some fixes for char decoding errors

+ Added `--disable-ipv6` option to disable ipv6 in aria2
+ Updated README to reflect argument changes

.github/stale.yml

@@ -0,0 +1,16 @@
+# Number of days of inactivity before an issue becomes stale
+daysUntilStale: 60
+# Number of days of inactivity before a stale issue is closed
+daysUntilClose: 7
+# Issues with these labels will never be considered stale
+exemptLabels:
+  - pinned
+  - security
+# Label to use when marking an issue as stale
+staleLabel: stale
+# Comment to post when marking an issue as stale. Set to `false` to disable
+markComment: >
+  This issue has been automatically marked as stale because it has not had
+  recent activity. It will be closed if no further activity occurs.
+# Comment to post when closing a stale issue. Set to `false` to disable
+closeComment: true

.gitignore

@@ -122,4 +122,5 @@ manifest.mpd
 saved
 *.aria2
 info.py
-.idea/
+.idea/
+cookies.txt

README.md

@@ -11,6 +11,7 @@
 # NOTE
 
 - **This tool will not work without decryption keys, and there currently no public way to get those keys. Do not bother installing unless you already have keys!**
+- **Downloading courses is against Udemy's Terms of Service, I am NOT held responsible for your account getting suspended as a result from the use of this program!**
 - This program is WIP, the code is provided as-is and I am not held resposible for any legal issues resulting from the use of this program.
 
 # Support
@@ -23,12 +24,12 @@ All code is licensed under the MIT license
 
 # Description
 
-Utility script to download Udemy courses, has support for DRM videos but requires the user to aquire the decryption key (for legal reasons).<br>
+Utility script to download Udemy courses, has support for DRM videos but requires the user to acquire the decryption key (for legal reasons).<br>
 Windows is the primary development OS, but I've made an effort to support Linux also.
 
 # Requirements
 
-1. You would need to download `ffmpeg`, `aria2c`, `mp4decrypt` (from Bento4 SDK) and ``yt-dlp`` (``pip install yt-dlp``). Ensure they are in the system path (typing their name in cmd should invoke them).
+1. You would need to download `ffmpeg`, `aria2c`, `mp4decrypt` (from Bento4 SDK) and `yt-dlp` (this is installed with the other requirements). Ensure they are in the system path (typing their name in cmd should invoke them).
 
 # Usage
 
@@ -43,10 +44,12 @@ You will need to get a few things before you can use this program:
 
 ### Setting up
 
+- install python 3.6+
+- install requirements: `pip install -r requirements.txt`
 - rename `.env.sample` to `.env` _(you only need to do this if you plan to use the .env file to store your bearer token)_
-- rename `keyfile.example.json` to `keyfile.json`
+- rename `keyfile.example.json` to `keyfile.json` _(this is only required if you plan to download DRM encrypted lectures)_
 
-### Aquire Bearer Token
+### Acquire Bearer Token
 
 - Firefox: [Udemy-DL Guide](https://github.com/r0oth3x49/udemy-dl/issues/389#issuecomment-491903900)
 - Chrome: [Udemy-DL Guide](https://github.com/r0oth3x49/udemy-dl/issues/389#issuecomment-492569372)
@@ -54,7 +57,7 @@ You will need to get a few things before you can use this program:
 
 ### Key ID and Key
 
-It is up to you to aquire the key and key ID. Please don't ask me for help acquiring these, decrypting DRM protected content can be considered piracy.
+I would rather not instruct you how to get these as its a grey area in terms of legality. I would prefer if you don't ask me for help getting these.
 
 - Enter the key and key id in the `keyfile.json`
 - ![keyfile example](https://i.imgur.com/e5aU0ng.png)
@@ -64,65 +67,120 @@ It is up to you to aquire the key and key ID. Please don't ask me for help acqui
 
 You can now run the program, see the examples below. The course will download to `out_dir`.
 
