├── README.md
└── code.js


/README.md:
--------------------------------------------------------------------------------
 1 | ## Google Doc to clean HTML converter ##
 2 | 
 3 |  1. Open your Google Doc and go to Tools menu, select Script Editor. You
 4 |     should see a new window open with a nice code editor. 
 5 |  2. Copy and paste the code from here: [GoogleDocs2Html][1]
 6 |  3. Then from the "Select Editor" menu, choose ConvertGoogleDocToCleanHtml
 7 |  4. Click the play button to run the script. 
 8 |  5. You will get an email containing the HTML output of
 9 |     the Google Doc with inline images.
10 |  6. You can easily forward that email to anyone or copy and paste in a        Wordpress post.
11 |  
12 | 
13 |   [1]: https://raw.githubusercontent.com/oazabir/GoogleDoc2Html/master/code.js
14 | 


--------------------------------------------------------------------------------
/code.js:
--------------------------------------------------------------------------------
  1 | function ConvertGoogleDocToCleanHtml() {
  2 |   var body = DocumentApp.getActiveDocument().getBody();
  3 |   var numChildren = body.getNumChildren();
  4 |   var output = [];
  5 |   var images = [];
  6 |   var listCounters = {};
  7 | 
  8 |   // Walk through all the child elements of the body.
  9 |   for (var i = 0; i < numChildren; i++) {
 10 |     var child = body.getChild(i);
 11 |     output.push(processItem(child, listCounters, images));
 12 |   }
 13 | 
 14 |   var html = output.join('\r');
 15 |   emailHtml(html, images);
 16 |   //createDocumentForHtml(html, images);
 17 | }
 18 | 
 19 | function emailHtml(html, images) {
 20 |   var attachments = [];
 21 |   for (var j=0; j<images.length; j++) {
 22 |     attachments.push( {
 23 |       "fileName": images[j].name,
 24 |       "mimeType": images[j].type,
 25 |       "content": images[j].blob.getBytes() } );
 26 |   }
 27 | 
 28 |   var inlineImages = {};
 29 |   for (var j=0; j<images.length; j++) {
 30 |     inlineImages[[images[j].name]] = images[j].blob;
 31 |   }
 32 | 
 33 |   var name = DocumentApp.getActiveDocument().getName()+".html";
 34 |   attachments.push({"fileName":name, "mimeType": "text/html", "content": html});
 35 |   MailApp.sendEmail({
 36 |      to: Session.getActiveUser().getEmail(),
 37 |      subject: name,
 38 |      htmlBody: html,
 39 |      inlineImages: inlineImages,
 40 |      attachments: attachments
 41 |    });
 42 | }
 43 | 
 44 | function createDocumentForHtml(html, images) {
 45 |   var name = DocumentApp.getActiveDocument().getName()+".html";
 46 |   var newDoc = DocumentApp.create(name);
 47 |   newDoc.getBody().setText(html);
 48 |   for(var j=0; j < images.length; j++)
 49 |     newDoc.getBody().appendImage(images[j].blob);
 50 |   newDoc.saveAndClose();
 51 | }
 52 | 
 53 | function dumpAttributes(atts) {
 54 |   // Log the paragraph attributes.
 55 |   for (var att in atts) {
 56 |     Logger.log(att + ":" + atts[att]);
 57 |   }
 58 | }
 59 | 
 60 | function processItem(item, listCounters, images) {
 61 |   var output = [];
 62 |   var prefix = "", suffix = "";
 63 | 
 64 |   if (item.getType() == DocumentApp.ElementType.PARAGRAPH) {
 65 |     switch (item.getHeading()) {
 66 |         // Add a # for each heading level. No break, so we accumulate the right number.
 67 |       case DocumentApp.ParagraphHeading.HEADING6: 
 68 |         prefix = "<h6>", suffix = "</h6>"; break;
 69 |       case DocumentApp.ParagraphHeading.HEADING5: 
 70 |         prefix = "<h5>", suffix = "</h5>"; break;
 71 |       case DocumentApp.ParagraphHeading.HEADING4:
 72 |         prefix = "<h4>", suffix = "</h4>"; break;
 73 |       case DocumentApp.ParagraphHeading.HEADING3:
 74 |         prefix = "<h3>", suffix = "</h3>"; break;
 75 |       case DocumentApp.ParagraphHeading.HEADING2:
 76 |         prefix = "<h2>", suffix = "</h2>"; break;
 77 |       case DocumentApp.ParagraphHeading.HEADING1:
 78 |         prefix = "<h1>", suffix = "</h1>"; break;
 79 |       default: 
 80 |         prefix = "<p>", suffix = "</p>";
 81 |     }
 82 | 
 83 |     if (item.getNumChildren() == 0)
 84 |       return "";
 85 |   }
 86 |   else if (item.getType() == DocumentApp.ElementType.INLINE_IMAGE)
 87 |   {
 88 |     processImage(item, images, output);
 89 |   }
 90 |   else if (item.getType()===DocumentApp.ElementType.LIST_ITEM) {
 91 |     var listItem = item;
 92 |     var gt = listItem.getGlyphType();
 93 |     var key = listItem.getListId() + '.' + listItem.getNestingLevel();
 94 |     var counter = listCounters[key] || 0;
 95 | 
 96 |     // First list item
 97 |     if ( counter == 0 ) {
 98 |       // Bullet list (<ul>):
 99 |       if (gt === DocumentApp.GlyphType.BULLET
100 |           || gt === DocumentApp.GlyphType.HOLLOW_BULLET
101 |           || gt === DocumentApp.GlyphType.SQUARE_BULLET) {
102 |         prefix = '<ul class="small"><li>', suffix = "</li>";
103 | 
