Add user agent and window size + minor changes

F33RNI · Nov 3, 2023 · 1c8d131 · 1c8d131
1 parent b41b0ae
commit 1c8d131
Show file tree

Hide file tree

Showing 4 changed files with 54 additions and 12 deletions.
diff --git a/README.md b/README.md
@@ -36,7 +36,9 @@ pip install git+https://github.com/F33RNI/LMSDownloader.git
 
 ### Usage in terminal
 ```
-lmsdownloader [-h] -l LOGIN -p PASSWORD -link LINK_TO_DOWNLOAD -path SAVE_TO [--login-link LOGIN_LINK] [--wait-between-pages WAIT_BETWEEN_PAGES] [--link-check-regex LINK_CHECK_REGEX] [--headless] [--no-logging-init]
+usage: lmsdownloader [-h] -l LOGIN -p PASSWORD -link LINK_TO_DOWNLOAD -path SAVE_TO [--login-link LOGIN_LINK]
+                     [--wait-between-pages WAIT_BETWEEN_PAGES] [--link-check-regex LINK_CHECK_REGEX]
+                     [--user-agent USER_AGENT] [--window-size WINDOW_SIZE] [--headless] [--no-logging-init]
 
 options:
   -h, --help            show this help message and exit
@@ -54,6 +56,10 @@ options:
                         how long to wait after going to next page
   --link-check-regex LINK_CHECK_REGEX
                         regex expression to check link_to_download (replace to "^" to bypass link check)
+  --user-agent USER_AGENT
+                        browser's user agent to prevent mobile version
+  --window-size WINDOW_SIZE
+                        browser's window size
   --headless            specify to open Chrome in headless mode
   --no-logging-init     specify to bypass logging initialization
 ```
@@ -84,6 +90,8 @@ Params:
 - `login_link` – Link to LMS login page
 - `wait_between_pages` – How long to wait after going to next page
 - `link_check_regex` – Regex expression to check link_to_download (replace to "^" to bypass link check)
+- `user_agent` - Browser's user agent to prevent mobile version
+- `window_size` - Default browser's window size
 - `headless` – Set True to open Chrome in headless mode
 
 ### LMSDownloader.download()

diff --git a/setup.py b/setup.py
@@ -23,7 +23,7 @@
 
 setup(
     name="LMSDownloader",
-    version="1.0.1",
+    version="1.1.0",
     license="Apache License 2.0",
     author="Fern Lane (aka F3RNI)",
     author_email="xxoinvizionxx@gmail.com",

diff --git a/src/LMSDownloader/LMSDownloader.py b/src/LMSDownloader/LMSDownloader.py
@@ -53,12 +53,21 @@
 CONTENT_TYPE_SCORM_BOOK = 1
 CONTENT_TYPE_H5P_PRESENTATION = 2
 
+# Default user agent
+USER_AGENT_DEFAULT = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) " \
+                     "AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36"
+
+# Default regex to check link_to_download
+LINK_CHECK_REGEX_DEFAULT = "^(http|https):\\/\\/online\\.mospolytech\\.ru\\/mod\\/(scorm|hvp)\\/view\\.php\\?id="
+
 
 class LMSDownloader:
     def __init__(self, lms_login: str, lms_password: str, link_to_download: str,
                  login_link: str = "https://online.mospolytech.ru/login/index.php",
                  wait_between_pages: float = 1.,
-                 link_check_regex: str = "^(http|https):\\/\\/online\\.mospolytech\\.ru\\/mod\\/(scorm|hvp)\\/view\\.php\\?id=",
+                 link_check_regex: str = LINK_CHECK_REGEX_DEFAULT,
+                 user_agent: str = USER_AGENT_DEFAULT,
+                 window_size: str = "960,1080",
                  headless: bool = True) -> None:
         """
         Initializes LMSDownloader class (just copies fields)
@@ -67,7 +76,9 @@ def __init__(self, lms_login: str, lms_password: str, link_to_download: str,
         :param link_to_download: LMS link to download
         :param login_link: Link to LMS login page
         :param wait_between_pages: How long to wait after going to next page
-        :param link_check_regex: Regex expression to check link_to_download (replace to "^" to bypass link check)
+        :param link_check_regex: Regex expression to check link_to_download, replace to "^" to bypass link check
+        :param user_agent: Browser's user agent to prevent mobile version
+        :param window_size: Default browser's window size
         :param headless: Set True to open Chrome in headless mode
         """
         self._lms_login = lms_login
@@ -76,6 +87,8 @@ def __init__(self, lms_login: str, lms_password: str, link_to_download: str,
         self._login_link = login_link
         self._wait_between_pages = wait_between_pages
         self._link_check_regex = link_check_regex
+        self._user_agent = user_agent
+        self._window_size = window_size
         self._headless = headless
 
