Working towards python 2.7 & 3 cross compatibility.

fanficfare/adapters/base_adapter.py

@@ -25,7 +25,7 @@ from functools import partial
 import traceback
 import copy
 
-import bs4
+from bs4 import BeautifulSoup
 
 from ..htmlcleanup import stripHTML
 from ..htmlheuristics import replace_br_with_p
@@ -397,7 +397,7 @@ class BaseSiteAdapter(Configurable):
             if isinstance(svalue,basestring):
                 # bs4/html5lib add html, header and body tags, which
                 # we don't want.  utf8FromSoup will strip the body tags for us.
-                svalue = bs4.BeautifulSoup(svalue,"html5lib").body
+                svalue = BeautifulSoup(svalue,"html5lib").body
             self.story.setMetadata('description',self.utf8FromSoup(url,svalue))
         else:
             self.story.setMetadata('description',stripHTML(svalue))
@@ -546,8 +546,8 @@ class BaseSiteAdapter(Configurable):
 
         ## soup and re-soup because BS4/html5lib is more forgiving of
         ## incorrectly nested tags that way.
-        soup = bs4.BeautifulSoup(data,'html5lib')
-        soup = bs4.BeautifulSoup(unicode(soup),'html5lib')
+        soup = BeautifulSoup(data,'html5lib')
+        soup = BeautifulSoup(unicode(soup),'html5lib')
 
         for ns in soup.find_all('fff_hide_noscript'):
             ns.name = 'noscript'

fanficfare/htmlcleanup.py

@@ -81,10 +81,10 @@ def removeEntities(text, space_only=False):
     
     try:
         t = text.decode('utf-8')
-    except (UnicodeEncodeError,UnicodeDecodeError), e:
+    except (UnicodeEncodeError,UnicodeDecodeError) as e:
         try:
             t = text.encode ('ascii', 'xmlcharrefreplace') 
-        except (UnicodeEncodeError,UnicodeDecodeError), e:
+        except (UnicodeEncodeError,UnicodeDecodeError) as e:
             t = text
     text = t 
     # replace numeric versions of [&<>] with named versions,
@@ -106,7 +106,7 @@ def removeEntities(text, space_only=False):
             continue
         try:
             text = text.replace(e, v)
-        except UnicodeDecodeError, ex:
+        except UnicodeDecodeError as ex:
             # for the pound symbol in constants.py
             text = text.replace(e, v.decode('utf-8'))
 

fanficfare/htmlheuristics.py

@@ -22,7 +22,7 @@ import codecs
 import bs4 as bs
 import HtmlTagStack as stack
 
-from . import exceptions as exceptions
+import exceptions
 
 def logdebug(s):
     # uncomment for debug output

fanficfare/mobi.py

@@ -10,7 +10,7 @@ import logging
 
 logger = logging.getLogger(__name__)
 
-from html import HtmlProcessor
+from mobihtml import HtmlProcessor
 
 # http://wiki.mobileread.com/wiki/MOBI
 # http://membres.lycos.fr/microfirst/palm/pdb.html

fanficfare/mobihtml.py

@@ -5,9 +5,11 @@
 
 import re
 import sys
-import StringIO
-import urllib
+from six import StringIO
+from six.moves import urllib
 
+# import bs4
+# BeautifulSoup = bs4.BeautifulSoup
 from bs4 import BeautifulSoup
 
 class HtmlProcessor:

fanficfare/story.py

@@ -18,7 +18,7 @@
 import os, re
 import copy
 from collections import defaultdict
-import urlparse
+from six.moves.urllib.parse import urlparse
 import string
 import json
 import datetime
@@ -26,7 +26,6 @@ from math import floor
 from functools import partial
 import logging
 logger = logging.getLogger(__name__)
-import urlparse as up
 
 import bs4
 
@@ -147,7 +146,7 @@ except:
 
 ## also used for explicit no image processing.
 def no_convert_image(url,data):
-    parsedUrl = up.urlparse(url)
+    parsedUrl = urlparse.urlparse(url)
 
     ext=parsedUrl.path[parsedUrl.path.rfind('.')+1:].lower()
 
@@ -1184,7 +1183,7 @@ class Story(Configurable):
                 else:
                     try:
                         sizes = [ int(x) for x in self.getConfigList('image_max_size') ]
-                    except Exception, e:
+                    except Exception as e:
                         raise exceptions.FailedToDownload("Failed to parse image_max_size from personal.ini:%s\nException: %s"%(self.getConfigList('image_max_size'),e))
                     grayscale = self.getConfig('grayscale_images')
                     imgtype = self.getConfig('convert_images_to')
@@ -1201,7 +1200,7 @@ class Story(Configurable):
                                                     removetrans,
                                                     imgtype,
                                                     background="#"+self.getConfig('background_color'))
-            except Exception, e:
+            except Exception as e:
                 logger.info("Failed to load or convert image, \nparent:%s\nskipping:%s\nException: %s"%(parenturl,imgurl,e))
                 return ("failedtoload","failedtoload")