Mirrors/udemy-downloader
1
0
Fork 0
mirror of https://cdm-project.com/Download-Tools/udemy-downloader.git synced 2025-04-30 17:44:33 +02:00
Code Issues Packages Projects Releases Wiki Activity

Path updates

Browse Source 
- Removed a few unused imports
+ Reworked the way paths are formed so they shouldn't be a problem on other operating systems

NOTE: the new dependencies in requirements.txt are NOT required at this time
This commit is contained in:
Puyodead1 2021-05-21 09:27:49 -04:00
parent f62bb52816
commit 88a411d708
2 changed files with 51 additions and 39 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

86
main.py
View File

@ -1,22 +1,16 @@
import os, requests, shutil, json, glob, urllib.request, argparse, sys, re import os, requests, json, glob, argparse, sys, re
from sanitize_filename import sanitize from sanitize_filename import sanitize
import urllib.request
from tqdm import tqdm from tqdm import tqdm
from dotenv import load_dotenv from dotenv import load_dotenv
from mpegdash.parser import MPEGDASHParser from mpegdash.parser import MPEGDASHParser
from mpegdash.nodes import Descriptor
from mpegdash.utils import (parse_attr_value, parse_child_nodes,
parse_node_value, write_attr_value,
write_child_node, write_node_value)
from utils import extract_kid from utils import extract_kid
from vtt_to_srt import convert from vtt_to_srt import convert
download_dir = "%s\out_dir" % os.getcwd() download_dir = os.path.join(os.getcwd(), "out_dir")
working_dir = "%s\working_dir" % os.getcwd( working_dir = os.path.join(os.getcwd(), "working_dir")
) # set the folder to download segments for DRM videos
retry = 3 retry = 3
home_dir = os.getcwd() home_dir = os.getcwd()
keyfile_path = "%s\keyfile.json" % os.getcwd() keyfile_path = os.path.join(os.getcwd(), "keyfile.json")
valid_qualities = [144, 360, 480, 720, 1080] valid_qualities = [144, 360, 480, 720, 1080]
if not os.path.exists(working_dir): if not os.path.exists(working_dir):
@ -86,7 +80,7 @@ def download_media(filename, url, lecture_working_dir, epoch=0):
unit='B', unit='B',
unit_scale=True, unit_scale=True,
desc=filename) desc=filename)
with open(f"{lecture_working_dir}\\{filename}", with open(os.path.join(lecture_working_dir, filename),
'wb') as video_file: 'wb') as video_file:
for chunk in media.iter_content(chunk_size=1024): for chunk in media.iter_content(chunk_size=1024):
if chunk: if chunk:
@ -135,9 +129,15 @@ def mux_process(video_title, lecture_working_dir, outfile):
@author Jayapraveen @author Jayapraveen
""" """
if os.name == "nt": if os.name == "nt":
command = f"ffmpeg -y -i \"{lecture_working_dir}\\decrypted_audio.mp4\" -i \"{lecture_working_dir}\\decrypted_video.mp4\" -acodec copy -vcodec copy -fflags +bitexact -map_metadata -1 -metadata title=\"{video_title}\" \"{outfile}\"" 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, outfile)
else: else:
command = f"nice -n 7 ffmpeg -y -i \"{lecture_working_dir}\\decrypted_audio.mp4\" -i \"{lecture_working_dir}\\decrypted_video.mp4\" -acodec copy -vcodec copy -fflags +bitexact -map_metadata -1 -metadata title=\"{video_title}\" \"{outfile}\"" 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, outfile)
os.system(command) os.system(command)
@ -150,13 +150,19 @@ def decrypt(kid, filename, lecture_working_dir):
except KeyError as error: except KeyError as error:
exit("Key not found") exit("Key not found")
if (os.name == "nt"): if (os.name == "nt"):
os.system( os.system("mp4decrypt --key 1:{} \"{}\" \"{}\"".format(
f"mp4decrypt --key 1:{key} \"{lecture_working_dir}\\encrypted_{filename}.mp4\" \"{lecture_working_dir}\\decrypted_{filename}.mp4\"" key,
) os.path.join(lecture_working_dir,
