Mirrors/udemy-downloader
1
0
Fork 0
mirror of https://cdm-project.com/Download-Tools/udemy-downloader.git synced 2025-04-30 04:04:27 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'Puyodead1:master' into master

Browse Source
This commit is contained in:
Biplob Sutradhar 2021-06-06 21:27:25 +06:00
commit 2b3fb655ca
4 changed files with 171 additions and 484 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
README.md
View File

@ -66,8 +66,8 @@ 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] [--skip-lectures] [--download-assets] [--download-captions]
[--keep-vtt] [--skip-hls] [--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
@ -81,6 +81,8 @@ optional arguments:
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
@ -117,6 +119,9 @@ optional arguments:
- `python main.py -c <Course URL> --skip-hls`
- Print course information only:
- `python main.py -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`
# Credits

366
main.py
View File

@ -1,4 +1,15 @@
import os, requests, json, glob, argparse, sys, re, time, asyncio, json, cloudscraper, m3u8
import os
import requests
import json
import glob
import argparse
import sys
import re
import time
import asyncio
import json
import cloudscraper
import m3u8
from tqdm import tqdm
from dotenv import load_dotenv
from mpegdash.parser import MPEGDASHParser
@ -7,10 +18,9 @@ from vtt_to_srt import convert
from requests.exceptions import ConnectionError as conn_error
from html.parser import HTMLParser as compat_HTMLParser
from sanitize import sanitize, slugify, SLUG_OK
from pyffmpeg import FFMPeg as FFMPEG
import subprocess
import yt_dlp
home_dir = os.getcwd()
download_dir = os.path.join(os.getcwd(), "out_dir")
working_dir = os.path.join(os.getcwd(), "working_dir")
keyfile_path = os.path.join(os.getcwd(), "keyfile.json")
@ -27,7 +37,7 @@ LOGIN_URL = "https://www.udemy.com/join/login-popup/?ref=&display_type=popup&loc
LOGOUT_URL = "https://www.udemy.com/user/logout"
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://www.udemy.com/api-2.0/users/me/subscribed-courses/?ordering=-last_accessed&fields[course]=id,title,url&page=1&page_size=12"
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"
@ -74,6 +84,7 @@ class Udemy:
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(
@ -85,6 +96,7 @@ class Udemy:
"filename": filename,
"extension": extension,
"download_url": download_url,
"id": id
})
elif asset_type == "sourcecode":
if download_urls and isinstance(download_urls, dict):
@ -98,6 +110,7 @@ class Udemy:
"filename": filename,
"extension": extension,
"download_url": download_url,
"id": id
})
elif asset_type == "externallink":
_temp.append({
@ -106,6 +119,7 @@ class Udemy:
"filename": filename,
"extension": "txt",
"download_url": external_url,
"id": id
})
return _temp
@ -113,6 +127,7 @@ class Udemy:
_temp = []
download_urls = assets.get("download_urls")
filename = assets.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")
@ -121,6 +136,7 @@ class Udemy:
"filename": filename,
"extension": extension,
"download_url": download_url,
"id": id
})
return _temp
@ -128,6 +144,7 @@ class Udemy:
_temp = []
download_urls = assets.get("download_urls")
filename = assets.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")
@ -136,6 +153,7 @@ class Udemy:
"filename": filename,
"extension": extension,
"download_url": download_url,
"id": id
})
return _temp
@ -143,6 +161,7 @@ class Udemy:
_temp = []
download_urls = assets.get("download_urls")
filename = assets.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")
@ -151,6 +170,7 @@ class Udemy:
"filename": filename,
"extension": extension,
"download_url": download_url,
"id": id
})
return _temp
@ -158,6 +178,7 @@ class Udemy:
_temp = []
download_urls = assets.get("download_urls")