         self.browser = None
@@ -123,7 +136,7 @@ def download(self, save_to_directory: str = "") -> list[str]:
 
         # SCORM
         if self.browser.find_elements(By.ID, "scorm_object"):
-            # Open iframe's src
+            logging.info("Switching to the iframe")
             iframe_src = self.browser.find_element(By.ID, "scorm_object").get_attribute("src")
             if iframe_src.lower().startswith("http"):
                 self.browser.get(iframe_src)
@@ -162,6 +175,7 @@ def download(self, save_to_directory: str = "") -> list[str]:
         # H5P
         elif self.browser.find_elements(By.CLASS_NAME, "h5p-iframe"):
             # Open iframe's src
+            logging.info("Switching to the iframe")
             self.browser.switch_to.frame(self.browser.find_element(By.CLASS_NAME, "h5p-iframe"))
 
             # Wait until loaded
@@ -333,8 +347,12 @@ def _start_browser(self) -> None:
         logging.info("Starting browser{}... Please wait".format(" in headless mode" if self._headless else ""))
         chrome_options = webdriver.ChromeOptions()
         if self._headless:
-            chrome_options.add_argument("--headless=new")
-        # chrome_options.add_argument("--window-size=1920,1920")
+            chrome_options.add_argument("--headless=old")
+        chrome_options.add_argument(f"--user-agent={self._user_agent}")
+        chrome_options.add_argument(f"--window-size={self._window_size}")
+        # chrome_options.add_argument("--start-maximized")
+        chrome_options.add_argument("--disable-gpu")
+        chrome_options.add_argument("--disable-blink-features=AutomationControlled")
         chrome_options.add_argument("--disable-infobars")
         chrome_options.add_argument("--disable-extensions")
         chrome_options.add_argument("--ignore-ssl-errors=yes")

diff --git a/src/LMSDownloader/main.py b/src/LMSDownloader/main.py
@@ -95,7 +95,21 @@ def main():
         help="regex expression to check link_to_download (replace to \"^\" to bypass link check)",
         type=str,
         required=False,
-        default="^(http|https):\\/\\/online\\.mospolytech\\.ru\\/mod\\/(scorm|hvp)\\/view\\.php\\?id="
+        default=LMSDownloader.LINK_CHECK_REGEX_DEFAULT
+    )
+    parser.add_argument(
+        "--user-agent",
+        help="browser's user agent to prevent mobile version",
+        type=str,
+        required=False,
+        default=LMSDownloader.USER_AGENT_DEFAULT
+    )
+    parser.add_argument(
+        "--window-size",
+        help="browser's window size",
+        type=str,
+        required=False,
+        default="960,1080"
     )
     parser.add_argument(
         "--headless",
@@ -117,10 +131,12 @@ def main():
 
     # Initialize class
     lms_downloader = LMSDownloader.LMSDownloader(args.login, args.password, args.link_to_download,
-                                                 args.login_link,
-                                                 args.wait_between_pages,
-                                                 args.link_check_regex,
-                                                 args.headless)
+                                                 login_link=args.login_link,
+                                                 wait_between_pages=args.wait_between_pages,
+                                                 link_check_regex=args.link_check_regex,
+                                                 user_agent=args.user_agent,
+                                                 window_size=args.window_size,
+                                                 headless=args.headless)
 
     # Download
     try: