fixed #594, fixed #595 (now you can specify to download all assets)..

r0oth3x49 · Dec 19, 2020 · f623df7 · f623df7
1 parent 4608ec3
commit f623df7
Show file tree

Hide file tree

Showing 5 changed files with 65 additions and 28 deletions.
diff --git a/README.md b/README.md
@@ -34,7 +34,7 @@
 - You would need FFmpeg to be installed and added to environment variable so that udemy-dl can access.
 - Download [FFmpeg from here](https://ffmpeg.org/download.html)
 - On ubuntu you can install it via `apt install ffmpeg`.
-- Add to environment variables then udemy-dl will be able to use it when download HLS streams.
+- Add to environment variables then udemy-dl will be able to use it when downloading HLS streams.
 
 ## ***Tested on***
 

diff --git a/udemy-dl.py b/udemy-dl.py
@@ -62,7 +62,9 @@ def download_assets(self, assets, filepath):
                 logger.info(msg=f"Downloading ({title})", new_line=True)
                 try:
                     retval = asset.download(
-                        filepath=filepath, quiet=True, callback=self.show_progress,
+                        filepath=filepath,
+                        quiet=True,
+                        callback=self.show_progress,
                     )
                     msg = retval.get("msg")
                     if msg == "already downloaded":
@@ -87,7 +89,9 @@ def download_lecture(self, lecture, filepath, current, total, quality):
             logger.info(msg=f"Downloading ({title})", new_line=True)
             try:
                 retval = lecture.download(
-                    filepath=filepath, quiet=True, callback=self.show_progress,
+                    filepath=filepath,
+                    quiet=True,
+                    callback=self.show_progress,
                 )
                 msg = retval.get("msg")
                 if msg == "already downloaded":
@@ -102,7 +106,7 @@ def download_lecture(self, lecture, filepath, current, total, quality):
 
     def download_subtitles(self, subtitles, filepath, language="en", keep_vtt=False):
         """This function will simply download the subtitles.."""
-        if language and subtitles:
+        if language and subtitles and language != "all":
             subtitle = subtitles[0]
             subtitles = subtitle.get_subtitle(language)
         if subtitles:
@@ -113,7 +117,9 @@ def download_subtitles(self, subtitles, filepath, language="en", keep_vtt=False)
                 logger.info(msg=f"Downloading ({title})", new_line=True)
                 try:
                     retval = sub.download(
-                        filepath=filepath, quiet=True, callback=self.show_progress,
+                        filepath=filepath,
+                        quiet=True,
+                        callback=self.show_progress,
                     )
                     msg = retval.get("msg")
                     if msg == "already downloaded":
@@ -241,7 +247,10 @@ def course_listdown(
                                 f"{asset}", asset.extension, human_readable
                             )
                             logger.info(
-                                indent=indent, msg=msg, new_line=True, cc=15,
+                                indent=indent,
+                                msg=msg,
+                                new_line=True,
+                                cc=15,
                             )
                     if lecture_subtitles:
                         for sub in lecture_subtitles:
@@ -253,7 +262,10 @@ def course_listdown(
                                 f"{sub}", sub.extension, human_readable
                             )
                             logger.info(
-                                indent=indent, msg=msg, new_line=True, cc=15,
+                                indent=indent,
+                                msg=msg,
+                                new_line=True,
+                                cc=15,
                             )
             print("")
 
@@ -329,7 +341,8 @@ def course_download(
                     msg=f"Chapter ({chapter_title})", new_line=True, cc=15, cc_msg=60
                 )
                 logger.info(
-                    msg=f"Found ({lectures_count}) lecture(s).", new_line=True,
+                    msg=f"Found ({lectures_count}) lecture(s).",
+                    new_line=True,
                 )
                 lecture_index = 0
                 if lecture_number:
@@ -580,7 +593,9 @@ def main():
     if not args.info:
         if args.quality and args.quality > 720 and args.skip_hls_stream:
             args.quality = ""
-            logger.warning(msg="You cannot use --skip-hls and -q/--quality options togather, considering --skip-hls only..")
+            logger.warning(
+                msg="You cannot use --skip-hls and -q/--quality options togather, considering --skip-hls only.."
+            )
         udemy_obj.course_download(
             path=args.output,
             quality=args.quality,