filename = assets.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")
@ -166,6 +187,7 @@ class Udemy:
"filename": filename,
"extension": extension,
"download_url": download_url,
"id": id
})
return _temp
@ -214,19 +236,17 @@ class Udemy:
return _temp
def _extract_media_sources(self, sources):
_audio = []
_video = []
_temp = []
if sources and isinstance(sources, list):
for source in sources:
_type = source.get("type")
src = source.get("src")
if _type == "application/dash+xml":
video, audio = self._extract_mpd(src)
if video and audio:
_video.extend(video)
_audio.extend(audio)
return (_video, _audio)
out = self._extract_mpd(src)
if out:
_temp.extend(out)
return _temp
def _extract_subtitles(self, tracks):
_temp = []
@ -285,83 +305,49 @@ class Udemy:
return _temp
def _extract_mpd(self, url):
"""extract mpd streams"""
_video = []
_audio = []
"""extracts mpd streams"""
_temp = []
try:
resp = self.session._get(url)
resp.raise_for_status()
raw_data = resp.text
mpd_object = MPEGDASHParser.parse(raw_data)
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()
for period in mpd_object.periods:
for adapt_set in period.adaptation_sets:
content_type = adapt_set.mime_type
if content_type == "video/mp4":
for rep in adapt_set.representations:
for segment in rep.segment_templates:
segment_count = 1
timeline = segment.segment_timelines[0]
segment_count += len(timeline.Ss)
for s in timeline.Ss:
if s.r:
segment_count += s.r
formats = results.get("formats")
segment_extension = segment.media.split(
".")[-1]
height = rep.height
width = rep.width
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 not in seen:
seen.add(height)
_video.append({
"type":
"dash",
"content_type":
"video",
"height":
height,
"width":
width,
"extension":
segment_extension,
"segment_count":
segment_count,
"media":
segment.media,
"initialization":
segment.initialization
})
elif content_type == "audio/mp4":
for rep in adapt_set.representations:
for segment in rep.segment_templates:
segment_count = 1
timeline = segment.segment_timelines[0]
segment_count += len(timeline.Ss)
for s in timeline.Ss:
if s.r:
segment_count += s.r
segment_extension = segment.media.split(
".")[-1]
_audio.append({
"type":
"dash",
"content_type":
"audio",
"extension":
segment_extension,
"segment_count":
segment_count,
"media":
segment.media,
"initialization":
segment.initialization
})
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"Udemy Says : '{error}' while fetching mpd manifest")
return (_video, _audio)
print(f"Error fetching MPD streams: '{error}'")
return _temp
def extract_course_name(self, url):
"""
@ -642,6 +628,7 @@ class Session(object):
# Thanks to a great open source utility youtube-dl ..
class HTMLAttributeParser(compat_HTMLParser): # pylint: disable=W
"""Trivial HTML parser to gather the attributes for a single element"""
def __init__(self):
self.attrs = {}
compat_HTMLParser.__init__(self)
@ -796,7 +783,7 @@ if not os.path.exists(working_dir):
if not os.path.exists(download_dir):
os.makedirs(download_dir)
#Get the keys
# Get the keys
with open(keyfile_path, 'r') as keyfile:
keyfile = keyfile.read()
keyfile = json.loads(keyfile)
@ -807,7 +794,7 @@ def durationtoseconds(period):
@author Jayapraveen
"""
#Duration format in PTxDxHxMxS
# Duration format in PTxDxHxMxS
if (period[:2] == "PT"):
period = period[2:]
day = int(period.split("D")[0] if 'D' in period else 0)
@ -841,24 +828,20 @@ def cleanup(path):
os.removedirs(path)
def mux_process(video_title, lecture_working_dir, output_path):
def mux_process(video_title, video_filepath, audio_filepath, output_path):
"""
@author Jayapraveen
"""
if os.name == "nt":
command = "ffmpeg -y -i \"{}\" -i \"{}\" -acodec copy -vcodec copy -fflags +bitexact -map_metadata -1 -metadata title=\"{}\" \"{}\"".format(
