Make it work

DiscordChatExporter.sln

@@ -0,0 +1,22 @@
+
+Microsoft Visual Studio Solution File, Format Version 12.00
+# Visual Studio 15
+VisualStudioVersion = 15.0.26430.13
+MinimumVisualStudioVersion = 10.0.40219.1
+Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "DiscordChatExporter", "DiscordChatExporter\DiscordChatExporter.csproj", "{4BE915D1-129C-49E2-860E-62045ACA5EAD}"
+EndProject
+Global
+	GlobalSection(SolutionConfigurationPlatforms) = preSolution
+		Debug|Any CPU = Debug|Any CPU
+		Release|Any CPU = Release|Any CPU
+	EndGlobalSection
+	GlobalSection(ProjectConfigurationPlatforms) = postSolution
+		{4BE915D1-129C-49E2-860E-62045ACA5EAD}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{4BE915D1-129C-49E2-860E-62045ACA5EAD}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{4BE915D1-129C-49E2-860E-62045ACA5EAD}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{4BE915D1-129C-49E2-860E-62045ACA5EAD}.Release|Any CPU.Build.0 = Release|Any CPU
+	EndGlobalSection
+	GlobalSection(SolutionProperties) = preSolution
+		HideSolutionNode = FALSE
+	EndGlobalSection
+EndGlobal

DiscordChatExporter/DiscordChatExporter.csproj

@@ -0,0 +1,27 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFramework>net45</TargetFramework>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <None Remove="Services\ExportTemplate.html" />
+  </ItemGroup>
+
+  <ItemGroup>
+    <EmbeddedResource Include="Services\ExportTemplate.html" />
+  </ItemGroup>
+
+  <ItemGroup>
+    <PackageReference Include="CommandLineParser" Version="1.9.71" />
+    <PackageReference Include="HtmlAgilityPack" Version="1.5.1" />
+    <PackageReference Include="Newtonsoft.json" Version="10.0.3" />
+    <PackageReference Include="Tyrrrz.Extensions" Version="1.4.0" />
+  </ItemGroup>
+
+  <ItemGroup>
+    <Reference Include="System.Net.Http" />
+  </ItemGroup>
+
+</Project>

DiscordChatExporter/Models/Attachment.cs

@@ -0,0 +1,21 @@
+namespace DiscordChatExporter.Models
+{
+    public class Attachment
+    {
+        public string Id { get; }
+
+        public string Url { get; }
+
+        public string FileName { get; }
+
+        public long ContentLength { get; }
+
+        public Attachment(string id, string url, string fileName, long contentLength)
+        {
+            Id = id;
+            Url = url;
+            FileName = fileName;
+            ContentLength = contentLength;
+        }
+    }
+}

DiscordChatExporter/Models/ChatLog.cs

@@ -0,0 +1,22 @@
+using System.Collections.Generic;
+using System.Linq;
+using Tyrrrz.Extensions;
+
+namespace DiscordChatExporter.Models
+{
+    public class ChatLog
+    {
+        public string ChannelId { get; }
+
+        public IReadOnlyList<User> Participants { get; }
+
+        public IReadOnlyList<Message> Messages { get; }
+
+        public ChatLog(string channelId, IEnumerable<Message> messages)
+        {
+            ChannelId = channelId;
+            Messages = messages.ToArray();
+            Participants = Messages.Select(m => m.Author).Distinct(a => a.Name).ToArray();
+        }
+    }
+}

DiscordChatExporter/Models/Message.cs

@@ -0,0 +1,33 @@
+using System;
+using System.Collections.Generic;
+using System.Linq;
+
+namespace DiscordChatExporter.Models
+{
+    public class Message
+    {
+        public string Id { get; }
+
+        public DateTime TimeStamp { get; }
+
+        public User Author { get; }
+
+        public string Content { get; }
+
+        public IReadOnlyList<Attachment> Attachments { get; }
+
+        public Message(string id, DateTime timeStamp, User author, string content, IEnumerable<Attachment> attachments)
+        {
+            Id = id;
+            TimeStamp = timeStamp;
+            Author = author;
+            Content = content;
+            Attachments = attachments.ToArray();
+        }
+
+        public override string ToString()
+        {
+            return Content;
+        }
+    }
+}

