Image Caption Bot: Skype workarounds for authentication and parsing urls

CSharp/intelligence-ImageCaption/Controllers/MessagesController.cs

@@ -2,9 +2,12 @@
 {
     using System;
     using System.Diagnostics;
+    using System.IO;
     using System.Linq;
     using System.Net;
     using System.Net.Http;
+    using System.Net.Http.Headers;
+    using System.Text.RegularExpressions;
     using System.Threading.Tasks;
     using System.Web.Http;
     using Microsoft.Bot.Connector;
@@ -28,7 +31,7 @@ public async Task<HttpResponseMessage> Post([FromBody]Activity activity)
 
                 try
                 {
-                    message = await this.GetCaptionAsync(activity);
+                    message = await this.GetCaptionAsync(activity, connector);
                 }
                 catch (ArgumentException e)
                 {
@@ -61,29 +64,88 @@ public async Task<HttpResponseMessage> Post([FromBody]Activity activity)
         /// and calling the appropriate caption service method.
         /// </summary>
         /// <param name="activity">The activity.</param>
+        /// <param name="connector">The connector.</param>
         /// <returns>The caption if found</returns>
         /// <exception cref="ArgumentException">The activity doesn't contain a valid image attachment or an image URL.</exception>
-        private async Task<string> GetCaptionAsync(Activity activity)
+        private async Task<string> GetCaptionAsync(Activity activity, ConnectorClient connector)
         {
-
             var imageAttachment = activity.Attachments?.FirstOrDefault(a => a.ContentType.Contains("image"));
             if (imageAttachment != null)
             {
-                var req = WebRequest.Create(imageAttachment.ContentUrl);
-
-                using (var stream = req.GetResponse().GetResponseStream())
+                using (var stream = await GetImageStream(connector, imageAttachment))
                 {
                     return await this.captionService.GetCaptionAsync(stream);
                 }
             }
-            else if (Uri.IsWellFormedUriString(activity.Text, UriKind.Absolute))
+
+            string url;
+            if (TryParseAnchorTag(activity.Text, out url))
+            {
+                return await this.captionService.GetCaptionAsync(url);
+            }
+
+            if (Uri.IsWellFormedUriString(activity.Text, UriKind.Absolute))
             {
                 return await this.captionService.GetCaptionAsync(activity.Text);
             }
 
             // If we reach here then the activity is neither an image attachment nor an image URL.
             throw new ArgumentException("The activity doesn't contain a valid image attachment or an image URL.");
         }
+
+        private static async Task<Stream> GetImageStream(ConnectorClient connector, Attachment imageAttachment)
+        {
+            using (var httpClient = new HttpClient())
+            {
+                // The Skype attachment URLs are secured by JwtToken,
+                // you should set the JwtToken of your bot as the authorization header for the GET request your bot initiates to fetch the image.
+                // https://github.com/Microsoft/BotBuilder/issues/662
+                var uri = new Uri(imageAttachment.ContentUrl);
+                if (uri.Host.EndsWith("skype.com") && uri.Scheme == "https")
+                {
+                    httpClient.DefaultRequestHeaders.Authorization = new AuthenticationHeaderValue("Bearer", await GetTokenAsync(connector));
+                    httpClient.DefaultRequestHeaders.Accept.Add(new MediaTypeWithQualityHeaderValue("application/octet-stream"));
+                }
+                else
+                {
+                    httpClient.DefaultRequestHeaders.Accept.Add(new MediaTypeWithQualityHeaderValue(imageAttachment.ContentType));
+                }
+
+                return await httpClient.GetStreamAsync(uri);
+            }
+        }
+
+        /// <summary>
+        /// Gets the href value in an anchor element.
+        /// </summary>
+        ///  Skype transforms raw urls to html. Here we extract the href value from the url
+        /// <param name="text">Anchor tag html.</param>
+        /// <param name="url">Url if valid anchor tag, null otherwise</param>
+        /// <returns>True if valid anchor element</returns>
+        private static bool TryParseAnchorTag(string text, out string url)
+        {
+            var regex = new Regex("^<a href=\"(?<href>[^\"]*)\">[^<]*</a>$", RegexOptions.IgnoreCase);
+            url = regex.Matches(text).OfType<Match>().Select(m => m.Groups["href"].Value).FirstOrDefault();
+            return url != null;
+        }
+
+
+        /// <summary>
+        /// Gets the JwT token of the bot. 
+        /// </summary>
+        /// <param name="connector"></param>
+        /// <returns>JwT token of the bot</returns>
+        private static async Task<string> GetTokenAsync(ConnectorClient connector)
+        {
+            var credentials = connector.Credentials as MicrosoftAppCredentials;
+            if (credentials != null)
+            {
+                return await credentials.GetTokenAsync();
+            }
+
+            return null;
+        }
+
         /// <summary>
         /// Handles the system activity.
         /// </summary>

