├── .gitattributes ├── .gitignore ├── DouyinCap.sln ├── DouyinCap ├── DouyinCap.csproj ├── Program.cs ├── Properties │ └── launchSettings.json └── Utils │ ├── ElementHandleExtensions.cs │ └── QueryHelper.cs └── readme.md /.gitattributes: -------------------------------------------------------------------------------- 1 | ############################################################################### 2 | # Set default behavior to automatically normalize line endings. 3 | ############################################################################### 4 | * text=auto 5 | 6 | ############################################################################### 7 | # Set default behavior for command prompt diff. 8 | # 9 | # This is need for earlier builds of msysgit that does not have it on by 10 | # default for csharp files. 11 | # Note: This is only used by command line 12 | ############################################################################### 13 | #*.cs diff=csharp 14 | 15 | ############################################################################### 16 | # Set the merge driver for project and solution files 17 | # 18 | # Merging from the command prompt will add diff markers to the files if there 19 | # are conflicts (Merging from VS is not affected by the settings below, in VS 20 | # the diff markers are never inserted). Diff markers may cause the following 21 | # file extensions to fail to load in VS. An alternative would be to treat 22 | # these files as binary and thus will always conflict and require user 23 | # intervention with every merge. To do so, just uncomment the entries below 24 | ############################################################################### 25 | #*.sln merge=binary 26 | #*.csproj merge=binary 27 | #*.vbproj merge=binary 28 | #*.vcxproj merge=binary 29 | #*.vcproj merge=binary 30 | #*.dbproj merge=binary 31 | #*.fsproj merge=binary 32 | #*.lsproj merge=binary 33 | #*.wixproj merge=binary 34 | #*.modelproj merge=binary 35 | #*.sqlproj merge=binary 36 | #*.wwaproj merge=binary 37 | 38 | ############################################################################### 39 | # behavior for image files 40 | # 41 | # image files are treated as binary by default. 42 | ############################################################################### 43 | #*.jpg binary 44 | #*.png binary 45 | #*.gif binary 46 | 47 | ############################################################################### 48 | # diff behavior for common document formats 49 | # 50 | # Convert binary document formats to text before diffing them. This feature 51 | # is only available from the command line. Turn it on by uncommenting the 52 | # entries below. 53 | ############################################################################### 54 | #*.doc diff=astextplain 55 | #*.DOC diff=astextplain 56 | #*.docx diff=astextplain 57 | #*.DOCX diff=astextplain 58 | #*.dot diff=astextplain 59 | #*.DOT diff=astextplain 60 | #*.pdf diff=astextplain 61 | #*.PDF diff=astextplain 62 | #*.rtf diff=astextplain 63 | #*.RTF diff=astextplain 64 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | ## Ignore Visual Studio temporary files, build results, and 2 | ## files generated by popular Visual Studio add-ons. 3 | ## 4 | ## Get latest from https://github.com/github/gitignore/blob/master/VisualStudio.gitignore 5 | 6 | # User-specific files 7 | *.rsuser 8 | *.suo 9 | *.user 10 | *.userosscache 11 | *.sln.docstates 12 | 13 | # User-specific files (MonoDevelop/Xamarin Studio) 14 | *.userprefs 15 | 16 | # Mono auto generated files 17 | mono_crash.