m3u8-dl-tool 0.1.0__tar.gz

m3u8_dl_tool-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 jxwubin
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

m3u8_dl_tool-0.1.0/PKG-INFO

@@ -0,0 +1,51 @@
+Metadata-Version: 2.4
+Name: m3u8-dl-tool
+Version: 0.1.0
+Summary: 跨平台m3u8下载工具，自动过滤广告分片，多线程下载
+Author-email: jxwubin <549719522@qq.com>
+License: MIT License
+        
+        Copyright (c) 2026 jxwubin
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+Project-URL: Homepage, https://github.com/xxx/xxx
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: requests>=2.31.0
+Requires-Dist: pycryptodome>=3.19.0
+Dynamic: license-file
+
+# m3u8‑dl‑tool
+跨平台m3u8视频下载工具，自动检测并删除重复广告分片，多线程高速下载，支持Windows / macOS / Linux。
+
+## ✨功能特点
+- 多线程并发下载TS分片
+- 自动计算分片哈希，过滤重复广告TS片段
+- AES加密m3u8自动解密
+- 下载完成自动合并TS为MP4
+- 自动清理临时TS文件
+- 参数说明
+max_workers：下载并发线程数，建议 10~30，不要设置过大，避免被服务器限流
+base_dir：自定义工作目录，不填则默认使用调用脚本所在文件夹
+run (max_workers=15,start_index=0, end_index=None, base_dir=r"D:\video_download")
+
+## 安装
+```bash
+pip install m3u8-dl-tool

m3u8_dl_tool-0.1.0/README.md

@@ -0,0 +1,17 @@
+# m3u8‑dl‑tool
+跨平台m3u8视频下载工具，自动检测并删除重复广告分片，多线程高速下载，支持Windows / macOS / Linux。
+
+## ✨功能特点
+- 多线程并发下载TS分片
+- 自动计算分片哈希，过滤重复广告TS片段
+- AES加密m3u8自动解密
+- 下载完成自动合并TS为MP4
+- 自动清理临时TS文件
+- 参数说明
+max_workers：下载并发线程数，建议 10~30，不要设置过大，避免被服务器限流
+base_dir：自定义工作目录，不填则默认使用调用脚本所在文件夹
+run (max_workers=15,start_index=0, end_index=None, base_dir=r"D:\video_download")
+
+## 安装
+```bash
+pip install m3u8-dl-tool

m3u8_dl_tool-0.1.0/pyproject.toml

@@ -0,0 +1,21 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "m3u8-dl-tool"
+version = "0.1.0"
+authors = [
+  { name="jxwubin", email="549719522@qq.com" }
+]
+description = "跨平台m3u8下载工具，自动过滤广告分片，多线程下载"
+requires-python = ">=3.9"
+dependencies = [
+    "requests>=2.31.0",
+    "pycryptodome>=3.19.0"
+]
+readme = "README.md"
+license = {file="LICENSE"}
+
+[project.urls]
+"Homepage" = "https://github.com/xxx/xxx"

m3u8_dl_tool-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

m3u8_dl_tool-0.1.0/src/m3u8_dl_tool.egg-info/PKG-INFO

@@ -0,0 +1,51 @@
+Metadata-Version: 2.4
+Name: m3u8-dl-tool
+Version: 0.1.0
+Summary: 跨平台m3u8下载工具，自动过滤广告分片，多线程下载
+Author-email: jxwubin <549719522@qq.com>
+License: MIT License
+        
+        Copyright (c) 2026 jxwubin
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+Project-URL: Homepage, https://github.com/xxx/xxx
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: requests>=2.31.0
+Requires-Dist: pycryptodome>=3.19.0
+Dynamic: license-file
+
+# m3u8‑dl‑tool
+跨平台m3u8视频下载工具，自动检测并删除重复广告分片，多线程高速下载，支持Windows / macOS / Linux。
+
+## ✨功能特点
+- 多线程并发下载TS分片
+- 自动计算分片哈希，过滤重复广告TS片段
+- AES加密m3u8自动解密
+- 下载完成自动合并TS为MP4
+- 自动清理临时TS文件
+- 参数说明
+max_workers：下载并发线程数，建议 10~30，不要设置过大，避免被服务器限流
+base_dir：自定义工作目录，不填则默认使用调用脚本所在文件夹
+run (max_workers=15,start_index=0, end_index=None, base_dir=r"D:\video_download")
+
+## 安装
+```bash
+pip install m3u8-dl-tool

m3u8_dl_tool-0.1.0/src/m3u8_dl_tool.egg-info/SOURCES.txt

@@ -0,0 +1,10 @@
+LICENSE
+README.md
+pyproject.toml
+src/m3u8_dl_tool.egg-info/PKG-INFO
+src/m3u8_dl_tool.egg-info/SOURCES.txt
+src/m3u8_dl_tool.egg-info/dependency_links.txt
+src/m3u8_dl_tool.egg-info/requires.txt
+src/m3u8_dl_tool.egg-info/top_level.txt
+src/m3u8dltool/M3u8DL.py
+src/m3u8dltool/__init__.py