os.path.join(lecture_working_dir, "decrypted_audio.mp4"),
os.path.join(lecture_working_dir, "decrypted_video.mp4"),
video_title, output_path)
video_filepath, audio_filepath, video_title, output_path)
else:
command = "nice -n 7 ffmpeg -y -i \"{}\" -i \"{}\" -acodec copy -vcodec copy -fflags +bitexact -map_metadata -1 -metadata title=\"{}\" \"{}\"".format(
os.path.join(lecture_working_dir, "decrypted_audio.mp4"),
os.path.join(lecture_working_dir, "decrypted_video.mp4"),
video_title, output_path)
video_filepath, audio_filepath, video_title, output_path)
os.system(command)
def decrypt(kid, filename, lecture_working_dir):
def decrypt(kid, in_filepath, out_filepath):
"""
@author Jayapraveen
"""
@ -867,101 +850,49 @@ def decrypt(kid, filename, lecture_working_dir):
key = keyfile[kid.lower()]
if (os.name == "nt"):
os.system(f"mp4decrypt --key 1:%s \"%s\" \"%s\"" %
(key,
os.path.join(lecture_working_dir,
"encrypted_{}.mp4".format(filename)),
os.path.join(lecture_working_dir,
"decrypted_{}.mp4".format(filename))))
(key, in_filepath, out_filepath))
else:
os.system(f"nice -n 7 mp4decrypt --key 1:%s \"%s\" \"%s\"" %
(key,
os.path.join(lecture_working_dir,
"encrypted_{}.mp4".format(filename)),
os.path.join(lecture_working_dir,
"decrypted_{}.mp4".format(filename))))
(key, in_filepath, out_filepath))
print("> Decryption complete")
except KeyError:
raise KeyError("Key not found")
def handle_segments(video_source, audio_source, video_title,
lecture_working_dir, output_path):
"""
@author Jayapraveen
"""
no_vid_segments = video_source.get("segment_count")
no_aud_segments = audio_source.get("segment_count")
audio_media = audio_source.get("media")
audio_init = audio_source.get("initialization")
audio_extension = audio_source.get("extension")
video_media = video_source.get("media")
video_init = video_source.get("initialization")
video_extension = video_source.get("extension")
audio_urls = audio_init + "\n dir={}\n out=audio_0.mp4\n".format(
lecture_working_dir)
video_urls = video_init + "\n dir={}\n out=video_0.mp4\n".format(
lecture_working_dir)
list_path = os.path.join(lecture_working_dir, "list.txt")
for i in range(1, no_aud_segments):
audio_urls += audio_media.replace(
"$Number$", str(i)) + "\n dir={}\n out=audio_{}.mp4\n".format(
lecture_working_dir, i)
for i in range(1, no_vid_segments):
video_urls += video_media.replace(
"$Number$", str(i)) + "\n dir={}\n out=video_{}.mp4\n".format(
lecture_working_dir, i)
with open(list_path, 'w') as f:
f.write("{}\n{}".format(audio_urls, video_urls))
f.close()
print("> Downloading Lecture Segments...")
def handle_segments(url, format_id, video_title, lecture_working_dir,
output_path, concurrent_connections):
temp_filepath = output_path.replace("%", "").replace(".mp4", "")
temp_filepath = temp_filepath + ".mpd-part"
video_filepath_enc = temp_filepath + ".mp4"
audio_filepath_enc = temp_filepath + ".m4a"
video_filepath_dec = temp_filepath + ".decrypted.mp4"
audio_filepath_dec = temp_filepath + ".decrypted.m4a"
print("> Downloading Lecture Tracks...")
ret_code = subprocess.Popen([
"aria2c", "-i", list_path, "-j16", "-s20", "-x16", "-c",
"--auto-file-renaming=false", "--summary-interval=0"
"yt-dlp", "--force-generic-extractor", "--allow-unplayable-formats",
"--concurrent-fragments", f"{concurrent_connections}", "--downloader",
"aria2c", "--fixup", "never", "-k", "-o", f"{temp_filepath}.%(ext)s",
"-f", format_id, f"{url}"
]).wait()
print("> Lecture Segments Downloaded")
print("> Lecture Tracks Downloaded")
print("Return code: " + str(ret_code))
os.remove(list_path)
video_kid = extract_kid(os.path.join(lecture_working_dir, "video_0.mp4"))
video_kid = extract_kid(video_filepath_enc)
print("KID for video file is: " + video_kid)