+# Udemy Subscription Plans
+
+To download a course included in a subscription plan that you did not purchase individually, you will need to follow a few more steps to get setup.
+
+## Getting your cookies
+
+- Go to the page of the course you want to download
+- press `control` + `shift` + `i` (this may be different depending on your OS, just google how to open developer tools)
+- click the `Console` tab
+- copy and paste `document.cookie` and press enter
+- copy the text between the quotes
+
+## Setup token file
+
+- Create a file called `cookies.txt`
+- Paste the cookie into the file
+- save and close the file
+
 # Advanced Usage
 
 ```
-usage: main.py [-h] -c COURSE_URL [-b BEARER_TOKEN] [-q QUALITY] [-l LANG] [-cd CONCURRENT_DOWNLOADS] [--skip-lectures] [--download-assets]
-               [--download-captions] [--keep-vtt] [--skip-hls] [--info]
+usage: udemy_downloader [-h] -c COURSE_URL [-b BEARER_TOKEN] [-q QUALITY] [-l LANG] [-cd CONCURRENT_CONNECTIONS]
+                        [--skip-lectures] [--download-assets] [--download-captions] [--keep-vtt] [--skip-hls] [--info]
+                        [--use-h265] [--h265-crf H265_CRF] [--ffmpeg-preset FFMPEG_PRESET]
+                        [--ffmpeg-framerate FFMPEG_FRAMERATE] [--h265-encoder H265_ENCODER] [--disable-ipv6] [-v]
 
 Udemy Downloader
 
-optional arguments:
+options:
   -h, --help            show this help message and exit
   -c COURSE_URL, --course-url COURSE_URL
                         The URL of the course to download
   -b BEARER_TOKEN, --bearer BEARER_TOKEN
                         The Bearer token to use
   -q QUALITY, --quality QUALITY
-                        Download specific video quality. If the requested quality isn't available, the closest quality will be used. If not
-                        specified, the best quality will be downloaded for each lecture
-  -l LANG, --lang LANG  The language to download for captions, specify 'all' to download all captions (Default is 'en')
-  -cd CONCURRENT_DOWNLOADS, --concurrent-downloads CONCURRENT_DOWNLOADS
-                        The number of maximum concurrent downloads for segments (HLS and DASH, must be a number 1-50)
+                        Download specific video quality. If the requested quality isn't available, the closest quality
+                        will be used. If not specified, the best quality will be downloaded for each lecture
+  -l LANG, --lang LANG  The language to download for captions, specify 'all' to download all captions (Default is
+                        'en')
+  -cd CONCURRENT_CONNECTIONS, --concurrent-connections CONCURRENT_CONNECTIONS
+                        The number of maximum concurrent connections per download for segments (HLS and DASH, must be
+                        a number 1-30)
   --skip-lectures       If specified, lectures won't be downloaded
   --download-assets     If specified, lecture assets will be downloaded
   --download-captions   If specified, captions will be downloaded
   --keep-vtt            If specified, .vtt files won't be removed
-  --skip-hls            If specified, hls streams will be skipped (faster fetching) (hls streams usually contain 1080p quality for non-drm
-                        lectures)
+  --skip-hls            If specified, hls streams will be skipped (faster fetching) (hls streams usually contain 1080p
+                        quality for non-drm lectures)
   --info                If specified, only course information will be printed, nothing will be downloaded
+  --use-h265            If specified, videos will be encoded with the H.265 codec
+  --h265-crf H265_CRF   Set a custom CRF value for H.265 encoding. FFMPEG default is 28
+  --ffmpeg-preset FFMPEG_PRESET
+                        Set a custom preset value for encoding. This can vary depending on the encoder
+  --ffmpeg-framerate FFMPEG_FRAMERATE
+                        Changes the FPS used for encoding. FFMPEG default is 30
+  --h265-encoder H265_ENCODER
+                        Changes the HEVC encder that is used. Default is copy when not using h265, otherwise the
+                        default is libx265
+  --disable-ipv6        If specified, ipv6 will be disabled in aria2
+  -v, --version         show program's version number and exit
 ```
 
 - Passing a Bearer Token and Course ID as an argument
-  - `python main.py -c <Course URL> -b <Bearer Token>`
-  - `python main.py -c https://www.udemy.com/courses/myawesomecourse -b <Bearer Token>`
+  - `python udemy_downloader -c <Course URL> -b <Bearer Token>`
+  - `python udemy_downloader -c https://www.udemy.com/courses/myawesomecourse -b <Bearer Token>`
 - Download a specific quality
-  - `python main.py -c <Course URL> -q 720`
+  - `python udemy_downloader -c <Course URL> -q 720`
 - Download assets along with lectures
-  - `python main.py -c <Course URL> --download-assets`
+  - `python udemy_downloader -c <Course URL> --download-assets`
 - Download assets and specify a quality
-  - `python main.py -c <Course URL> -q 360 --download-assets`
+  - `python udemy_downloader -c <Course URL> -q 360 --download-assets`
 - Download captions (Defaults to English)
-  - `python main.py -c <Course URL> --download-captions`
+  - `python udemy_downloader -c <Course URL> --download-captions`
 - Download captions with specific language
-  - `python main.py -c <Course URL> --download-captions -l en` - English subtitles
-  - `python main.py -c <Course URL> --download-captions -l es` - Spanish subtitles
-  - `python main.py -c <Course URL> --download-captions -l it` - Italian subtitles
-  - `python main.py -c <Course URL> --download-captions -l pl` - Polish Subtitles
-  - `python main.py -c <Course URL> --download-captions -l all` - Downloads all subtitles
+  - `python udemy_downloader -c <Course URL> --download-captions -l en` - English subtitles
+  - `python udemy_downloader -c <Course URL> --download-captions -l es` - Spanish subtitles
+  - `python udemy_downloader -c <Course URL> --download-captions -l it` - Italian subtitles
+  - `python udemy_downloader -c <Course URL> --download-captions -l pl` - Polish Subtitles
+  - `python udemy_downloader -c <Course URL> --download-captions -l all` - Downloads all subtitles
   - etc
 - Skip downloading lecture videos
-  - `python main.py -c <Course URL> --skip-lectures --download-captions` - Downloads only captions
-  - `python main.py -c <Course URL> --skip-lectures --download-assets` - Downloads only assets
+  - `python udemy_downloader -c <Course URL> --skip-lectures --download-captions` - Downloads only captions
+  - `python udemy_downloader -c <Course URL> --skip-lectures --download-assets` - Downloads only assets
 - Keep .VTT caption files:
-  - `python main.py -c <Course URL> --download-captions --keep-vtt`
+  - `python udemy_downloader -c <Course URL> --download-captions --keep-vtt`
 - Skip parsing HLS Streams (HLS streams usually contain 1080p quality for Non-DRM lectures):
-  - `python main.py -c <Course URL> --skip-hls`
+  - `python udemy_downloader -c <Course URL> --skip-hls`
 - Print course information only:
-  - `python main.py -c <Course URL> --info`
+  - `python udemy_downloader -c <Course URL> --info`
 - Specify max number of concurrent downloads:
-  - `python main.py -c <Course URL> --concurrent-downloads 20`
-  - `python main.py -c <Course URL> -cd 20`
+  - `python udemy_downloader -c <Course URL> --concurrent-downloads 20`
+  - `python udemy_downloader -c <Course URL> -cd 20`
+- Encode in H.265:
+  - `python udemy_downloader -c <Course URL> --use-h265`
+- Encode in H.265 with custom CRF:
+  - `python udemy_downloader -c <Course URL> --use-h265 -h265-crf 20`
+- Encode in H.265 with custom preset using the default encoder (libx265):
+  - `python udemy_downloader -c <Course URL> --use-h265 --h265-preset faster`
+- Encode in H.265 with custom preset using a custom encoder:
+  - **Note**: _The presets may be different depending on the encoder! For example: `hevc_nvenc` default is `p4` and `libx265` is `medium`_
+  - _You can view encoder help with `ffmpeg -h encoder=<encoder name>`, ex: `ffmpeg -h encoder=hevc_nvenc`_
+  - `python udemy_downloader -c <Course URL> --use-h265 --h265-encoder hevc_nvenc --h265-preset p7`
+- Encode in H.265 with a custom framerate:
+  - `python udemy_downloader -c <Course URL> --use-h265 --ffmpeg-framerate 24`
+
+If you encounter errors while downloading such as
+
+`errorCode=1 Network problem has occurred. cause:Unknown socket error 10051 (0x2743)`
+
+or
+
+`errorCode=1 Network problem has occurred. cause:A socket operation was attempted to an unreachable network.`
+
+Then try disabling ipv6 in aria2 using the `--disable-ipv6` option
 
