Working and up to date. WIP misc manual actions

app/utils_worker/download/browser.py

@@ -2,6 +2,7 @@ import time
 import datetime
 import logging
 import os
+import sys
 import base64
 import requests
 from selenium import webdriver
@@ -21,18 +22,19 @@ class PDFDownloader:
     def start(self):
         options=Options()
         options.profile = config["browser_profile_path"]
-        # TODO: Get headless mode interactively
-        options.add_argument('--headless')
-        # options.add_argument("--disable-infobars")
-        # options.set_preference("javascript.enabled", False)
-        # options.add_argument("--disable-popup-blocking")
+        if "notheadless" in sys.argv:
+            self.logger.warning("Opening browser GUI because of Argument 'notheadless'")
+        else:
+            options.add_argument('--headless')
+
         # Print to pdf
         options.set_preference("print_printer", "Mozilla Save to PDF")
         options.set_preference("print.always_print_silent", True)
         options.set_preference("print.show_print_progress", False)
         options.set_preference('print.save_as_pdf.links.enabled', True)
+
+        # Just save if the filetype is pdf already, does not work!
         options.set_preference("print.printer_Mozilla_Save_to_PDF.print_to_file", True)
-        # Save existing pdf
         options.set_preference("browser.download.folderList", 2)
         # options.set_preference("browser.helperApps.neverAsk.saveToDisk", "application/pdf")
         # options.set_preference("pdfjs.disabled", True)
@@ -140,7 +142,7 @@ class PDFDownloader:
         hrefs = [h for h in hrefs \
             if not sum([(domain in h) for domain in blacklisted]) # sum([True, False, False, False]) == 1 (esp. not 0)
             ] # filter a tiny bit at least
-        self.logger.info(f"Hrefs result (before:{len_old}, after: {len(hrefs)})")
+        self.logger.info(f"Hrefs filtered (before: {len_old}, after: {len(hrefs)})")
         return hrefs