audio_kid = extract_kid(os.path.join(lecture_working_dir, "audio_0.mp4"))
audio_kid = extract_kid(audio_filepath_enc)
print("KID for audio file is: " + audio_kid)
os.chdir(lecture_working_dir)
if os.name == "nt":
video_concat_command = "copy /b " + "+".join([
f"video_{i}.{video_extension}" for i in range(0, no_vid_segments)
]) + " encrypted_video.mp4"
audio_concat_command = "copy /b " + "+".join([
f"audio_{i}.{audio_extension}" for i in range(0, no_aud_segments)
]) + " encrypted_audio.mp4"
else:
video_concat_command = "cat " + " ".join([
f"video_{i}.{video_extension}" for i in range(0, no_aud_segments)
]) + " > encrypted_video.mp4"
audio_concat_command = "cat " + " ".join([
f"audio_{i}.{audio_extension}" for i in range(0, no_vid_segments)
]) + " > encrypted_audio.mp4"
os.system(video_concat_command)
os.system(audio_concat_command)
os.chdir(home_dir)
try:
decrypt(video_kid, "video", lecture_working_dir)
decrypt(audio_kid, "audio", lecture_working_dir)
os.chdir(home_dir)
mux_process(video_title, lecture_working_dir, output_path)
cleanup(lecture_working_dir)
decrypt(video_kid, video_filepath_enc, video_filepath_dec)
decrypt(audio_kid, audio_filepath_enc, audio_filepath_dec)
mux_process(video_title, video_filepath_dec, audio_filepath_dec,
output_path)
os.remove(video_filepath_enc)
os.remove(audio_filepath_enc)
os.remove(video_filepath_dec)
os.remove(audio_filepath_dec)
except Exception as e:
print(f"Error: ", e)
@ -1089,31 +1020,31 @@ def process_caption(caption, lecture_title, lecture_dir, keep_vtt, tries=0):
print(f" > Error converting caption: {e}")
def process_lecture(lecture, lecture_path, lecture_dir, quality, access_token):
def process_lecture(lecture, lecture_path, lecture_dir, quality, access_token,
concurrent_connections):
lecture_title = lecture.get("lecture_title")
is_encrypted = lecture.get("is_encrypted")
lecture_video_sources = lecture.get("video_sources")
lecture_audio_sources = lecture.get("audio_sources")
lecture_sources = lecture.get("video_sources")
if is_encrypted:
if len(lecture_audio_sources) > 0 and len(lecture_video_sources) > 0:
if len(lecture_sources) > 0:
lecture_working_dir = os.path.join(working_dir,
str(lecture.get("asset_id")))
if not os.path.isfile(lecture_path):
video_source = lecture_video_sources[
-1] # last index is the best quality
audio_source = lecture_audio_sources[-1]
source = lecture_sources[-1] # last index is the best quality
if isinstance(quality, int):
video_source = min(
lecture_video_sources,
source = min(
lecture_sources,
key=lambda x: abs(int(x.get("height")) - quality))
if not os.path.exists(lecture_working_dir):
os.mkdir(lecture_working_dir)
print(f" > Lecture '%s' has DRM, attempting to download" %
lecture_title)
handle_segments(video_source, audio_source, lecture_title,
lecture_working_dir, lecture_path)
handle_segments(source.get("download_url"),
source.get("format_id"), lecture_title,
lecture_working_dir, lecture_path,
concurrent_connections)
else:
print(
" > Lecture '%s' is already downloaded, skipping..." %
@ -1121,7 +1052,7 @@ def process_lecture(lecture, lecture_path, lecture_dir, quality, access_token):
else:
print(f" > Lecture '%s' is missing media links" %
lecture_title)
print(len(lecture_audio_sources), len(lecture_video_sources))
print(len(lecture_sources))
else:
sources = lecture.get("sources")
sources = sorted(sources,
@ -1149,8 +1080,14 @@ def process_lecture(lecture, lecture_path, lecture_dir, quality, access_token):
if source_type == "hls":
temp_filepath = lecture_path.replace(".mp4", "")
temp_filepath = temp_filepath + ".hls-part.mp4"
retVal = FFMPEG(None, url, access_token,
temp_filepath).download()
# retVal = FFMPEG(None, url, access_token,
# temp_filepath).download()
ret_code = subprocess.Popen([
