Skip to content
Browse files

tweaking to be consistent with naming conventions, etc

  • Loading branch information...
1 parent c00010f commit 747e3da5b4010abc22c6865b4747cbd57d2dbe62 @ptwobrussell committed Jan 27, 2011
Showing with 2 additions and 2 deletions.
  1. +2 −2 recipe__summarize_webpage.py
View
4 recipe__summarize_webpage.py
@@ -111,7 +111,7 @@ def summarize(txt):
# be spent here trying to extract the core content, detecting headers, footers, margins,
# navigation, etc.
-def cleanHtml(html):
+def clean_html(html):
return BeautifulStoneSoup(nltk.clean_html(html),
convertEntities=BeautifulStoneSoup.HTML_ENTITIES).contents[0]
@@ -122,7 +122,7 @@ def cleanHtml(html):
# The good news is that summarize algorithm inherently accounts for handling
# a lot of this noise.
- clean_page = cleanHtml(page)
+ clean_page = clean_html(page)
summary = summarize(clean_page)

0 comments on commit 747e3da

Please sign in to comment.
Something went wrong with that request. Please try again.