DiscordChatExporter/Models/User.cs

@@ -0,0 +1,29 @@
+using Tyrrrz.Extensions;
+
+namespace DiscordChatExporter.Models
+{
+    public class User
+    {
+        public string Id { get; }
+
+        public string Name { get; }
+
+        public string AvatarHash { get; }
+
+        public string AvatarUrl => AvatarHash.IsNotBlank()
+            ? $"https://cdn.discordapp.com/avatars/{Id}/{AvatarHash}.png?size=256"
+            : "https://discordapp.com/assets/6debd47ed13483642cf09e832ed0bc1b.png";
+
+        public User(string id, string name, string avatarHash)
+        {
+            Id = id;
+            Name = name;
+            AvatarHash = avatarHash;
+        }
+
+        public override string ToString()
+        {
+            return Name;
+        }
+    }
+}

DiscordChatExporter/Options.cs

@@ -0,0 +1,32 @@
+using CommandLine;
+using CommandLine.Text;
+
+namespace DiscordChatExporter
+{
+    public class Options
+    {
+        [Option('t', "token", Required = true, HelpText = "Discord access token")]
+        public string Token { get; set; }
+
+        [Option('c', "channel", Required = true, HelpText = "ID of the text channel to export")]
+        public string ChannelId { get; set; }
+
+        [HelpOption]
+        public string GetUsage()
+        {
+            var help = new HelpText
+            {
+                Heading = new HeadingInfo("DiscordChatExporter"),
+                Copyright = new CopyrightInfo("Alexey 'Tyrrrz' Golub", 2017),
+                AdditionalNewLineAfterOption = true,
+                AddDashesToOption = true
+            };
+            help.AddPreOptionsLine("Usage: DiscordChatExporter.exe " +
+                                   "-t REkOTVqm9RWOTNOLCdiuMpWd.QiglBz.Lub0E0TZ1xX4ZxCtnwtpBhWt3v1 " +
+                                   "-c 459360869055190534");
+            help.AddOptions(this);
+
+            return help;
+        }
+    }
+}

DiscordChatExporter/Program.cs

@@ -0,0 +1,37 @@
+using System;
+using System.Threading.Tasks;
+using DiscordChatExporter.Models;
+using DiscordChatExporter.Services;
+
+namespace DiscordChatExporter
+{
+    public static class Program
+    {
+        private static readonly Options Options = new Options();
+
+        private static readonly DiscordApiService DiscordApiService = new DiscordApiService();
+        private static readonly ExportService ExportService = new ExportService();
+
+        private static async Task MainAsync(string[] args)
+        {
+            // Parse cmd args
+            CommandLine.Parser.Default.ParseArgumentsStrict(args, Options);
+
+            // Get messages
+            Console.WriteLine("Getting messages...");
+            var messages = await DiscordApiService.GetMessagesAsync(Options.Token, Options.ChannelId);
+            var chatLog = new ChatLog(Options.ChannelId, messages);
+
+            // Export
+            Console.WriteLine("Exporting messages...");
+            ExportService.Export($"{Options.ChannelId}.html", chatLog);
+        }
+
+        public static void Main(string[] args)
+        {
+            Console.Title = "Discord Chat Exporter";
+
+            MainAsync(args).GetAwaiter().GetResult();
+        }
+    }
+}

