apscheduler
 urllib3==2.2.3
     # via requests
+    # via twine
 uvloop==0.21.0
     # via hssp
 virtualenv==20.27.1

hs_m3u8-0.1.4/src/example/kyt.py

@@ -0,0 +1,41 @@
+import asyncio
+
+from hs_m3u8 import M3u8Downloader, M3u8Key
+
+
+async def main():
+    url = "https://r1-ndr-private.ykt.cbern.com.cn/edu_product/esp/assets/68b6bed7-d093-7c8c-9133-95cf8205d21d.t/zh-CN/1712805650284/transcode/videos/68b6bed7-d093-7c8c-9133-95cf8205d21d-1920x1080-true-47fe81c5c8d91daf25e9fffd7082f934-eed6db5a85074b6dbbe5fa71f1243b26.m3u8"
+    name = "ykt"
+    headers = {
+        "Accept": "*/*",
+        "Accept-Language": "zh-CN,zh;q=0.9,en-US;q=0.8,en;q=0.7",
+        "Cache-Control": "no-cache",
+        "Connection": "keep-alive",
+        "Origin": "https://basic.smartedu.cn",
+        "Pragma": "no-cache",
+        "Referer": "https://basic.smartedu.cn/",
+        "Sec-Fetch-Dest": "empty",
+        "Sec-Fetch-Mode": "cors",
+        "Sec-Fetch-Site": "cross-site",
+        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
+        "Chrome/126.0.0.0 Safari/537.36",
+        "X-ND-AUTH": 'MAC id="7F938B205F876FC3C7550081F114A1A4028222C3BFB978FD9B439192D004CB8EEB65E66BB'
+        'C63E66FED6DD51F34F99411A6039E623E9A9D05",nonce="1742462574752:Z4IGAAV6"'
+        ',mac="EUr56dXrCO1YGd3Ub1fj9MyJY9NxQPi7ZI14N/GFwpQ="',
+        "sec-ch-ua": '"Not/A)Brand";v="8", "Chromium";v="126", "Google Chrome";v="126"',
+        "sec-ch-ua-mobile": "?0",
+        "sec-ch-ua-platform": '"Windows"',
+    }
+    key = M3u8Key(key=bytes.fromhex("34623235336163353939353834643437"))
+    dl = M3u8Downloader(
+        m3u8_url=url,
+        save_path=f"../../downloads/{name}",
+        max_workers=64,
+        headers=headers,
+        key=key,
+    )
+    await dl.run(del_hls=False, merge=True)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

hs_m3u8-0.1.4/src/example/siyuanren.py

@@ -0,0 +1,14 @@
+import asyncio
+
+from hs_m3u8 import M3u8Downloader
+
+
+async def main():
+    url = "http://1251107588.vod2.myqcloud.com/40f34e4dvodtransgzp1251107588/722ec94f387702303749471522/voddrm.token.eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9~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~OvCFF2x41XbwQK_C1fUE6Orr77BeCttlt6-H5Uj8izg.video_1407500_1.m3u8?encdomain=cmv1&sign=b574e853145eeb93fcec3b26d28b9665&t=7fffffff"
+    name = "siyuanren"
+    dl = M3u8Downloader(m3u8_url=url, save_path=f"../../downloads/{name}", max_workers=64)
+    await dl.run(del_hls=False, merge=True)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

hs_m3u8-0.1.4/src/example/x.py

@@ -0,0 +1,16 @@
+import asyncio
+
+from hs_m3u8 import M3u8Downloader
+
+
+async def main():
+    url = (
+        "https://video.twimg.com/ext_tw_video/1879556885663342592/pu/pl/Vcvv0UK9lOhezJt1.m3u8?variant_version=1&tag=12"
+    )
+    name = "x"
+    dl = M3u8Downloader(m3u8_url=url, save_path=f"../../downloads/{name}", max_workers=64)
+    await dl.run(del_hls=False, merge=True)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

hs_m3u8-0.1.4/src/hs_m3u8/__init__.py

@@ -0,0 +1,3 @@
+from hs_m3u8.main import M3u8Downloader, M3u8Key
+
+__version__ = "0.1.4"

