0x2620/scrapeit
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

tighter keyword parsing

Browse source
This commit is contained in:
j 2007-07-12 19:06:12 +00:00
parent ee5864a99d
commit 23e27d1b36
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
scrapeit/imdb.py
View file

@ -320,7 +320,7 @@ class IMDb:
def parseKeywords(self): def parseKeywords(self):
soup = BeautifulSoup(self.getKeywords()) soup = BeautifulSoup(self.getKeywords())
keywords = [] keywords = []
for key in soup('a', {'href': re.compile('/keyword')}): for key in soup('a', {'href': re.compile('^/keyword/')}):
keywords.append(htmldecode(key.string)) keywords.append(htmldecode(key.string))
self.keywords = keywords self.keywords = keywords
return self.keywords return self.keywords