* 18 | 19 | # Build results 20 | [Dd]ebug/ 21 | [Dd]ebugPublic/ 22 | [Rr]elease/ 23 | [Rr]eleases/ 24 | x64/ 25 | x86/ 26 | [Ww][Ii][Nn]32/ 27 | [Aa][Rr][Mm]/ 28 | [Aa][Rr][Mm]64/ 29 | bld/ 30 | [Bb]in/ 31 | [Oo]bj/ 32 | [Oo]ut/ 33 | [Ll]og/ 34 | [Ll]ogs/ 35 | 36 | # Visual Studio 2015/2017 cache/options directory 37 | .vs/ 38 | # Uncomment if you have tasks that create the project's static files in wwwroot 39 | #wwwroot/ 40 | 41 | # Visual Studio 2017 auto generated files 42 | Generated\ Files/ 43 | 44 | # MSTest test Results 45 | [Tt]est[Rr]esult*/ 46 | [Bb]uild[Ll]og.* 47 | 48 | # NUnit 49 | *.VisualState.xml 50 | TestResult.xml 51 | nunit-*.xml 52 | 53 | # Build Results of an ATL Project 54 | [Dd]ebugPS/ 55 | [Rr]eleasePS/ 56 | dlldata.c 57 | 58 | # Benchmark Results 59 | BenchmarkDotNet.Artifacts/ 60 | 61 | # .NET Core 62 | project.lock.json 63 | project.fragment.lock.json 64 | artifacts/ 65 | 66 | # ASP.NET Scaffolding 67 | ScaffoldingReadMe.txt 68 | 69 | # StyleCop 70 | StyleCopReport.xml 71 | 72 | # Files built by Visual Studio 73 | *_i.c 74 | *_p.c 75 | *_h.h 76 | *.ilk 77 | *.meta 78 | *.obj 79 | *.iobj 80 | *.pch 81 | *.pdb 82 | *.ipdb 83 | *.pgc 84 | *.pgd 85 | *.rsp 86 | *.sbr 87 | *.tlb 88 | *.tli 89 | *.tlh 90 | *.tmp 91 | *.tmp_proj 92 | *_wpftmp.csproj 93 | *.log 94 | *.vspscc 95 | *.vssscc 96 | .builds 97 | *.pidb 98 | *.svclog 99 | *.scc 100 | 101 | # Chutzpah Test files 102 | _Chutzpah* 103 | 104 | # Visual C++ cache files 105 | ipch/ 106 | *.aps 107 | *.ncb 108 | *.opendb 109 | *.opensdf 110 | *.sdf 111 | *.cachefile 112 | *.VC.db 113 | *.VC.VC.opendb 114 | 115 | # Visual Studio profiler 116 | *.psess 117 | *.vsp 118 | *.vspx 119 | *.sap 120 | 121 | # Visual Studio Trace Files 122 | *.e2e 123 | 124 | # TFS 2012 Local Workspace 125 | $tf/ 126 | 127 | # Guidance Automation Toolkit 128 | *.gpState 129 | 130 | # ReSharper is a .NET coding add-in 131 | _ReSharper*/ 132 | *.[Rr]e[Ss]harper 133 | *.DotSettings.user 134 | 135 | # TeamCity is a build add-in 136 | _TeamCity* 137 | 138 | # DotCover is a Code Coverage Tool 139 | *.dotCover 140 | 141 | # AxoCover is a Code Coverage Tool 142 | .axoCover/* 143 | !.axoCover/settings.json 144 | 145 | # Coverlet is a free, cross platform Code Coverage Tool 146 | coverage*.json 147 | coverage*.xml 148 | coverage*.info 149 | 150 | # Visual Studio code coverage results 151 | *.coverage 152 | *.coveragexml 153 | 154 | # NCrunch 155 | _NCrunch_* 156 | .*crunch*.local.xml 157 | nCrunchTemp_* 158 | 159 | # MightyMoose 160 | *.mm.* 161 | AutoTest.Net/ 162 | 163 | # Web workbench (sass) 164 | .sass-cache/ 165 | 166 | # Installshield output folder 167 | [Ee]xpress/ 168 | 169 | # DocProject is a documentation generator add-in 170 | DocProject/buildhelp/ 171 | DocProject/Help/*.HxT 172 | DocProject/Help/*.HxC 173 | DocProject/Help/*.hhc 174 | DocProject/Help/*.hhk 175 | DocProject/Help/*.hhp 176 | DocProject/Help/Html2 177 | DocProject/Help/html 178 | 179 | # Click-Once directory 180 | publish/ 181 | 182 | # Publish Web Output 183 | *.