mirror of
https://cdm-project.com/Download-Tools/udemy-downloader.git
synced 2025-04-30 17:34:25 +02:00
Feat: Info argument
+ Added info argument to print course information + Updated spacing of some text to be more 'tree' like and easier to read
This commit is contained in:
Puyodead1
parent
66aad0dc50
commit
1ad4f1edde
1
.gitignore
vendored
1
.gitignore
vendored
@ -122,3 +122,4 @@ manifest.mpd
|
||||
.vscode
|
||||
saved
|
||||
*.aria2
|
||||
info.py
|
||||
@ -69,7 +69,7 @@ You can now run `python main.py` to start downloading. The course will download
|
||||
|
||||
```
|
||||
usage: main.py [-h] -c COURSE_URL [-b BEARER_TOKEN] [-q QUALITY] [-l LANG] [--skip-lectures] [--download-assets] [--download-captions]
|
||||
[--keep-vtt] [--skip-hls]
|
||||
[--keep-vtt] [--skip-hls] [--info]
|
||||
|
||||
Udemy Downloader
|
||||
|
||||
@ -89,6 +89,7 @@ optional arguments:
|
||||
--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)
|
||||
--info If specified, only course information will be printed, nothing will be downloaded
|
||||
```
|
||||
|
||||
- Passing a Bearer Token and Course ID as an argument
|
||||
@ -116,6 +117,8 @@ optional arguments:
|
||||
- `python main.py -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`
|
||||
- Print course information only:
|
||||
- `python main.py -c <Course URL> --info`
|
||||
|
||||
# Credits
|
||||
|
||||
|
||||
116
main.py
116
main.py
@ -1040,8 +1040,6 @@ def process_lecture(lecture, lecture_path, lecture_dir, quality, access_token):
|
||||
|
||||
if is_encrypted:
|
||||
if len(lecture_audio_sources) > 0 and len(lecture_video_sources) > 0:
|
||||
print(f"> Lecture '%s' has DRM, attempting to download" %
|
||||
lecture_title)
|
||||
lecture_working_dir = os.path.join(working_dir,
|
||||
str(lecture.get("asset_id")))
|
||||
|
||||
@ -1055,16 +1053,19 @@ def process_lecture(lecture, lecture_path, lecture_dir, quality, access_token):
|
||||
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)
|
||||
else:
|
||||
print("> Lecture '%s' is already downloaded, skipping..." %
|
||||
print(
|
||||
" > Lecture '%s' is already downloaded, skipping..." %
|
||||
lecture_title)
|
||||
else:
|
||||
print(f"> Lecture '%s' is missing media links" % lecture_title)
|
||||
print(f" > Lecture '%s' is missing media links" %
|
||||
lecture_title)
|
||||
print(len(lecture_audio_sources), len(lecture_video_sources))
|
||||
else:
|
||||
print("> Lecture doesn't have DRM, attempting to download...")
|
||||
sources = lecture.get("sources")
|
||||
sources = sorted(sources,
|
||||
key=lambda x: int(x.get("height")),
|
||||
@ -1075,14 +1076,17 @@ def process_lecture(lecture, lecture_path, lecture_dir, quality, access_token):
|
||||
if not os.path.exists(lecture_working_dir):
|
||||
os.mkdir(lecture_working_dir)
|
||||
if not os.path.isfile(lecture_path):
|
||||
print(
|
||||
" > Lecture doesn't have DRM, attempting to download..."
|
||||
)
|
||||
source = sources[0] # first index is the best quality
|
||||
if isinstance(quality, int):
|
||||
source = min(
|
||||
sources,
|
||||
key=lambda x: abs(int(x.get("height")) - quality))
|
||||
try:
|
||||
print("====== Selected quality: ", source.get("type"),
|
||||
source.get("height"))
|
||||
print(" ====== Selected quality: ",
|
||||
source.get("type"), source.get("height"))
|
||||
url = source.get("download_url")
|
||||
source_type = source.get("type")
|
||||
if source_type == "hls":
|
||||
@ -1098,10 +1102,11 @@ def process_lecture(lecture, lecture_path, lecture_dir, quality, access_token):
|
||||
except Exception as e:
|
||||
print(f" > Error downloading lecture: ", e)
|
||||
else:
|
||||
print("> Lecture '%s' is already downloaded, skipping..." %
|
||||
print(
|
||||
" > Lecture '%s' is already downloaded, skipping..." %
|
||||
lecture_title)
|
||||
else:
|
||||
print("Missing sources for lecture", lecture)
|
||||
print(" > Missing sources for lecture", lecture)
|
||||
|
||||
|
||||
def parse_new(_udemy, quality, skip_lectures, dl_assets, dl_captions,
|
||||
@ -1131,7 +1136,8 @@ def parse_new(_udemy, quality, skip_lectures, dl_assets, dl_captions,
|
||||
lecture_index = lecture.get("lecture_index")
|
||||
|
||||
extension = lecture.get("extension")
|
||||
print(f"> Processing lecture {lecture_index} of {total_lectures}")
|
||||
print(
|
||||
f" > Processing lecture {lecture_index} of {total_lectures}")
|
||||
if not skip_lectures:
|
||||
if extension == "html":
|
||||
html_content = lecture.get("html_content").encode(
|
||||
@ -1143,7 +1149,7 @@ def parse_new(_udemy, quality, skip_lectures, dl_assets, dl_captions,
|
||||
f.write(html_content)
|
||||
f.close()
|
||||
except Exception as e:
|
||||
print("Failed to write html file: ", e)
|
||||
print(" > Failed to write html file: ", e)
