fix: unescape HTML entities in the returned text.

weblyzard · Nov 15, 2018 · 4cd3a87 · 4cd3a87
1 parent 4a2fb5d
commit 4cd3a87
Show file tree

Hide file tree

Showing 2 changed files with 8 additions and 2 deletions.
diff --git a/setup.py b/setup.py
@@ -13,7 +13,7 @@
 setup(
       # Metadata
       name="inscriptis",
-      version="0.0.3.3",
+      version="0.0.3.4",
       description='inscriptis - HTML to text converter.',
       long_description=long_description,
       long_description_content_type='text/markdown',

diff --git a/src/inscriptis/html_engine.py b/src/inscriptis/html_engine.py
@@ -14,6 +14,12 @@
 from inscriptis.html_properties import Display, WhiteSpace, Line
 from inscriptis.table_engine import Table
 
+try:
+    # python 2 compatibility
+    from HTMLParser import HTMLParser
+except ImportError:
+    from html import unescape
+
 
 class Inscriptis(object):
 
@@ -102,7 +108,7 @@ def get_text(self):
         ::returns:
            a text representation of the parsed content
         '''
-        return '\n'.join(chain(*self.clean_text_lines))
+        return unescape('\n'.join(chain(*self.clean_text_lines)))
 
     def write_line(self, force=False):
         '''