Archives/breadability
2
0
Fork 0
mirror of https://github.com/bookieio/breadability synced 2024-11-16 12:13:11 +00:00
Code Issues Projects Releases Wiki Activity

Refactored computing of link density

Browse Source
This commit is contained in:
Mišo Belica 2013-03-08 23:23:30 +01:00
parent 3f71e1b7d4
commit baaefeda3c
1 changed files with 7 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
breadability/scoring.py
View File

@ -52,20 +52,17 @@ def generate_hash_id(node):
def get_link_density(node, node_text=None):
"""Generate a value for the number of links in the node.
"""
Generates a value for the number of links in the node.
:param node: pared elementree node
:param node_text: if we already have the text_content() make this easier
on us.
:param node_text: if we already have the text_content() make
this easier on us.
:returns float:
"""
link_length = sum([len(a.text_content()) or 0
for a in node.findall(".//a")])
if node_text:
text_length = len(node_text)
else:
text_length = len(node.text_content())
link_length = sum(len(a.text_content()) or 0 for a in node.findall(".//a"))
text_length = len(node_text if node_text else node.text_content())
return float(link_length) / max(text_length, 1)