From ae7cd120d223e4238c6b4b1e4fd1d91c1932a8c3 Mon Sep 17 00:00:00 2001
From: Fabio Manganiello <blacklight86@gmail.com>
Date: Sun, 21 Oct 2018 14:47:52 +0200
Subject: [PATCH] Wrapped the RSS parsing loop in a try-except block to prevent
 the backend from continuously crashing if there are encoding issues on the
 RSS titles

---
 .../backend/http/request/rss/__init__.py      | 56 ++++++++++---------
 1 file changed, 30 insertions(+), 26 deletions(-)

diff --git a/platypush/backend/http/request/rss/__init__.py b/platypush/backend/http/request/rss/__init__.py
index aac0198e3..2c00945a2 100644
--- a/platypush/backend/http/request/rss/__init__.py
+++ b/platypush/backend/http/request/rss/__init__.py
@@ -127,38 +127,42 @@ class RssUpdates(HttpRequest):
             if not entry.published_parsed:
                 continue
 
-            entry_timestamp = datetime.datetime(*entry.published_parsed[:6])
+            try:
+                entry_timestamp = datetime.datetime(*entry.published_parsed[:6])
 
-            if latest_update is None \
-                    or entry_timestamp > latest_update:
-                self.logger.info('Processed new item from RSS feed <{}>: "{}"'
-                             .format(self.url, entry.title))
+                if latest_update is None \
+                        or entry_timestamp > latest_update:
+                    self.logger.info('Processed new item from RSS feed <{}>: "{}"'
+                                .format(self.url, entry.title))
 
-                entry.summary = entry.summary if hasattr(entry, 'summary') else None
+                    entry.summary = entry.summary if hasattr(entry, 'summary') else None
 
-                if self.mercury_api_key:
-                    entry.content = self._parse_entry_content(entry.link)
-                elif hasattr(entry, 'summary'):
-                    entry.content = entry.summary
-                else:
-                    entry.content = None
+                    if self.mercury_api_key:
+                        entry.content = self._parse_entry_content(entry.link)
+                    elif hasattr(entry, 'summary'):
+                        entry.content = entry.summary
+                    else:
+                        entry.content = None
 
-                digest += '<h1 style="page-break-before: always">{}</h1>{}' \
-                    .format(entry.title, entry.content)
+                    digest += '<h1 style="page-break-before: always">{}</h1>{}' \
+                        .format(entry.title, entry.content)
 
-                e = {
-                    'entry_id': entry.id,
-                    'title': entry.title,
-                    'link': entry.link,
-                    'summary': entry.summary,
-                    'content': entry.content,
-                    'source_id': source_record.id,
-                    'published': entry_timestamp,
-                }
+                    e = {
+                        'entry_id': entry.id,
+                        'title': entry.title,
+                        'link': entry.link,
+                        'summary': entry.summary,
+                        'content': entry.content,
+                        'source_id': source_record.id,
+                        'published': entry_timestamp,
+                    }
 
-                entries.append(e)
-                session.add(FeedEntry(**e))
-                if self.max_entries and len(entries) > self.max_entries: break
+                    entries.append(e)
+                    session.add(FeedEntry(**e))
+                    if self.max_entries and len(entries) > self.max_entries: break
+            except Exception as e:
+                self.logger.warning('Exception encountered while parsing RSS ' +
+                                    'RSS feed {}: {}'.format(self.url, str(e)))
 
         source_record.last_updated_at = parse_start_time
         digest_filename = None