feed: Add 'default' argument to Feed._html2text for HTMLParseError

This allows us to easily fall back on an unconverted string in the
event that the input HTML is malformed.  We already caught
HTMLParseError when converting HTML to plain test for non-html mail,
but we didn't catch it in Feed._get_entry_title.  Now we gracefully
handle the situation by treating the malformed HTML as plain text.

diff --git a/rss2email/feed.py b/rss2email/feed.py
index 3999b0c7dcf3e4d5968da25a841da8b6a16112ac..16191e266065f95aa998241b784ef491d1c41dc2 100644 (file)
--- a/rss2email/feed.py
+++ b/rss2email/feed.py
@@ -416,9 +416,14 @@ class Feed (object):
             not version):
             raise _error.ProcessingError(parsed=parsed, feed=feed)
 
             not version):
             raise _error.ProcessingError(parsed=parsed, feed=feed)
 

-    def _html2text(self, html, baseurl=''):
+    def _html2text(self, html, baseurl='', default=None):

         self.config.setup_html2text(section=self.section)
         self.config.setup_html2text(section=self.section)

-        return _html2text.html2text(html=html, baseurl=baseurl)
+        try:
+            return _html2text.html2text(html=html, baseurl=baseurl)
+        except _html_parser.HTMLParseError as e:
+            if default is not None:
+                return default
+            raise

 
     def _process_entry(self, parsed, entry):
         id_ = self._get_entry_id(entry)
 
     def _process_entry(self, parsed, entry):
         id_ = self._get_entry_id(entry)


@@ -501,12 +506,12 @@ class Feed (object):
         if hasattr(entry, 'title_detail') and entry.title_detail:
             title = entry.title_detail.value
             if 'html' in entry.title_detail.type:
         if hasattr(entry, 'title_detail') and entry.title_detail:
             title = entry.title_detail.value
             if 'html' in entry.title_detail.type:

-                title = self._html2text(title)
+                title = self._html2text(title, default=title)

         else:
             content = self._get_entry_content(entry)
             value = content['value']
             if content['type'] in ('text/html', 'application/xhtml+xml'):
         else:
             content = self._get_entry_content(entry)
             value = content['value']
             if content['type'] in ('text/html', 'application/xhtml+xml'):

-                value = self._html2text(value)
+                value = self._html2text(value, default=value)

             title = value[:70]
         title = title.replace('\n', ' ').strip()
         return title
             title = value[:70]
         title = title.replace('\n', ' ').strip()
         return title