 # Credits
 

_version.py

@@ -1 +0,0 @@
-__version__ = "1.1.2"

requirements.txt

@@ -10,5 +10,7 @@ m3u8
 colorama
 yt-dlp
 bitstring
-cloudscraper
 unidecode
+six
+beautifulsoup4
+lxml

setup.py

@@ -0,0 +1,31 @@
+from setuptools import setup, Command, find_packages
+
+exec(compile(open('udemy_downloader/version.py').read(), 'udemy_downloader/version.py', 'exec'))
+
+packages = find_packages()
+
+setup(
+    name="udemy-downloader",
+    version="1.2.2",
+    author="Puyodead1",
+    author_email="puyodead@protonmail.com",
+    description="Utility script to download DRM encrypted lectures from Udemy",
+    url="https://github.com/Puyodead1/udemy-downloader",
+    project_urls={
+        "Bug Tracker": "https://github.com/Puyodead1/udemy-downloader/issues",
+    },
+    classifiers=[
+        "Programming Language :: Python :: 3",
+        "License :: OSI Approved :: MIT License",
+        "Operating System :: OS Independent",
+        "Natural Language :: English",
+        "Topic :: Multimedia",
+        "Topic :: Utilities"
+    ],
+    install_requires=["mpegdash", "sanitize_filename", "tqdm", "requests", "python-dotenv", "protobuf", "webvtt-py", "pysrt", "m3u8", "colorama", "yt-dlp", "bitstring", "unidecode", "six"],
+    packages=packages,
+    python_requires=">=3.6",
+    entry_points={
+        'console_scripts': ["udemy-downloader = udemy_downloader:UdemyDownloader"]
+    }
+)

udemy_downloader/Session.py

@@ -0,0 +1,59 @@
+"""
+This file was modified from udemy-dl
+https://github.com/r0oth3x49/udemy-dl/
+
+Copyright (c) 2018-2025 Nasir Khan (r0ot h3x49)
+
+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.
+"""
+
+
+import time
+import requests
+from constants import HEADERS
+
+
+class Session(object):
+    def __init__(self):
+        self._headers = HEADERS
+        self._session = requests.sessions.Session()
+
+    def _set_auth_headers(self, access_token="", cookies={}):
+        self._headers["Authorization"] = "Bearer {}".format(access_token)
+        self._headers["X-Udemy-Authorization"] = "Bearer {}".format(
+            access_token)
+        self._headers["Cookie"] = cookies
+
+    def _get(self, url):
+        for i in range(10):
+            session = self._session.get(url, headers=self._headers)
+            if session.ok or session.status_code in [502, 503]:
+                return session
+            if not session.ok:
+                print('Failed request '+url)
+                print(
+                    f"{session.status_code} {session.reason}, retrying (attempt {i} )...")
+                time.sleep(0.8)
+
+    def _post(self, url, data, redirect=True):
+        session = self._session.post(url,
+                                     data,
+                                     headers=self._headers,
+                                     allow_redirects=redirect)
+        if session.ok:
+            return session
+        if not session.ok:
+            raise Exception(f"{session.status_code} {session.reason}")
+
+    def terminate(self):
+        self._set_auth_headers()
+        return

