[BUG FIX] Latin1 encoding issue resolved :)

e592af7f · Administrator · 8e08ba93 · e592af7f
Commit e592af7f authored Jan 12, 2015 by Administrator
Hide whitespace changes
Inline Side-by-side

Showing with 8 additions and 6 deletions

EuropressFileParser.py parsing/FileParsers/EuropressFileParser.py +8 -6

No files found.
--- a/parsing/FileParsers/EuropressFileParser.py
+++ b/parsing/FileParsers/EuropressFileParser.py
@@ -25,12 +25,14 @@ class EuropressFileParser(FileParser):
        #return []
        encoding = self.detect_encoding(contents)
        #print(encoding)
-        #if encoding != "utf-8":
-        try:
-            contents = contents.decode(encoding, errors='replace').encode(codif)
-        except Exception as error:
-            print(error)
-            pass
+        if encoding != "utf-8":
+            try:
+                contents = contents.decode("latin1", errors='replace').encode(codif)
+            except :
+                try:
+                    contents = contents.decode(encoding, errors='replace').encode(codif)
+                except Exception as error:
+                    print(error)

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