From 74f81eb97f7116db184bc6749999c6fb2d61b4e1 Mon Sep 17 00:00:00 2001 From: Kartik Prabhu Date: Tue, 4 Mar 2014 19:40:15 -0600 Subject: [PATCH] add absolute url maker url property now normalises to a given base url. referring to #12 --- mf2py/parse_property.py | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/mf2py/parse_property.py b/mf2py/parse_property.py index 5870723..79bacdd 100644 --- a/mf2py/parse_property.py +++ b/mf2py/parse_property.py @@ -1,5 +1,6 @@ from bs4 import Tag from dom_helpers import get_attr +from urlparse import urljoin ## functions to parse the propertis of elements def text(el): @@ -20,19 +21,19 @@ def text(el): # strip here? return el.get_text() -def url(el): +def url(el, base_url=''): ## do the normalise absolute url thing prop_value = get_attr(el, "href", check_name=("a","area")) if prop_value is not None: - return prop_value + return urljoin(base_url, prop_value) prop_value = get_attr(el, "src", check_name="img") if prop_value is not None: - return prop_value + return urljoin(base_url, prop_value) prop_value = get_attr(el, "data", check_name="object") if prop_value is not None: - return prop_value + return urljoin(base_url, prop_value) # add value-class-pattern