Mirrors/udemy-downloader
1
0
Fork 0
mirror of https://cdm-project.com/Download-Tools/udemy-downloader.git synced 2025-05-05 09:24:28 +02:00
Code Issues Packages Projects Releases Wiki Activity

bug fix: subscription courses fail to download

Browse Source 
+ Fixed cookies not getting loaded correctly leading to failures getting course information
This commit is contained in:
Puyodead1 2022-01-05 13:50:30 -05:00
parent 046344796c
commit b97b12344b
1 changed files with 48 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
main.py
View File

@ -46,11 +46,12 @@ course_url = None
info = None info = None
keys = {} keys = {}
id_as_course_name = False id_as_course_name = False
is_subscription_course = False
# this is the first function that is called, we parse the arguments, setup the logger, and ensure that required directories exist # this is the first function that is called, we parse the arguments, setup the logger, and ensure that required directories exist
def pre_run(): def pre_run():
global dl_assets, skip_lectures, dl_captions, caption_locale, quality, bearer_token, portal_name, course_name, keep_vtt, skip_hls, concurrent_downloads, disable_ipv6, load_from_file, save_to_file, bearer_token, course_url, info, logger, keys, id_as_course_name global cookies, dl_assets, skip_lectures, dl_captions, caption_locale, quality, bearer_token, portal_name, course_name, keep_vtt, skip_hls, concurrent_downloads, disable_ipv6, load_from_file, save_to_file, bearer_token, course_url, info, logger, keys, id_as_course_name, is_subscription_course
# make sure the directory exists # make sure the directory exists
if not os.path.exists(DOWNLOAD_DIR): if not os.path.exists(DOWNLOAD_DIR):
@ -167,6 +168,12 @@ def pre_run():
action="store_true", action="store_true",
help="If specified, the course id will be used in place of the course name for the output directory. This is a 'hack' to reduce the path length", help="If specified, the course id will be used in place of the course name for the output directory. This is a 'hack' to reduce the path length",
) )
parser.add_argument(
"--subscription-course",
dest="is_subscription_course",
action="store_true",
help="Mark the course as a subscription based course, use this if you are having problems with the program auto detecting it",
)
parser.add_argument( parser.add_argument(
"--save-to-file", "--save-to-file",
@ -247,6 +254,8 @@ def pre_run():
stream.setLevel(logging.INFO) stream.setLevel(logging.INFO)
if args.id_as_course_name: if args.id_as_course_name:
id_as_course_name = args.id_as_course_name id_as_course_name = args.id_as_course_name
if args.is_subscription_course:
is_subscription_course = args.is_subscription_course
Path(DOWNLOAD_DIR).mkdir(parents=True, exist_ok=True) Path(DOWNLOAD_DIR).mkdir(parents=True, exist_ok=True)
Path(SAVED_DIR).mkdir(parents=True, exist_ok=True) Path(SAVED_DIR).mkdir(parents=True, exist_ok=True)
@ -796,9 +805,27 @@ class Udemy:
results = webpage.get("results", []) results = webpage.get("results", [])
return results return results
def _extract_subscription_course_info(self, url):
course_html = self.session._get(url).text
soup = BeautifulSoup(course_html, "lxml")
data = soup.find(
"div", {"class": "ud-component--course-taking--app"})
if not data:
logger.fatal(
"Unable to extract arguments from course page! Make sure you have a cookies.txt file!")
self.session.terminate()
sys.exit(1)
data_args = data.attrs["data-module-args"]
data_json = json.loads(data_args)
course_id = data_json.get("courseId", None)
portal_name = self.extract_portal_name(url)
return course_id, portal_name
def _extract_course_info(self, url): def _extract_course_info(self, url):
portal_name, course_name = self.extract_course_name(url) portal_name, course_name = self.extract_course_name(url)
course = {} course = {}
if not is_subscription_course:
results = self._subscribed_courses(portal_name=portal_name, results = self._subscribed_courses(portal_name=portal_name,
course_name=course_name) course_name=course_name)
course = self._extract_course(response=results, course = self._extract_course(response=results,
@ -817,20 +844,9 @@ class Udemy:
course = self._extract_course(response=results, course = self._extract_course(response=results,
course_name=course_name) course_name=course_name)
if not course: if not course or is_subscription_course:
course_html = self.session._get(url).text course_id, portal_name = self._extract_subscription_course_info(
soup = BeautifulSoup(course_html, "lxml") url)
data = soup.find(
"div", {"class": "ud-component--course-taking--app"})
if not data:
logger.fatal(
"Unable to extract arguments from course page! Make sure you have a cookies.txt file!")
self.session.terminate()
sys.exit(1)
data_args = data.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( course = self._extract_course_info_json(
url, course_id, portal_name) url, course_id, portal_name)