"yt-dlp", "--force-generic-extractor",
"--concurrent-fragments",
f"{concurrent_connections}", "--downloader",
"aria2c", "-o", f"{temp_filepath}", f"{url}"
]).wait()
if retVal:
os.rename(temp_filepath, lecture_path)
print(" > HLS Download success")
@ -1167,7 +1104,7 @@ def process_lecture(lecture, lecture_path, lecture_dir, quality, access_token):
def parse_new(_udemy, quality, skip_lectures, dl_assets, dl_captions,
caption_locale, keep_vtt, access_token):
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})")
@ -1210,9 +1147,11 @@ def parse_new(_udemy, quality, skip_lectures, dl_assets, dl_captions,
continue
else:
lecture_path = os.path.join(
chapter_dir, "{}.mp4".format(sanitize(lecture_title)))
chapter_dir,
sanitize(lecture_title) + ".mp4")
process_lecture(lecture, lecture_path, chapter_dir,
quality, access_token)
quality, access_token,
concurrent_connections)
if dl_assets:
assets = lecture.get("assets")
@ -1223,6 +1162,7 @@ def parse_new(_udemy, quality, skip_lectures, dl_assets, dl_captions,
asset_type = asset.get("type")
filename = asset.get("filename")
download_url = asset.get("download_url")
asset_id = asset.get("id")
if asset_type == "article":
print(
@ -1246,7 +1186,8 @@ def parse_new(_udemy, quality, skip_lectures, dl_assets, dl_captions,
print("AssetType: Video; AssetData: ", asset)
elif asset_type == "audio" or asset_type == "e-book" or asset_type == "file" or asset_type == "presentation":
try:
download_aria(download_url, chapter_dir, filename)
download_aria(download_url, chapter_dir,
f"{asset_id}-{filename}")
except Exception as e:
print("> Error downloading asset: ", e)
continue
@ -1372,16 +1313,22 @@ if __name__ == "__main__":
"--quality",
dest="quality",
type=int,
help=
"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",
help="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",
)
parser.add_argument(
"-l",
"--lang",
dest="lang",
type=str,
help="The language to download for captions, specify 'all' to download all captions (Default is 'en')",
)
parser.add_argument(
"-cd",
"--concurrent-downloads",
dest="concurrent_downloads",
type=int,
help=
"The language to download for captions, specify 'all' to download all captions (Default is 'en')",
"The number of maximum concurrent downloads for segments (HLS and DASH, must be a number 1-30)",
)
parser.add_argument(
"--skip-lectures",
@ -1411,15 +1358,13 @@ if __name__ == "__main__":
"--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)",
help="If specified, hls streams will be skipped (faster fetching) (hls streams usually contain 1080p quality for non-drm lectures)",
)
parser.add_argument(
"--info",
dest="info",
action="store_true",
help=
"If specified, only course information will be printed, nothing will be downloaded",
help="If specified, only course information will be printed, nothing will be downloaded",
)
parser.add_argument(
@ -1445,6 +1390,7 @@ if __name__ == "__main__":
course_name = None
keep_vtt = False
skip_hls = False
concurrent_downloads = 10
args = parser.parse_args()
if args.download_assets:
@ -1461,13 +1407,22 @@ if __name__ == "__main__":
keep_vtt = args.keep_vtt
if args.skip_hls:
skip_hls = args.skip_hls
if args.concurrent_downloads:
concurrent_downloads = args.concurrent_downloads
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_downloads = 10
elif concurrent_downloads > 30:
# if the user gave a number thats greater than 30, set cc to the max of 30
concurrent_downloads = 30
aria_ret_val = check_for_aria()
if not aria_ret_val:
print("> Aria2c is missing from your system or path!")
sys.exit(1)
ffmpeg_ret_val = check_for_aria()
ffmpeg_ret_val = check_for_ffmpeg()
if not ffmpeg_ret_val:
print("> FFMPEG is missing from your system or path!")
