support for html unescaping for all python versions added

src/html_unescaping.py

@@ -0,0 +1,19 @@
+import sys
+
+if sys.version_info.major == 3 and sys.version_info.minor >= 4:
+    # Python 3.4+
+    from html import unescape
+else:
+    if sys.version_info.major <= 2:
+        # Python 2
+        import HTMLParser
+
+        html_parser = HTMLParser.HTMLParser()
+    else:
+        # Python 3.0 - 3.3
+        import html.parser
+
+        html_parser = html.parser.HTMLParser()
+
+    def unescape(string):
+        return html_parser.unescape(string)

src/transcript_api.py

@@ -6,6 +6,8 @@ import logging
 
 import requests
 
+from .html_unescaping import unescape
+
 
 logger = logging.getLogger(__name__)
 
@@ -112,7 +114,7 @@ class _TranscriptParser():
     def parse(self):
         return [
             {
-                'text': re.sub(self.HTML_TAG_REGEX, '', xml_element.text),
+                'text': re.sub(self.HTML_TAG_REGEX, '', unescape(xml_element.text)),
                 'start': float(xml_element.attrib['start']),
                 'duration': float(xml_element.attrib['dur']),
             }