{hs_m3u8-0.1.2 → hs_m3u8-0.1.4}/src/hs_m3u8/main.py

@@ -8,10 +8,8 @@ import posixpath
 import shutil
 import subprocess
 from collections.abc import Callable
-from enum import Enum, auto
 from hashlib import md5
 from pathlib import Path
-from typing import Any
 from urllib.parse import urljoin, urlparse
 from zipfile import ZipFile
 
@@ -46,16 +44,6 @@ def get_ffmpeg():
     return ffmpeg_bin
 
 
-class ContentType(Enum):
-    """
-    获取URL数据的，类型枚举
-    """
-
-    Text = auto()
-    Json = auto()
-    Bytes = auto()
-
-
 class M3u8Key:
     """
     M3u8key
@@ -66,8 +54,9 @@ class M3u8Key:
         :param key: 密钥
         :param iv: 偏移
         """
+        iv = bytes.fromhex(iv[2:]) if iv and iv.startswith("0x") else iv
         self.key = key
-        self.iv = iv or key
+        self.iv = iv
 
 
 class M3u8Downloader:
@@ -80,6 +69,7 @@ class M3u8Downloader:
     ts_url_list: list = []
     ts_path_list: list = []
     ts_key: M3u8Key = None
+    mp4_head_hrl: str = None
     m3u8_md5 = ""
 
     def __init__(
@@ -89,6 +79,7 @@ class M3u8Downloader:
         decrypt=False,
         max_workers=None,
         headers=None,
+        key: M3u8Key = None,
         get_m3u8_func: Callable = None,
     ):
         """
@@ -112,6 +103,7 @@ class M3u8Downloader:
         self.save_dir = Path(save_path) / "hls"
         self.save_name = Path(save_path).name
         self.key_path = self.save_dir / "key.key"
+        self.custom_key = key
 
         if not self.save_dir.exists():
             self.save_dir.mkdir(parents=True)
@@ -165,7 +157,7 @@ class M3u8Downloader:
         if not merge:
             return True
 
-        if self.merge():
+        if await self.merge():
             self.logger.info("合并成功")
         else:
             self.logger.error(
@@ -185,30 +177,6 @@ class M3u8Downloader:
         self.ts_path_list = [None] * len(self.ts_url_list)
         await asyncio.gather(*[self._download_ts(url) for url in self.ts_url_list])
 
-    async def get_url_content(self, url: str, content_type: ContentType) -> bytes | str | Any:
-        """
-        按照类型获取url内容
-        :param url: 请求地址
-        :param content_type: 内容类型
-        :return:
-        """
-        data = None
-        try:
-            resp = await self.net.get(url, headers=self.headers)
-            if content_type == ContentType.Bytes:
-                data = resp.content
-            if content_type == ContentType.Text:
-                data = resp.text
-            if content_type == ContentType.Json:
-                data = resp.json
-            if resp.status_code != 200:
-                self.logger.error(f"请求{url}内容时返回码不正确，类型为：{content_type}, 返回码为:{resp.status_code}")
-                return None
-        except BaseException as exception:
-            self.logger.error(f"请求{url}内容时发生异常，类型为：{content_type}, 异常信息为:{exception}")
-
-        return data
-
     async def get_ts_list(self, url) -> list[dict]:
         """
         解析m3u8并保存至列表
@@ -235,6 +203,14 @@ class M3u8Downloader:
             self.logger.info(f"选择的播放地址：{play_url}，比特率：{bandwidth}")
             return await self.get_ts_list(urlparse(play_url))
 