[Pp]ublish.xml 184 | *.azurePubxml 185 | # Note: Comment the next line if you want to checkin your web deploy settings, 186 | # but database connection strings (with potential passwords) will be unencrypted 187 | *.pubxml 188 | *.publishproj 189 | 190 | # Microsoft Azure Web App publish settings. Comment the next line if you want to 191 | # checkin your Azure Web App publish settings, but sensitive information contained 192 | # in these scripts will be unencrypted 193 | PublishScripts/ 194 | 195 | # NuGet Packages 196 | *.nupkg 197 | # NuGet Symbol Packages 198 | *.snupkg 199 | # The packages folder can be ignored because of Package Restore 200 | **/[Pp]ackages/* 201 | # except build/, which is used as an MSBuild target. 202 | !**/[Pp]ackages/build/ 203 | # Uncomment if necessary however generally it will be regenerated when needed 204 | #!**/[Pp]ackages/repositories.config 205 | # NuGet v3's project.json files produces more ignorable files 206 | *.nuget.props 207 | *.nuget.targets 208 | 209 | # Microsoft Azure Build Output 210 | csx/ 211 | *.build.csdef 212 | 213 | # Microsoft Azure Emulator 214 | ecf/ 215 | rcf/ 216 | 217 | # Windows Store app package directories and files 218 | AppPackages/ 219 | BundleArtifacts/ 220 | Package.StoreAssociation.xml 221 | _pkginfo.txt 222 | *.appx 223 | *.appxbundle 224 | *.appxupload 225 | 226 | # Visual Studio cache files 227 | # files ending in .cache can be ignored 228 | *.[Cc]ache 229 | # but keep track of directories ending in .cache 230 | !?*.[Cc]ache/ 231 | 232 | # Others 233 | ClientBin/ 234 | ~$* 235 | *~ 236 | *.dbmdl 237 | *.dbproj.schemaview 238 | *.jfm 239 | *.pfx 240 | *.publishsettings 241 | orleans.codegen.cs 242 | 243 | # Including strong name files can present a security risk 244 | # (https://github.com/github/gitignore/pull/2483#issue-259490424) 245 | #*.snk 246 | 247 | # Since there are multiple workflows, uncomment next line to ignore bower_components 248 | # (https://github.com/github/gitignore/pull/1529#issuecomment-104372622) 249 | #bower_components/ 250 | 251 | # RIA/Silverlight projects 252 | Generated_Code/ 253 | 254 | # Backup & report files from converting an old project file 255 | # to a newer Visual Studio version. Backup files are not needed, 256 | # because we have git ;-) 257 | _UpgradeReport_Files/ 258 | Backup*/ 259 | UpgradeLog*.XML 260 | UpgradeLog*.htm 261 | ServiceFabricBackup/ 262 | *.rptproj.bak 263 | 264 | # SQL Server files 265 | *.mdf 266 | *.ldf 267 | *.ndf 268 | 269 | # Business Intelligence projects 270 | *.rdl.data 271 | *.bim.layout 272 | *.bim_*.settings 273 | *.rptproj.rsuser 274 | *- [Bb]ackup.rdl 275 | *- [Bb]ackup ([0-9]).rdl 276 | *- [Bb]ackup ([0-9][0-9]).rdl 277 | 278 | # Microsoft Fakes 279 | FakesAssemblies/ 280 | 281 | # GhostDoc plugin setting file 282 | *.GhostDoc.xml 283 | 284 | # Node.js Tools for Visual Studio 285 | .ntvs_analysis.dat 286 | node_modules/ 287 | 288 | # Visual Studio 6 build log 289 | *.plg 290 | 291 | # Visual Studio 6 workspace options file 292 | *.opt 293 | 294 | # Visual Studio 6 auto-generated workspace file (contains which files were open etc.) 295 | *.vbw 296 | 297 | # Visual Studio LightSwitch build output 298 | **/*.HTMLClient/GeneratedArtifacts 299 | **/*.DesktopClient/GeneratedArtifacts 300 | **/*.DesktopClient/ModelManifest.xml 301 | **/*.Server/GeneratedArtifacts 302 | **/*.Server/ModelManifest.xml 