104 |           suffix += "</ul>";
105 |         }
106 |       else {
107 |         // Ordered list (<ol>):
108 |         prefix = "<ol><li>", suffix = "</li>";
109 |       }
110 |     }
111 |     else {
112 |       prefix = "<li>";
113 |       suffix = "</li>";
114 |     }
115 | 
116 |     if (item.isAtDocumentEnd() || (item.getNextSibling() && item.getNextSibling().getType() != DocumentApp.ElementType.LIST_ITEM)) {
117 |       if (gt === DocumentApp.GlyphType.BULLET
118 |           || gt === DocumentApp.GlyphType.HOLLOW_BULLET
119 |           || gt === DocumentApp.GlyphType.SQUARE_BULLET) {
120 |         suffix += "</ul>";
121 |       }
122 |       else {
123 |         // Ordered list (<ol>):
124 |         suffix += "</ol>";
125 |       }
126 | 
127 |     }
128 | 
129 |     counter++;
130 |     listCounters[key] = counter;
131 |   }
132 | 
133 |   output.push(prefix);
134 | 
135 |   if (item.getType() == DocumentApp.ElementType.TEXT) {
136 |     processText(item, output);
137 |   }
138 |   else {
139 | 
140 | 
141 |     if (item.getNumChildren) {
142 |       var numChildren = item.getNumChildren();
143 | 
144 |       // Walk through all the child elements of the doc.
145 |       for (var i = 0; i < numChildren; i++) {
146 |         var child = item.getChild(i);
147 |         output.push(processItem(child, listCounters, images));
148 |       }
149 |     }
150 | 
151 |   }
152 | 
153 |   output.push(suffix);
154 |   return output.join('');
155 | }
156 | 
157 | 
158 | function processText(item, output) {
159 |   var text = item.getText();
160 |   var indices = item.getTextAttributeIndices();
161 | 
162 |   if (indices.length <= 1) {
163 |     // Assuming that a whole para fully italic is a quote
164 |     if(item.isBold()) {
165 |       output.push('<b>' + text + '</b>');
166 |     }
167 |     else if(item.isItalic()) {
168 |       output.push('<blockquote>' + text + '</blockquote>');
169 |     }
170 |     else if (text.trim().indexOf('http://') == 0) {
171 |       output.push('<a href="' + text + '" rel="nofollow">' + text + '</a>');
172 |     }
173 |     else {
174 |       output.push(text);
175 |     }
176 |   }
177 |   else {
178 | 
179 |     for (var i=0; i < indices.length; i ++) {
180 |       var partAtts = item.getAttributes(indices[i]);
181 |       var startPos = indices[i];
182 |       var endPos = i+1 < indices.length ? indices[i+1]: text.length;
183 |       var partText = text.substring(startPos, endPos);
184 |       
185 |       // Logger.log(partAtts);
186 |       // Logger.log(partText);
187 |       // Logger.log(partText.trim().indexOf('http://'));
188 | 
189 |       if (partAtts.ITALIC) {
190 |         output.push('<i>');
191 |       }
192 |       if (partAtts.BOLD) {
193 |         output.push('<b>');
194 |       }
195 |       if (partAtts.UNDERLINE) {
196 |         output.push('<u>');
197 |       }
198 | 
199 |       // If someone has written [xxx] and made this whole text some special font, like superscript
200 |       // then treat it as a reference and make it superscript.
201 |       // Unfortunately in Google Docs, there's no way to detect superscript
202 |       if (partText.indexOf('[')==0 && partText[partText.length-1] == ']') {
203 |         output.push('<sup>' + partText + '</sup>');
204 |       }
205 |       /*else if (partText.trim().indexOf('http://') == 0) {
206 |         output.push('<a href="' + partText + '" rel="nofollow">' + partText + '</a>');
207 |       }*/
208 |       else if (partAtts.LINK_URL) {
209 |         output.push('<a href="' + partAtts.LINK_URL + '" rel="nofollow">' + partText + '</a>');
210 |       }
211 |       else {
212 |         output.push(partText);
213 |       }
214 | 
215 |       if (partAtts.ITALIC) {
216 |         output.push('</i>');
217 |       }
218 |       if (partAtts.BOLD) {
219 |         output.push('</b>');
220 |       }
221 |       if (partAtts.UNDERLINE) {
222 |         output.push('</u>');
223 |       }
224 | 
225 |     }
226 |   }
227 | }
228 | 
229 | 
230 | function processImage(item, images, output)
231 | {
232 |   images = images || [];
233 |   var blob = item.getBlob();
234 |   var contentType = blob.getContentType();
235 |   var extension = "";
236 |   if (/\/png$/.test(contentType)) {
237 |     extension = ".png";
238 |   } else if (/\/gif$/.test(contentType)) {
239 |     extension = ".gif";
240 |   } else if (/\/jpe?g$/.test(contentType)) {
241 |     extension = ".jpg";
242 |   } else {
243 |     throw "Unsupported image type: "+contentType;
244 |   }
245 |   var imagePrefix = "Image_";
246 |   var imageCounter = images.length;
247 |   var name = imagePrefix + imageCounter + extension;
248 |   imageCounter++;
249 |   output.push('<img src="cid:'+name+'" />');
250 |   images.push( {
251 |     "blob": blob,
252 |     "type": contentType,
253 |     "name": name});
254 | }
255 | 


--------------------------------------------------------------------------------