+        # 处理具有 #EXT-X-MAP:URI="*.mp4" 的情况
+        segment_map_count = len(m3u8_obj.segment_map)
+        if segment_map_count > 0:
+            if segment_map_count > 1:
+                raise ValueError("暂不支持segment_map有多个的情况，请提交issues，并告知m3u8的地址，方便做适配")
+            self.mp4_head_hrl = prefix + m3u8_obj.segment_map[0].uri
+            m3u8_obj.segment_map[0].uri = "head.mp4"
+
         # 遍历ts文件
         for index, segments in enumerate(m3u8_obj.segments):
             ts_uri = segments.uri if "http" in m3u8_obj.segments[index].uri else segments.absolute_uri
@@ -243,10 +219,16 @@ class M3u8Downloader:
 
         # 保存解密key
         if len(m3u8_obj.keys) > 0 and m3u8_obj.keys[0]:
-            resp = await self.net.get(m3u8_obj.keys[0].absolute_uri, headers=self.headers)
-            key_data = resp.content
+            iv = m3u8_obj.keys[0].iv
+            if not self.custom_key:
+                resp = await self.net.get(m3u8_obj.keys[0].absolute_uri, headers=self.headers)
+                key_data = resp.content
+            else:
+                key_data = self.custom_key.key
+                iv = self.custom_key.iv or iv
+
             self.save_file(key_data, self.key_path)
-            self.ts_key = M3u8Key(key=key_data, iv=m3u8_obj.keys[0].iv)
+            self.ts_key = M3u8Key(key=key_data, iv=iv)
             key = m3u8_obj.segments[0].key
             key.uri = "key.key"
             m3u8_obj.segments[0].key = key
@@ -271,7 +253,7 @@ class M3u8Downloader:
         if Path(ts_path).exists():
             self.ts_path_list[index] = str(ts_path)
             return
-        resp = await self.net.get(ts_item["uri"])
+        resp = await self.net.get(ts_item["uri"], self.headers)
         ts_content = resp.content
         if ts_content is None:
             return
@@ -283,7 +265,7 @@ class M3u8Downloader:
         self.logger.info(f"{ts_uri}下载成功")
         self.ts_path_list[index] = str(ts_path)
 
-    def merge(self):
+    async def merge(self):
         """
         合并ts文件为mp4文件
         :return:
@@ -301,8 +283,17 @@ class M3u8Downloader:
         # mp4路径
         mp4_path = self.save_dir.parent / f"{self.save_name}.mp4"
 
+        # 如果保护mp4的头，则把ts放到后面
+        mp4_head_data = b""
+        if self.mp4_head_hrl:
+            resp = await self.net.get(self.mp4_head_hrl)
+            mp4_head_data = resp.content
+            mp4_head_file = self.save_dir / "head.mp4"
+            mp4_head_file.write_bytes(mp4_head_data)
+
         # 把ts文件整合到一起
         big_ts_file = big_ts_path.open("ab+")
+        big_ts_file.write(mp4_head_data)
         for path in self.ts_path_list:
             with open(path, "rb") as ts_file:
                 data = ts_file.read()
@@ -316,7 +307,7 @@ class M3u8Downloader:
         ffmpeg_bin = get_ffmpeg()
         command = (
             f'{ffmpeg_bin} -i "{big_ts_path}" '
-            f'-c copy -map 0:v -map 0:a -bsf:a aac_adtstoasc -threads 32 "{mp4_path}" -y'
+            f'-c copy -map 0:v -map 0:a? -bsf:a aac_adtstoasc -threads 32 "{mp4_path}" -y'
         )
         self.logger.info(f"ts整合成功，开始转为mp4。 command：{command}")
         result = subprocess.run(command, shell=True, capture_output=True, text=True)

hs_m3u8-0.1.2/src/hs_m3u8/__init__.py

@@ -1,3 +0,0 @@
-from hs_m3u8.main import M3u8Downloader
-
-__version__ = "0.1.2"