diff --git a/udemy/compat.py b/udemy/compat.py
@@ -48,7 +48,7 @@
 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,published_title&fields[user_has_subscribed_courses_collection]=@all&page=1&page_size=1000"
 MY_COURSES_URL = "https://{portal_name}.udemy.com/api-2.0/users/me/subscribed-courses?fields[course]=id,url,published_title&ordering=-last_accessed,-access_time&page=1&page_size=10000"
 COURSE_SEARCH = "https://{portal_name}.udemy.com/api-2.0/users/me/subscribed-courses?fields[course]=id,url,published_title&page=1&page_size=1000&ordering=-last_accessed,-access_time&search={course_name}"
-COURSE_URL = "https://{portal_name}.udemy.com/api-2.0/courses/{course_id}/cached-subscriber-curriculum-items?fields[asset]=results,external_url,time_estimation,download_urls,slide_urls,filename,asset_type,captions,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_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,stream_urls,body&fields[chapter]=object_index,title,sort_order&fields[lecture]=id,title,object_index,asset,supplementary_assets,view_html&page_size=10000"
 SUBSCRIBED_COURSES = "https://www.udemy.com/api-2.0/users/me/subscribed-courses/?ordering=-last_accessed&fields[course]=id,url&page=1&page_size=12"
 HEADERS = {
     "Origin": "www.udemy.com",

diff --git a/udemy/extract.py b/udemy/extract.py
@@ -83,14 +83,16 @@ def _login(self, username="", password="", cookies=""):
         is_exists, conf = auth.is_session_exists()
         if is_exists and username and password:
             logger.info(
-                msg="Using existing session..", new_line=True,
+                msg="Using existing session..",
+                new_line=True,
             )
             cookies = conf.get("cookies")
         if not is_exists:
             cookies = None
             if not username and not password:
                 logger.info(
-                    msg="Updating session cookie..", new_line=True,
+                    msg="Updating session cookie..",
+                    new_line=True,
                 )
                 username = conf.get("username")
                 password = conf.get("password")
@@ -102,7 +104,9 @@ def _login(self, username="", password="", cookies=""):
                     password = getpass.getpass(prompt="Password : ")
                 print("\n")
                 if not cookies and not username and not password:
-                    logger.error(msg=f"You should either provide Fresh Access Token or Username/Password to create new udemy session..")
+                    logger.error(
+                        msg=f"You should either provide Fresh Access Token or Username/Password to create new udemy session.."
+                    )
                     sys.exit(0)
         if not cookies:
             auth.username = username
@@ -301,12 +305,14 @@ def _extract_course_info(self, url):
                 new_line=True,
             )
             logger.info(
-                msg="Trying to logout now...", new_line=True,
+                msg="Trying to logout now...",
+                new_line=True,
             )
             if not self._cookies:
                 self._logout()
             logger.info(
-                msg="Logged out successfully.", new_line=True,
+                msg="Logged out successfully.",
+                new_line=True,
             )
             sys.exit(0)
 