DiscordChatExporter/Services/DiscordApiService.cs

@@ -0,0 +1,94 @@
+using System;
+using System.Collections.Generic;
+using System.Net.Http;
+using System.Threading.Tasks;
+using DiscordChatExporter.Models;
+using Newtonsoft.Json.Linq;
+using Tyrrrz.Extensions;
+
+namespace DiscordChatExporter.Services
+{
+    public class DiscordApiService
+    {
+        private const string ApiRoot = "https://discordapp.com/api";
+        private readonly HttpClient _httpClient = new HttpClient();
+
+        private IEnumerable<Message> ParseMessages(string json)
+        {
+            var messagesJson = JArray.Parse(json);
+            foreach (var messageJson in messagesJson)
+            {
+                // Get basic data
+                string id = messageJson.Value<string>("id");
+                var timeStamp = messageJson.Value<DateTime>("timestamp");
+                string content = messageJson.Value<string>("content");
+
+                // Get author
+                var authorJson = messageJson["author"];
+                string authorId = authorJson.Value<string>("id");
+                string authorName = authorJson.Value<string>("username");
+                string authorAvatarHash = authorJson.Value<string>("avatar");
+
+                // Get attachment
+                var attachmentsJson = messageJson["attachments"];
+                var attachments = new List<Attachment>();
+                foreach (var attachmentJson in attachmentsJson)
+                {
+                    string attachmentId = attachmentJson.Value<string>("id");
+                    string attachmentUrl = attachmentJson.Value<string>("url");
+                    string attachmentFileName = attachmentJson.Value<string>("filename");
+                    long attachmentContentLength = attachmentJson.Value<long>("size");
+
+                    var attachment = new Attachment(attachmentId, attachmentUrl, attachmentFileName, attachmentContentLength);
+                    attachments.Add(attachment);
+                }
+
+                var author = new User(authorId, authorName, authorAvatarHash);
+                var message = new Message(id, timeStamp, author, content, attachments);
+
+                yield return message;
+            }
+        }
+
+        public async Task<IEnumerable<Message>> GetMessagesAsync(string token, string channelId)
+        {
+            var result = new List<Message>();
+
+            // We are going backwards from last message to first
+            // ...collecting everything between them in batches
+            string beforeId = null;
+            while (true)
+            {
+                // Form request url
+                string url = $"{ApiRoot}/channels/{channelId}/messages?token={token}&limit=100";
+                if (beforeId.IsNotBlank())
+                    url += $"&before={beforeId}";
+
+                // Get response
+                string response = await _httpClient.GetStringAsync(url);
+
+                // Parse
+                var messages = ParseMessages(response);
+
+                // Add messages to list
+                string currentMessageId = null;
+                foreach (var message in messages)
+                {
+                    result.Add(message);
+                    currentMessageId = message.Id;
+                }
+
+                // If no messages - break
+                if (currentMessageId == null) break;
+
+                // Otherwise offset the next request
+                beforeId = currentMessageId;
+            }
+
+            // Messages appear newest first, we need to reverse
+            result.Reverse();
+
+            return result;
+        }
+    }
+}

