用 YouTube 字幕能做什么产品

import requests

API = "https://www.youtubetranscript.dev/api/v2"
HEADERS = {"Authorization": "Bearer yt_sk_live_YOUR_KEY"}

res = requests.post(f"{API}/transcribe", headers=HEADERS, json={
    "video": "https://www.youtube.com/watch?v=VIDEO_ID",
    "format": {"timestamp": True, "paragraphs": True},
}).json()

transcript = res["data"]["transcript"]
print(transcript["text"][:500])        # plain text for your LLM prompt
for seg in transcript["segments"][:3]:  # timestamps for deep links
    print(seg["start"], seg["text"])

WATCHLIST = ["@somechannel", "@anotherchannel"]
KEYWORDS = ["your brand", "competitor"]
seen = set()  # persist this in a database in production

for handle in WATCHLIST:
    latest = requests.post(f"{API}/channels/resolve", headers=HEADERS,
                           json={"handle": handle, "limit": 10}).json()
    for video in latest["items"]:
        if video["video_id"] in seen:
            continue
        seen.add(video["video_id"])
        t = requests.post(f"{API}/transcribe", headers=HEADERS,
                          json={"video": video["video_id"]}).json()
        text = t.get("data", {}).get("transcript", {}).get("text", "").lower()
        hits = [k for k in KEYWORDS if k in text]
        if hits:
            print(f"ALERT {video['title']}: {hits}")

playlist = requests.post(f"{API}/playlists/resolve", headers=HEADERS,
                         json={"playlist_url": "https://www.youtube.com/playlist?list=PLAYLIST_ID",
                               "limit": 100}).json()

ids = [v["video_id"] for v in playlist["items"]]
batch = requests.post(f"{API}/batch", headers=HEADERS, json={
    "video_ids": ids,
    "format": {"timestamp": True, "paragraphs": True},
}).json()

# Large batches run async: poll GET /batch/{batch_id} until status is "completed"
for r in batch.get("results", []):
    if r["status"] == "completed":
        for p in r["data"]["transcript"].get("paragraphs") or []:
            store(video_id=r["video_id"], start=p["start"], text=p["text"])  # your vector DB