sys.exit(1)
@ -1537,7 +1492,8 @@ if __name__ == "__main__":
course_info(_udemy)
else:
parse_new(_udemy, quality, skip_lectures, dl_assets, dl_captions,
caption_locale, keep_vtt, access_token)
caption_locale, keep_vtt, access_token,
concurrent_downloads)
else:
_udemy = {}
_udemy["access_token"] = access_token
@ -1593,6 +1549,9 @@ if __name__ == "__main__":
counter += 1
if lecture_id:
print(
f"Processing {course.index(entry)} of {len(course)}"
)
retVal = []
if isinstance(asset, dict):
@ -1679,12 +1638,11 @@ if __name__ == "__main__":
# encrypted
data = asset.get("media_sources")
if data and isinstance(data, list):
video_media_sources, audio_media_sources = udemy._extract_media_sources(
data)
sources = udemy._extract_media_sources(data)
tracks = asset.get("captions")
# duration = asset.get("time_estimation")
subtitles = udemy._extract_subtitles(tracks)
sources_count = len(video_media_sources)
sources_count = len(sources)
subtitle_count = len(subtitles)
lectures.append({
"index": lecture_counter,
@ -1694,8 +1652,7 @@ if __name__ == "__main__":
# "duration": duration,
"assets": retVal,
"assets_count": len(retVal),
"video_sources": video_media_sources,
"audio_sources": audio_media_sources,
"video_sources": sources,
"subtitles": subtitles,
"subtitle_count": subtitle_count,
"sources_count": sources_count,
@ -1770,4 +1727,5 @@ if __name__ == "__main__":
course_info(_udemy)
else:
parse_new(_udemy, quality, skip_lectures, dl_assets, dl_captions,
caption_locale, keep_vtt, access_token)
caption_locale, keep_vtt, access_token,
concurrent_downloads)

277
pyffmpeg.py
View File

@ -1,277 +0,0 @@
#!/usr/bin/python3
# pylint: disable=R,C,W,E
"""
Author : Nasir Khan (r0ot h3x49)
Github : https://github.com/r0oth3x49
License : MIT
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 re
import time
import subprocess
import sys
from colorama import Fore, Style
class FFMPeg:
_PROGRESS_PATTERN = re.compile(
r"(frame|fps|total_size|out_time|bitrate|speed|progress)\s*\=\s*(\S+)")
def __init__(self,
duration,
url,
token,
filepath,
quiet=False,
callback=lambda *x: None):
self.url = url
self.filepath = filepath
self.quiet = quiet
self.duration = duration
self.callback = callback
self.token = token
def _command(self):
"""
ffmpeg.exe -headers "Authorization: Bearer {token}" -i "" -c copy -bsf:a aac_adtstoasc out.mp4
"""
command = [
"ffmpeg",
"-headers",
f"Authorization: Bearer {self.token}",
"-i",
f"{self.url}",
"-c",
"copy",
"-bsf:a",
"aac_adtstoasc",
f"{self.filepath}",
"-y",
"-progress",
"pipe:2",
]
return command
def _fetch_total_duration(self, line):
duration_in_secs = 0
duration_regex = re.compile(
r"Duration: (\d{2}):(\d{2}):(\d{2})\.\d{2}")
mobj = duration_regex.search(line)
if mobj:
duration_tuple = mobj.groups()
duration_in_secs = (int(duration_tuple[0]) * 60 +
int(duration_tuple[1]) * 60 +
int(duration_tuple[2]))
else:
duration_in_secs = self.duration
return duration_in_secs
def _fetch_current_duration_done(self, time_str):
time_str = time_str.split(":")
return (int(time_str[0]) * 60 + int(time_str[1]) * 60 +
int(time_str[2].split(".")[0]))
def _prepare_time_str(self, secs):
(mins, secs) = divmod(secs, 60)
(hours, mins) = divmod(mins, 60)
if hours > 99:
time_str = "--:--:--"
if hours == 0:
time_str = "%02d:%02ds" % (mins, secs)
else:
time_str = "%02d:%02d:%02ds" % (hours, mins, secs)
return time_str
def _progress(self,
iterations,
total,
bytesdone,
speed,
elapsed,
bar_length=30,
fps=None):
offset = 0
filled_length = int(round(bar_length * iterations / float(total)))
percents = format(100.00 * (iterations * 1.0 / float(total)), ".2f")
if bytesdone <= 1048576:
_receiving = round(float(bytesdone) / 1024.00, 2)
_received = format(
