Skip to content

Commit

Permalink
Revert "Merge branch 'feat-mkv'"
Browse files Browse the repository at this point in the history 
This reverts commit e835ab6, reversing
changes made to 034fcc6.
  • Loading branch information
@Puyodead1
Puyodead1 committed Aug 10, 2021
1 parent bb60297 commit a2748d9
Show file tree
Hide file tree
Showing 2 changed files with 58 additions and 72 deletions.
33 changes: 11 additions & 22 deletions README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@ Windows is the primary development OS, but I've made an effort to support Linux

# 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`` (``pip install yt-dlp``). Ensure they are in the system path (typing their name in cmd should invoke them).

# Usage

Expand Down Expand Up @@ -67,9 +67,8 @@ You can now run the program, see the examples below. The course will download to
# Advanced Usage

```
usage: main.py [-h] -c COURSE_URL [-b BEARER_TOKEN] [-q QUALITY] [-l LANG] [-cc CONCURRENT_CONNECTIONS]
[--skip-lectures] [--download-assets] [--download-captions] [--keep-vtt] [--skip-hls] [--use_mkv]
[--info]
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]
Udemy Downloader
Expand All @@ -80,30 +79,20 @@ optional arguments:
-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')
-cc CONCURRENT_CONNECTIONS, --concurrent-connections CONCURRENT_CONNECTIONS
The number of maximum concurrent connections for segments (HLS and DASH, must be a number
1-30)
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)
--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)
--use_mkv If specified, MKV container will be used instead of MP4, subtitles will be muxed (if subtitles
are requested)
--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
```

<br>

### NOTE: Loading bearer token from a .env file or system environment is deprecated and may break in the future, pass the token as a command argument instead!

## Command Examples:

- 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>`
Expand Down Expand Up @@ -132,7 +121,7 @@ optional arguments:
- Print course information only:
- `python main.py -c <Course URL> --info`
- Specify max number of concurrent downloads:
- `python main.py -c <Course URL> --concurrent-connections 20`
- `python main.py -c <Course URL> --concurrent-downloads 20`
- `python main.py -c <Course URL> -cd 20`

# Credits
Expand Down
97 changes: 47 additions & 50 deletions main.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -23,23 +23,8 @@
home_dir = os.getcwd()
download_dir = os.path.join(os.getcwd(), "out_dir")
keyfile_path = os.path.join(os.getcwd(), "keyfile.json")
keys = None
retry = 3
downloader = None
dl_assets = False
skip_lectures = False
dl_captions = False
caption_locale = "en"
quality = None
bearer_token = None
portal_name = None
course_name = None
keep_vtt = False
skip_hls = False
use_mkv = False
concurrent_connections = 10
access_token = None

HEADERS = {
"Origin": "www.udemy.com",
"User-Agent":
Expand Down Expand Up @@ -794,6 +779,11 @@ def authenticate(self, access_token="", client_id=""):
if not os.path.exists(download_dir):
os.makedirs(download_dir)

# Get the keys
with open(keyfile_path, 'r') as keyfile:
keyfile = keyfile.read()
keyfile = json.loads(keyfile)


def durationtoseconds(period):
"""
Expand Down Expand Up @@ -853,7 +843,7 @@ def decrypt(kid, in_filepath, out_filepath):
"""
print("> Decrypting, this might take a minute...")
try:
key = keys[kid.lower()]
key = keyfile[kid.lower()]
if (os.name == "nt"):
os.system(f"mp4decrypt --key 1:%s \"%s\" \"%s\"" %
(key, in_filepath, out_filepath))
Expand Down Expand Up @@ -994,7 +984,7 @@ def download_aria(url, file_dir, filename):
print("Return code: " + str(ret_code))


def process_caption(caption, lecture_title, lecture_dir, tries=0):
def process_caption(caption, lecture_title, lecture_dir, keep_vtt, tries=0):
filename = f"%s_%s.%s" % (sanitize(lecture_title), caption.get("language"),
caption.get("extension"))
filename_no_ext = f"%s_%s" % (sanitize(lecture_title),
Expand Down Expand Up @@ -1030,7 +1020,8 @@ def process_caption(caption, lecture_title, lecture_dir, tries=0):
print(f" > Error converting caption: {e}")


def process_lecture(lecture, lecture_path, lecture_file_name, chapter_dir):
def process_lecture(lecture, lecture_path, lecture_file_name, quality, access_token,
concurrent_connections, chapter_dir):
lecture_title = lecture.get("lecture_title")
is_encrypted = lecture.get("is_encrypted")
lecture_sources = lecture.get("video_sources")
Expand All @@ -1046,7 +1037,8 @@ def process_lecture(lecture, lecture_path, lecture_file_name, chapter_dir):
lecture_title)
handle_segments(source.get("download_url"),
source.get(
"format_id"), lecture_title, lecture_path, lecture_file_name, chapter_dir)
"format_id"), lecture_title, lecture_path, lecture_file_name,
concurrent_connections, chapter_dir)
else:
print(f" > Lecture '%s' is missing media links" %
lecture_title)
Expand Down Expand Up @@ -1095,7 +1087,8 @@ def process_lecture(lecture, lecture_path, lecture_file_name, chapter_dir):
print(" > Missing sources for lecture", lecture)