303 | _Pvt_Extensions 304 | 305 | # Paket dependency manager 306 | .paket/paket.exe 307 | paket-files/ 308 | 309 | # FAKE - F# Make 310 | .fake/ 311 | 312 | # CodeRush personal settings 313 | .cr/personal 314 | 315 | # Python Tools for Visual Studio (PTVS) 316 | __pycache__/ 317 | *.pyc 318 | 319 | # Cake - Uncomment if you are using it 320 | # tools/** 321 | # !tools/packages.config 322 | 323 | # Tabs Studio 324 | *.tss 325 | 326 | # Telerik's JustMock configuration file 327 | *.jmconfig 328 | 329 | # BizTalk build output 330 | *.btp.cs 331 | *.btm.cs 332 | *.odx.cs 333 | *.xsd.cs 334 | 335 | # OpenCover UI analysis results 336 | OpenCover/ 337 | 338 | # Azure Stream Analytics local run output 339 | ASALocalRun/ 340 | 341 | # MSBuild Binary and Structured Log 342 | *.binlog 343 | 344 | # NVidia Nsight GPU debugger configuration file 345 | *.nvuser 346 | 347 | # MFractors (Xamarin productivity tool) working folder 348 | .mfractor/ 349 | 350 | # Local History for Visual Studio 351 | .localhistory/ 352 | 353 | # BeatPulse healthcheck temp database 354 | healthchecksdb 355 | 356 | # Backup folder for Package Reference Convert tool in Visual Studio 2017 357 | MigrationBackup/ 358 | 359 | # Ionide (cross platform F# VS Code tools) working folder 360 | .ionide/ 361 | 362 | # Fody - auto-generated XML schema 363 | FodyWeavers.xsd -------------------------------------------------------------------------------- /DouyinCap.sln: -------------------------------------------------------------------------------- 1 |  2 | Microsoft Visual Studio Solution File, Format Version 12.00 3 | # Visual Studio Version 17 4 | VisualStudioVersion = 17.2.32427.441 5 | MinimumVisualStudioVersion = 10.0.40219.1 6 | Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "DouyinCap", "DouyinCap\DouyinCap.csproj", "{B5CBB812-B4C8-4BA7-AFDE-C054A68F01B7}" 7 | EndProject 8 | Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "Solution Items", "Solution Items", "{BAFB70D9-402C-492B-B6C4-93A705269B9C}" 9 | ProjectSection(SolutionItems) = preProject 10 | readme.md = readme.md 11 | EndProjectSection 12 | EndProject 13 | Global 14 | GlobalSection(SolutionConfigurationPlatforms) = preSolution 15 | Debug|Any CPU = Debug|Any CPU 16 | Release|Any CPU = Release|Any CPU 17 | EndGlobalSection 18 | GlobalSection(ProjectConfigurationPlatforms) = postSolution 19 | {B5CBB812-B4C8-4BA7-AFDE-C054A68F01B7}.Debug|Any CPU.ActiveCfg = Debug|Any CPU 20 | {B5CBB812-B4C8-4BA7-AFDE-C054A68F01B7}.Debug|Any CPU.Build.0 = Debug|Any CPU 21 | {B5CBB812-B4C8-4BA7-AFDE-C054A68F01B7}.Release|Any CPU.ActiveCfg = Release|Any CPU 22 | {B5CBB812-B4C8-4BA7-AFDE-C054A68F01B7}.Release|Any CPU.Build.0 = Release|Any CPU 23 | EndGlobalSection 24 | GlobalSection(SolutionProperties) = preSolution 25 | HideSolutionNode = FALSE 26 | EndGlobalSection 27 | GlobalSection(ExtensibilityGlobals) = postSolution 28 | SolutionGuid = {9FC9EB31-C92F-42B8-ADFB-E823B67702CE} 29 | EndGlobalSection 30 | EndGlobal 31 | -------------------------------------------------------------------------------- /DouyinCap/DouyinCap.csproj: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | Exe 5 | net6.0 6 | enable 7 | enable 8 | SlimeNull 9 | Null.