option to read a list of page titles from a file

Author: mackuba

import_logs.py

@@ -764,6 +764,11 @@ def _create_parser(self):
             "changed General.action_title_category_delimiter in your Matomo configuration, you need to set this "
             "option to the same value in order to get a pretty page titles report."
         )
+        option_parser.add_option(
+            '--page-titles-from', dest='page_titles_from', default=None,
+            help="Loads a mapping of URLs to page titles from a given file so that titles can be displayed "
+            "in the page titles report."
+        )
         option_parser.add_option(
             '--dump-log-regex', dest='dump_log_regex', action='store_true', default=False,
             help="Prints out the regex string used to parse log lines and exists. Can be useful for using formats "
@@ -923,6 +928,15 @@ def _parse_args(self, option_parser):
         else:
             logging.debug('Accepted hostnames: all')
 
+        self.page_titles_map = {}
+
+        if self.options.page_titles_from:
+            for line in open(self.options.page_titles_from).readlines():
+                separator = line.index('=')
+                url = line[0:separator].strip()
+                title = line[separator+1:-1].strip()
+                self.page_titles_map[url] = title
+
         if self.options.log_format_regex:
             self.format = RegexFormat('custom', self.options.log_format_regex, self.options.log_date_format)
         elif self.options.log_format_name:
@@ -1908,6 +1922,10 @@ def _get_hit_args(self, hit):
                     urllib.quote(args['urlref'], '')
                 ) if args['urlref'] != ''  else '')
             )
+        else:
+            page_title = config.page_titles_map.get(args['url'])
+            if page_title:
+                args['action_name'] = page_title
 
         if hit.generation_time_milli > 0:
             args['gt_ms'] = int(hit.generation_time_milli)