small refactor of image extraction

shaneaevans · shaneaevans · commit a1c3fa5dd827 · 2011-02-15T15:42:10.000-02:00
diff --git a/scrapy/contrib/ibl/extractors.py b/scrapy/contrib/ibl/extractors.py
@@ -132,6 +132,10 @@ def image_url(http://github.com/txt):
         ['http://s7d5.scene7.com/is/image/wasserstrom/165133?wid=227&hei=227&defaultImage=noimage_wasserstrom']
 
     """
+    imgurl = extract_image_url(http://github.com/txt)
+    return [safe_url_string(remove_entities(url(http://github.com/imgurl)))] if imgurl else None
+
+def extract_image_url(http://github.com/txt):
     txt = url(http://github.com/txt)
     imgurl = None
     if txt:
@@ -153,4 +157,4 @@ def image_url(http://github.com/txt):
             imgurl = urlparse.urlunparse(parsed)
         if not imgurl:
             imgurl = txt
-    return [safe_url_string(remove_entities(url(http://github.com/imgurl)))] if imgurl else None
+    return imgurl

-Original file line number
+Diff line change
         ['http://s7d5.scene7.com/is/image/wasserstrom/165133?wid=227&hei=227&defaultImage=noimage_wasserstrom']
     """
 +    imgurl = extract_image_url(txt)
 +    return [safe_url_string(remove_entities(url(imgurl)))] if imgurl else None
++
 +def extract_image_url(txt):
     txt = url(txt)
     imgurl = None
     if txt:
             imgurl = urlparse.urlunparse(parsed)
         if not imgurl:
             imgurl = txt
 -    return [safe_url_string(remove_entities(url(imgurl)))] if imgurl else None
 +    return imgurl