Changeset 225

Timestamp:

05/22/09 11:04:44 (3 years ago)

Author:

david

Message:

handle links, RSS, courselist, amongst other things

Location:

plone-export/trunk

Files:

• plone-static-export.py (modified) (10 diffs)
• static_export.cpy (modified) (2 diffs)

plone-export/trunk/plone-static-export.py

@@ -90 +90 @@
                  'bookmarklets.gif',
                  'bullet.gif',
-                 'courselist',
                  'document_icon.gif',
                  'eduCommonsDivision.gif',
@@ -105 +104 @@
                  'rss_icon.gif',
                  'py.png',
+                 '@@rss_feeds',
                  'robots.txt',
                  'search_icon.gif',
@@ -127 +127 @@
         if file in ['accessibility-info', 'sitemap']:
             target += '.html'
-        if file == 'courselist':
-            target += '.html'
+        elif file == '@@rss_feeds':
+            target = target.replace('@@rss_feeds', 'courselist/@@rss_feeds.html')   
         DownloadResource(source, target)
     
@@ -154 +154 @@
             if not os.path.exists(directory):
                 CreateDirectory(directory)
-            DownloadResource(source, target)
+            DownloadResource(source, target)          
             if 'portal_css' in line:
                 DownloadCSSImages(source, target, css_images)
@@ -328 +328 @@
     return link, target
 
-
-
 def FindFilesToModify():
     ''' Find files to modify them  '''
@@ -350 +348 @@
     for root, dirs, files in os.walk('./'):
         for file in files:
-            
             # Files which are looking for changes
             if file.find('.html') >= 0 or file.find('.htm') >= 0:
@@ -396 +393 @@
     for tag in soup.findAll('base'):
         soup.base.extract()
+        
+
+    for tag in soup.head.findAll('link'):
+        if tag.has_key('rel'):
+            #find objects with RDF link tags, and download the associated RDF document
+            if tag['rel'] == 'alternate':
+                if tag['type'] == 'application/rss+xml':
+                    href = tag['href'].replace('RSS', 'rss')
+                    tag['href'] = href.replace(fqsubdomain, '')
+                elif tag['type'] == 'application/rdf+xml':    
+                    source = tag['href']
+                    rdf_file = tag['href'].replace('/rdf', '.rdf')                  
+                    target = rdf_file.replace(fqsubdomain + '/', '')
+                    tag['href'] = '../%s' % target
+                    DownloadResource(source, target)
+            #generic URL rewriter
+            href = tag['href']
+            href = href.replace(fqsubdomain + '/', rel_path)
+            #handle root url case
+            href = href.replace(fqsubdomain, rel_path)
+            tag['href'] = href
+            
     
     #replace style tags subdomain 
@@ -423 +442 @@
 
  
+    #Rebuild links to zip file download to always point to course, since there is no acquisition
+    for dl in soup.findAll('dl'):
+       if dl.has_key('class'):
+           if dl['class'] == 'portlet portletReuseCourse':
+               path_parts = dl.dd.a['href'].replace(fqsubdomain + '/', '').split('/')
+               zip_path = path_parts[0:2] + path_parts[-1:]
+               zip_path = rel_path + string.join(zip_path, '/')                        
+               dl.dd.a['href'] = zip_path
+ 
+    for div in soup.findAll('div', id='portal-personaltools-wrapper'):
+        div.extract()
+ 
+ 
     for link in soup.findAll('a'):
+    
         if link.has_key('href'):
             href = link['href']
@@ -430 +463 @@
                 if href == 'http://demo.educommons.com':
                     href = '%s/index.html' % href
+                # download rss feeds
+                elif href.endswith('/rss'):
+                    DownloadResource(href, href.replace(fqsubdomain, ''))
+                #replace with static url
+                elif href.endswith('@@rss'):
+                    #rewrite views in rss_feeds.html page, no need to create duplicate copies of RSS feeds
+                    if 'courselist' in href:
+                        href = replace('courselist/', '')
+                    href = href.replace('@@rss', 'rss')
+                #convert spaces to _    
                 elif '%20' in href:
                     href = href.replace('%20','_')
-                # change folder links to folder/index.html if link ends in /folder                 
+                #remove front-page path
+                elif 'front-page' in href:
+                    href = href.replace('front-page/', '')
+                #rewrite links to zip file downloads of courses
                 for folder in folder_list:
                     if folder in href and href.endswith(folder):
@@ -438 +484 @@
                         if debug_mode >= 4:
                             DebugOutput('ModifyForStaticHTML -3', href)
+            #remove odd  courselist/rss on front page
+            elif 'courselist/rss' == href:
+                href = href.replace('courselist/', '')                 
                 
             #remove http://DOMAIN/ and replace w/ rel_path

plone-export/trunk/static_export.cpy

@@ -13 +13 @@
    for content in context.portal_catalog(portal_type='Course', review_state='Published', sort_order = 'Date'):
       objects += [content.getURL(),]      
+    
+   # Add Courselist folder  
+   objects += [context.courselist.absolute_url(),]
 
 else:
@@ -60 +63 @@
       objects[obj_url] = obj_url 
 
+   # Generate list of FSS files
+   for content in context.portal_catalog(portal_type='FSSFile', review_state='Published', sort_order = 'Date'):
+      obj_url = content.getURL()
+      objects[obj_url] = obj_url
+               
+   # Add courselist folder
+   obj_url = content.courselist.absolute_url()
+   tar_url = '%s/index.html' % obj_url
+   objects[obj_url] = tar_url
+
 # return the list of objects
 return objects
-