From c0a4f1f9937bb98896ce78ddc00ec09c6c8c99d1 Mon Sep 17 00:00:00 2001 From: unknown Date: Tue, 28 Sep 2010 22:38:05 +0200 Subject: [PATCH 3/3] added strip --- imdb/parser/http/personParser.py | 4 +++- 1 files changed, 3 insertions(+), 1 deletions(-) diff --git a/imdb/parser/http/personParser.py b/imdb/parser/http/personParser.py index e30de5d..01885e6 100644 --- a/imdb/parser/http/personParser.py +++ b/imdb/parser/http/personParser.py @@ -102,7 +102,9 @@ class DOMHTMLMaindetailsParser(DOMParserBase): Extractor(label='name', path="//h1[@class='header']", attrs=Attribute(key='name', - path="./text()")), + path="./text()"), + postprocess=lambda x: x.strip() + ), Extractor(label='birth info', path="//div[h5='Date of Birth:']", -- 1.7.0.2.msysgit.0