"encrypted_{}.mp4".format(filename)),
os.path.join(lecture_working_dir,
"decrypted{}.mp4".format(filename))))
else: else:
os.system( os.system("nice -n 7 mp4decrypt --key 1:{} \"{}\" \"{}\"".format(
f"nice -n 7 mp4decrypt --key 1:{key} \"{lecture_working_dir}\\encrypted_{filename}.mp4\" \"{lecture_working_dir}\\decrypted_{filename}.mp4\"" key,
) os.path.join(lecture_working_dir,
"encrypted_{}.mp4".format(filename)),
os.path.join(lecture_working_dir,
"decrypted{}.mp4".format(filename))))
def handle_irregular_segments(media_info, video_title, lecture_working_dir, def handle_irregular_segments(media_info, video_title, lecture_working_dir,
@ -166,10 +172,12 @@ def handle_irregular_segments(media_info, video_title, lecture_working_dir,
""" """
no_segment, video_url, video_init, video_extension, no_segment, audio_url, audio_init, audio_extension = media_info no_segment, video_url, video_init, video_extension, no_segment, audio_url, audio_init, audio_extension = media_info
download_media("video_0.seg.mp4", video_init, lecture_working_dir) download_media("video_0.seg.mp4", video_init, lecture_working_dir)
video_kid = extract_kid(f"{lecture_working_dir}\\video_0.seg.mp4") video_kid = extract_kid(
os.path.join(lecture_working_dir, "video_0.seg.mp4"))
print("KID for video file is: " + video_kid) print("KID for video file is: " + video_kid)
download_media("audio_0.seg.mp4", audio_init, lecture_working_dir) download_media("audio_0.seg.mp4", audio_init, lecture_working_dir)
audio_kid = extract_kid(f"{lecture_working_dir}\\audio_0.seg.mp4") audio_kid = extract_kid(
os.path.join(lecture_working_dir, "audio_0.seg.mp4"))
print("KID for audio file is: " + audio_kid) print("KID for audio file is: " + audio_kid)
for count in range(1, no_segment): for count in range(1, no_segment):
video_segment_url = video_url.replace("$Number$", str(count)) video_segment_url = video_url.replace("$Number$", str(count))
@ -313,7 +321,7 @@ def process_caption(caption,
caption.get("locale_id"), caption.get("ext")) caption.get("locale_id"), caption.get("ext"))
filename_no_ext = f"%s. %s_%s" % (lecture_index, sanitize(lecture_title), filename_no_ext = f"%s. %s_%s" % (lecture_index, sanitize(lecture_title),
caption.get("locale_id")) caption.get("locale_id"))
filepath = f"%s\\%s" % (lecture_dir, filename) filepath = os.path.join(lecture_dir, filename)
if os.path.isfile(filepath): if os.path.isfile(filepath):
print("> Captions '%s' already downloaded." % filename) print("> Captions '%s' already downloaded." % filename)
@ -374,8 +382,8 @@ def process_lecture(lecture, lecture_index, lecture_path, lecture_dir, quality,
# encrypted # encrypted
print(f"> Lecture '%s' has DRM, attempting to download" % print(f"> Lecture '%s' has DRM, attempting to download" %
lecture_title) lecture_title)
lecture_working_dir = "%s\%s" % ( lecture_working_dir = os.path.join(
working_dir, lecture_asset["id"] working_dir, str(lecture_asset["id"])
) # set the folder to download ephemeral files ) # set the folder to download ephemeral files
media_sources = lecture_asset["media_sources"] media_sources = lecture_asset["media_sources"]
if not os.path.exists(lecture_working_dir): if not os.path.exists(lecture_working_dir):
@ -411,7 +419,7 @@ def process_lecture(lecture, lecture_index, lecture_path, lecture_dir, quality,
if download_url: if download_url:
try: try:
download(download_url, download(download_url,
f"%s\\%s" % (lecture_dir, asset_filename), os.path.join(lecture_dir, asset_filename),
asset_filename) asset_filename)
except Exception as e: except Exception as e:
print( print(
@ -420,19 +428,18 @@ def process_lecture(lecture, lecture_index, lecture_path, lecture_dir, quality,
