Handling the goto site steps which were previously skipped in the browser steps processing

changedetectionio/content_fetchers/base.py

@@ -113,14 +113,14 @@ def get_all_headers(self):
  def browser_steps_get_valid_steps(self):
  if self.browser_steps is not None and len(self.browser_steps):
  valid_steps = filter(
- lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'),
- self.browser_steps)
+ lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one'),
+ self.browser_steps[1:]) # Skip the first one, it is already handled before the browser steps are run
 
  return valid_steps
 
  return None
 
- def iterate_browser_steps(self):
+ def iterate_browser_steps(self, start_url):
  from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
  from playwright._impl._errors import TimeoutError, Error
  from changedetectionio.safe_jinja import render as jinja_render
@@ -146,6 +146,11 @@ def iterate_browser_steps(self):
  if '{%' in step['selector'] or '{{' in step['selector']:
  selector = jinja_render(template_str=step['selector'])
 
+ # If the operation is Goto site, change it to Goto URL and use the url as the optional value
+ if step['operation'] == 'Goto site':
+ step['operation'] = 'Goto URL'
+ optional_value = start_url
+
  getattr(interface, "call_action")(action_name=step['operation'],
  selector=selector,
  optional_value=optional_value)

changedetectionio/content_fetchers/playwright.py

@@ -172,7 +172,7 @@ def run(self,
 
  # Run Browser Steps here
  if self.browser_steps_get_valid_steps():
- self.iterate_browser_steps()
+ self.iterate_browser_steps(start_url = url)
 
  self.page.wait_for_timeout(extra_wait * 1000)
 

changedetectionio/content_fetchers/puppeteer.py

@@ -173,7 +173,7 @@ async def fetch_page(self,
  # Run Browser Steps here
  # @todo not yet supported, we switch to playwright in this case
  # if self.browser_steps_get_valid_steps():
- # self.iterate_browser_steps()
+ # self.iterate_browser_steps(start_url = url)
 
  await asyncio.sleep(1 + extra_wait)
 
@@ -244,4 +244,3 @@ def run(self, url, timeout, request_headers, request_body, request_method, ignor
  ), timeout=max_time))
  except asyncio.TimeoutError:
  raise(BrowserFetchTimedOut(msg=f"Browser connected but was unable to process the page in {max_time} seconds."))
-