@zetagoaurum-dev/straw 1.1.1 → 1.2.1

package/CHANGELOG.md

@@ -2,6 +2,13 @@
 
 All notable changes to this project will be documented in this file.
 
+## [1.2.1] "Hotfix" - 2026-02-27
+- **Fix:** Removed accidentally tracked `ytInitialData_dump.json` and local `test_*.js` scripts from the previous NPM deployment bundle to ensure zero-bloat runtime.
+
+## [1.2.0] "Deep Metadata & Formats Engine" - 2026-02-27
+- **Feat:** Integrated extracting `subscribers`, `likes`, and `comments` directly from YouTube's `ytInitialData` payload without external parsing overhead.
+- **Feat:** Segregated `formats` array into three exact categorical bins: `video` (combined), `videoOnly`, and `audio` (audio-only), ensuring zero-ambiguity when downloading specific streams.
+
 ## [1.1.1] "Performance Patch" - 2026-02-27
 - **Perf:** Re-engineered the YouTube scraper in Node.js and Python to use the `IOS` InnerTube API directly, injecting localized `visitorData` tokens to seamlessly bypass bot checks and cipher encryption. Video format lists are returned instantaneously for optimal downloading infrastructure.
 - **Fix:** Fixed HTML parser blocking on high-volume deployed servers by upgrading to the direct `POST /youtubei/v1/player` endpoints.

package/dist/index.d.mts

@@ -51,11 +51,18 @@ interface YouTubeFormats {
 interface YouTubeResult {
     title: string;
     author: string;
+    subscribers: string;
     description: string;
     views: string;
+    likes: string;
+    comments: string;
     durationSeconds: string;
     thumbnail: string;
-    formats: YouTubeFormats[];
+    formats: {
+        video: YouTubeFormats[];
+        videoOnly: YouTubeFormats[];
+        audio: YouTubeFormats[];
+    };
 }
 declare class YouTubeScraper {
     private client;

package/dist/index.d.ts

@@ -51,11 +51,18 @@ interface YouTubeFormats {
 interface YouTubeResult {
     title: string;
     author: string;
+    subscribers: string;
     description: string;
     views: string;
+    likes: string;
+    comments: string;
     durationSeconds: string;
     thumbnail: string;
-    formats: YouTubeFormats[];
+    formats: {
+        video: YouTubeFormats[];
+        videoOnly: YouTubeFormats[];
+        audio: YouTubeFormats[];
+    };
 }
 declare class YouTubeScraper {
     private client;

