Fetching pages - Custom browser endpoints should not have default pro…

…xy info added
dgtlmoon · Feb 12, 2024 · ccb42bc · ccb42bc
1 parent 4163030
commit ccb42bc
Show file tree

Hide file tree

Showing 4 changed files with 37 additions and 13 deletions.
diff --git a/changedetectionio/content_fetchers/exceptions/__init__.py b/changedetectionio/content_fetchers/exceptions/__init__.py
@@ -36,6 +36,13 @@ def __init__(self, msg):
         logger.error(f"Browser connection error {msg}")
         return
 
+class BrowserFetchTimedOut(Exception):
+    msg = ''
+    def __init__(self, msg):
+        self.msg = msg
+        logger.error(f"Browser processing took too long - {msg}")
+        return
+
 class BrowserStepsStepException(Exception):
     def __init__(self, step_n, original_e):
         self.step_n = step_n

diff --git a/changedetectionio/content_fetchers/puppeteer.py b/changedetectionio/content_fetchers/puppeteer.py
@@ -6,7 +6,7 @@
 
 from loguru import logger
 from changedetectionio.content_fetchers.base import Fetcher
-from changedetectionio.content_fetchers.exceptions import PageUnloadable, Non200ErrorCodeReceived, EmptyReply, ScreenshotUnavailable, BrowserConnectError
+from changedetectionio.content_fetchers.exceptions import PageUnloadable, Non200ErrorCodeReceived, EmptyReply, BrowserFetchTimedOut, BrowserConnectError
 
 
 class fetcher(Fetcher):
@@ -221,14 +221,21 @@ async def main(self, **kwargs):
     def run(self, url, timeout, request_headers, request_body, request_method, ignore_status_codes=False,
             current_include_filters=None, is_binary=False):
 
+        #@todo make update_worker async which could run any of these content_fetchers within memory and time constraints
+        max_time = os.getenv('PUPPETEER_MAX_PROCESSING_TIMEOUT_SECONDS', 180)
+
         # This will work in 3.10 but not >= 3.11 because 3.11 wants tasks only
-        asyncio.run(self.main(
-            url=url,
-            timeout=timeout,
-            request_headers=request_headers,
-            request_body=request_body,
-            request_method=request_method,
-            ignore_status_codes=ignore_status_codes,
-            current_include_filters=current_include_filters,
-            is_binary=is_binary
-        ))
+        try:
+            asyncio.run(asyncio.wait_for(self.main(
+                url=url,
+                timeout=timeout,
+                request_headers=request_headers,
+                request_body=request_body,
+                request_method=request_method,
+                ignore_status_codes=ignore_status_codes,
+                current_include_filters=current_include_filters,
+                is_binary=is_binary
+            ), timeout=max_time))
+        except asyncio.TimeoutError:
+            raise(BrowserFetchTimedOut(msg=f"Browser connected but was unable to process the page in {max_time} seconds."))
+
diff --git a/changedetectionio/processors/__init__.py b/changedetectionio/processors/__init__.py
@@ -75,8 +75,12 @@ def call_browser(self):
 
         proxy_url = None
         if preferred_proxy_id:
-            proxy_url = self.datastore.proxy_list.get(preferred_proxy_id).get('url')
-            logger.debug(f"Selected proxy key '{preferred_proxy_id}' as proxy URL '{proxy_url}' for {url}")
+            # Custom browser endpoints should not have a proxy added
+            if not preferred_proxy_id.startswith('ui-'):
+                proxy_url = self.datastore.proxy_list.get(preferred_proxy_id).get('url')
+                logger.debug(f"Selected proxy key '{preferred_proxy_id}' as proxy URL '{proxy_url}' for {url}")
+            else:
+                logger.debug(f"Skipping adding proxy data when custom Browser endpoint is specified.")
 
         # Now call the fetcher (playwright/requests/etc) with arguments that only a fetcher would need.
         # When browser_connection_url is None, it method should default to working out whats the best defaults (os env vars etc)

diff --git a/changedetectionio/update_worker.py b/changedetectionio/update_worker.py
@@ -369,6 +369,12 @@ def run(self):
                                                                 }
                                                     )
                         process_changedetection_results = False
+                    except content_fetchers.exceptions.BrowserFetchTimedOut as e:
+                        self.datastore.update_watch(uuid=uuid,
+                                                    update_obj={'last_error': e.msg
+                                                                }
+                                                    )
+                        process_changedetection_results = False
                     except content_fetchers.exceptions.BrowserStepsStepException as e:
 
                         if not self.datastore.data['watching'].get(uuid):