$(AssemblyName) 10 | 抖音直播间弹幕抓取工具 11 | 12 | 13 | 14 | 15 | 16 | 17 | 18 | 19 | 20 | -------------------------------------------------------------------------------- /DouyinCap/Program.cs: -------------------------------------------------------------------------------- 1 | using CommandLine; 2 | using PuppeteerSharp; 3 | using RestSharp; 4 | 5 | namespace DouyinCap 6 | { 7 | class Program 8 | { 9 | static Browser? browser; 10 | static void Main(string[] args) 11 | { 12 | Parser.Default 13 | .ParseArguments(args) 14 | .WithParsed(MainAction); 15 | } 16 | 17 | static void AppExit(object? sender, EventArgs e) 18 | { 19 | browser?.Dispose(); 20 | } 21 | 22 | static void ConsoleAppExit(object? sender, ConsoleCancelEventArgs e) 23 | { 24 | browser?.Dispose(); 25 | e.Cancel = true; 26 | } 27 | static void Fetcher_DownloadProgressChanged(object sender, System.Net.DownloadProgressChangedEventArgs e) 28 | { 29 | Console.Write($"\rBrowser downloading... [{e.ProgressPercentage}%] {new string('.', DateTime.Now.Second % 4).PadRight(4)}"); 30 | } 31 | 32 | static void MainAction(StartupOptions options) 33 | { 34 | async Task MainActionAsync() 35 | { 36 | using var fetcher = new BrowserFetcher(); 37 | 38 | if (!fetcher.LocalRevisions().Contains(BrowserFetcher.DefaultChromiumRevision)) 39 | { 40 | fetcher.DownloadProgressChanged += Fetcher_DownloadProgressChanged; 41 | await fetcher.DownloadAsync(BrowserFetcher.DefaultChromiumRevision); 42 | Console.WriteLine(); // add a new line 43 | } 44 | 45 | Console.WriteLine($"Starting browser..."); 46 | using Browser browser = await Puppeteer.LaunchAsync(new LaunchOptions() 47 | { 48 | Headless = !options.ShowBrowser, 49 | }); 50 | 51 | Program.browser = browser; // 存储到静态变量 52 | 53 | AppDomain.CurrentDomain.ProcessExit += AppExit; // 自动关闭 54 | Console.CancelKeyPress += ConsoleAppExit; 55 | 56 | RestClient? client = null; 57 | long roomId = options.RoomId; 58 | string liveHomeAddr = $"https://live.douyin.com/"; 59 | string liveRoomAddr = $"https://live.douyin.com/{roomId}"; 60 | 61 | if (options.PostAddress != null) 62 | client = new RestClient(options.PostAddress); 63 | 64 | Console.WriteLine($"Loading page..."); 65 | using Page page = (await browser.PagesAsync())[0]; 66 | 67 | await page.GoToAsync(liveHomeAddr); 68 | await page.GoToAsync(liveRoomAddr); 69 | string? lastDataId = null; 70 | 71 | while (true) 72 | { 73 | string query = QueryHelper.AllChatMessagesAfter(lastDataId); 74 | ElementHandle[]? items = await page.QuerySelectorAllAsync(query); 75 | 76 | if (items.Length == 0) 77 | { 78 | string msgQuery = QueryHelper.AllChatMessages(); 79 | ElementHandle[]? msgs = await page.QuerySelectorAllAsync(msgQuery); 80 | 81 | if (msgs.Length == 0) 82 | lastDataId = null; 83 | 84 | continue; 85 | } 86 | 87 | foreach (var item in items) 88 | { 89 | var nameNode = await item.QuerySelectorAsync(".tfObciRM"); 90 | var valueNode = await item.QuerySelectorAsync(".Wz8LGswb"); 91 | 92 | if (nameNode != null && valueNode != null) 93 | { 94 | string name = await nameNode.GetInnerTextAsync(); 95 | string value = await valueNode.GetInnerTextAsync(); 96 | 97 | name = name.TrimEnd(':', '：'); 98 | 99 | Console.WriteLine($"{name}: {value}"); 100 | 101 | if (client != null) 102 | { 103 | var request = new RestRequest() 104 | .AddJsonBody(new 105 | { 106 | Name = name, 107 | Value = value, 108 | }); 109 | await client.PostAsync(request); 110 | } 111 | } 112 | } 113 | 114 | if (items.Length > 0) 115 | lastDataId = await items[^1].GetAttributeAsync("data-id"); 116 | } 117 | } 118 | 119 | try 120 | { 121 | MainActionAsync().Wait(); 122 | } 123 | catch { } 124 | } 125 | 126 | class StartupOptions 127 | { 128 | [Option("show-browser", Default = false, HelpText = "Show browser window.")] 