package/dist/index.js

@@ -191,12 +191,20 @@ var YouTubeScraper = class {
     }
     const videoId = videoIdMatch[1];
     const html = await this.client.getText(url, {
-      headers: { "Cookie": "CONSENT=YES+cb.20230501-14-p0.en+FX+430" }
+      headers: { "Cookie": "CONSENT=YES+cb.20230501-14-p0.en+FX+430", "Accept-Language": "en-US,en;q=0.9" }
     });
     const regex = /ytInitialPlayerResponse\s*=\s*({.*?});(?:var|<\/script>)/;
     const match = html.match(regex);
     let visitorData = "";
     let details = {};
+    let initialData = {};
+    const dataMatch = html.match(/var ytInitialData\s*=\s*({.*?});(?:<\/script>)/);
+    if (dataMatch && dataMatch[1]) {
+      try {
+        initialData = JSON.parse(dataMatch[1]);
+      } catch (e) {
+      }
+    }
     if (match && match[1]) {
       const data = JSON.parse(match[1]);
       details = data?.videoDetails || {};
@@ -232,6 +240,7 @@ var YouTubeScraper = class {
       body: JSON.stringify(payload)
     });
     const apiData = await res.json();
+    console.log("Playability Status:", apiData?.playabilityStatus?.status, "StreamingData keys:", Object.keys(apiData?.streamingData || {}));
     if (!details.title) {
       details = apiData?.videoDetails || {};
     }
@@ -239,12 +248,31 @@ var YouTubeScraper = class {
     if (!details) {
       throw new Error("Video details not found inside player response.");
     }
-    const formats = [];
+    let subscribers = "";
+    let likes = "";
+    let comments = "";
+    try {
+      const secInfo = initialData?.contents?.twoColumnWatchNextResults?.results?.results?.contents?.find((c) => c.videoSecondaryInfoRenderer)?.videoSecondaryInfoRenderer;
+      if (secInfo?.owner?.videoOwnerRenderer?.subscriberCountText?.simpleText) {
+        subscribers = secInfo.owner.videoOwnerRenderer.subscriberCountText.simpleText;
+      }
+      const factoids = initialData?.engagementPanels?.find((p) => p.engagementPanelSectionListRenderer?.targetId === "engagement-panel-structured-description")?.engagementPanelSectionListRenderer?.content?.structuredDescriptionContentRenderer?.items?.find((i) => i.videoDescriptionHeaderRenderer)?.videoDescriptionHeaderRenderer?.factoid || [];
+      const likesFactoid = factoids.find((f) => f.factoidRenderer?.accessibilityText?.toLowerCase().includes("like"));
+      if (likesFactoid) likes = likesFactoid.factoidRenderer.accessibilityText;
+      const commentsPanel = initialData?.engagementPanels?.find((p) => p.engagementPanelSectionListRenderer?.panelIdentifier === "engagement-panel-comments-section");
+      if (commentsPanel) {
+        comments = commentsPanel.engagementPanelSectionListRenderer.header.engagementPanelTitleHeaderRenderer.contextualInfo?.runs?.[0]?.text || "";
+      }
+    } catch (e) {
+    }
+    const video = [];
+    const videoOnly = [];
+    const audio = [];
     const rawFormats = [...streamingData?.formats || [], ...streamingData?.adaptiveFormats || []];
     for (const format of rawFormats) {
       if (format.url) {
         const mimeType = format.mimeType || "";
-        formats.push({
+        const formatObj = {
           url: format.url,
           mimeType,
           width: format.width,
@@ -253,19 +281,27 @@ var YouTubeScraper = class {
           bitrate: format.bitrate,
           hasAudio: mimeType.includes("audio/"),
           hasVideo: mimeType.includes("video/")
-        });
-      } else if (format.signatureCipher) {
-        continue;
+        };
+        if (formatObj.hasVideo && formatObj.hasAudio) video.push(formatObj);
+        else if (formatObj.hasVideo) videoOnly.push(formatObj);
+        else if (formatObj.hasAudio) audio.push(formatObj);
       }
     }
     return {
       title: details.title || "",
       author: details.author || "",
+      subscribers,
       description: details.shortDescription || "",
       views: details.viewCount || "0",
+      likes,
+      comments,
       durationSeconds: details.lengthSeconds || "0",
       thumbnail: details.thumbnail?.thumbnails?.[details.thumbnail.thumbnails.length - 1]?.url || "",
-      formats
+      formats: {
+        video,
+        videoOnly,
+        audio
+      }
     };
   }
 };

package/dist/index.mjs

@@ -151,12 +151,20 @@ var YouTubeScraper = class {
     }
     const videoId = videoIdMatch[1];
     const html = await this.client.getText(url, {
-      headers: { "Cookie": "CONSENT=YES+cb.20230501-14-p0.en+FX+430" }
+      headers: { "Cookie": "CONSENT=YES+cb.20230501-14-p0.en+FX+430", "Accept-Language": "en-US,en;q=0.9" }
     });
     const regex = /ytInitialPlayerResponse\s*=\s*({.*?});(?:var|<\/script>)/;
     const match = html.match(regex);
     let visitorData = "";
     let details = {};
+    let initialData = {};
+    const dataMatch = html.match(/var ytInitialData\s*=\s*({.*?});(?:<\/script>)/);
+    if (dataMatch && dataMatch[1]) {
+      try {
+        initialData = JSON.parse(dataMatch[1]);
+      } catch (e) {
+      }
+    }
     if (match && match[1]) {
       const data = JSON.parse(match[1]);
       details = data?.videoDetails || {};
@@ -192,6 +200,7 @@ var YouTubeScraper = class {
       body: JSON.stringify(payload)
     });
     const apiData = await res.json();
+    console.log("Playability Status:", apiData?.playabilityStatus?.status, "StreamingData keys:", Object.keys(apiData?.streamingData || {}));
     if (!details.title) {
       details = apiData?.videoDetails || {};
     }
@@ -199,12 +208,31 @@ var YouTubeScraper = class {
     if (!details) {
       throw new Error("Video details not found inside player response.");
     }
-    const formats = [];
+    let subscribers = "";
+    let likes = "";
+    let comments = "";
+    try {
+      const secInfo = initialData?.contents?.twoColumnWatchNextResults?.results?.results?.contents?.find((c) => c.videoSecondaryInfoRenderer)?.videoSecondaryInfoRenderer;
+      if (secInfo?.owner?.videoOwnerRenderer?.subscriberCountText?.simpleText) {
+        subscribers = secInfo.owner.videoOwnerRenderer.subscriberCountText.simpleText;
+      }
+      const factoids = initialData?.engagementPanels?.find((p) => p.engagementPanelSectionListRenderer?.targetId === "engagement-panel-structured-description")?.engagementPanelSectionListRenderer?.content?.structuredDescriptionContentRenderer?.items?.find((i) => i.videoDescriptionHeaderRenderer)?.videoDescriptionHeaderRenderer?.factoid || [];
+      const likesFactoid = factoids.find((f) => f.factoidRenderer?.accessibilityText?.toLowerCase().includes("like"));
+      if (likesFactoid) likes = likesFactoid.factoidRenderer.accessibilityText;
+      const commentsPanel = initialData?.engagementPanels?.find((p) => p.engagementPanelSectionListRenderer?.panelIdentifier === "engagement-panel-comments-section");
+      if (commentsPanel) {
+        comments = commentsPanel.engagementPanelSectionListRenderer.header.engagementPanelTitleHeaderRenderer.contextualInfo?.runs?.[0]?.text || "";
+      }
+    } catch (e) {
+    }
+    const video = [];
+    const videoOnly = [];
+    const audio = [];
     const rawFormats = [...streamingData?.formats || [], ...streamingData?.adaptiveFormats || []];
     for (const format of rawFormats) {
       if (format.url) {
         const mimeType = format.mimeType || "";
-        formats.push({
+        const formatObj = {
           url: format.url,
           mimeType,
           width: format.width,
@@ -213,19 +241,27 @@ var YouTubeScraper = class {
           bitrate: format.bitrate,
           hasAudio: mimeType.includes("audio/"),
           hasVideo: mimeType.includes("video/")
-        });
-      } else if (format.signatureCipher) {
-        continue;
+        };
+        if (formatObj.hasVideo && formatObj.hasAudio) video.push(formatObj);
+        else if (formatObj.hasVideo) videoOnly.push(formatObj);
+        else if (formatObj.hasAudio) audio.push(formatObj);
       }
     }
     return {
       title: details.title || "",
       author: details.author || "",
+      subscribers,
       description: details.shortDescription || "",
       views: details.viewCount || "0",
+      likes,
+      comments,
       durationSeconds: details.lengthSeconds || "0",
       thumbnail: details.thumbnail?.thumbnails?.[details.thumbnail.thumbnails.length - 1]?.url || "",
-      formats
+      formats: {
+        video,
+        videoOnly,
+        audio
+      }
     };
   }
 };