udemy_downloader/Udemy.py

@@ -0,0 +1,596 @@
+"""
+This file was modified from udemy-dl
+https://github.com/r0oth3x49/udemy-dl/
+
+Copyright (c) 2018-2025 Nasir Khan (r0ot h3x49)
+
+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.
+"""
+
+import time
+import sys
+import m3u8
+import yt_dlp
+import re
+import json
+from requests.exceptions import ConnectionError as conn_error
+from UdemyAuth import UdemyAuth
+from utils import _clean
+from constants import COURSE_SEARCH, COURSE_URL, COURSE_INFO_URL, MY_COURSES_URL, COLLECTION_URL
+from bs4 import BeautifulSoup
+
+
+class Udemy:
+    def __init__(self, access_token, cookies):
+        self.session = None
+        self.access_token = None
+        self.auth = UdemyAuth(cache_session=False)
+        if not self.session:
+            self.session, self.access_token = self.auth.authenticate(
+                access_token=access_token, cookies=cookies)
+
+        if self.session and self.access_token:
+            self.session._headers.update(
+                {"Authorization": "Bearer {}".format(self.access_token)})
+            self.session._headers.update({
+                "X-Udemy-Authorization":
+                "Bearer {}".format(self.access_token)
+            })
+            print("Login Success")
+        else:
+            print("Login Failure!")
+            sys.exit(1)
+
+    def _extract_supplementary_assets(self, supp_assets):
+        _temp = []
+        for entry in supp_assets:
+            title = _clean(entry.get("title"))
+            filename = entry.get("filename")
+            download_urls = entry.get("download_urls")
+            external_url = entry.get("external_url")
+            asset_type = entry.get("asset_type").lower()
+            id = entry.get("id")
+            if asset_type == "file":
+                if download_urls and isinstance(download_urls, dict):
+                    extension = filename.rsplit(
+                        ".", 1)[-1] if "." in filename else ""
+                    download_url = download_urls.get("File", [])[0].get("file")
+                    _temp.append({
+                        "type": "file",
+                        "title": title,
+                        "filename": filename,
+                        "extension": extension,
+                        "download_url": download_url,
+                        "id": id
+                    })
+            elif asset_type == "sourcecode":
+                if download_urls and isinstance(download_urls, dict):
+                    extension = filename.rsplit(
+                        ".", 1)[-1] if "." in filename else ""
+                    download_url = download_urls.get("SourceCode",
+                                                     [])[0].get("file")
+                    _temp.append({
+                        "type": "source_code",
+                        "title": title,
+                        "filename": filename,
+                        "extension": extension,
+                        "download_url": download_url,
+                        "id": id
+                    })
+            elif asset_type == "externallink":
+                _temp.append({
+                    "type": "external_link",
+                    "title": title,
+                    "filename": filename,
+                    "extension": "txt",
+                    "download_url": external_url,
+                    "id": id
+                })
+        return _temp
+
+    def _extract_ppt(self, asset):
+        _temp = []
+        download_urls = asset.get("download_urls")
+        filename = asset.get("filename")
+        id = asset.get("id")
+        if download_urls and isinstance(download_urls, dict):
+            extension = filename.rsplit(".", 1)[-1] if "." in filename else ""
+            download_url = download_urls.get("Presentation", [])[0].get("file")
+            _temp.append({
+                "type": "presentation",
+                "filename": filename,
+                "extension": extension,
+                "download_url": download_url,
+                "id": id
+            })
+        return _temp
+
+    def _extract_file(self, asset):
+        _temp = []
+        download_urls = asset.get("download_urls")
+        filename = asset.get("filename")
+        id = asset.get("id")
+        if download_urls and isinstance(download_urls, dict):
+            extension = filename.rsplit(".", 1)[-1] if "." in filename else ""
+            download_url = download_urls.get("File", [])[0].get("file")
+            _temp.append({
+                "type": "file",
+                "filename": filename,
+                "extension": extension,
+                "download_url": download_url,
+                "id": id
+            })
+        return _temp
+
+    def _extract_ebook(self, asset):
+        _temp = []
+        download_urls = asset.get("download_urls")
+        filename = asset.get("filename")
+        id = asset.get("id")
+        if download_urls and isinstance(download_urls, dict):
+            extension = filename.rsplit(".", 1)[-1] if "." in filename else ""
+            download_url = download_urls.get("E-Book", [])[0].get("file")
+            _temp.append({
+                "type": "ebook",
+                "filename": filename,
+                "extension": extension,
+                "download_url": download_url,
+                "id": id
+            })
+        return _temp
+
+    def _extract_audio(self, asset):
+        _temp = []
+        download_urls = asset.get("download_urls")
+        filename = asset.get("filename")
+        id = asset.get("id")
+        if download_urls and isinstance(download_urls, dict):
+            extension = filename.rsplit(".", 1)[-1] if "." in filename else ""
+            download_url = download_urls.get("Audio", [])[0].get("file")
+            _temp.append({
+                "type": "audio",
+                "filename": filename,
+                "extension": extension,
+                "download_url": download_url,
+                "id": id
+            })
+        return _temp
+
+    def _extract_sources(self, sources, skip_hls):
+        _temp = []
+        if sources and isinstance(sources, list):
+            for source in sources:
+                label = source.get("label")
+                download_url = source.get("file")
+                if not download_url:
+                    continue
+                if label.lower() == "audio":
+                    continue
+                height = label if label else None
+                if height == "2160":
+                    width = "3840"
+                elif height == "1440":
+                    width = "2560"
+                elif height == "1080":
+                    width = "1920"
+                elif height == "720":
+                    width = "1280"
+                elif height == "480":
+                    width = "854"
+                elif height == "360":
+                    width = "640"
+                elif height == "240":
+                    width = "426"
+                else:
+                    width = "256"
+                if (source.get("type") == "application/x-mpegURL"
+                        or "m3u8" in download_url):
+                    if not skip_hls:
+                        out = self._extract_m3u8(download_url)
+                        if out:
+                            _temp.extend(out)
+                else:
+                    _type = source.get("type")
+                    _temp.append({
+                        "type": "video",
+                        "height": height,