_receiving if _receiving < 1024.00 else _receiving / 1024.00,
".2f")
suffix_recvd = "KB" if _receiving < 1024.00 else "MB"
else:
_receiving = round(float(bytesdone) / 1048576, 2)
_received = format(
_receiving if _receiving < 1024.00 else _receiving / 1024.00,
".2f")
suffix_recvd = "MB" if _receiving < 1024.00 else "GB"
suffix_rate = "Kb/s" if speed < 1024.00 else "Mb/s"
if fps:
suffix_rate += f" {fps}/fps"
if elapsed:
rate = ((float(iterations) - float(offset)) / 1024.0) / elapsed
eta = (total - iterations) / (rate * 1024.0)
else:
rate = 0
eta = 0
rate = format(speed if speed < 1024.00 else speed / 1024.00, ".2f")
(mins, secs) = divmod(eta, 60)
(hours, mins) = divmod(mins, 60)
if hours > 99:
eta = "--:--:--"
if hours == 0:
eta = "eta %02d:%02ds" % (mins, secs)
else:
eta = "eta %02d:%02d:%02ds" % (hours, mins, secs)
if secs == 0:
eta = "\n"
total_time = self._prepare_time_str(total)
done_time = self._prepare_time_str(iterations)
downloaded = f"{total_time}/{done_time}"
received_bytes = str(_received) + str(suffix_recvd)
percents = f"{received_bytes} {percents}"
self.hls_progress(
downloaded=downloaded,
percents=percents,
filled_length=filled_length,
rate=str(rate) + str(suffix_rate),
suffix=eta,
bar_length=bar_length,
)
def hls_progress(self,
downloaded,
percents,
filled_length,
rate,
suffix,
bar_length=30):
bar = (Fore.CYAN + Style.DIM + "#" * filled_length + Fore.WHITE +
Style.DIM + "-" * (bar_length - filled_length))
sys.stdout.write(
"\033[2K\033[1G\r\r{}{}[{}{}*{}{}] : {}{}{} {}% |{}{}{}| {} {}".
format(
Fore.CYAN,
Style.DIM,
Fore.MAGENTA,
Style.BRIGHT,
Fore.CYAN,
Style.DIM,
Fore.GREEN,
Style.BRIGHT,
downloaded,
percents,
bar,
Fore.GREEN,
Style.BRIGHT,
rate,
suffix,
))
sys.stdout.flush()
def _parse_progress(self, line):
items = {
key: value
for key, value in self._PROGRESS_PATTERN.findall(line)
}
return items
def download(self):
total_time = None
t0 = time.time()
progress_lines = []
active = True
retVal = {}
command = self._command()
bytes_done = 0
download_speed = 0
try:
with subprocess.Popen(command,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE) as proc:
while active:
elapsed = time.time() - t0
try:
line = proc.stderr.readline().decode("utf-8").strip()
if not total_time:
total_time = self._fetch_total_duration(line)
if "progress=end" in line:
try:
self._progress(
total_time,
total_time,
bytes_done,
download_speed,
elapsed,
)
except KeyboardInterrupt:
retVal = {
"status": "False",
"msg": "Error: KeyboardInterrupt",
}
raise KeyboardInterrupt
except Exception as err:
{"status": "False", "msg": f"Error: {err}"}
active = False
retVal = {"status": "True", "msg": "download"}
break
if "progress" not in line:
progress_lines.append(line)
else:
lines = "\n".join(progress_lines)
items = self._parse_progress(lines)
if items:
secs = self._fetch_current_duration_done(
items.get("out_time"))
_tsize = (
items.get("total_size").lower().replace(
"kb", ""))
_brate = (items.get("bitrate").lower().replace(
"kbits/s", ""))
fps = items.get("fps")
bytes_done = float(
_tsize) if _tsize != "n/a" else 0
download_speed = float(
_brate) if _brate != "n/a" else 0
try:
self._progress(
secs,
total_time,
bytes_done,
download_speed,
elapsed,
fps=fps,
)
except KeyboardInterrupt:
retVal = {
"status": "False",
"msg": "Error: KeyboardInterrupt",
}
raise KeyboardInterrupt
except Exception as err:
{"status": "False", "msg": f"Error: {err}"}
progress_lines = []
except KeyboardInterrupt:
active = False
retVal = {
"status": "False",
"msg": "Error: KeyboardInterrupt"
}
raise KeyboardInterrupt
except KeyboardInterrupt:
raise KeyboardInterrupt
return retVal

3
requirements.txt
View File

@ -7,4 +7,5 @@ protobuf
webvtt-py
pysrt
m3u8
colorama
colorama
yt-dlp