package/package.json

@@ -1,44 +1,44 @@
-{
-  "name": "@zetagoaurum-dev/straw",
-  "version": "1.1.1",
-  "description": "Enterprise-grade unified JS/TS and Python scraping library for Web, YouTube, and Media (Images, Audio, Video, Documents)",
-  "main": "dist/index.js",
-  "module": "dist/index.mjs",
-  "types": "dist/index.d.ts",
-  "exports": {
-    ".": {
-      "require": "./dist/index.js",
-      "import": "./dist/index.mjs",
-      "types": "./dist/index.d.ts"
-    }
-  },
-  "scripts": {
-    "build": "tsup src/index.ts --format cjs,esm --dts --clean",
-    "dev": "tsup src/index.ts --format cjs,esm --dts --watch",
-    "test": "tsx tests/test.ts"
-  },
-  "keywords": [
-    "scraping",
-    "scraper",
-    "youtube-scraper",
-    "media-extractor",
-    "anti-cors"
-  ],
-  "author": "ZetaGo-Aurum",
-  "license": "MIT",
-  "repository": {
-    "type": "git",
-    "url": "https://github.com/ZetaGo-Aurum/straw.git"
-  },
-  "devDependencies": {
-    "@types/node": "^25.3.2",
-    "ts-node": "^10.9.2",
-    "tsup": "^8.5.1",
-    "tsx": "^4.21.0",
-    "typescript": "^5.9.3"
-  },
-  "dependencies": {
-    "cheerio": "^1.2.0",
-    "undici": "^7.22.0"
-  }
-}
+{
+  "name": "@zetagoaurum-dev/straw",
+  "version": "1.2.1",
+  "description": "Enterprise-grade unified JS/TS and Python scraping library for Web, YouTube, and Media (Images, Audio, Video, Documents)",
+  "main": "dist/index.js",
+  "module": "dist/index.mjs",
+  "types": "dist/index.d.ts",
+  "exports": {
+    ".": {
+      "require": "./dist/index.js",
+      "import": "./dist/index.mjs",
+      "types": "./dist/index.d.ts"
+    }
+  },
+  "scripts": {
+    "build": "tsup src/index.ts --format cjs,esm --dts --clean",
+    "dev": "tsup src/index.ts --format cjs,esm --dts --watch",
+    "test": "tsx tests/test.ts"
+  },
+  "keywords": [
+    "scraping",
+    "scraper",
+    "youtube-scraper",
+    "media-extractor",
+    "anti-cors"
+  ],
+  "author": "ZetaGo-Aurum",
+  "license": "MIT",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/ZetaGo-Aurum/straw.git"
+  },
+  "devDependencies": {
+    "@types/node": "^25.3.2",
+    "ts-node": "^10.9.2",
+    "tsup": "^8.5.1",
+    "tsx": "^4.21.0",
+    "typescript": "^5.9.3"
+  },
+  "dependencies": {
+    "cheerio": "^1.2.0",
+    "undici": "^7.22.0"
+  }
+}