+                        "width": width,
+                        "extension": _type.replace("video/", ""),
+                        "download_url": download_url,
+                    })
+        return _temp
+
+    def _extract_media_sources(self, sources):
+        _temp = []
+        if sources and isinstance(sources, list):
+            for source in sources:
+                _type = source.get("type")
+                src = source.get("src")
+
+                if _type == "application/dash+xml":
+                    out = self._extract_mpd(src)
+                    if out:
+                        _temp.extend(out)
+        return _temp
+
+    def _extract_subtitles(self, tracks):
+        _temp = []
+        if tracks and isinstance(tracks, list):
+            for track in tracks:
+                if not isinstance(track, dict):
+                    continue
+                if track.get("_class") != "caption":
+                    continue
+                download_url = track.get("url")
+                if not download_url or not isinstance(download_url, str):
+                    continue
+                lang = (track.get("language") or track.get("srclang")
+                        or track.get("label")
+                        or track["locale_id"].split("_")[0])
+                ext = "vtt" if "vtt" in download_url.rsplit(".",
+                                                            1)[-1] else "srt"
+                _temp.append({
+                    "type": "subtitle",
+                    "language": lang,
+                    "extension": ext,
+                    "download_url": download_url,
+                })
+        return _temp
+
+    def _extract_m3u8(self, url):
+        """extracts m3u8 streams"""
+        _temp = []
+        try:
+            resp = self.session._get(url)
+            resp.raise_for_status()
+            raw_data = resp.text
+            m3u8_object = m3u8.loads(raw_data)
+            playlists = m3u8_object.playlists
+            seen = set()
+            for pl in playlists:
+                resolution = pl.stream_info.resolution
+                codecs = pl.stream_info.codecs
+                if not resolution:
+                    continue
+                if not codecs:
+                    continue
+                width, height = resolution
+                download_url = pl.uri
+                if height not in seen:
+                    seen.add(height)
+                    _temp.append({
+                        "type": "hls",
+                        "height": height,
+                        "width": width,
+                        "extension": "mp4",
+                        "download_url": download_url,
+                    })
+        except Exception as error:
+            print(f"Udemy Says : '{error}' while fetching hls streams..")
+        return _temp
+
+    def _extract_mpd(self, url):
+        """extracts mpd streams"""
+        _temp = []
+        try:
+            ytdl = yt_dlp.YoutubeDL({
+                'quiet': True,
+                'no_warnings': True,
+                "allow_unplayable_formats": True
+            })
+            results = ytdl.extract_info(url,
+                                        download=False,
+                                        force_generic_extractor=True)
+            seen = set()
+            formats = results.get("formats")
+
+            format_id = results.get("format_id")
+            best_audio_format_id = format_id.split("+")[1]
+            best_audio = next((x for x in formats
+                               if x.get("format_id") == best_audio_format_id),
+                              None)
+            for f in formats:
+                if "video" in f.get("format_note"):
+                    # is a video stream
+                    format_id = f.get("format_id")
+                    extension = f.get("ext")
+                    height = f.get("height")
+                    width = f.get("width")
+
+                    if height and height not in seen:
+                        seen.add(height)
+                        _temp.append({
+                            "type": "dash",
+                            "height": str(height),
+                            "width": str(width),
+                            "format_id": f"{format_id},{best_audio_format_id}",
+                            "extension": extension,
+                            "download_url": f.get("manifest_url")
+                        })
+                else:
+                    # unknown format type
+                    continue
+        except Exception as error:
+            print(f"Error fetching MPD streams: '{error}'")
+        return _temp
+
+    def extract_course_name(self, url):
+        """
+        @author r0oth3x49
+        """
+        obj = re.search(
+            r"(?i)(?://(?P<portal_name>.+?).udemy.com/(?:course(/draft)*/)?(?P<name_or_id>[a-zA-Z0-9_-]+))",
+            url,
+        )
+        if obj:
+            return obj.group("portal_name"), obj.group("name_or_id")
+
+    def extract_portal_name(self, url):
+        obj = re.search(r"(?i)(?://(?P<portal_name>.+?).udemy.com)", url)
+        if obj:
+            return obj.group("portal_name")
+
+    def _subscribed_courses(self, portal_name, course_name):
+        results = []
+        self.session._headers.update({
+            "Host":
+            "{portal_name}.udemy.com".format(portal_name=portal_name),
+            "Referer":
+            "https://{portal_name}.udemy.com/home/my-courses/search/?q={course_name}"
+            .format(portal_name=portal_name, course_name=course_name),
+        })
+        url = COURSE_SEARCH.format(portal_name=portal_name,
+                                   course_name=course_name)
+        try:
+            webpage = self.session._get(url).json()
+        except conn_error as error:
+            print(f"Udemy Says: Connection error, {error}")
+            time.sleep(0.8)
+            sys.exit(0)
+        except (ValueError, Exception) as error:
+            print(f"Udemy Says: {error} on {url}")
+            time.sleep(0.8)
+            sys.exit(0)
+        else:
+            results = webpage.get("results", [])
+        return results
+
+    def _extract_course_info_json(self, url, course_id, portal_name):
+        self.session._headers.update({"Referer": url})
+        url = COURSE_INFO_URL.format(
+            portal_name=portal_name, course_id=course_id)
+        try:
+            resp = self.session._get(url).json()
+        except conn_error as error:
+            print(f"Udemy Says: Connection error, {error}")
+            time.sleep(0.8)
+            sys.exit(0)
+        else:
+            return resp
+
+    def _extract_course_json(self, url, course_id, portal_name):
+        self.session._headers.update({"Referer": url})
+        url = COURSE_URL.format(portal_name=portal_name, course_id=course_id)
+        try:
+            resp = self.session._get(url)
+            if resp.status_code in [502, 503]:
+                print(
+                    "> The course content is large, using large content extractor..."
+                )
+                resp = self._extract_large_course_content(url=url)
+            else:
+                resp = resp.json()
+        except conn_error as error:
+            print(f"Udemy Says: Connection error, {error}")
+            time.sleep(0.8)
+            sys.exit(0)
+        except (ValueError, Exception):
+            resp = self._extract_large_course_content(url=url)
+            return resp
+        else:
+            return resp
+
+    def _extract_large_course_content(self, url):