m3u8_dl_tool-0.1.0/src/m3u8_dl_tool.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

m3u8_dl_tool-0.1.0/src/m3u8_dl_tool.egg-info/requires.txt

@@ -0,0 +1,2 @@
+requests>=2.31.0
+pycryptodome>=3.19.0

m3u8_dl_tool-0.1.0/src/m3u8_dl_tool.egg-info/top_level.txt

@@ -0,0 +1 @@
+m3u8dltool

m3u8_dl_tool-0.1.0/src/m3u8dltool/M3u8DL.py

@@ -0,0 +1,337 @@
+import time
+from urllib import parse
+import requests
+from Crypto.Cipher import AES
+import re
+import os
+import hashlib
+from collections import Counter
+from concurrent.futures import ThreadPoolExecutor
+import json
+import inspect
+
+
+class M3u8Downloader:
+    @staticmethod
+    def _get_caller_script_dir():
+        """自动获取外部执行脚本所在目录"""
+        import sys
+        this_module = sys.modules[__name__].__file__
+        for frame in inspect.stack():
+            fname = frame.filename
+            # 跳过本库自身文件
+            if fname == this_module:
+                continue
+            if os.path.exists(fname) and not fname.startswith("<"):
+                return os.path.dirname(os.path.abspath(fname))
+        return os.getcwd()
+
+    def __init__(self, max_workers=30, base_dir=None):
+        if base_dir is None:
+            self.BASE_DIR = self._get_caller_script_dir()
+        else:
+            self.BASE_DIR = base_dir
+
+        self.JSON_FILE = os.path.join(self.BASE_DIR, 'm3u8_url.json')
+        self.TS_ROOT = os.path.join(self.BASE_DIR, "m3u8_ts")
+        self.OUTPUT_ROOT = os.path.join(self.BASE_DIR, "MP4")
+        self.max_workers = max_workers
+
+        if not os.path.exists(self.TS_ROOT):
+            os.makedirs(self.TS_ROOT)
+        if not os.path.exists(self.OUTPUT_ROOT):
+            os.makedirs(self.OUTPUT_ROOT)
+
+    class _SingleVideoDownload:
+        """内部嵌套类，对应原来的 download_m3u8"""
+        def __init__(self, m3u8_url, video_name, ts_root, output_root, max_workers) -> None:
+            self.TS_ROOT = ts_root
+            self.OUTPUT_ROOT = output_root
+            self.video_name = video_name
+            self.m3u8_url = m3u8_url
+            self.ts_dir_name = f'ts_{self.video_name}'
+            self.ts_path = os.path.join(self.TS_ROOT, self.ts_dir_name)
+            self.output_path = os.path.join(self.OUTPUT_ROOT, f'{video_name}.mp4')
+            self.num = 1
+            # 接收外部传入线程数
+            self.max_workers = max_workers
+
+        # 一、下载 ts 文件
+        def download(self):
+            # 主线程读取m3u8，只在主线使用requests，无并发，安全
+            m3u8 = requests.get(self.m3u8_url, timeout=15).text
+            mixed_m3u8_url = None
+            if '.m3u8' in m3u8:
+                mixed_m3u8_url = m3u8.split()[-1]
+                mixed_m3u8_url = parse.urljoin(self.m3u8_url, mixed_m3u8_url)
+                m3u8 = requests.get(mixed_m3u8_url, timeout=15).text[:-2]
+            # 【取加密 key 的网址】
+            key = None
+            if '.key' in m3u8:
+                zz = re.findall('"([^"]*)"', m3u8)[0]
+                key_url = parse.urljoin(self.m3u8_url, zz)
+                key = requests.get(key_url, timeout=15).content
+                print(f'key-->{key}')
+            # 【下载 ts 文件到本地】
+            ts_dir_full = os.path.join(self.TS_ROOT, f'ts_{self.video_name}')
+            if not os.path.exists(ts_dir_full):
+                os.makedirs(ts_dir_full)
+            self.ts_path = ts_dir_full
+            download_tasks = []
+            ts_count = []
+            n = 1
+            # 使用实例保存的线程数 self.max_workers
+            with ThreadPoolExecutor(self.max_workers) as executor:
+                for line in m3u8.split('\n'):
+                    if line.startswith("#"):
+                        continue
+                    if len(line) == 0:
+                        continue
+                    if mixed_m3u8_url:
+                        line = parse.urljoin(mixed_m3u8_url, line)
+                    else:
+                        line = parse.urljoin(self.m3u8_url, line)
+                    ts_count.append(line)
+                    ts_name = str(n).zfill(5)
+                    n += 1
+                    ts_file = os.path.join(self.ts_path, f'{ts_name}.ts')
+                    download_tasks.append(
+                        executor.submit(
+                            self.download_single_ts,
+                            line,
+                            ts_count,
+                            ts_file,
+                            key if '.key' in m3u8 else None