package/release.bat

@@ -1,4 +1,4 @@
 git add .
-git commit -m "v1.1.1 Performance Patch (InnerTube API Bypass)"
+git commit -m "v1.2.0 Deep Metadata & Formats Engine"
 git push origin master -f
 npm publish

package/src/scrapers/youtube.ts

@@ -14,11 +14,18 @@ export interface YouTubeFormats {
 export interface YouTubeResult {
     title: string;
     author: string;
+    subscribers: string;
     description: string;
     views: string;
+    likes: string;
+    comments: string;
     durationSeconds: string;
     thumbnail: string;
-    formats: YouTubeFormats[];
+    formats: {
+        video: YouTubeFormats[];
+        videoOnly: YouTubeFormats[];
+        audio: YouTubeFormats[];
+    };
 }
 
 export class YouTubeScraper {
@@ -40,7 +47,7 @@ export class YouTubeScraper {
         const videoId = videoIdMatch[1];
 
         const html = await this.client.getText(url, {
-            headers: { 'Cookie': 'CONSENT=YES+cb.20230501-14-p0.en+FX+430' }
+            headers: { 'Cookie': 'CONSENT=YES+cb.20230501-14-p0.en+FX+430', 'Accept-Language': 'en-US,en;q=0.9' }
         });
         
         const regex = /ytInitialPlayerResponse\s*=\s*({.*?});(?:var|<\/script>)/;
@@ -48,6 +55,12 @@ export class YouTubeScraper {
         let visitorData = '';
         let details: any = {};
         
+        let initialData: any = {};
+        const dataMatch = html.match(/var ytInitialData\s*=\s*({.*?});(?:<\/script>)/);
+        if (dataMatch && dataMatch[1]) {
+            try { initialData = JSON.parse(dataMatch[1]); } catch(e) {}
+        }
+        
         if (match && match[1]) {
             const data = JSON.parse(match[1]);
             details = data?.videoDetails || {};
@@ -96,13 +109,37 @@ export class YouTubeScraper {
             throw new Error('Video details not found inside player response.');
         }
 
-        const formats: YouTubeFormats[] = [];
+        let subscribers = '';
+        let likes = '';
+        let comments = '';
+
+        try {
+            const secInfo = initialData?.contents?.twoColumnWatchNextResults?.results?.results?.contents?.find((c: any) => c.videoSecondaryInfoRenderer)?.videoSecondaryInfoRenderer;
+            if (secInfo?.owner?.videoOwnerRenderer?.subscriberCountText?.simpleText) {
+                subscribers = secInfo.owner.videoOwnerRenderer.subscriberCountText.simpleText;
+            }
+            
+            const factoids = initialData?.engagementPanels?.find((p: any) => p.engagementPanelSectionListRenderer?.targetId === 'engagement-panel-structured-description')
+                ?.engagementPanelSectionListRenderer?.content?.structuredDescriptionContentRenderer?.items?.find((i: any) => i.videoDescriptionHeaderRenderer)?.videoDescriptionHeaderRenderer?.factoid || [];
+            const likesFactoid = factoids.find((f: any) => f.factoidRenderer?.accessibilityText?.toLowerCase().includes('like'));
+            if (likesFactoid) likes = likesFactoid.factoidRenderer.accessibilityText;
+            
+            const commentsPanel = initialData?.engagementPanels?.find((p: any) => p.engagementPanelSectionListRenderer?.panelIdentifier === 'engagement-panel-comments-section');
+            if (commentsPanel) {
+                comments = commentsPanel.engagementPanelSectionListRenderer.header.engagementPanelTitleHeaderRenderer.contextualInfo?.runs?.[0]?.text || '';
+            }
+        } catch (e) {}
+
+        const video: YouTubeFormats[] = [];
+        const videoOnly: YouTubeFormats[] = [];
+        const audio: YouTubeFormats[] = [];
+
         const rawFormats = [...(streamingData?.formats || []), ...(streamingData?.adaptiveFormats || [])];
         
