Fixes for status code and screenshot info

changedetectionio/content_fetcher.py

@@ -396,6 +396,8 @@ class base_html_playwright(Fetcher):
                 # https://github.com/dgtlmoon/changedetection.io/discussions/2122#discussioncomment-8241962
                 logger.critical(f"Response from the browser/Playwright did not have a status_code! Response follows.")
                 logger.critical(response)
+                context.close()
+                browser.close()
                 raise PageUnloadable(url=url, status_code=None, message=str(e))
 
             if self.status_code != 200 and not ignore_status_codes:
@@ -436,14 +438,15 @@ class base_html_playwright(Fetcher):
             # which will significantly increase the IO size between the server and client, it's recommended to use the lowest
             # acceptable screenshot quality here
             try:
-                # The actual screenshot
+                # The actual screenshot - this always base64 and needs decoding! horrible! huge CPU usage
-                self.screenshot = self.page.screenshot(type='jpeg', full_page=True,
+                self.screenshot = self.page.screenshot(type='jpeg',
-                                                       quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
+                                                       full_page=True,
+                                                       quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)),
+                                                       )
             except Exception as e:
-                context.close()
+                # It's likely the screenshot was too long/big and something crashed
-                browser.close()
+                raise ScreenshotUnavailable(url=url, status_code=self.status_code)
-                raise ScreenshotUnavailable(url=url, status_code=response.status_code)
+            finally:
-
                 context.close()
                 browser.close()
 

changedetectionio/update_worker.py

@@ -411,7 +411,7 @@ class update_worker(threading.Thread):
                                                                            'last_check_status': e.status_code})
                         process_changedetection_results = False
                     except content_fetcher.ScreenshotUnavailable as e:
-                        err_text = "Screenshot unavailable, page did not render fully in the expected time - try increasing 'Wait seconds before extracting text'"
+                        err_text = "Screenshot unavailable, page did not render fully in the expected time or page was too long - try increasing 'Wait seconds before extracting text'"
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            'last_check_status': e.status_code})
                         process_changedetection_results = False