ignore digits
This commit is contained in:
parent
233d1c94bf
commit
737634e740
1 changed files with 2 additions and 0 deletions
|
@ -44,6 +44,8 @@ class FileScanner(HTMLParser):
|
|||
score = 10
|
||||
if word in EXCLUDED_WORDS:
|
||||
continue
|
||||
if word.isdigit():
|
||||
continue
|
||||
if word in title_words:
|
||||
score *= 4
|
||||
word_length = len(word)
|
||||
|
|
Loading…
Reference in a new issue