FS updates and corrections

app/utils_worker/download/browser.py

@@ -5,13 +5,13 @@ import os
 import base64
 import requests
 from selenium import webdriver
-from selenium.webdriver.firefox.options import Options
 import configuration
 import json
 
 config = configuration.parsed["DOWNLOADS"]
 blacklisted = json.loads(config["blacklisted_href_domains"])
 
+
 class PDFDownloader:
     """Saves a given url. Fills the object it got as a parameter"""
     logger = logging.getLogger(__name__)
@@ -19,10 +19,8 @@ class PDFDownloader:
     running = False
     
     def start(self):
-        try:
-            self.finish()
-        except:
-            self.logger.info("gecko driver not yet running")
+        self.finish() # clear up
+            
         options = webdriver.FirefoxOptions()
         options.profile = config["browser_profile_path"]
         # should be options.set_preference("profile", config["browser_profile_path"]) as of selenium 4 but that doesn't work
@@ -56,13 +54,15 @@ class PDFDownloader:
 
     def autostart(self):
         if not self.running:
-            self.start() # relaunch the dl util    
+            self.start()  # relaunch the dl util
 
     def finish(self):
-        self.logger.info("Exiting gecko driver")
-        self.driver.quit()
-        self.running = False
-
+        if self.running:
+            self.logger.info("Exiting gecko driver")
+            self.driver.quit()
+            self.running = False
+        else:
+            self.logger.info("Gecko driver not yet running")
 
     def download(self, article_object):
         sleep_time = 1
@@ -74,14 +74,14 @@ class PDFDownloader:
         except Exception as e:
             self.logger.critical("Selenium .get(url) failed with error {}".format(e))
             self.finish()
-            return article_object # without changes
+            return article_object  # without changes
         
         time.sleep(sleep_time)
         # leave the page time to do any funky business
 
         # in the mean time, get a page title if required
         if article_object.is_title_bad:
-            article_object.title = self.driver.title.replace(".pdf","")
+            article_object.title = self.driver.title.replace(".pdf", "")
             # will be propagated to dst as well
 
         fname = article_object.fname_template
@@ -105,7 +105,7 @@ class PDFDownloader:
         else:
             article_object.file_name = ""
         
-        return article_object # this change is saved later manually
+        return article_object  # this change is saved later manually
 
 
     def get_exisiting_pdf(self, url, dst):