+                        )
+                    )
+                # 等待所有下载任务完成
+                print("=====等待全部下载线程结束=====")
+                for future in download_tasks:
+                    future.result()
+                time.sleep(2)
+                print("\n\n=====全部ts下载完成，开始检测重复分片(广告)=====", flush=True)
+            # 所有分片下载完成后，按内容去重
+            self.remove_duplicate_ts()
+
+        def download_single_ts(self, line, ts_count, ts_file, key=None):
+            retry_count = 1
+            while retry_count < 10:
+                try:
+                    with open(ts_file, mode="wb") as f:
+                        # 独立请求，不加共用session，增加超时，防止永久挂起
+                        resp = requests.get(line, timeout=15)
+                        ts = resp.content
+                        if key:
+                            crypto = AES.new(key, AES.MODE_CBC, key)
+                            f.write(crypto.decrypt(ts))
+                        else:
+                            f.write(ts)
+                        print(
+                            f'\r 下载成功({self.num}/{len(ts_count)})-->'
+                            + os.path.basename(ts_file),
+                            end='',
+                            flush=True
+                        )
+                        self.num += 1
+                    break
+                except Exception as e:
+                    print(
+                        f"\n---->下载失败，重新下载(第{retry_count}次)"
+                        f"-->{os.path.basename(ts_file)}--{line}"
+                    )
+                    retry_count += 1
+                    time.sleep(1)
+
+        # 新增：计算文件的 SHA‑256
+        @staticmethod
+        def get_file_hash(file_path):
+            sha256 = hashlib.sha256()
+            try:
+                with open(file_path, 'rb') as f:
+                    for chunk in iter(lambda: f.read(1024 * 1024), b''):
+                        sha256.update(chunk)
+                return sha256.hexdigest()
+            except Exception as e:
+                print(f"读取哈希失败跳过文件：{file_path} 错误：{e}")
+                return None
+
+        # 新增：删除所有内容重复的 TS 文件
+        def remove_duplicate_ts(self):
+            ts_files = [
+                os.path.join(self.ts_path, filename)
+                for filename in os.listdir(self.ts_path)
+                if filename.lower().endswith('.ts')
+            ]
+            # 建立“文件路径 -> 文件内容哈希”的对应关系
+            file_hashes = {}
+            for fp in ts_files:
+                h = self.get_file_hash(fp)
+                if h is not None:
+                    file_hashes[fp] = h
+            # 统计每种哈希出现次数
+            hash_counts = Counter(file_hashes.values())
+            # 出现两次及以上，全部删除（广告分片）
+            duplicate_files = [
+                file_path
+                for file_path in file_hashes.keys()
+                if hash_counts[file_hashes[file_path]] >= 2
+            ]
+            for file_path in duplicate_files:
+                try:
+                    os.remove(file_path)
+                except Exception as e:
+                    print(f"删除重复分片失败：{file_path}，错误：{e}", flush=True)
+            print(
+                f'重复 TS 检查完成：发现并过滤 '
+                f'{len(duplicate_files)} 个重复片段'
+            )
+            if duplicate_files:
+                print(
+                    '被过滤的文件：'
+                    + ', '.join(os.path.basename(path) for path in duplicate_files)
+                )
+
+        # 二、合并为 MP4【跨平台版本，不用copy命令】
+        def cmd_merge(self):
+            print("ts文件合并中......", flush=True)
+            ts_dir_full = os.path.join(self.TS_ROOT, f'ts_{self.video_name}')
+            out_mp4 = os.path.join(self.OUTPUT_ROOT, f"{self.video_name}.mp4")
+
+            ts_files = []
+            for fname in os.listdir(ts_dir_full):
+                if fname.lower().endswith(".ts"):
+                    ts_files.append(fname)
+            ts_files.sort()
+            # 分块读写，避免大视频占满内存
+            block_size = 4 * 1024 * 1024
+            with open(out_mp4, "wb") as fw:
+                for fname in ts_files:
+                    fp = os.path.join(ts_dir_full, fname)
+                    with open(fp, "rb") as fr:
+                        while True:
+                            chunk = fr.read(block_size)
+                            if not chunk:
+                                break
+                            fw.write(chunk)