+        url = url.replace("10000", "50") if url.endswith("10000") else url
+        try:
+            data = self.session._get(url).json()
+        except conn_error as error:
+            print(f"Udemy Says: Connection error, {error}")
+            time.sleep(0.8)
+            sys.exit(0)
+        else:
+            _next = data.get("next")
+            while _next:
+                print("Downloading course information.. ")
+                try:
+                    resp = self.session._get(_next).json()
+                except conn_error as error:
+                    print(f"Udemy Says: Connection error, {error}")
+                    time.sleep(0.8)
+                    sys.exit(0)
+                else:
+                    _next = resp.get("next")
+                    results = resp.get("results")
+                    if results and isinstance(results, list):
+                        for d in resp["results"]:
+                            data["results"].append(d)
+            return data
+
+    def _extract_course(self, response, course_name):
+        _temp = {}
+        if response:
+            for entry in response:
+                course_id = str(entry.get("id"))
+                published_title = entry.get("published_title")
+                if course_name in (published_title, course_id):
+                    _temp = entry
+                    break
+        return _temp
+
+    def _my_courses(self, portal_name):
+        results = []
+        try:
+            url = MY_COURSES_URL.format(portal_name=portal_name)
+            webpage = self.session._get(url).json()
+        except conn_error as error:
+            print(f"Udemy Says: Connection error, {error}")
+            time.sleep(0.8)
+            sys.exit(0)
+        except (ValueError, Exception) as error:
+            print(f"Udemy Says: {error}")
+            time.sleep(0.8)
+            sys.exit(0)
+        else:
+            results = webpage.get("results", [])
+        return results
+
+    def _subscribed_collection_courses(self, portal_name):
+        url = COLLECTION_URL.format(portal_name=portal_name)
+        courses_lists = []
+        try:
+            webpage = self.session._get(url).json()
+        except conn_error as error:
+            print(f"Udemy Says: Connection error, {error}")
+            time.sleep(0.8)
+            sys.exit(0)
+        except (ValueError, Exception) as error:
+            print(f"Udemy Says: {error}")
+            time.sleep(0.8)
+            sys.exit(0)
+        else:
+            results = webpage.get("results", [])
+            if results:
+                [
+                    courses_lists.extend(courses.get("courses", []))
+                    for courses in results if courses.get("courses", [])
+                ]
+        return courses_lists
+
+    def _archived_courses(self, portal_name):
+        results = []
+        try:
+            url = MY_COURSES_URL.format(portal_name=portal_name)
+            url = f"{url}&is_archived=true"
+            webpage = self.session._get(url).json()
+        except conn_error as error:
+            print(f"Udemy Says: Connection error, {error}")
+            time.sleep(0.8)
+            sys.exit(0)
+        except (ValueError, Exception) as error:
+            print(f"Udemy Says: {error}")
+            time.sleep(0.8)
+            sys.exit(0)
+        else:
+            results = webpage.get("results", [])
+        return results
+
+    def _my_courses(self, portal_name):
+        results = []
+        try:
+            url = MY_COURSES_URL.format(portal_name=portal_name)
+            webpage = self.session._get(url).json()
+        except conn_error as error:
+            print(f"Udemy Says: Connection error, {error}")
+            time.sleep(0.8)
+            sys.exit(0)
+        except (ValueError, Exception) as error:
+            print(f"Udemy Says: {error}")
+            time.sleep(0.8)
+            sys.exit(0)
+        else:
+            results = webpage.get("results", [])
+        return results
+
+    def _subscribed_collection_courses(self, portal_name):
+        url = COLLECTION_URL.format(portal_name=portal_name)
+        courses_lists = []
+        try:
+            webpage = self.session._get(url).json()
+        except conn_error as error:
+            print(f"Udemy Says: Connection error, {error}")
+            time.sleep(0.8)
+            sys.exit(0)
+        except (ValueError, Exception) as error:
+            print(f"Udemy Says: {error}")
+            time.sleep(0.8)
+            sys.exit(0)
+        else:
+            results = webpage.get("results", [])
+            if results:
+                [
+                    courses_lists.extend(courses.get("courses", []))
+                    for courses in results if courses.get("courses", [])
+                ]
+        return courses_lists
+
+    def _archived_courses(self, portal_name):
+        results = []
+        try:
+            url = MY_COURSES_URL.format(portal_name=portal_name)
+            url = f"{url}&is_archived=true"
+            webpage = self.session._get(url).json()
+        except conn_error as error:
+            print(f"Udemy Says: Connection error, {error}")
+            time.sleep(0.8)
+            sys.exit(0)
+        except (ValueError, Exception) as error:
+            print(f"Udemy Says: {error}")
+            time.sleep(0.8)
+            sys.exit(0)
+        else:
+            results = webpage.get("results", [])
+        return results
+
+    def _extract_course_info(self, url):
+        portal_name, course_name = self.extract_course_name(url)
+        course = {}
+        results = self._subscribed_courses(portal_name=portal_name,
+                                           course_name=course_name)
+        course = self._extract_course(response=results,
+                                      course_name=course_name)
+        if not course:
+            results = self._my_courses(portal_name=portal_name)
+            course = self._extract_course(response=results,
+                                          course_name=course_name)
+        if not course:
+            results = self._subscribed_collection_courses(
+                portal_name=portal_name)
+            course = self._extract_course(response=results,
+                                          course_name=course_name)
+        if not course:
+            results = self._archived_courses(portal_name=portal_name)
+            course = self._extract_course(response=results,
+                                          course_name=course_name)
+
+        if not course:
+            course_html = self.session._get(url).text
+            soup = BeautifulSoup(course_html, "lxml")
+            data_args = soup.find(
+                "div", {"class": "ud-component--course-taking--app"}).attrs["data-module-args"]
+            data_json = json.loads(data_args)
+            course_id = data_json.get("courseId", None)
+            portal_name = self.extract_portal_name(url)
+            course = self._extract_course_info_json(
+                url, course_id, portal_name)
+
+        if course:
+            course.update({"portal_name": portal_name})
+            return course
+        if not course:
+            print("Downloading course information, course id not found .. ")
+            print(
+                "It seems either you are not enrolled or you have to visit the course atleast once while you are logged in.",
+            )
+            print("Trying to logout now...", )
+            self.session.terminate()
+            print("Logged out successfully.", )
+            sys.exit(0)