DiscordChatExporter/Services/ExportService.cs

@@ -0,0 +1,180 @@
+using System;
+using System.Collections.Generic;
+using System.Linq;
+using System.Reflection;
+using System.Text.RegularExpressions;
+using DiscordChatExporter.Models;
+using HtmlAgilityPack;
+using Tyrrrz.Extensions;
+
+namespace DiscordChatExporter.Services
+{
+    public class ExportService
+    {
+        private class MessageGroup
+        {
+            public User Author { get; }
+
+            public DateTime FirstTimeStamp { get; }
+
+            public IReadOnlyList<Message> Messages { get; }
+
+            public MessageGroup(User author, DateTime firstTimeStamp, IEnumerable<Message> messages)
+            {
+                Author = author;
+                FirstTimeStamp = firstTimeStamp;
+                Messages = messages.ToArray();
+            }
+        }
+
+        private HtmlDocument GetTemplate()
+        {
+            const string templateName = "DiscordChatExporter.Services.ExportTemplate.html";
+            var assembly = Assembly.GetExecutingAssembly();
+            using (var stream = assembly.GetManifestResourceStream(templateName))
+            {
+                var doc = new HtmlDocument();
+                doc.Load(stream);
+                return doc;
+            }
+        }
+
+        private IEnumerable<MessageGroup> GroupMessages(IEnumerable<Message> messages)
+        {
+            var result = new List<MessageGroup>();
+
+            // Group adjacent messages by timestamp and author
+            var buffer = new List<Message>();
+            foreach (var message in messages)
+            {
+                var bufferFirst = buffer.FirstOrDefault();
+
+                // Group break condition
+                bool breakCondition =
+                    bufferFirst != null &&
+                    (
+                        message.Author.Id != bufferFirst.Author.Id ||
+                        (message.TimeStamp - bufferFirst.TimeStamp).TotalHours > 1 ||
+                        message.TimeStamp.Hour != bufferFirst.TimeStamp.Hour
+                    );
+
+                // If condition is true - flush buffer
+                if (breakCondition)
+                {
+                    var group = new MessageGroup(bufferFirst.Author, bufferFirst.TimeStamp, buffer);
+                    result.Add(group);
+                    buffer.Clear();
+                }
+
+                // Add message to buffer
+                buffer.Add(message);
+            }
+
+            // Add what's remaining in buffer
+            if (buffer.Any())
+            {
+                var bufferFirst = buffer.First();
+                var group = new MessageGroup(bufferFirst.Author, bufferFirst.TimeStamp, buffer);
+                result.Add(group);
+            }
+
+            return result;
+        }
+
+        private string FormatMessageContent(string content)
+        {
+            // Encode HTML
+            content = HtmlDocument.HtmlEncode(content);
+
+            // Links from URLs
+            content = Regex.Replace(content, "((^|\\s)(https?|ftp)://[^\\s/$.?#].[^\\s]*($|\\s))",
+                "<a href=\"$1\">$1</a>");
+
+            // Preformatted multiline
+            content = Regex.Replace(content, "```([^`]*?)```", e => "<pre>" + e.Groups[1].Value + "</pre>");
+
+            // Preformatted
+            content = Regex.Replace(content, "`([^`]*?)`", e => "<pre>" + e.Groups[1].Value + "</pre>");
+
+            // Bold
+            content = Regex.Replace(content, "\\*\\*([^\\*]*?)\\*\\*", "<b>$1</b>");
+
+            // Italic
+            content = Regex.Replace(content, "\\*([^\\*]*?)\\*", "<i>$1</i>");
+
+            // Underline
+            content = Regex.Replace(content, "__([^_]*?)__", "<u>$1</u>");
+
+            // Strike through
+            content = Regex.Replace(content, "~~([^~]*?)~~", "<s>$1</s>");
+
+            // New lines
+            content = content.Replace("\n", "</br>");
+
+            return content;
+        }
+
+        public void Export(string filePath, ChatLog chatLog)
+        {
+            var doc = GetTemplate();
+
+            // Info
+            var infoHtml = doc.GetElementbyId("info");
+            infoHtml.AppendChild(HtmlNode.CreateNode($"<div>Channel ID: <b>{chatLog.ChannelId}</b></div>"));
+            string participants = HtmlDocument.HtmlEncode(chatLog.Participants.Select(u => u.Name).JoinToString(", "));
+            infoHtml.AppendChild(HtmlNode.CreateNode($"<div>Participants: <b>{participants}</b></div>"));
+            infoHtml.AppendChild(HtmlNode.CreateNode($"<div>Messages: <b>{chatLog.Messages.Count:N0}</b></div>"));
+
+            // Messages
+            var logHtml = doc.GetElementbyId("log");
+            var messageGroups = GroupMessages(chatLog.Messages);
+            foreach (var messageGroup in messageGroups)
+            {
+                // Container
+                var messageHtml = logHtml.AppendChild(HtmlNode.CreateNode("<div class=\"msg\"></div>"));
+
+                // Avatar
+                messageHtml.AppendChild(HtmlNode.CreateNode("<img class=\"msg-avatar\" " +
+                                                            $"src=\"{messageGroup.Author.AvatarUrl}\"></img>"));
+
+                // Body
+                var messageBodyHtml = messageHtml.AppendChild(HtmlNode.CreateNode("<div class=\"msg-body\"></div>"));
+
+                // Author
+                string authorName = HtmlDocument.HtmlEncode(messageGroup.Author.Name);
+                messageBodyHtml.AppendChild(HtmlNode.CreateNode($"<span class=\"msg-user\">{authorName}</span>"));
+
+                // Date
+                string timeStamp = HtmlDocument.HtmlEncode(messageGroup.FirstTimeStamp.ToString("g"));
+                messageBodyHtml.AppendChild(HtmlNode.CreateNode($"<span class=\"msg-date\">{timeStamp}</span>"));
+
+                // Separate messages
+                foreach (var message in messageGroup.Messages)
+                {
+                    // Content
+                    if (message.Content.IsNotBlank())
+                    {
+                        string content = FormatMessageContent(message.Content);
+                        messageBodyHtml.AppendChild(HtmlNode.CreateNode($"<div class=\"msg-content\">{content}</div>"));
+                    }
+
+                    // Attachments
+                    if (message.Attachments.Any())
+                    {
+                        // Attachments
+                        foreach (var attachment in message.Attachments)
+                        {
+                            messageBodyHtml.AppendChild(
+                                HtmlNode.CreateNode("<div class=\"msg-attachment\">" +
+                                                    $"<a href=\"{attachment.Url}\">" +
+                                                    $"<img class=\"msg-attachment\" src=\"{attachment.Url}\" />" +
+                                                    "</a></div>"));
+                        }
+                    }
+                }
+            }
+
+            doc.Save(filePath);
+        }
+    }
+}