def parse_new(_udemy):
def parse_new(_udemy, quality, skip_lectures, dl_assets, dl_captions,
caption_locale, keep_vtt, access_token, concurrent_connections):
total_chapters = _udemy.get("total_chapters")
total_lectures = _udemy.get("total_lectures")
print(f"Chapter(s) ({total_chapters})")
Expand Down Expand Up @@ -1154,8 +1147,9 @@ def parse_new(_udemy):
print(" > Failed to write html file: ", e)
continue
else:
process_lecture(lecture, lecture_path,
lecture_file_name, chapter_dir)
process_lecture(lecture, lecture_path, lecture_file_name,
quality, access_token,
concurrent_connections, chapter_dir)

if dl_assets:
assets = lecture.get("assets")
Expand Down Expand Up @@ -1224,7 +1218,8 @@ def parse_new(_udemy):
for subtitle in subtitles:
lang = subtitle.get("language")
if lang == caption_locale or caption_locale == "all":
process_caption(subtitle, lecture_title, chapter_dir)
process_caption(subtitle, lecture_title, chapter_dir,
keep_vtt)


def _print_course_info(course_data):
Expand Down Expand Up @@ -1336,11 +1331,11 @@ def get_version_string():
help="The language to download for captions, specify 'all' to download all captions (Default is 'en')",
)
parser.add_argument(
"-cc",
"--concurrent-connections",
dest="concurrent_connections",
"-cd",
"--concurrent-downloads",
dest="concurrent_downloads",
type=int,
help="The number of maximum concurrent connections for segments (HLS and DASH, must be a number 1-30)",
help="The number of maximum concurrent downloads for segments (HLS and DASH, must be a number 1-30)",
)
parser.add_argument(
"--skip-lectures",
Expand Down Expand Up @@ -1370,13 +1365,7 @@ def get_version_string():
"--skip-hls",
dest="skip_hls",
action="store_true",
help="If specified, HLS streams will be skipped (faster fetching, HLS streams usually contain 1080p quality for non-DRM lectures)",
)
parser.add_argument(
"--use_mkv",
dest="use_mkv",
action="store_true",
help="If specified, MKV container will be used instead of MP4, subtitles will be muxed (if subtitles are requested)",
help="If specified, hls streams will be skipped (faster fetching) (hls streams usually contain 1080p quality for non-drm lectures)",
)
parser.add_argument(
"--info",
Expand All @@ -1400,6 +1389,18 @@ def get_version_string():
parser.add_argument("-v", "--version", action="version",
version='You are running version {version}'.format(version=get_version_string()))

dl_assets = False
skip_lectures = False
dl_captions = False
caption_locale = "en"
quality = None
bearer_token = None
portal_name = None
course_name = None
keep_vtt = False
skip_hls = False
concurrent_downloads = 10

args = parser.parse_args()
if args.download_assets:
dl_assets = True
Expand All @@ -1415,17 +1416,15 @@ def get_version_string():
keep_vtt = args.keep_vtt
if args.skip_hls:
skip_hls = args.skip_hls
if args.use_mkv:
use_mkv = args.use_mkv
if args.concurrent_connections:
concurrent_connections = args.concurrent_connections
if args.concurrent_downloads:
concurrent_downloads = args.concurrent_downloads

if concurrent_connections <= 0:
if concurrent_downloads <= 0:
# if the user gave a number that is less than or equal to 0, set cc to default of 10
concurrent_connections = 10
elif concurrent_connections > 30:
concurrent_downloads = 10
elif concurrent_downloads > 30:
# if the user gave a number thats greater than 30, set cc to the max of 30
concurrent_connections = 30
concurrent_downloads = 30

aria_ret_val = check_for_aria()
if not aria_ret_val:
Expand Down Expand Up @@ -1453,15 +1452,11 @@ def get_version_string():
"> 'save_to_file' was specified, data will be saved to json files")

if not os.path.isfile(keyfile_path):
print("❗ Keyfile not found! Did you rename the file correctly? ❗")
print("> Keyfile not found! Did you rename the file correctly?")
sys.exit(1)

# Read keys
with open(keyfile_path, 'r') as keyfile:
keyfile = keyfile.read()
keyfile = json.loads(keyfile)

load_dotenv()
access_token = None
if args.bearer_token:
access_token = args.bearer_token
else:
Expand Down Expand Up @@ -1505,7 +1500,9 @@ def get_version_string():
if args.info:
_print_course_info(_udemy)
else:
parse_new(_udemy)
parse_new(_udemy, quality, skip_lectures, dl_assets, dl_captions,
caption_locale, keep_vtt, access_token,
concurrent_downloads)
else:
_udemy = {}
_udemy["access_token"] = access_token
Expand Down Expand Up @@ -1740,4 +1737,4 @@ def get_version_string():
else:
parse_new(_udemy, quality, skip_lectures, dl_assets, dl_captions,
caption_locale, keep_vtt, access_token,
concurrent_connections)
concurrent_downloads)

0 comments on commit a2748d9

Please sign in to comment.