continue continue
elif asset["asset_type"] == "Article": elif asset["asset_type"] == "Article":
assets.append(asset) assets.append(asset)
asset_path = f"%s\\%s.html" % (lecture_dir, asset_path = os.path.join(lecture_dir, sanitize(lecture_title))
sanitize(lecture_title))
with open(asset_path, 'w') as f: with open(asset_path, 'w') as f:
f.write(asset["body"]) f.write(asset["body"])
elif asset["asset_type"] == "ExternalLink": elif asset["asset_type"] == "ExternalLink":
assets.append(asset) assets.append(asset)
asset_path = f"%s\\%s. External URLs.txt" % (lecture_dir, asset_path = os.path.join(
lecture_index) lecture_dir, "{}. External URLs.txt".format(lecture_index))
# with open(asset_path, 'a') as f: # with open(asset_path, 'a') as f:
# f.write(f"%s : %s\n" % # f.write(f"%s : %s\n" %
# (asset["title"], asset["external_url"])) # (asset["title"], asset["external_url"]))
text_assets += f"%s: %s\n" % (asset["title"], text_assets += "{}: {}\n".format(asset["title"],
asset["external_url"]) asset["external_url"])
if not text_assets == "": if not text_assets == "":
with open(asset_path, 'w') as f: with open(asset_path, 'w') as f:
@ -470,7 +477,7 @@ def process_lecture(lecture, lecture_index, lecture_path, lecture_dir, quality,
def parse(data, course_id, course_name, skip_lectures, dl_assets, dl_captions, def parse(data, course_id, course_name, skip_lectures, dl_assets, dl_captions,
quality, caption_locale): quality, caption_locale):
course_dir = f"%s\\%s" % (download_dir, course_name) course_dir = os.path.join(download_dir, course_name)
if not os.path.exists(course_dir): if not os.path.exists(course_dir):
os.mkdir(course_dir) os.mkdir(course_dir)
chapters = [] chapters = []
@ -488,22 +495,25 @@ def parse(data, course_id, course_name, skip_lectures, dl_assets, dl_captions,
# This is caused by there not being a starting chapter # This is caused by there not being a starting chapter
lectures.append(obj) lectures.append(obj)
lecture_index = lectures.index(obj) + 1 lecture_index = lectures.index(obj) + 1
lecture_path = f"%s\\%s. %s.mp4" % (course_dir, lecture_index, lecture_path = os.path.join(
sanitize(obj["title"])) course_dir, "{}. {}.mp4".format(lecture_index,
sanitize(obj["title"])))
process_lecture(obj, lecture_index, lecture_path, download_dir, process_lecture(obj, lecture_index, lecture_path, download_dir,
quality, skip_lectures, dl_assets, dl_captions, quality, skip_lectures, dl_assets, dl_captions,
caption_locale) caption_locale)
for chapter in chapters: for chapter in chapters:
chapter_dir = f"%s\\%s. %s" % (course_dir, chapters.index(chapter) + 1, chapter_dir = os.path.join(
sanitize(chapter["title"])) course_dir, "{}. {}".format(
chapters.index(chapter) + 1, sanitize(chapter["title"])))
if not os.path.exists(chapter_dir): if not os.path.exists(chapter_dir):
os.mkdir(chapter_dir) os.mkdir(chapter_dir)
for lecture in chapter["lectures"]: for lecture in chapter["lectures"]:
lecture_index = chapter["lectures"].index(lecture) + 1 lecture_index = chapter["lectures"].index(lecture) + 1
lecture_path = f"%s\\%s. %s.mp4" % (chapter_dir, lecture_index, lecture_path = os.path.join(
sanitize(lecture["title"])) chapter_dir, "{}. {}.mp4".format(lecture_index,
sanitize(lecture["title"])))
process_lecture(lecture, lecture_index, lecture_path, chapter_dir, process_lecture(lecture, lecture_index, lecture_path, chapter_dir,
quality, skip_lectures, dl_assets, dl_captions, quality, skip_lectures, dl_assets, dl_captions,
caption_locale) caption_locale)

4
requirements.txt
View File

@ -5,4 +5,6 @@ requests
python-dotenv python-dotenv
protobuf protobuf
webvtt-py webvtt-py
pysrt pysrt
aiohttp
aiofiles