Caption-Based Content Extraction

import os, requests, time

VM = os.environ["VIMEO_ACCESS_TOKEN"]
MV = os.environ["MAVERA_API_KEY"]
VM_BASE = "https://api.vimeo.com"
MV_BASE = "https://app.mavera.io/api/v1"
VM_H = {"Authorization": f"Bearer {VM}", "Accept": "application/vnd.vimeo.*+json;version=3.4"}
MV_H = {"Authorization": f"Bearer {MV}", "Content-Type": "application/json"}

VIDEO_IDS = ["123456789", "987654321", "456789012"]

all_repurposed = []

for video_id in VIDEO_IDS:
    # 1. Fetch text tracks
    tracks_resp = requests.get(
        f"{VM_BASE}/videos/{video_id}/texttracks", headers=VM_H
    ).json()

    tracks = tracks_resp.get("data", [])
    if not tracks:
        print(f"No captions for video {video_id} — skipping")
        continue

    caption_track = next(
        (t for t in tracks if t.get("type") == "captions" and t.get("language") == "en"),
        tracks[0]
    )

    # 2. Download the transcript file
    transcript_url = caption_track.get("link")
    if not transcript_url:
        print(f"No download link for video {video_id} — skipping")
        continue

    transcript_raw = requests.get(transcript_url).text

    # 3. Clean VTT/SRT formatting to plain text
    lines = []
    for line in transcript_raw.split("\n"):
        line = line.strip()
        if not line or line.startswith("WEBVTT") or "-->" in line or line.isdigit():
            continue
        lines.append(line)
    transcript = " ".join(lines)

    # 4. Get video metadata for context
    video_meta = requests.get(f"{VM_BASE}/videos/{video_id}", headers=VM_H, params={
        "fields": "name,description,duration",
    }).json()
    video_name = video_meta.get("name", f"Video {video_id}")

    print(f"Processing: \"{video_name}\" ({len(transcript)} chars transcript)")

    # 5. Extract key messages via Mave Chat
    extraction = requests.post(f"{MV_BASE}/mave/chat", headers=MV_H, json={
        "message": f"""Extract structured content from this video transcript.

VIDEO: "{video_name}"
TRANSCRIPT:
{transcript[:8000]}

Extract:
1. **Key Messages** (3-5 core points the speaker makes)
2. **Claims & Statistics** (any data points, percentages, or factual claims)
3. **CTAs** (calls to action — explicit or implied)
4. **Quotable Lines** (5-7 sentences that work standalone as social posts)
5. **Topic Tags** (10 keywords for SEO/categorization)""",
    }).json()

    extracted = extraction.get("content", "")

    # 6. Generate repurposed content
    repurpose = requests.post(f"{MV_BASE}/generate", headers=MV_H, json={
        "prompt": f"""Using this extracted content from a video, generate repurposed written assets.

SOURCE VIDEO: "{video_name}"
EXTRACTED CONTENT:
{extracted[:4000]}

Generate these assets:

1. **Blog Post Outline** — 800-word post structure with H2s, key points per section, and SEO title
2. **LinkedIn Post** — 150-word thought leadership post with hook, insight, CTA
3. **Twitter/X Thread** — 5-tweet thread with a hook tweet and numbered insights
4. **Email Newsletter Block** — 100-word summary for a weekly newsletter with subject line
5. **Instagram Caption** — 80 words max with relevant hashtags""",
    }).json()

    all_repurposed.append({
        "video": video_name,
        "video_id": video_id,
        "transcript_length": len(transcript),
        "extracted": extracted[:1000],
        "repurposed": repurpose.get("content", "")[:2000],
    })
    time.sleep(1)