129 | public bool ShowBrowser { get; set; } 130 | 131 | 132 | [Option("post-addr", Default = null, HelpText = "Specify a http server to post chat message data.")] 133 | public string? PostAddress { get; set; } 134 | 135 | 136 | [Value(0, MetaName = "room-id", HelpText = "Live room Id", Required = true)] 137 | public long RoomId { get; set; } 138 | } 139 | } 140 | } -------------------------------------------------------------------------------- /DouyinCap/Properties/launchSettings.json: -------------------------------------------------------------------------------- 1 | { 2 | "profiles": { 3 | "DouyinCap": { 4 | "commandName": "Project", 5 | "commandLineArgs": "--show-browser 912794613665" 6 | } 7 | } 8 | } -------------------------------------------------------------------------------- /DouyinCap/Utils/ElementHandleExtensions.cs: -------------------------------------------------------------------------------- 1 | using PuppeteerSharp; 2 | 3 | static class ElementHandleExtensions 4 | { 5 | public static Task GetAttributeAsync(this ElementHandle element, string attributeName) 6 | { 7 | return element.EvaluateFunctionAsync($"(item)=>item.getAttribute('{attributeName}')"); 8 | } 9 | 10 | public static async Task GetOuterHtmlAsync(this ElementHandle element) 11 | { 12 | var outerHtmlHandle = await element.GetPropertyAsync("outerHTML"); 13 | return await outerHtmlHandle.JsonValueAsync(); 14 | } 15 | 16 | public static async Task GetInnerTextAsync(this ElementHandle element) 17 | { 18 | var outerHtmlHandle = await element.GetPropertyAsync("innerText"); 19 | return await outerHtmlHandle.JsonValueAsync(); 20 | } 21 | } -------------------------------------------------------------------------------- /DouyinCap/Utils/QueryHelper.cs: -------------------------------------------------------------------------------- 1 |  2 | //Console.WriteLine(await page.Frames[page.Frames.Length - 1].GetContentAsync()); 3 | //Console.ReadLine(); 4 | 5 | static class QueryHelper 6 | { 7 | public static string AllChatMessages() 8 | { 9 | return ".webcast-chatroom___messages .webcast-chatroom___items > div > .webcast-chatroom___item.webcast-chatroom___enter-done"; 10 | } 11 | 12 | public static string ChatMessage(string? dataId) 13 | { 14 | return $".webcast-chatroom___messages .webcast-chatroom___items > div > .webcast-chatroom___item.webcast-chatroom___enter-done[data-id=\"{dataId}\"]"; 15 | } 16 | 17 | public static string AllChatMessagesAfter(string? dataId) 18 | { 19 | if (dataId == null) 20 | return AllChatMessages(); 21 | 22 | return $".webcast-chatroom___messages .webcast-chatroom___items > div > .webcast-chatroom___item.webcast-chatroom___enter-done[data-id=\"{dataId}\"] ~ .webcast-chatroom___item.webcast-chatroom___enter-done"; 23 | } 24 | } -------------------------------------------------------------------------------- /readme.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SlimeNull/DouyinCap/7b9ac2576abdcc1134161a5078ae63260d265f82/readme.md --------------------------------------------------------------------------------