quick n dirty gallery replacement

mmdc_create_json.py

@@ -89,7 +89,7 @@ def api_category(category, year): #Find all pages incategory and add to allworks
         print '-------------'
         print 
 
-api_category('Graduation work', '2015')
+api_category('Graduation work', '2012')
 json_allworks = open('allworks_mmdc.json', 'w') # save json 
 json.dump(allworks, json_allworks )
 

mmdc_modules.py

@@ -1,3 +1,5 @@
+#! /usr/bin/env python
+# -*- coding: utf-8 -*-
 
 import urllib2, json, pprint, re
 import xml.etree.ElementTree as ET
@@ -15,7 +17,6 @@ def api_request(action, pagename): #get page: content, metadata, images, imageif
 #    pprint.pprint( json_dic )
     page_id =  json_dic.keys()[0]
     page_content = json_dic.get(page_id)
-    print 'API Resquest URL:', url
     return page_content
 
 def api_page(pageid, query):
@@ -66,3 +67,28 @@ def pandoc2html(mw_content):
         p2 = subprocess.Popen(args_pandoc, stdin=p1.stdout, stdout=subprocess.PIPE)
         html = (p2.communicate())[0]
         return html
+
+def img_fullurl(parent):
+    imgs = parent.findall('.//img')
+    print 'len IMG', len(imgs)
+    for img in imgs:
+        src = img.get('src')
+        fullurl =  api_thumb_url(src)
+        print '----- IMG', ET.tostring(img ), src, fullurl
+        if fullurl != None:            
+            img.set('src', fullurl)
+
+        #        fileurl = api_request(src, endpoint)# find url of file
+        
+def replace_youtube(parent, youtube_id): 
+    youtube = parent.findall('.//youtube')[0]
+    youtube.text=""
+    youtube_url = "http://www.youtube.com/embed/{}".format(youtube_id)
+    ET.SubElement(parent, 'iframe', {"width":"560", "height":"315", "frameborder": "0", "allowfullscreen": "allowfullscreen", "src": youtube_url})
+    parent.remove(youtube)
+
+# def replace_gallery(parent):
+#     galleries = parent.findall('.//gallery')
+#     for gallery in galleries:
+#         print 'GALLERY', gallery.text()
+

mmdc_pages.py

@@ -6,58 +6,87 @@
 #####
 import xml.etree.ElementTree as ET
 import html5lib, urllib2, json, pprint, re
-from mmdc_modules import api_thumb_url, pandoc2html
+from mmdc_modules import api_thumb_url, pandoc2html, img_fullurl
 #import mmdc_create_json import api_thumb_url
 json_allworks_file = open('allworks_mmdc.json', 'r') # save json 
 json_allworks = json.loads(json_allworks_file.read())
 pages_path = 'web/work'
 
 #def generate_xml():
-    
+gallery_exp=re.compile('<gallery>.*?</gallery>')
+file_exp=re.compile('File:(.*?)(?=File:|<\/gallery>)')
+img_exp=re.compile('(^.*?\.(gif|jpg|jpeg|png))', re.I)
+
+def replace_gallery(content):
+    # from <gallery>.*</gallery> imgs, return list of img ET elements
+    # replace <gallery>.*</gallery> with ''
+    gallery_imgs = []
+    gallery_found = re.findall(gallery_exp, content)
+    content = re.sub(gallery_exp,  '', content)
+    print 'gallery_found', gallery_found
+    for gallery in gallery_found: # in case there is more than 1 <gallery>
+        print 'GALLERY', gallery
+        allfiles =re.findall(file_exp, gallery)
+        print 'ALLFILES', allfiles
+        for imgfile in allfiles:
+            img = ((re.search(img_exp, imgfile)).group(0))#.decode('utf-8')
+            imgsrc = api_thumb_url(img)
+            img_el = ET.Element('img', attrib={'src': imgsrc})
+            gallery_imgs.append(img_el)
+            print 'gallery img', img, ET.tostring(img_el)
+    return content, gallery_imgs
+        # need to return a list of images that is the gallery
+        # need to replace <gallery>.*</gallery> with ''
     
 def create_workpage( allworks_dict, work_key): # replace text content in dict with html nodes, holding the content    
     for key in allworks_dict.keys():
-        print key
+        if key in ['Description', 'Extra']: 
-        if key in ['Description', 'Extra']: #need conversion to html, dealing:imgs,<gallery>, vimeo/youtube
+            mw_content = allworks_dict[key]
-            allworks_dict[key] = pandoc2html( allworks_dict[key] if key in allworks_dict.keys() else '' ) # convert to HTML
+            if re.search(gallery_exp, mw_content):
-            htmlnode = ET.fromstring(allworks_dict[key]) # make them into node
+                mw_content, gallery_imgs = replace_gallery(mw_content)
+                print gallery_imgs
+                print mw_content.encode('utf-8')            
+
+
+
+
+            allworks_dict[key] = pandoc2html( mw_content if key in allworks_dict.keys() else '' ) # convert to HTML
+ #           print 'allworks_dict[key]', key#, allworks_dict[key]
+            work_htmltree = html5lib.parseFragment(allworks_dict[key], namespaceHTMLElements=False)
+#            replace_gallery(work_htmltree)
+            
+#            print work_htmltree
+#            print ET.tostring(work_htmltree)
+
+            # vimeo/youtube: {{vimeo|44977056}}
+            # External urls: [http://www.scribd.com/doc/105882261/THE-DICTATOR-S-PRACTICAL-INTERNET-GUIDE-TO-POWER-RETENTION scribd]
+            
         elif key in ['Website']:
-            htmlnode = ET.Element('a', attrib={'href': allworks_dict[key], 'id':key})
+            work_htmltree = ET.Element('a', attrib={'href': allworks_dict[key], 'id':key})
-            htmlnode.text = allworks_dict[key]
+            work_htmltree.text = allworks_dict[key]
         elif key in ['Title']:
-            htmlnode = ET.Element('h1', attrib={'id': key})
+            work_htmltree = ET.Element('h1', attrib={'id': key})
-            htmlnode.text
+            work_htmltree.text
         elif key in ['Creator', 'Date', 'Bio']:
-            htmlnode = ET.Element('p', attrib={'id': key})
+            work_htmltree = ET.Element('p', attrib={'id': key})
-            htmlnode.text
+            work_htmltree.text
         elif key in ['Thumbnail_url']:
-            htmlnode = ET.Element('img', attrib={'src': allworks_dict[key], 'id': key})
+            work_htmltree = ET.Element('img', attrib={'src': allworks_dict[key], 'id': key})
-
+            print ET.tostring(work_htmltree)
         else:
-            htmlnode = None
+            work_htmltree = None
             # remove keys with None value?
             
-        print htmlnode
+#        print work_htmltree
-        allworks_dict[key] = htmlnode
+        allworks_dict[key] = work_htmltree
         allworks_dict.pop('Thumbnail', None) #remove thumnail
-    pprint.pprint(allworks_dict)
+#    pprint.pprint(allworks_dict)
-
-            
-
-        #     #p
-        # elif key in ['Thumbnail_url']:
-        #     #<img>
-
 
-#        else:
-#            generate_xml()
-#            work_dict[key] = allworks_dict[key] if key in allworks_dict.keys() else ''
-#        print work_dict
             
     
 for key in json_allworks.keys():
         graduation_work=json_allworks[key]
-        print graduation_work['Creator']
+        print (graduation_work['Creator']).encode('utf-8')
 
 #        pprint.pprint(graduation_work)