Fetching - Browser Step enabled watches should also identify 404/non-200 status situations (#1907)

changedetectionio/content_fetcher.py

@@ -472,12 +472,18 @@ class base_html_playwright(Fetcher):
             browsersteps_interface = steppable_browser_interface()
             browsersteps_interface.page = self.page
 
-            try:
             response = browsersteps_interface.action_goto_url(value=url)
+            self.headers = response.all_headers()
 
+            if response is None:
+                context.close()
+                browser.close()
+                print("Content Fetcher > Response object was none")
+                raise EmptyReply(url=url, status_code=None)
+
+            try:
                 if self.webdriver_js_execute_code is not None and len(self.webdriver_js_execute_code):
                     browsersteps_interface.action_execute_js(value=self.webdriver_js_execute_code, selector=None)
-
             except playwright._impl._api_types.TimeoutError as e:
                 context.close()
                 browser.close()
@@ -489,31 +495,24 @@ class base_html_playwright(Fetcher):
                 browser.close()
                 raise PageUnloadable(url=url, status_code=None, message=str(e))
 
-            if response is None:
-                context.close()
-                browser.close()
-                print("Content Fetcher > Response object was none")
-                raise EmptyReply(url=url, status_code=None)
-
-            extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
-            self.page.wait_for_timeout(extra_wait * 1000)
-
-            # Run Browser Steps here
-            self.iterate_browser_steps()
-
             extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
             self.page.wait_for_timeout(extra_wait * 1000)
 
             self.content = self.page.content()
             self.status_code = response.status
+
+            if self.status_code != 200 and not ignore_status_codes:
+                raise Non200ErrorCodeReceived(url=url, status_code=self.status_code)
+
             if len(self.page.content().strip()) == 0:
                 context.close()
                 browser.close()
                 print("Content Fetcher > Content was empty")
                 raise EmptyReply(url=url, status_code=response.status)
 
-            self.status_code = response.status
+            # Run Browser Steps here
-            self.headers = response.all_headers()
+            self.iterate_browser_steps()
+            self.page.wait_for_timeout(extra_wait * 1000)
 
             # So we can find an element on the page where its selector was entered manually (maybe not xPath etc)
             if current_include_filters is not None:
@@ -539,7 +538,7 @@ class base_html_playwright(Fetcher):
             except Exception as e:
                 context.close()
                 browser.close()
-                raise ScreenshotUnavailable(url=url, status_code=None)
+                raise ScreenshotUnavailable(url=url, status_code=response.status_code)
 
             context.close()
             browser.close()

changedetectionio/tests/visualselector/test_fetch_data.py

@@ -1,18 +1,19 @@
 #!/usr/bin/python3
 
 import time
+import os
 from flask import url_for
 from ..util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
 
+def test_setup(client, live_server):
+    live_server_setup(live_server)
+
 # Add a site in paused mode, add an invalid filter, we should still have visual selector data ready
 def test_visual_selector_content_ready(client, live_server):
     import os
     import json
 
     assert os.getenv('PLAYWRIGHT_DRIVER_URL'), "Needs PLAYWRIGHT_DRIVER_URL set for this test"
-    time.sleep(1)
-    live_server_setup(live_server)
-
 
     # Add our URL to the import page, because the docker container (playwright/selenium) wont be able to connect to our usual test url
     test_url = "https://changedetection.io/ci-test/test-runjs.html"
@@ -60,4 +61,67 @@ def test_visual_selector_content_ready(client, live_server):
         follow_redirects=True
     )
     assert b'notification_screenshot' in res.data
+    client.get(
+        url_for("form_delete", uuid="all"),
+        follow_redirects=True
+    )
 
+def test_basic_browserstep(client, live_server):
+
+    assert os.getenv('PLAYWRIGHT_DRIVER_URL'), "Needs PLAYWRIGHT_DRIVER_URL set for this test"
+    #live_server_setup(live_server)
+
+    # Add our URL to the import page, because the docker container (playwright/selenium) wont be able to connect to our usual test url
+    test_url = "https://changedetection.io/ci-test/test-runjs.html"
+
+    res = client.post(
+        url_for("form_quick_watch_add"),
+        data={"url": test_url, "tags": '', 'edit_and_watch_submit_button': 'Edit > Watch'},
+        follow_redirects=True
+    )
+    assert b"Watch added in Paused state, saving will unpause" in res.data
+
+    res = client.post(
+        url_for("edit_page", uuid="first", unpause_on_save=1),
+        data={
+              "url": test_url,
+              "tags": "",
+              "headers": "",
+              'fetch_backend': "html_webdriver",
+              'browser_steps-0-operation': 'Goto site',
+              'browser_steps-1-operation': 'Click element',
+              'browser_steps-1-selector': 'button[name=test-button]',
+              'browser_steps-1-value': ''
+        },
+        follow_redirects=True
+    )
+    assert b"unpaused" in res.data
+    wait_for_all_checks(client)
+    uuid = extract_UUID_from_client(client)
+
+
+    # now test for 404 errors
+    res = client.post(
+        url_for("edit_page", uuid=uuid, unpause_on_save=1),
+        data={
+              "url": "https://changedetection.io/404",
+              "tags": "",
+              "headers": "",
+              'fetch_backend': "html_webdriver",
+              'browser_steps-0-operation': 'Goto site',
+              'browser_steps-1-operation': 'Click element',
+              'browser_steps-1-selector': 'button[name=test-button]',
+              'browser_steps-1-value': ''
+        },
+        follow_redirects=True
+    )
+    assert b"unpaused" in res.data
+    wait_for_all_checks(client)
+
+    res = client.get(url_for("index"))
+    assert b'Error - 404' in res.data
+
+    client.get(
+        url_for("form_delete", uuid="all"),
+        follow_redirects=True
+    )