         for (const format of rawFormats) {
             if (format.url) {
                 const mimeType = format.mimeType || '';
-                formats.push({
+                const formatObj = {
                     url: format.url,
                     mimeType: mimeType,
                     width: format.width,
@@ -111,23 +148,29 @@ export class YouTubeScraper {
                     bitrate: format.bitrate,
                     hasAudio: mimeType.includes('audio/'),
                     hasVideo: mimeType.includes('video/')
-                });
-            } else if (format.signatureCipher) {
-                // To avoid bloatware, we do not implement the complex decipher algorithm here.
-                // Modern APIs usually provide the URL directly for lower qualities or we can fallback to other APIs.
-                // Implementing decipher requires porting youtube-dl's sig logic or using ytdl-core.
-                continue;
+                };
+
+                if (formatObj.hasVideo && formatObj.hasAudio) video.push(formatObj);
+                else if (formatObj.hasVideo) videoOnly.push(formatObj);
+                else if (formatObj.hasAudio) audio.push(formatObj);
             }
         }
 
         return {
             title: details.title || '',
             author: details.author || '',
+            subscribers: subscribers,
             description: details.shortDescription || '',
             views: details.viewCount || '0',
+            likes: likes,
+            comments: comments,
             durationSeconds: details.lengthSeconds || '0',
             thumbnail: details.thumbnail?.thumbnails?.[details.thumbnail.thumbnails.length - 1]?.url || '',
-            formats
+            formats: {
+                video,
+                videoOnly,
+                audio
+            }
         };
     }
 }

package/straw/youtube.py

@@ -13,17 +13,28 @@ class YouTubeScraper:
             raise Exception("Invalid YouTube URL")
         video_id = match.group(1)
 
-        headers = {'Cookie': 'CONSENT=YES+cb.20230501-14-p0.en+FX+430'}
+        headers = {'Cookie': 'CONSENT=YES+cb.20230501-14-p0.en+FX+430', 'Accept-Language': 'en-US,en;q=0.9'}
         html = await self.client.get_text(url, headers=headers)
         
         visitor_data = ""
         details = {}
+        initial_data = {}
         
         player_match = re.search(r'ytInitialPlayerResponse\s*=\s*({.*?});(?:var|<\/script>)', html)
         if player_match:
-            data_html = json.loads(player_match.group(1))
-            details = data_html.get('videoDetails', {})
-            visitor_data = data_html.get('responseContext', {}).get('visitorData', '')
+            try:
+                data_html = json.loads(player_match.group(1))
+                details = data_html.get('videoDetails', {})
+                visitor_data = data_html.get('responseContext', {}).get('visitorData', '')
+            except:
+                pass
+                
+        data_match = re.search(r'var ytInitialData\s*=\s*({.*?});(?:<\/script>)', html)
+        if data_match:
+            try:
+                initial_data = json.loads(data_match.group(1))
+            except:
+                pass
             
         if not visitor_data:
             vd_match = re.search(r'"visitorData"\s*:\s*"([^"]+)"', html)
@@ -64,22 +75,66 @@ class YouTubeScraper:
         if not details:
             raise Exception("Video details not found inside player response.")
 
-        formats = []
+        subscribers = ""
+        likes = ""
+        comments = ""
+        
+        try:
+            contents = initial_data.get('contents', {}).get('twoColumnWatchNextResults', {}).get('results', {}).get('results', {}).get('contents', [])
+            for c in contents:
+                sec_info = c.get('videoSecondaryInfoRenderer')
+                if sec_info:
+                    stext = sec_info.get('owner', {}).get('videoOwnerRenderer', {}).get('subscriberCountText', {}).get('simpleText')
+                    if stext: subscribers = stext
+
+            panels = initial_data.get('engagementPanels', [])
+            for p in panels:
+                sr = p.get('engagementPanelSectionListRenderer', {})
+                if sr.get('targetId') == 'engagement-panel-structured-description':
+                    items = sr.get('content', {}).get('structuredDescriptionContentRenderer', {}).get('items', [])
+                    for i in items:
+                        factoids = i.get('videoDescriptionHeaderRenderer', {}).get('factoid', [])
+                        for f in factoids:
+                            acc = f.get('factoidRenderer', {}).get('accessibilityText', '')
+                            if 'like' in acc.lower():
+                                likes = acc
+                                
+                if sr.get('panelIdentifier') == 'engagement-panel-comments-section':
+                    runs = sr.get('header', {}).get('engagementPanelTitleHeaderRenderer', {}).get('contextualInfo', {}).get('runs', [])
+                    if runs:
+                        comments = runs[0].get('text', '')
+        except:
+            pass
+
+        video_combined = []
+        video_only = []
+        audio_only = []
+        
         raw_formats = streaming_data.get('formats', []) + streaming_data.get('adaptiveFormats', [])
 
