Comments ar now saved as HTML instead of text

Basilisk/MACAO/macao_12/extracted/extract_page.py

 import re
 from pprint import pprint
-from typing import List
+from typing import Any, List
 
 from lxml import html
 from rdflib import Graph, Literal
@@ -12,7 +12,8 @@ class Comment:
     id: str
     num: int
     text: str
-    html: str
+    html: Any
+    elem: Any
 
     def __repr__(self):
         return str(self.__dict__)
@@ -49,7 +50,8 @@ def parse_page(graph: Graph, filepath: str, id: str):
     for cmt_div in zi:
         comment = Comment()
         comment.text = cmt_div.text_content()
-        comment.html = cmt_div
+        comment.html = html.tostring(cmt_div, encoding="unicode")
+        comment.elem = cmt_div
         comment.id = cmt_div.get("id")
         # Split id in two parts (non-digits and digits), then match on these parts
         m = regex_comment.match(comment.id)
@@ -59,16 +61,16 @@ def parse_page(graph: Graph, filepath: str, id: str):
                     print(f"Comment, num={num}")
                     comment.num = int(num)
                     page.comments_misc.append(comment)
-                    graph.add((NS[id], NS["commentaireInfo"], Literal(comment.text)))
+                    graph.add((NS[id], NS["commentaireInfo"], Literal(comment.html)))
                 case ["divSugg", num]:
                     print(f"Suggestion, num={num}")
                     comment.num = int(num)
                     page.comments_sugg.append(comment)
-                    graph.add((NS[id], NS["commentaireSugg"], Literal(comment.text)))
+                    graph.add((NS[id], NS["commentaireSugg"], Literal(comment.html)))
                 case ["divCmtSucces", _]:
                     print(f"Succès")
                     page.comment_success = comment
-                    graph.add((NS[id], NS["commentaireSucces"], Literal(comment.text)))
+                    graph.add((NS[id], NS["commentaireSucces"], Literal(comment.html)))
                 case [other, _]:
                     print(f"other: {other}")
     pprint(page)