|
||||
continue
|
||||
else:
|
||||
lecture_path = os.path.join(
|
||||
@ -1220,6 +1226,75 @@ def parse_new(_udemy, quality, skip_lectures, dl_assets, dl_captions,
|
||||
keep_vtt)
|
||||
|
||||
|
||||
def course_info(course_data):
|
||||
print("\n\n\n\n")
|
||||
course_title = course_data.get("title")
|
||||
chapter_count = course_data.get("total_chapters")
|
||||
lecture_count = course_data.get("total_lectures")
|
||||
|
||||
print("> Course: {}".format(course_title))
|
||||
print("> Total Chapters: {}".format(chapter_count))
|
||||
print("> Total Lectures: {}".format(lecture_count))
|
||||
print("\n")
|
||||
|
||||
chapters = course_data.get("chapters")
|
||||
for chapter in chapters:
|
||||
chapter_title = chapter.get("chapter_title")
|
||||
chapter_index = chapter.get("chapter_index")
|
||||
chapter_lecture_count = chapter.get("lecture_count")
|
||||
chapter_lectures = chapter.get("lectures")
|
||||
|
||||
print("> Chapter: {} ({} of {})".format(chapter_title, chapter_index,
|
||||
chapter_count))
|
||||
|
||||
for lecture in chapter_lectures:
|
||||
lecture_title = lecture.get("lecture_title")
|
||||
lecture_index = lecture.get("index")
|
||||
lecture_asset_count = lecture.get("assets_count")
|
||||
lecture_is_encrypted = lecture.get("is_encrypted")
|
||||
lecture_subtitles = lecture.get("subtitles")
|
||||
lecture_extension = lecture.get("extension")
|
||||
lecture_sources = lecture.get("sources")
|
||||
lecture_video_sources = lecture.get("video_sources")
|
||||
|
||||
if lecture_sources:
|
||||
lecture_sources = sorted(lecture.get("sources"),
|
||||
key=lambda x: int(x.get("height")),
|
||||
reverse=True)
|
||||
if lecture_video_sources:
|
||||
lecture_video_sources = sorted(
|
||||
lecture.get("video_sources"),
|
||||
key=lambda x: int(x.get("height")),
|
||||
reverse=True)
|
||||
|
||||
if lecture_is_encrypted:
|
||||
lecture_qualities = [
|
||||
"{}@{}x{}".format(x.get("type"), x.get("width"),
|
||||
x.get("height"))
|
||||
for x in lecture_video_sources
|
||||
]
|
||||
elif not lecture_is_encrypted and lecture_sources:
|
||||
lecture_qualities = [
|
||||
"{}@{}x{}".format(x.get("type"), x.get("height"),
|
||||
x.get("width")) for x in lecture_sources
|
||||
]
|
||||
|
||||
if lecture_extension:
|
||||
continue
|
||||
|
||||
print(" > Lecture: {} ({} of {})".format(lecture_title,
|
||||
lecture_index,
|
||||
chapter_lecture_count))
|
||||
print(" > DRM: {}".format(lecture_is_encrypted))
|
||||
print(" > Asset Count: {}".format(lecture_asset_count))
|
||||
print(" > Captions: {}".format(
|
||||
[x.get("language") for x in lecture_subtitles]))
|
||||
print(" > Qualities: {}".format(lecture_qualities))
|
||||
|
||||
if chapter_index != chapter_count:
|
||||
print("\n\n")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser(description='Udemy Downloader')
|
||||
parser.add_argument("-c",
|
||||
@ -1282,6 +1357,13 @@ if __name__ == "__main__":
|
||||
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",
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"--save-to-file",
|
||||
@ -1360,8 +1442,9 @@ if __name__ == "__main__":
|
||||
access_token = os.getenv("UDEMY_BEARER")
|
||||
|
||||
udemy = Udemy(access_token)
|
||||
print("> Fetching course information, this may take a minute...")
|
||||
|
||||
print("> Fetching course information, this may take a minute...")
|
||||
if not args.load_from_file:
|
||||
course_id, course_info = udemy._extract_course_info(args.course_url)
|
||||
print("> Course information retrieved!")
|
||||
if course_info and isinstance(course_info, dict):
|
||||
@ -1374,6 +1457,9 @@ if __name__ == "__main__":
|
||||
course_json = json.loads(
|
||||
open(os.path.join(os.getcwd(), "saved", "course_content.json"),
|
||||
'r').read())
|
||||
title = course_json.get("title")
|
||||
course_title = course_json.get("published_title")
|
||||
portal_name = course_json.get("portal_name")
|
||||
else:
|
||||
course_json = udemy._extract_course_json(args.course_url, course_id,
|
||||
portal_name)
|
||||
@ -1390,6 +1476,9 @@ if __name__ == "__main__":
|
||||
if args.load_from_file:
|
||||
_udemy = json.loads(
|
||||
open(os.path.join(os.getcwd(), "saved", "_udemy.json")).read())
|
||||
if args.info:
|
||||
course_info(_udemy)
|
||||
else:
|
||||
parse_new(_udemy, quality, skip_lectures, dl_assets, dl_captions,
|
||||
caption_locale, keep_vtt, access_token)
|
||||
else:
|
||||
@ -1620,5 +1709,8 @@ if __name__ == "__main__":
|
||||
f.close()
|
||||
print("Saved parsed data to json")
|
||||
|
||||
if args.info:
|
||||
course_info(_udemy)
|
||||
else:
|
||||
parse_new(_udemy, quality, skip_lectures, dl_assets, dl_captions,
|
||||
caption_locale, keep_vtt, access_token)
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user