         for f in raw_formats:
             if 'url' in f:
                 mime_type = f.get('mimeType', '')
-                formats.append({
+                has_audio = 'audio/' in mime_type
+                has_video = 'video/' in mime_type
+                
+                f_obj = {
                     'url': f['url'],
                     'mimeType': mime_type,
                     'width': f.get('width'),
                     'height': f.get('height'),
                     'quality': f.get('qualityLabel') or f.get('quality'),
                     'bitrate': f.get('bitrate'),
-                    'hasAudio': 'audio/' in mime_type,
-                    'hasVideo': 'video/' in mime_type
-                })
+                    'hasAudio': has_audio,
+                    'hasVideo': has_video
+                }
+                
+                if has_video and has_audio:
+                    video_combined.append(f_obj)
+                elif has_video:
+                    video_only.append(f_obj)
+                elif has_audio:
+                    audio_only.append(f_obj)
 
         thumbnails = details.get('thumbnail', {}).get('thumbnails', [])
         best_thumbnail = thumbnails[-1]['url'] if thumbnails else ''
@@ -87,9 +142,16 @@ class YouTubeScraper:
         return {
             'title': details.get('title', ''),
             'author': details.get('author', ''),
+            'subscribers': subscribers,
             'description': details.get('shortDescription', ''),
             'views': details.get('viewCount', '0'),
+            'likes': likes,
+            'comments': comments,
             'durationSeconds': details.get('lengthSeconds', '0'),
             'thumbnail': best_thumbnail,
-            'formats': formats
+            'formats': {
+                'video': video_combined,
+                'videoOnly': video_only,
+                'audio': audio_only
+            }
         }

package/tests/test.py

@@ -24,9 +24,13 @@ async def run_tests():
         print("2. Testing YouTube Scraper...")
         yt = YouTubeScraper()
         yt_res = await yt.scrape_video("https://www.youtube.com/watch?v=aqz-KE-bpKQ")
-        print(f"YouTube Scraper Output: Title = {yt_res['title']}")
-        print(f"YouTube Scraper Output: Duration = {yt_res['durationSeconds']} seconds")
-        print(f"YouTube Scraper Output: Found {len(yt_res['formats'])} formats")
+        print(f"YouTube Scraper Output: Title = {yt_res.get('title')}")
+        print(f"YouTube Scraper Output: Subscribers = {yt_res.get('subscribers')}")
+        print(f"YouTube Scraper Output: Likes = {yt_res.get('likes')}")
+        print(f"YouTube Scraper Output: Comments = {yt_res.get('comments')}")
+        print(f"YouTube Scraper Output: Duration = {yt_res.get('durationSeconds')} seconds")
+        formats = yt_res.get('formats', {})
+        print(f"YouTube Scraper Output: Found {len(formats.get('video', []))} video, {len(formats.get('videoOnly', []))} video-only, and {len(formats.get('audio', []))} audio formats")
         await yt.client.close()
 
         print("\n" + "-" * 33)

package/tests/test.ts

@@ -19,9 +19,12 @@ async function runTests() {
         const ytClient = straw.youtube();
         // Use a generic test video like Big Buck Bunny
         const ytResult = await ytClient.scrapeVideo('https://www.youtube.com/watch?v=aqz-KE-bpKQ');
-        console.log(`YouTube Scraper Output: Title = ${ytResult.title}`);
-        console.log(`YouTube Scraper Output: Duration = ${ytResult.durationSeconds} seconds`);
-        console.log(`YouTube Scraper Output: Found ${ytResult.formats.length} formats`);
+        console.log('YouTube Scraper Output: Title =', ytResult.title);
+  console.log('YouTube Scraper Output: Subscribers =', ytResult.subscribers);
+  console.log('YouTube Scraper Output: Likes =', ytResult.likes);
+  console.log('YouTube Scraper Output: Comments =', ytResult.comments);
+  console.log('YouTube Scraper Output: Duration =', ytResult.durationSeconds, 'seconds');
+  console.log(`YouTube Scraper Output: Found ${ytResult.formats.video.length} video (combined), ${ytResult.formats.videoOnly.length} video-only, and ${ytResult.formats.audio.length} audio formats.`);
 
         console.log('\n---------------------------------');
 

