From 3d90849c0be98f090322ee71dbdb86b03edf18cc Mon Sep 17 00:00:00 2001
From: Jim Miller <retiefjimm@gmail.com>
Date: Tue, 31 Mar 2015 09:16:41 -0500
Subject: [PATCH] Explicit html parse for BS4 when reading in existing epub. 
 For cal 1.48.

---
 fanficdownloader/epubutils.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fanficdownloader/epubutils.py b/fanficdownloader/epubutils.py
index 2e1b041f..f55745df 100644
--- a/fanficdownloader/epubutils.py
+++ b/fanficdownloader/epubutils.py
@@ -107,7 +107,7 @@ def get_update_data(inputio,
                         pass # corner case I bumped into while testing.
                 if re.match(r'.*/(file|chapter)\d+\.x?html',href):
                     if getsoups:
-                        soup = bs.BeautifulSoup(epub.read(href).decode("utf-8"))
+                        soup = bs.BeautifulSoup(epub.read(href).decode("utf-8"),"html5lib")
                         for img in soup.findAll('img'):
                             newsrc=''
                             longdesc=''