Adapt page list parsing to Macao3

tetras_extraction/script/src/extract_mosetp.py

@@ -46,6 +46,11 @@ def parse_mosetp(graph: Graph, filepath: str, id: str):
     :param id: text identifier of the subsection
     """
     # Prepare regex with capturing groups to match lines
+    if Context.version == "macao_3":
+        regex = re.compile(
+            r'.*new PageContenu\("(.*)", "(.*)", "(.*)", "", "", "", "(.*)"\);'
+        )
+    else:
         regex = re.compile(r'.*new PageContenu\("(.*)", "(.*)", "(.*)", ""\);')
     # The lines we need are fairly basic, grep is much faster
     # than a Python HTML parser to filter them