package/test_api.js

@@ -1,42 +0,0 @@
-const undici = require('undici');
-
-async function testInnerTube() {
-  const videoId = '_4j1Abt_AiM';
-  
-  const payload = {
-    context: {
-      client: {
-        hl: 'en',
-        gl: 'US',
-        clientName: 'IOS',
-        clientVersion: '19.28.1',
-        osName: 'iOS',
-        osVersion: '17.5.1',
-        deviceMake: 'Apple',
-        deviceModel: 'iPhone16,2'
-      }
-    },
-    videoId: videoId
-  };
-
-  const res = await undici.request('https://www.youtube.com/youtubei/v1/player', {
-    method: 'POST',
-    headers: {
-      'Content-Type': 'application/json',
-      'User-Agent': 'com.google.ios.youtube/19.28.1 (iPhone16,2; U; CPU iOS 17_5_1 like Mac OS X; en_US)'
-    },
-    body: JSON.stringify(payload)
-  });
-
-  const body = await res.body.json();
-  console.log('Full JSON Response Keys:', Object.keys(body));
-  console.log('Raw JSON String (Truncated):', JSON.stringify(body).slice(0, 1000));
-  console.log('Playability:', body.playabilityStatus);
-  console.log('Title:', body.videoDetails?.title);
-  
-  const formats = [...(body.streamingData?.formats || []), ...(body.streamingData?.adaptiveFormats || [])];
-  console.log('Total Formats:', formats.length);
-  
-}
-
-testInnerTube();

package/test_api_clients.js

@@ -1,39 +0,0 @@
-const undici = require('undici');
-
-async function testClient(clientName, clientVersion, userAgent, osName='', osVersion='') {
-  const payload = {
-    context: {
-      client: {
-        hl: 'en',
-        gl: 'US',
-        clientName,
-        clientVersion,
-        osName,
-        osVersion
-      }
-    },
-    videoId: '_4j1Abt_AiM'
-  };
-
-  const res = await undici.request('https://www.youtube.com/youtubei/v1/player', {
-    method: 'POST',
-    headers: {
-      'Content-Type': 'application/json',
-      'User-Agent': userAgent
-    },
-    body: JSON.stringify(payload)
-  });
-
-  const body = await res.body.json();
-  const formats = [...(body.streamingData?.formats || []), ...(body.streamingData?.adaptiveFormats || [])];
-  console.log(`[${clientName}] Playability:`, body.playabilityStatus?.status, '| Formats:', formats.length);
-}
-
-async function runAll() {
-  await testClient('WEB_EMBED', '1.20230209.00.00', 'Mozilla/5.0 (Windows NT 10.0; Win64; x64)');
-  await testClient('TVHTML5', '7.20230209.00.00', 'Mozilla/5.0 (Web0S; Linux/SmartTV) AppleWebKit/537.36 (KHTML, like Gecko)');
-  await testClient('ANDROID', '17.31.35', 'com.google.android.youtube/17.31.35 (Linux; U; Android 11)', 'Android', '11');
-  await testClient('IOS', '19.28.1', 'com.google.ios.youtube/19.28.1 (iPhone16,2; U; CPU iOS 17_5_1 like Mac OS X; en_US)', 'iOS', '17.5.1');
-}
-
-runAll();

package/test_client.js

@@ -1,37 +0,0 @@
-const { StrawClient } = require('./dist/core/client.js');
-
-async function test() {
-  const client = new StrawClient();
-  const payload = {
-    context: {
-        client: {
-            hl: 'en',
-            gl: 'US',
-            clientName: 'IOS',
-            clientVersion: '19.28.1',
-            osName: 'iOS',
-            osVersion: '17.5.1',
-            deviceMake: 'Apple',
-            deviceModel: 'iPhone16,2'
-        }
-    },
-    videoId: '_4j1Abt_AiM'
-  };
-
-  const res = await client.request('https://www.youtube.com/youtubei/v1/player', {
-    method: 'POST',
-    headers: {
-        'Content-Type': 'application/json',
-        'User-Agent': 'com.google.ios.youtube/19.28.1 (iPhone16,2; U; CPU iOS 17_5_1 like Mac OS X; en_US)'
-    },
-    body: JSON.stringify(payload)
-  });
-
-  const data = await res.json();
-  console.log(Object.keys(data));
-  if (data.playabilityStatus) {
-    console.log('Playability:', data.playabilityStatus);
-  }
-}
-
-test();

package/test_embed.js

@@ -1,26 +0,0 @@
-const undici = require('undici');
-
-async function testEmbed() {
-  const url = 'https://www.youtube.com/embed/_4j1Abt_AiM';
-  const res = await undici.request(url, {
-    headers: {
-      'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36',
-      'Accept-Language': 'en-US,en;q=0.9',
-      'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
-    }
-  });
-  const html = await res.body.text();
-  
-  const regex = /ytInitialPlayerResponse\s*=\s*({.*?});(?:var|<\/script>)/;
-  const match = html.match(regex);
-  if (match) {
-    const data = JSON.parse(match[1]);
-    const formats = [...(data.streamingData?.formats || []), ...(data.streamingData?.adaptiveFormats || [])];
-    console.log('Embed playability:', data.playabilityStatus?.status);
-    console.log('Formats found:', formats.length);
-  } else {
-    console.log('No ytInitialPlayerResponse found in embed HTML');
-  }
-}
-
-testEmbed();