# 7. Output
print("\nCAPTION-BASED CONTENT EXTRACTION")
print("=" * 60)
for item in all_repurposed:
    print(f"\n{'─' * 60}")
    print(f"VIDEO: {item['video']} ({item['transcript_length']:,} chars)")
    print(f"\nEXTRACTED CONTENT:")
    print(item["extracted"][:600])
    print(f"\nREPURPOSED ASSETS:")
    print(item["repurposed"][:1200])

const VM = process.env.VIMEO_ACCESS_TOKEN;
const MV = process.env.MAVERA_API_KEY;
const VM_BASE = "https://api.vimeo.com";
const MV_BASE = "https://app.mavera.io/api/v1";
const VM_H = { Authorization: `Bearer ${VM}`, Accept: "application/vnd.vimeo.*+json;version=3.4" };
const MV_H = { Authorization: `Bearer ${MV}`, "Content-Type": "application/json" };

const VIDEO_IDS = ["123456789", "987654321", "456789012"];
const allRepurposed = [];

for (const videoId of VIDEO_IDS) {
  // 1. Fetch text tracks
  const tracksResp = await fetch(
    `${VM_BASE}/videos/${videoId}/texttracks`, { headers: VM_H }
  ).then(r => r.json());

  const tracks = tracksResp.data || [];
  if (!tracks.length) { console.log(`No captions for ${videoId}`); continue; }

  const captionTrack = tracks.find(t => t.type === "captions" && t.language === "en") || tracks[0];

  // 2. Download transcript
  if (!captionTrack.link) { console.log(`No link for ${videoId}`); continue; }
  const transcriptRaw = await fetch(captionTrack.link).then(r => r.text());

  // 3. Clean VTT/SRT to plain text
  const transcript = transcriptRaw.split("\n")
    .map(l => l.trim())
    .filter(l => l && !l.startsWith("WEBVTT") && !l.includes("-->") && !/^\d+$/.test(l))
    .join(" ");

  // 4. Video metadata
  const videoMeta = await fetch(
    `${VM_BASE}/videos/${videoId}?fields=name,description,duration`, { headers: VM_H }
  ).then(r => r.json());
  const videoName = videoMeta.name || `Video ${videoId}`;

  console.log(`Processing: "${videoName}" (${transcript.length} chars)`);

  // 5. Extract key messages
  const extraction = await fetch(`${MV_BASE}/mave/chat`, {
    method: "POST", headers: MV_H,
    body: JSON.stringify({
      message: `Extract from transcript.\n\nVIDEO: "${videoName}"\nTRANSCRIPT:\n${transcript.slice(0, 8000)}\n\nExtract:\n1. Key Messages (3-5)\n2. Claims & Statistics\n3. CTAs\n4. Quotable Lines (5-7)\n5. Topic Tags (10 keywords)`,
    }),
  }).then(r => r.json());

  const extracted = extraction.content || "";

  // 6. Generate repurposed content
  const repurpose = await fetch(`${MV_BASE}/generate`, {
    method: "POST", headers: MV_H,
    body: JSON.stringify({
      prompt: `From this extracted video content, generate:\n\nSOURCE: "${videoName}"\nCONTENT:\n${extracted.slice(0, 4000)}\n\n1. Blog Post Outline (800-word structure with H2s, SEO title)\n2. LinkedIn Post (150 words, hook+insight+CTA)\n3. Twitter/X Thread (5 tweets, hook + numbered insights)\n4. Email Newsletter Block (100 words + subject line)\n5. Instagram Caption (80 words + hashtags)`,
    }),
  }).then(r => r.json());

  allRepurposed.push({
    video: videoName, videoId,
    transcriptLength: transcript.length,
    extracted: extracted.slice(0, 1000),
    repurposed: (repurpose.content || "").slice(0, 2000),
  });
  await new Promise(r => setTimeout(r, 1000));
}

// 7. Output
console.log("\nCAPTION-BASED CONTENT EXTRACTION");
console.log("=".repeat(60));
for (const item of allRepurposed) {
  console.log(`\n${"─".repeat(60)}`);
  console.log(`VIDEO: ${item.video} (${item.transcriptLength.toLocaleString()} chars)`);
  console.log(`\nEXTRACTED:\n${item.extracted.slice(0, 600)}`);
  console.log(`\nREPURPOSED:\n${item.repurposed.slice(0, 1200)}`);
}