@@ -419,7 +425,7 @@ def _extract_m3u8(self, url):
     def _extract_ppt(self, assets):
         _temp = []
         download_urls = assets.get("download_urls")
-        filename = self._sanitize(assets.get("filename"))
+        filename = assets.get("filename")
         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")
@@ -436,7 +442,7 @@ def _extract_ppt(self, assets):
     def _extract_file(self, assets):
         _temp = []
         download_urls = assets.get("download_urls")
-        filename = self._sanitize(assets.get("filename"))
+        filename = assets.get("filename")
         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")
@@ -453,7 +459,7 @@ def _extract_file(self, assets):
     def _extract_ebook(self, assets):
         _temp = []
         download_urls = assets.get("download_urls")
-        filename = self._sanitize(assets.get("filename"))
+        filename = assets.get("filename")
         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")
@@ -470,7 +476,7 @@ def _extract_ebook(self, assets):
     def _extract_audio(self, assets):
         _temp = []
         download_urls = assets.get("download_urls")
-        filename = self._sanitize(assets.get("filename"))
+        filename = assets.get("filename")
         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")
@@ -563,7 +569,8 @@ def _extract_subtitles(self, tracks):
     def _extract_supplementary_assets(self, supp_assets):
         _temp = []
         for entry in supp_assets:
-            filename = self._sanitize(entry.get("filename"))
+            title = self._clean(entry.get("title"))
+            filename = entry.get("filename")
             download_urls = entry.get("download_urls")
             external_url = entry.get("external_url")
             asset_type = entry.get("asset_type").lower()
@@ -574,6 +581,7 @@ def _extract_supplementary_assets(self, supp_assets):
                     _temp.append(
                         {
                             "type": "file",
+                            "title": title,
                             "filename": filename,
                             "extension": extension,
                             "download_url": download_url,
@@ -586,6 +594,7 @@ def _extract_supplementary_assets(self, supp_assets):
                     _temp.append(
                         {
                             "type": "source_code",
+                            "title": title,
                             "filename": filename,
                             "extension": extension,
                             "download_url": download_url,
@@ -595,6 +604,7 @@ def _extract_supplementary_assets(self, supp_assets):
                 _temp.append(
                     {
                         "type": "external_link",
+                        "title": title,
                         "filename": filename,
                         "extension": "txt",
                         "download_url": external_url,
@@ -625,12 +635,14 @@ def _real_extract(self, url="", skip_hls_stream=False):
                     msg=f"Udemy Says : '{resource}' cookies seems to be expired"
                 )
             logger.info(
-                msg="Trying to logout now...", new_line=True,
+                msg="Trying to logout now...",
+                new_line=True,
             )
             if not self._cookies:
                 self._logout()
             logger.info(
-                msg="Logged out successfully.", new_line=True,
+                msg="Logged out successfully.",
+                new_line=True,
             )
             sys.exit(0)
 

diff --git a/udemy/internal.py b/udemy/internal.py
@@ -75,7 +75,9 @@ def _fetch_course(self):
         if auth.get("login") == "successful":
             logger.info(msg="Logged in successfully.", new_line=True)
             logger.info(msg="Downloading course information ..")
-            self._info = self._real_extract(self._url, skip_hls_stream=self._skip_hls_stream)
+            self._info = self._real_extract(
+                self._url, skip_hls_stream=self._skip_hls_stream
+            )
             time.sleep(1)
             logger.success(msg="Downloaded course information .. ")
             access_token = self._info["access_token"]
@@ -88,12 +90,14 @@ def _fetch_course(self):
                 for z in self._info["chapters"]
             ]
             logger.info(
-                msg="Trying to logout now...", new_line=True,
+                msg="Trying to logout now...",
+                new_line=True,
             )
             if not self._cookies:
                 self._logout()
             logger.info(
-                msg="Logged out successfully.", new_line=True,
+                msg="Logged out successfully.",
+                new_line=True,
             )
             self._have_basic = True
         if auth.get("login") == "failed":
@@ -192,9 +196,15 @@ def __init__(self, assets, parent):
 
         self._mediatype = assets.get("type")
         self._extension = assets.get("extension")
-        self._filename = "{0:03d} {1!s}".format(
-            parent._lecture_index, assets.get("filename")
-        )
+        title = assets.get("title", "")
+        if not title:
+            title = assets.get("filename")
+        if title and title.endswith(self._extension):
+            ok = "{0:03d} ".format(parent._lecture_index) + title
+            self._filename = ok
+        else:
+            ok = "{0:03d} ".format(parent._lecture_index) + assets.get("filename")
+            self._filename = ok
         self._url = assets.get("download_url")