From 42473d4f1d32120ebbb77542f434f6fb4dfc21ec Mon Sep 17 00:00:00 2001 From: Jim Miller Date: Mon, 30 Jul 2012 17:00:13 -0500 Subject: [PATCH] Remove extra html body from ancient ffnet chapters. --- fanficdownloader/adapters/adapter_fanfictionnet.py | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/fanficdownloader/adapters/adapter_fanfictionnet.py b/fanficdownloader/adapters/adapter_fanfictionnet.py index f70f984..52cd433 100644 --- a/fanficdownloader/adapters/adapter_fanfictionnet.py +++ b/fanficdownloader/adapters/adapter_fanfictionnet.py @@ -239,6 +239,15 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter): ## additional to what ever the ## slow_down_sleep_time setting is. data = self._fetchUrl(url) + + # some ancient stories have body tags inside them that cause + # soup parsing to discard the content. For story text we + # don't care about anything before "