package/test_html.js

@@ -1,26 +0,0 @@
-const undici = require('undici');
-
-async function testHtml() {
-  const url = 'https://www.youtube.com/watch?v=_4j1Abt_AiM';
-  const res = await undici.request(url, {
-    method: 'GET',
-    headers: {
-      'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/115.0',
-      'Accept-Language': 'en-US,en;q=0.9',
-      'Cookie': 'CONSENT=YES+cb.20230501-14-p0.en+FX+430'
-    }
-  });
-
-  const html = await res.body.text();
-  const match = html.match(/ytInitialPlayerResponse\s*=\s*({.*?});(?:var|<\/script>)/);
-  if (match) {
-    const data = JSON.parse(match[1]);
-    const formats = [...(data.streamingData?.formats || []), ...(data.streamingData?.adaptiveFormats || [])];
-    console.log('Got HTML Response with Player:', data.playabilityStatus?.status);
-    console.log('Formats:', formats.length);
-  } else {
-    console.log('No ytInitialPlayerResponse found in direct HTML fetching.');
-  }
-}
-
-testHtml();

package/test_visitor.js

@@ -1,56 +0,0 @@
-const undici = require('undici');
-
-async function testVisitor() {
-  const videoId = '_4j1Abt_AiM';
-  const url = `https://www.youtube.com/watch?v=${videoId}`;
-  
-  const htmlRes = await undici.request(url, {
-    method: 'GET',
-    headers: {
-      'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) Chrome/115.0.0.0 Safari/537.36',
-      'Cookie': 'CONSENT=YES+cb.20230501-14-p0.en+FX+430'
-    }
-  });
-
-  const html = await htmlRes.body.text();
-  
-  let visitorData = '';
-  const match = html.match(/"visitorData"\s*:\s*"([^"]+)"/);
-  if (match) visitorData = match[1];
-  
-  console.log('Got Visitor Data:', visitorData);
-
-  const payload = {
-    context: {
-      client: {
-        hl: 'en',
-        gl: 'US',
-        clientName: 'IOS',
-        clientVersion: '19.28.1',
-        osName: 'iOS',
-        osVersion: '17.5.1',
-        deviceMake: 'Apple',
-        deviceModel: 'iPhone16,2',
-        visitorData: visitorData
-      }
-    },
-    videoId: videoId
-  };
-
-  const res = await undici.request('https://www.youtube.com/youtubei/v1/player', {
-    method: 'POST',
-    headers: {
-      'Content-Type': 'application/json',
-      'User-Agent': 'com.google.ios.youtube/19.28.1 (iPhone16,2; U; CPU iOS 17_5_1 like Mac OS X; en_US)'
-    },
-    body: JSON.stringify(payload)
-  });
-
-  const body = await res.body.json();
-  const formats = [...(body.streamingData?.formats || []), ...(body.streamingData?.adaptiveFormats || [])];
-  
-  console.log('Target Playability:', body.playabilityStatus?.status);
-  console.log('Target Formats:', formats.length);
-}
-
-testVisitor();

package/test_vr.js

@@ -1,27 +0,0 @@
-const undici = require('undici');
-
-async function testVR() {
-  const payload = {
-    context: {
-      client: {
-        clientName: 'ANDROID_TESTSUITE',
-        clientVersion: '1.9',
-        androidSdkVersion: 30,
-        hl: 'en',
-        gl: 'US',
-        utcOffsetMinutes: 0
-      }
-    },
-    videoId: '_4j1Abt_AiM'
-  };
-  const res = await undici.request('https://www.youtube.com/youtubei/v1/player', {
-    method: 'POST',
-    headers: { 'Content-Type': 'application/json', 'User-Agent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11)' },
-    body: JSON.stringify(payload)
-  });
-  const body = await res.body.json();
-  const formats = [...(body.streamingData?.formats || []), ...(body.streamingData?.adaptiveFormats || [])];
-  console.log('Playability:', body.playabilityStatus?.status);
-  console.log('Formats:', formats.length);
-}
-testVR();

package/test_yt.js

@@ -1,17 +0,0 @@
-const straw = require('./dist/index.js');
-
-async function run() {
-  console.time('YouTube Scrape');
-  const yt = new straw.YouTubeScraper();
-  try {
-    const res = await yt.scrapeVideo('https://youtu.be/_4j1Abt_AiM?si=qJY_gv4F_adBYMYP');
-    console.log('Title:', res.title);
-    console.log('Formats:', res.formats.length);
-    console.log('First format URL (truncated):', res.formats[0]?.url?.substring(0, 100));
-  } catch (e) {
-    console.error('Scrape failed:', e);
-  }
-  console.timeEnd('YouTube Scrape');
-}
-
-run();