Merge pull request #117 from bigmadkev/headers-for-corporate-account

Headers for corporate account

.gitignore

@@ -5,4 +5,7 @@ local.*
 *.egg-info
 build
 dist
-*.txt
+*.txt
+*.srt
+*.zip
+venv

README.md

@@ -7,9 +7,11 @@
 - [Common questions](#common)
     - [How do I find the course slug?](#course-slug)
     - [Cookie-based authentication](#setup-cookie-based)
+    - [Header-based authentication](#setup-header-based)
 - [Examples](#examples)
     - [Accessing llvd documentation](#llvd-doc)
     - [Using cookie-based authentication](#use-cookie-based)
+    - [Using header-based authentication](#use-header-based)
     - [Download a course at a specific resolution](#specific-res)
     - [Download a course with subtitles](#with-sub)
     - [Download a course path with throttling between 30 to 120 seconds](#course-path)
@@ -105,6 +107,25 @@ li_at=xxxxx
 JSESSIONID="ajax:xxxxxx"
 ```
 
+<a name="setup-header-based"/>
+
+## How do I setup header-based corporate account access?
+
+If you have a corporate connected account you can fix the download issue by using a `headers.txt` as per below.
+
+1. Create a file named `headers.txt` and place it in the folder you want to download your courses to
+2.  Right click on the page and select view source
+    - You can also reach here by using the keyboard combination: `ctrl`+`U`.
+3. Search for `enterpriseProfileHash` using `ctrl`+`F`
+4. `enterpriseProfileHash&quot;:&quot;XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX&quot;,&quot;` copy the code between the double `&quot;`
+<img src="https://raw.githubusercontent.com/bigmadkev/knowbee-hosting/master/assets/llvd_FindCodeInSourceCode.png" width="auto" height="auto"/>
+5. Open the `headers.txt` file and paste in the values of `x-li-identity` from the above.
+
+```sh
+x-li-identity=XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
+User-Agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36 
+```
+
 <a name="examples"/>
 
 # Examples
@@ -124,6 +145,15 @@ $ llvd --help
 $ llvd -c "course-slug" --cookies
 ```
 
+<a name="use-headers-based"/>
+
+## Using header-based authentication
+Has to use cookies in conjection with headers
+
+```cli
+$ llvd -c "course-slug" --cookies --headers
+```
+
 <a name="specific-res"/>
 
 ## Download a course at a specific resolution

cookies.example

@@ -0,0 +1,2 @@
+JSESSIONID="ajax:813767358989e02053245"
+li_at=

headers.example

@@ -0,0 +1,2 @@
+x-li-identity=
+User-Agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36 

llvd/__init__.py

@@ -1,3 +1,3 @@
 # -*- encoding: utf-8 -*-
 """Linkedin Learning Video Downloader."""
-__version__ = "3.0.6"
+__version__ = "3.0.7"

llvd/app.py

@@ -67,7 +67,7 @@ def login(self, session, login_data):
                 )
             )
 
-    def run(self, cookies=None):
+    def run(self, cookies=None, headers={}):
         """
         Main function, tries to login the user and when it succeeds, tries to download the course
         """
@@ -76,6 +76,8 @@ def run(self, cookies=None):
             if cookies is not None:
                 self.cookies["JSESSIONID"] = cookies.get("JSESSIONID")
                 self.cookies["li_at"] = cookies.get("li_at")
+
+                self.headers=headers
                 self.headers["Csrf-Token"] = cookies.get("JSESSIONID")
 
                 # remove empty files

llvd/cli.py

@@ -5,7 +5,7 @@
 import click
 import sys
 from llvd import config
-from llvd.process_io import parse_cookie_file
+from llvd.process_io import parse_cookie_file, parse_header_file
 from llvd.utils import clean_dir
 
 
@@ -21,6 +21,11 @@
     is_flag=True,
     help="Authenticate with cookies by following the guidelines provided in the documentation",
 )
+@click.option(
+    "--headers",
+    is_flag=True,
+    help="Change request headers",
+)
 @click.option(
     "--resolution",
     "-r",
@@ -40,7 +45,7 @@
     "-t",
     help="A min,max wait in seconds before downloading next video. Example: -t 30,120",
 )
-def main(cookies, course, resolution, caption, exercise, path, throttle):
+def main(cookies, headers, course, resolution, caption, exercise, path, throttle):
     """
     Linkedin learning video downloader cli tool
     example: llvd --course "java-8-essential"
@@ -93,7 +98,12 @@ def main(cookies, course, resolution, caption, exercise, path, throttle):
             click.echo(click.style(f"Using cookie info from cookies.txt", fg="green"))
 
         app = App(email, password, course_slug, resolution, caption, exercise, throttle)
-        app.run(cookie_dict)
+        if headers:
+            header_dict = parse_header_file()
+            app.run(cookie_dict, header_dict)
+        else:
+            app.run(cookie_dict)
+
     else:
         if email == "":
             email = click.prompt("Please enter your Linkedin email address")

llvd/process_io.py

@@ -18,3 +18,18 @@ def parse_cookie_file():
         click.echo(
             click.style(f"cookies.txt not found or is empty", fg="red"))
         sys.exit(0)
+
+def parse_header_file(path = "headers.txt"):
+    headers = {}
+    try:
+        with open(path, "r", encoding="utf8") as cookies_file:
+            lines = cookies_file.readlines()
+            for line in lines:
+                parts = line.split("=",1)
+                key, value = parts + [None]*(2-len(parts))
+                headers[key] = value.replace("\"", "").strip()
+        return headers
+    except FileNotFoundError:
+        click.echo(
+            click.style(f"{path} not found or is empty", fg="red"))
+        sys.exit(0)