+            print('合并完成', flush=True)
+
+        # 三、删除 ts 文件及文件夹【跨平台版本，不用del命令】
+        def del_ts(self):
+            print("开始清理ts临时文件夹", flush=True)
+            ts_dir_full = os.path.join(self.TS_ROOT, f'ts_{self.video_name}')
+            try:
+                for fname in os.listdir(ts_dir_full):
+                    fpath = os.path.join(ts_dir_full, fname)
+                    if os.path.isfile(fpath):
+                        os.remove(fpath)
+                os.rmdir(ts_dir_full)
+                print('ts 文件夹已删除')
+            except Exception as e:
+                print(f"清理ts文件夹失败：{ts_dir_full}，错误：{e}", flush=True)
+
+        # 四、运行
+        def run(self):
+            print(f'\n{"=" * 30}')
+            print(f'开始下载: {self.video_name}')
+            print(f'{"=" * 30}')
+            print('【1】 >>>>>>>>>>>>>>> 开始下载 ts')
+            self.download()
+            print('\n【2】 >>>>>>>>>>>>>>> 开始合并 ts')
+            self.cmd_merge()
+            print('【3】 >>>>>>>>>>>>>>> 开始删除 ts')
+            self.del_ts()
+            print(f'【完成】 {self.video_name} 下载完成！')
+
+    def load_video_list(self, json_file_path):
+        """读取 JSON 文件，如果文件不存在则自动生成示例 m3u8_url.json，返回 None；存在就读取返回列表"""
+        if not os.path.exists(json_file_path):
+            # 构造示例模板内容
+            demo_data = [
+                {
+                    "title": "视频名称1",
+                    "url": "m3u8地址"
+                },
+                {
+                    "title": "视频名称2",
+                    "url": "m3u8地址"
+                }
+            ]
+            # 写入示例文件
+            with open(json_file_path, 'w', encoding='utf-8') as fw:
+                json.dump(demo_data, fw, ensure_ascii=False, indent=4)
+            print(f"\n【提示】未找到 {json_file_path}，已自动生成示例json文件！", flush=True)
+            print("请打开该文件，添加下载任务后，重新运行脚本！", flush=True)
+            # 文件新建成功，返回 None，告诉上层不要继续下载
+            return None
+        # 文件存在，正常读取
+        with open(json_file_path, 'r', encoding='utf-8') as f:
+            video_list = json.load(f)
+        return video_list
+
+    def batch_download(self, start_index=0, end_index=None):
+        """
+        批量下载视频。
+         Args:
+            start_index: 起始索引，从 0 开始
+            end_index: 结束索引，不包含；None 表示到最后
+        """
+        json_file_path = self.JSON_FILE
+        video_list = self.load_video_list(json_file_path)
+        if video_list is None:
+            return
+        if end_index is None:
+            end_index = len(video_list)
+        video_list = video_list[start_index:end_index]
+        total = len(video_list)
+        print(f'>>> 共找到 {total} 个视频待下载')
+        for idx, video in enumerate(video_list, 1):
+            title = video.get('title')
+            url = video.get('url')
+            if not title or not url:
+                print(f'跳过无效条目: {video}')
+                continue
+            print(f'>>> 当前进度: {idx}/{total}')
+            try:
+                downloader = self._SingleVideoDownload(
+                    m3u8_url=url,
+                    video_name=title,
+                    ts_root=self.TS_ROOT,
+                    output_root=self.OUTPUT_ROOT,
+                    max_workers=self.max_workers
+                )
+                downloader.run()
+            except Exception as e:
+                print(f'下载 {title} 时出错: {e}')
+                continue
+            time.sleep(1)
+        print(f'\n{"=" * 30}')
+        print('所有视频下载完成！')
+        print(f'{"=" * 30}')
+
+    def run(self, start_index=0, end_index=None, max_workers=None):
+        """统一入口：执行全部批量下载并统计总耗时
+        :param start_index: 起始下标
+        :param end_index: 结束下标
+        :param max_workers: 线程池并发数，不传使用实例初始化的数值
+        """
+        # 如果调用run传入线程数，优先使用传入的值
+        if max_workers is not None:
+            self.max_workers = max_workers
+
+        start = time.perf_counter()
+        self.batch_download(start_index=start_index, end_index=end_index)
+        end = time.perf_counter()
+        print(f"耗时：{end - start:.2f} 秒")
+
+
+if __name__ == '__main__':
+    # 方式1：初始化时指定线程数
+    # app = M3u8Downloader(max_workers=15)
+    # app.run()
+
+    # 方式2：run()调用时动态修改线程数（推荐）
+    app = M3u8Downloader()
+    app.run(max_workers=15)
+
+    # 限定范围下载示例
+    # app.run(start_index=0, end_index=5, max_workers=20)

m3u8_dl_tool-0.1.0/src/m3u8dltool/__init__.py

@@ -0,0 +1,4 @@
+from .M3u8DL import M3u8Downloader
+
+__version__ = "0.1.0"
+__all__ = ["M3u8Downloader"]