Node/intelligence-ImageCaption/app.js

@@ -9,6 +9,7 @@ const builder = require('botbuilder'),
     captionService = require('./caption-service'),
     needle = require("needle"),
     restify = require('restify'),
+    url = require('url');
     validUrl = require('valid-url');
 
 //=========================================================
@@ -17,7 +18,7 @@ const builder = require('botbuilder'),
 
 // Setup Restify Server
 const server = restify.createServer();
-server.listen(process.env.port || process.env.PORT || 3978, () => {
+server.listen(process.env.port || process.env.PORT || 3979, () => {
     console.log('%s listening to %s', server.name, server.url);
 });
 
@@ -57,18 +58,17 @@ bot.on('conversationUpdate', message => {
 // Gets the caption by checking the type of the image (stream vs URL) and calling the appropriate caption service method.
 bot.dialog('/', session => {
     if (hasImageAttachment(session)) {
-        var stream = needle.get(session.message.attachments[0].contentUrl);        
+        var stream = getImageStreamFromUrl(session.message.attachments[0]);
         captionService
             .getCaptionFromStream(stream)
             .then(caption => handleSuccessResponse(session, caption))
             .catch(error => handleErrorResponse(session, error));
     }
-    else if (validUrl.isUri(session.message.text)) {
+    else if(imageUrl = (parseAnchorTag(session.message.text) || (validUrl.isUri(session.message.text)? session.message.text : null))) {
         captionService
-            .getCaptionFromUrl(session.message.text)
+            .getCaptionFromUrl(imageUrl)
             .then(caption => handleSuccessResponse(session, caption))
             .catch(error => handleErrorResponse(session, error));
-
     }
     else {
         session.send("Did you upload an image? I'm more of a visual person. Try sending me an image or an image URL");
@@ -82,6 +82,46 @@ const hasImageAttachment = session => {
     return ((session.message.attachments.length > 0) && (session.message.attachments[0].contentType.indexOf("image") !== -1));
 }
 
+const getImageStreamFromUrl = attachment => {
+    var headers = {};
+    if (isSkypeAttachment(attachment)) {
+        // The Skype attachment URLs are secured by JwtToken,
+        // you should set the JwtToken of your bot as the authorization header for the GET request your bot initiates to fetch the image.
+        // https://github.com/Microsoft/BotBuilder/issues/662
+        connector.getAccessToken((error, token) => {
+            var tok = token;
+            headers['Authorization'] = 'Bearer ' + token;
+            headers['Content-Type'] = 'application/octet-stream';
+
+            return needle.get(imageUrl, { headers: headers });
+        });
+    }
+
+    headers['Content-Type'] = attachment.contentType;
+    return needle.get(attachment.contentUrl, { headers: headers });
+}
+
+const isSkypeAttachment = attachment => {
+    if (url.parse(attachment.contentUrl).hostname.substr(-"skype.com".length) == "skype.com") {
+        return true;
+    }
+
+    return false;
+}
+
+/**
+ * Gets the href value in an anchor element.
+ * Skype transforms raw urls to html. Here we extract the href value from the url
+ */
+const parseAnchorTag = input => {
+    var match = input.match("^<a href=\"([^\"]*)\">[^<]*</a>$");
+    if(match && match[1]) {
+        return match[1];
+    }
+
+    return null;
+}
+
 //=========================================================
 // Response Handling
 //=========================================================

Node/intelligence-ImageCaption/package.json

@@ -13,6 +13,7 @@
     "needle": "^1.1.2",
     "request": "^2.75.0",
     "restify": "^4.1.1",
+    "url": "^0.11.0",
     "valid-url": "^1.0.9"
   }
 }