[udemy] Update User-Agent and detect captcha (closes #14713, closes #15839, closes...

[youtube-dl] / youtube_dl / extractor / udemy.py

diff --git a/youtube_dl/extractor/udemy.py b/youtube_dl/extractor/udemy.py
index 79c45f80e0f827d07a2ef362597b6e7fbab122e7..89a7f6adefb55652f09e25ced2f163341309c717 100644 (file)
--- a/youtube_dl/extractor/udemy.py
+++ b/youtube_dl/extractor/udemy.py
@@ -122,9 +122,23 @@ class UdemyIE(InfoExtractor):
             raise ExtractorError(error_str, expected=True)
 
     def _download_webpage_handle(self, *args, **kwargs):
-        kwargs.setdefault('headers', {})['User-Agent'] = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_5) AppleWebKit/603.2.4 (KHTML, like Gecko) Version/10.1.1 Safari/603.2.4'
-        return super(UdemyIE, self)._download_webpage_handle(
+        headers = kwargs.get('headers', {}).copy()
+        headers['User-Agent'] = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.109 Safari/537.36'
+        kwargs['headers'] = headers
+        ret = super(UdemyIE, self)._download_webpage_handle(
             *args, **compat_kwargs(kwargs))
+        if not ret:
+            return ret
+        webpage, _ = ret
+        if any(p in webpage for p in (
+                '>Please verify you are a human',
+                'Access to this page has been denied because we believe you are using automation tools to browse the website',
+                '"_pxCaptcha"')):
+            raise ExtractorError(
+                'Udemy asks you to solve a CAPTCHA. Login with browser, '
+                'solve CAPTCHA, then export cookies and pass cookie file to '
+                'youtube-dl with --cookies.', expected=True)
+        return ret
 
     def _download_json(self, url_or_request, *args, **kwargs):
         headers = {