udemy_downloader/UdemyAuth.py

@@ -0,0 +1,38 @@
+"""
+This file was modified from udemy-dl
+https://github.com/r0oth3x49/udemy-dl/
+
+Copyright (c) 2018-2025 Nasir Khan (r0ot h3x49)
+
+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.
+"""
+
+from Session import Session
+import sys
+
+
+class UdemyAuth(object):
+    def __init__(self, username="", password="", cache_session=False):
+        self.username = username
+        self.password = password
+        self._cache = cache_session
+        self._session = Session()
+
+    def authenticate(self, access_token, cookies):
+        if access_token:
+            self._session._set_auth_headers(
+                access_token=access_token, cookies=cookies)
+            self._session._session.cookies.update(
+                {"access_token": access_token})
+            return self._session, access_token
+        else:
+            raise RuntimeError("No access token is present")

udemy_downloader/__init__.py

@@ -0,0 +1 @@
+from UdemyDownloader import UdemyDownloader

udemy_downloader/__main__.py

@@ -0,0 +1,4 @@
+from UdemyDownloader import UdemyDownloader
+
+if __name__ == "__main__":
+    UdemyDownloader()

udemy_downloader/constants.py

@@ -0,0 +1,16 @@
+HEADERS = {
+    "Origin": "www.udemy.com",
+    # "User-Agent":
+    # "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:90.0) Gecko/20100101 Firefox/90.0",
+    "Accept": "*/*",
+    "Accept-Encoding": None,
+}
+
+LOGIN_URL = "https://www.udemy.com/join/login-popup/?ref=&display_type=popup&loc"
+LOGOUT_URL = "https://www.udemy.com/user/logout"
+COURSE_INFO_URL = "https://{portal_name}.udemy.com/api-2.0/courses/{course_id}/"
+COURSE_URL = "https://{portal_name}.udemy.com/api-2.0/courses/{course_id}/cached-subscriber-curriculum-items?fields[asset]=results,title,external_url,time_estimation,download_urls,slide_urls,filename,asset_type,captions,media_license_token,course_is_drmed,media_sources,stream_urls,body&fields[chapter]=object_index,title,sort_order&fields[lecture]=id,title,object_index,asset,supplementary_assets,view_html&page_size=10000"
+COURSE_SEARCH = "https://{portal_name}.udemy.com/api-2.0/users/me/subscribed-courses?fields[course]=id,url,title,published_title&page=1&page_size=500&search={course_name}"
+SUBSCRIBED_COURSES = "https://{portal_name}.udemy.com/api-2.0/users/me/subscribed-courses/?ordering=-last_accessed&fields[course]=id,title,url&page=1&page_size=12"
+MY_COURSES_URL = "https://{portal_name}.udemy.com/api-2.0/users/me/subscribed-courses?fields[course]=id,url,title,published_title&ordering=-last_accessed,-access_time&page=1&page_size=10000"
+COLLECTION_URL = "https://{portal_name}.udemy.com/api-2.0/users/me/subscribed-courses-collections/?collection_has_courses=True&course_limit=20&fields[course]=last_accessed_time,title,published_title&fields[user_has_subscribed_courses_collection]=@all&page=1&page_size=1000"

udemy_downloader/mp4parse.py

@@ -4,6 +4,27 @@ http://download.macromedia.com/f4v/video_file_format_spec_v10_1.pdf
 @author: Alastair McCormack
 @license: MIT License
 
+The MIT License (MIT)
+
+Copyright (c) 2015 use-sparingly
+
+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.
 """
 
 import bitstring

udemy_downloader/sanitize.py

@@ -1,4 +1,17 @@
-# This file is from https://github.com/r0oth3x49/udemy-dl/blob/master/udemy/sanitize.py
+"""
+Copyright (c) 2018-2025 Nasir Khan (r0ot h3x49)
+
+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.
+"""
 
 from __future__ import unicode_literals
 

udemy_downloader/utils.py

@@ -0,0 +1,177 @@
+import codecs
+import base64
+import re
+import os
+import glob
+import subprocess
+import sys
+from mp4parse import F4VParser
+from widevine_pssh_pb2 import WidevinePsshData
+from sanitize import sanitize, slugify, SLUG_OK
+
+
+def extract_kid(mp4_file):
+    """
+    Parameters
+    ----------
+    mp4_file : str
+        MP4 file with a PSSH header
+
+
+    Returns
+    -------
+    String
+
+    """
+
+    boxes = F4VParser.parse(filename=mp4_file)
+    for box in boxes:
+        if box.header.box_type == 'moov':
+            pssh_box = next(x for x in box.pssh if x.system_id ==
+                            "edef8ba979d64acea3c827dcd51d21ed")
+            hex = codecs.decode(pssh_box.payload, "hex")
+
+            pssh = WidevinePsshData()
+            pssh.ParseFromString(hex)
+            content_id = base64.b16encode(pssh.content_id)
+            return content_id.decode("utf-8")
+
+    # No Moof or PSSH header found
+    return None
+
+
+def _clean(text):
+    ok = re.compile(r'[^\\/:*?!"<>|]')
+    text = "".join(x if ok.match(x) else "_" for x in text)
+    text = re.sub(r"\.+$", "", text.strip())
+    return text
+
+
+def _sanitize(self, unsafetext):
+    text = _clean(sanitize(
+        slugify(unsafetext, lower=False, spaces=True, ok=SLUG_OK + "().[]")))
+    return text
+
+
+def durationtoseconds(period):
+    """
+    @author Jayapraveen
+    """
+
+    # Duration format in PTxDxHxMxS
+    if (period[:2] == "PT"):
+        period = period[2:]
+        day = int(period.split("D")[0] if 'D' in period else 0)
+        hour = int(period.split("H")[0].split("D")[-1] if 'H' in period else 0)
+        minute = int(
+            period.split("M")[0].split("H")[-1] if 'M' in period else 0)
+        second = period.split("S")[0].split("M")[-1]
+        print("Total time: " + str(day) + " days " + str(hour) + " hours " +
+              str(minute) + " minutes and " + str(second) + " seconds")
+        total_time = float(
+            str((day * 24 * 60 * 60) + (hour * 60 * 60) + (minute * 60) +
+                (int(second.split('.')[0]))) + '.' +
+            str(int(second.split('.')[-1])))
+        return total_time
+
+    else:
+        print("Duration Format Error")
+        return None
+
+
+def cleanup(path):
+    """
+    @author Jayapraveen
+    """
+    leftover_files = glob.glob(path + '/*.mp4', recursive=True)
+    for file_list in leftover_files:
+        try:
+            os.remove(file_list)
+        except OSError:
+            print(f"Error deleting file: {file_list}")
+    os.removedirs(path)
+
+
+def remove_files(files):
+    for file in files:
+        os.remove(file)
+
+
+def merge(video_title, video_filepath, audio_filepath, output_path, use_h265, h265_crf, ffmpeg_preset, h265_encoder, ffmpeg_framerate):
+    """
+    @author Jayapraveen
+    """
+    if os.name == "nt":
+        if use_h265:
+            command = "ffmpeg -y -i \"{}\" -i \"{}\" -c:v {} -filter:v fps={} -crf {} -preset {} -c:a copy -fflags +bitexact -map_metadata -1 -metadata title=\"{}\" \"{}\"".format(
+                video_filepath, audio_filepath, h265_encoder, ffmpeg_framerate, h265_crf, ffmpeg_preset, video_title, output_path)
+        else:
+            command = "ffmpeg -y -i \"{}\" -i \"{}\" -c:v {} -filter:v fps={} -preset {} -c:a copy -fflags +bitexact -map_metadata -1 -metadata title=\"{}\" \"{}\"".format(
+                video_filepath, audio_filepath, h265_encoder, ffmpeg_framerate, ffmpeg_preset, video_title, output_path)
+    else:
+        if use_h265:
+            command = "nide -n 7 ffmpeg -y -i \"{}\" -i \"{}\" -c:v {} -filter:v fps={} -crf {} -preset {} -c:a copy -fflags +bitexact -map_metadata -1 -metadata title=\"{}\" \"{}\"".format(
+                video_filepath, audio_filepath, h265_encoder, ffmpeg_framerate, h265_crf, ffmpeg_preset, video_title, output_path)
+        else:
+            command = "nide -n 7 ffmpeg -y -i \"{}\" -i \"{}\" -c:v {} -filter:v fps={} -preset {} -c:a copy -fflags +bitexact -map_metadata -1 -metadata title=\"{}\" \"{}\"".format(
+                video_filepath, audio_filepath, h265_encoder, ffmpeg_framerate, ffmpeg_preset, video_title, output_path)
+    return os.system(command)
+
+
+def decrypt(key, in_filepath, out_filepath):
+    """
+    @author Jayapraveen
+    """
+    if (os.name == "nt"):
+        ret_code = os.system(f"mp4decrypt --key 1:%s \"%s\" \"%s\"" %
+                             (key, in_filepath, out_filepath))
+    else:
+        ret_code = os.system(f"nice -n 7 mp4decrypt --key 1:%s \"%s\" \"%s\"" %
+                             (key, in_filepath, out_filepath))
+
+    return ret_code
+
+
+def check_for_aria():
+    try:
+        subprocess.Popen(["aria2c", "-v"],
+                         stdout=subprocess.DEVNULL,
+                         stderr=subprocess.DEVNULL).wait()
+        return True
+    except FileNotFoundError:
+        return False
+    except Exception as e:
+        print(
+            "> Unexpected exception while checking for Aria2c, please tell the program author about this! ",
+            e)
+        return True
+
+
+def check_for_ffmpeg():
+    try:
+        subprocess.Popen(["ffmpeg"],
+                         stderr=subprocess.DEVNULL,
+                         stdout=subprocess.DEVNULL).wait()
+        return True
+    except FileNotFoundError:
+        return False
+    except Exception as e:
+        print(
+            "> Unexpected exception while checking for FFMPEG, please tell the program author about this! ",
+            e)
+        return True
+
+
+def check_for_mp4decrypt():
+    try:
+        subprocess.Popen(["mp4decrypt"],
+                         stderr=subprocess.DEVNULL,
+                         stdout=subprocess.DEVNULL).wait()
+        return True
+    except FileNotFoundError:
+        return False
+    except Exception as e:
+        print(
+            "> Unexpected exception while checking for MP4Decrypt, please tell the program author about this! ",
+            e)
+        return True

udemy_downloader/version.py

@@ -0,0 +1 @@
+__version__ = '1.2.3-develop'

udemy_downloader/vtt_to_srt.py

@@ -8,7 +8,7 @@ def convert(directory, filename):
     index = 0
     vtt_filepath = os.path.join(directory, filename + ".vtt")
     srt_filepath = os.path.join(directory, filename + ".srt")
-    srt = open(srt_filepath, "w")
+    srt = open(srt_filepath, 'w')
 
     for caption in WebVTT().read(vtt_filepath):
         index += 1

utils.py

@@ -1,32 +0,0 @@
-import mp4parse
-import codecs
-import widevine_pssh_pb2
-import base64
-
-def extract_kid(mp4_file):
-    """
-    Parameters
-    ----------
-    mp4_file : str
-        MP4 file with a PSSH header
-
-
-    Returns
-    -------
-    String
-
-    """
-
-    boxes = mp4parse.F4VParser.parse(filename=mp4_file)
-    for box in boxes:
-        if box.header.box_type == 'moov':
-            pssh_box = next(x for x in box.pssh if x.system_id == "edef8ba979d64acea3c827dcd51d21ed")
-            hex = codecs.decode(pssh_box.payload, "hex")
-
-            pssh = widevine_pssh_pb2.WidevinePsshData()
-            pssh.ParseFromString(hex)
-            content_id = base64.b16encode(pssh.content_id)
-            return content_id.decode("utf-8")
-
-    # No Moof or PSSH header found
-    return None