[BUG FIX] parsing execption for irregular files.

301f2a2c · Administrator · 62e6d443 · 301f2a2c
Commit 301f2a2c authored Jan 08, 2015 by Administrator
Hide whitespace changes
Inline Side-by-side

Showing with 5 additions and 1 deletion

EuropressFileParser.py parsing/FileParsers/EuropressFileParser.py +5 -1

No files found.
--- a/parsing/FileParsers/EuropressFileParser.py
+++ b/parsing/FileParsers/EuropressFileParser.py
@@ -26,7 +26,11 @@ class EuropressFileParser(FileParser):
        encoding = self.detect_encoding(contents)
        #print(encoding)
        #if encoding != "utf-8":
-        contents = contents.decode(encoding, errors='replace').encode(codif)
+        try:
+            contents = contents.decode(encoding, errors='replace').encode(codif)
+        except Exception as error:
+            print(error)
+            pass

        try:
            html_parser = etree.HTMLParser(encoding=codif)