updated regexs for av material-using mw widgets

mmdc_modules.py

@@ -153,13 +153,18 @@ def replace_gallery(content):
     content = re.sub(gallery_exp, '\g<1>', content) #remove gallery wrapper
     return content
 
-video_exp=re.compile('\{\{(.*?)\|(.*?)\}\}')
-vimeo_exp=re.compile('\{\{vimeo\|(.*?)\}\}')
-youtube_exp=re.compile('\{\{youtube\|(.*?)\}\}')
+video_exp=re.compile('{\{\#widget\:Html5media.*url\=\<a.*\>(.*?)\<\/a\>.*?\}\}')
+vimeo_exp=re.compile('\{\{\#widget\:Vimeo\|id\=(.*?)\}\}')
+youtube_exp=re.compile('{\{\#widget\:YouTube\|id\=(.*?)\}\}')
 
 def replace_video(content):
+    print '*** VIDEO ***'
     content = re.sub(vimeo_exp,"<iframe src='https://player.vimeo.com/video/\g<1>' width='600px' height='450px'> </iframe>", content)
     content = re.sub(youtube_exp, "<iframe src='https://www.youtube.com/embed/\g<1>' width='600px' height='450px'> </iframe>", content)
+    content = re.sub(video_exp, "<video controls='controls' src='\g<1>' ></video>", content)
+
+    
+    
     return content
 
 img_exp=re.compile('^.*?\.(?:jpg|jpeg|JPG|JPEG|png|gif)')

mmdc_wiki2web.py

@@ -2,8 +2,8 @@
 # -*- coding: utf-8 -*-
 
 import xml.etree.ElementTree as ET
-import html5lib, urllib, pprint
-from mmdc_modules import pandoc2html, parse_work, write_html_file, mw_cats, mw_page_imgsurl, mw_img_url, mw_page_text, mwsite, mw_page_cats, mw_page, remove_cats, find_authors, replace_video, replace_img_a_tag, index_addwork, years
+import html5lib, urllib, pprint, re
+from mmdc_modules import pandoc2html, parse_work, write_html_file, mw_cats, mw_page_imgsurl, mw_img_url, mw_page_text, mwsite, mw_page_cats, mw_page, remove_cats, find_authors, replace_video, replace_img_a_tag, index_addwork, years, vimeo_exp
 from argparse import ArgumentParser
 from random import shuffle
 ###### REQUIRES #####
@@ -37,6 +37,10 @@ print 'args', args
 ######
 # DEFS:  create_pages create_index
 ######
+
+test_exp=re.compile('\{\{\#widget\:Vimeo\|id\=(.*?)\}\}')
+
+
 def create_pages(memberpages, mode):
     indexdict = {} #parent dict: contains articledict instances
     for member in memberpages:
@@ -45,17 +49,29 @@ def create_pages(memberpages, mode):
         articledict = parse_work(site, member, page_text) # create dictionary
         # Title, Creator, Date, Website, Thumbnail, Bio, Description, Extra
         if len(articledict['Creator'])>0 and len(articledict['Title'])>0  and len(articledict['Thumbnail'])>0:
+
             for key in articledict.keys():
+                print key
+
                 if key in ['Extra', 'Description', 'Bio']:
+                    print '3 keys'
                     articledict[key] =  pandoc2html(articledict[key])
-                elif key in ['Creator']:
-                     articledict[key] =  articledict[key].replace(',','' )
-                elif key in ['Content']:
-                     articledict[key] = remove_cats(articledict['Content'])
-                     articledict[key] = replace_video(articledict['Content'])
+                elif key is 'Creator':
+                   print 'creator'
+                   articledict[key] =  articledict[key].replace(',','' )
+
+                if key is 'Extra':
+                    print 'extra', type( articledict['Extra'])
+                    articledict[key] = remove_cats(articledict['Extra'])
+                    articledict[key] = replace_video(articledict['Extra'])  
+#                    found = re.findall(vimeo_exp, articledict['Extra'])
+#                    print 'FOUND:', found
+                     
+
+            pprint.pprint( articledict)
           
             articledict['Imgs'] = mw_page_imgsurl(site, page, articledict['Thumbnail'] )
-            #pprint.pprint( articledict)
+            
         year = articledict['Date']
         page_template = open("./work-{}-template.html".format(year), "r") # a template for each year            
         page_tree = html5lib.parse(page_template, namespaceHTMLElements=False)
@@ -174,7 +190,7 @@ for key in indexdict.keys(): # populate indexdict_byyear with works
     indexdict_byyear[ int(indexdict[key]['Date'])][key] = indexdict[key]
 
 #print '\n\n******* indexdict_byyear ***********\n\n'
-pprint.pprint( indexdict_byyear )    
+#pprint.pprint( indexdict_byyear )    
 
 for year in indexdict_byyear.keys(): # create index page for each year ie 2016.html
     print '\n***** ', year, ' *****\n'