[BUG FIX] Adding try/except for ugly encoded corpora.

parsing/FileParsers/EuropressFileParser.py

@@ -42,7 +42,7 @@ class EuropressFileParser(FileParser):
         # initialize the list of metadata
         metadata_list = []
         # parse all the articles, one by one
-
+        try:
             for html_article in html_articles:
                 
                 metadata = {}
@@ -59,7 +59,12 @@ class EuropressFileParser(FileParser):
                                 metadata['source'] = name.text.encode(codif)
 
                     for header in html_article.xpath("./tr/td/span[@class = 'DocHeader']"):
+                        try:
                             text = header.text
+                        except Exception as error:
+                            print(error)
+
+                        
                         if isinstance(text, bytes):
                             text = text.decode(encoding)
 
@@ -177,6 +182,10 @@ class EuropressFileParser(FileParser):
                     metadata_list.append(metadata)
                     count += 1
         
+        except Exception as error:
+            print(error)
+            pass
+
 #       from pprint import pprint
 #       pprint(metadata_list)
 #       return []