DiscordChatExporter/Services/ExportTemplate.html

@@ -0,0 +1,84 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <title>Discord Chat Log</title>
+    <meta charset="utf-8"/>
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+
+    <style>
+        body {
+            background-color: #ffffff;
+            font-size: 15px;
+            font-family: Whitney, Helvetica Neue, Helvetica, Arial, sans-serif;
+        }
+        a {
+            text-decoration: none;
+            color: #37bcf7;
+        }
+        a:hover {
+            text-decoration: underline;
+        }
+        pre {
+            margin: 0;
+            padding-left: 2px;
+            padding-right: 2px;
+            background-color: #f9f9f9;
+            font-family: Consolas, Courier New, Courier, Monospace;
+            display: inline;
+        }
+        div#info {
+            width: 100%;
+            margin-bottom: 20px;
+            color: #939799;
+        }
+        div#log {
+            width: 100%;            
+        }
+        div.msg {
+            display: flex;
+            margin-left: 10px;
+            margin-right: 10px;
+            padding-top: 15px;
+            padding-bottom: 15px;
+            border-top: 1px solid #eceeef;
+        }
+        img.msg-avatar {
+            flex: 0;
+            width: 40px;
+            height: 40px;
+            border-radius: 50%;
+        }
+        div.msg-body {
+            flex: 1;
+            margin-left: 15px;
+        }
+        span.msg-user {            
+            color: #2f3136;
+            font-size: 1.15em;
+        }
+        span.msg-date {
+            margin-left: 5px;
+            color: #b7bcbf;
+            font-size: 0.8em;
+            font-weight: 200;
+        }
+        div.msg-content {
+            padding-top: 5px;
+            color: #939799;
+        }
+        div.msg-attachment {
+            margin-top: 5px;
+            margin-bottom: 5px;
+        }
+        img.msg-attachment {
+            max-width: 50%;
+            max-height: 500px;
+        }
+    </style>
+</head>
+
+<body>
+    <div id="info" />
+    <div id="log" />
+</body>
+</html>