rewriting all mechanism from scrath - w/out json

mmdc_modules.py

@@ -64,11 +64,59 @@ def write_html_file(html_tree, filename):
     edited.write(html)
     edited.close()
 
+# mw article modules
+
+def parse_work_page(title, content):
+#    content = content.encode('utf-8')
+    if re.match('\{\{\Graduation work', content):
+        work_dict = {}
+        work_dict['Title']=title
+        template, extra = (re.findall('\{\{Graduation work\n(.*?)\}\}(.*)', content, re.DOTALL))[0]
+        # template's key/value pair
+        keyval = re.findall('\|(.*?)\=(.*?\n)', template, re.DOTALL)
+        if extra:
+            extra = ('Extra', extra)
+            keyval.append(extra)
+
+#        checkkeys = [keyval[i] for i in range(len(keyval)) if keyval[i][0] in mainkeys and len(keyval[i][1])>3] #list mainkeys present, w/ values, in tuples [(key, val),(key, val)...]
+ #       if len(checkkeys) == 3 : # checkkeys contains all mainkeys and values 
+            for pair in keyval:
+                key = pair[0]
+                val = pair[1]
+                val = val.replace('\n','')            
+                if 'Creator' in key:
+                    val = val.replace(', ', '')
+                elif 'Thumbnail' in key:
+                    thumburl = api_thumb_url(val)
+                    work_dict['Thumbnail_url']=thumburl
+                    print 'THUMB:', thumburl
+                work_dict[key]=val
+            return work_dict, extra
+
+
+# Alternative to parse_work_page - W/out dictionary        
+def parse_work(title, content):
+    if re.match('\{\{\Graduation work', content):
+        template, extra = (re.findall('\{\{Graduation work\n(.*?)\}\}(.*)', content, re.DOTALL))[0]
+        # template's key/value pair
+        keyval = re.findall('\|(.*?)\=(.*?\n)', template, re.DOTALL)
+        for pair in keyval:
+            key = pair[0]
+            val = pair[1]
+            if 'Description' in key:
+                description = val
+
+        print keyval
+        
+    return extra, description
+
+
+
     
 # Conversion Modules
 def pandoc2html(mw_content):
     if mw_content:
-        mw_content = mw_content.encode('utf-8')
+        mw_content = mw_content#.encode('utf-8')
         # convert from mw to html
         args_echo =shlex.split( ('echo "{}"'.format(mw_content)) )
         args_pandoc = shlex.split( 'pandoc -f mediawiki -t html5' )
@@ -90,7 +138,11 @@ def pandoc(filename, title, creator, date, website, thumbnail, bio, description,
 #    return html
 
 # pandoc either reades input from stdin or through input file
-# pandoc DOES NOT convert variables
+# pandoc DOES NOT convert variables; it has to receive the input from stdin.
+# to create html convert: bio, description, extra, of at time
+# insert them into HTML template by:
+## gerating html in python? and insertion sub elements ?
+## ??
                                
                                #     pandoc = 'pandoc -s -f mediawiki -t html5 \
 # --template template_article.html \

mmdc_pages.py

@@ -183,16 +183,21 @@ for key in json_allworks.keys():
 
     print work_file, website
     # if key in work.keys() else ''
-    pandoc( filename=work_file, \
-            template='web/work-template.html', \
-            title=title, \
-            creator=creator, \
-            date=date, \
-            website=website, \
-            thumbnail=thumbnail, \
-            bio=bio, \
-            description=description, \
-            extra=extra ) # convert to HTML
+
+    if extra:
+        extra_html = pandoc2html(extra)
+        print (extra_html)
+
+    # pandoc( filename=work_file, \
+    #         template='web/work-template.html', \
+    #         title=title, \
+    #         creator=creator, \
+    #         date=date, \
+    #         website=website, \
+    #         thumbnail=thumbnail, \
+    #         bio=bio, \
+    #         description=description, \
+    #         extra=extra ) # convert to HTML
     # print '= = = = = = ='
     # print html_content 
     # print '= = = = = = ='

prototype_page.py

@@ -0,0 +1,31 @@
+#! /usr/bin/env python
+# -*- coding: utf-8 -*-
+
+###########
+# Testing downloading and converting mw page content to html
+###########
+from mmdc_modules import api_request, api_page, api_thumb_url, pandoc2html, parse_work_page, parse_work
+
+template = open("web/page-template.html", "r")
+template =  template.read()
+template =  template.format(title="This is My Title", creator='', date='', website='', thumbnail='', bio='',description='', extra=''  )
+# download
+pageid='15965'
+article = api_page(pageid, 'content')
+#print article
+#print '----------- article -----'
+
+# parsing article
+extra, description = parse_work('Qq', article)
+
+# placing mw content inside dict makes it non convertable. Why?
+#print extra #work_dict['Extra']
+
+html_extra = pandoc2html(extra.encode('utf-8'))
+html_description = pandoc2html(description.encode('utf-8'))
+
+print '----------- html -----'
+print html_description
+#print html_extra
+
+print template

web/page-template.html

@@ -0,0 +1,22 @@
+<!DOCTYPE html>
+<html>
+  <head>
+    <meta charset="UTF-8">
+    <title>{title}</title> <!-- Work title will go to here --> 
+    <link rel="stylesheet" href="css/style.css">
+  </head>
+  <body>
+    <div id="header">
+      <div id="title"><h1>{title}</h1></div>
+      <div id="creator"><h2>{creator}</h2></div>
+      <div id="date">{date}</div>
+      <div id="website"><a href="{website}">{website}</a></div>
+      <div id="thumbnail"><img src="{thumbnail}" class="" alt="" /></div>
+      <div id="bio">{bio}</div>
+    </div>    
+    <div id="body">
+      <div id="description">{description}</div>
+      <div id="extra">{extra}</div>
+    </div>
+  </body>
+</html>