Backup_Repos/FanFicFare
1
0
Fork 0
mirror of https://github.com/JimmXinu/FanFicFare.git synced 2026-05-08 21:11:59 +02:00
Code Issues Projects Releases Wiki Activity

htmlheuristics needed to chek if the parsed body actually had any tags in it,

Browse source 
and is now removing ASCII character x!0 (whitespace) as it interfered with
  regexp.
base_adapter called replace_br_with_p with two argument, where teh function
  only support one.
This commit is contained in:
asbjorn grandt 2013-10-27 23:01:09 +01:00
parent df5a91daed
commit 9d8508ee6f
2 changed files with 12 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
fanficdownloader/adapters/base_adapter.py
View file

@ -372,7 +372,7 @@ class BaseSiteAdapter(Configurable):
if self.getConfig("replace_br_with_p"):
# Apply heuristic processing to replace <br> paragraph
# breaks with <p> tags.
retval = replace_br_with_p(self,retval)
retval = replace_br_with_p(retval)
if self.getConfig('replace_hr'):
# replacing a self-closing tag with a container tag in the

11
fanficdownloader/htmlheuristics.py
View file

@ -23,6 +23,17 @@ from . import exceptions as exceptions
def replace_br_with_p(body):
logger.debug('Body Length.: %d' % len(body))
logger.debug('Body First >: %d' % body.find('>'))
logger.debug('Body Last <.: %d' % body.rfind("<"))
# Ascii character (and Unicode as well) xA0 is a non-breaking space, ascii code 160.
# However, Python Regex does not recognize it as a whitespace, so we'll be changing it to a reagular space.
body = body.replace(u'\xa0', u' ')
if body.find('>') == -1 or body.rfind("<") == -1:
return body
# change surrounding div to a p and remove attrs Top surrounding
# tag in all cases now should be div, to just strip the first and
# last tags.