import os, requests, time, tempfile
YT = os.environ["YOUTUBE_API_KEY"]
MV = os.environ["MAVERA_API_KEY"]
YT_BASE = "https://www.googleapis.com/youtube/v3"
MV_BASE = "https://app.mavera.io/api/v1"
MV_H = {"Authorization": f"Bearer {MV}", "Content-Type": "application/json"}
COMPETITORS = ["Nike", "Adidas", "Puma"]
all_analyses = []
for brand in COMPETITORS:
# 1. Search for competitor ads (100 quota units per call)
search = requests.get(f"{YT_BASE}/search", params={
"key": YT, "q": f"{brand} official ad 2026",
"type": "video", "part": "snippet",
"maxResults": 3, "order": "viewCount",
"videoDuration": "short",
}).json()
if "error" in search:
print(f"YouTube API error for {brand}: {search['error']['message']}")
continue
for item in search.get("items", []):
video_id = item["id"]["videoId"]
title = item["snippet"]["title"]
# 2. Get video details for download URL (1 quota unit)
details = requests.get(f"{YT_BASE}/videos", params={
"key": YT, "id": video_id,
"part": "snippet,contentDetails,statistics",
}).json()
video_info = (details.get("items") or [{}])[0]
view_count = int(video_info.get("statistics", {}).get("viewCount", 0))
# 3. Upload video URL to Mavera for analysis
upload = requests.post(f"{MV_BASE}/assets", headers=MV_H, json={
"url": f"https://www.youtube.com/watch?v={video_id}",
"name": f"{brand} — {title[:50]}",
"type": "video",
}).json()
# 4. Run Video Analysis
analysis = requests.post(f"{MV_BASE}/video-analysis", headers=MV_H, json={
"asset_id": upload["id"],
"analysis_types": [
"message_clarity", "emotional_impact", "brand_attribution",
"hook_score", "cognitive_load", "pacing",
],
"metadata": {"brand": brand, "video_id": video_id, "views": view_count},
}).json()
# 5. Poll for completion
status = {}
for _ in range(30):
time.sleep(3)
status = requests.get(
f"{MV_BASE}/video-analysis/{analysis['id']}", headers=MV_H
).json()
if status.get("status") == "completed":
break
results = status.get("results", {})
all_analyses.append({
"brand": brand, "title": title[:50], "video_id": video_id,
"views": view_count,
"message_clarity": results.get("message_clarity", {}).get("score", 0),
"emotional_impact": results.get("emotional_impact", {}).get("score", 0),
"brand_attribution": results.get("brand_attribution", {}).get("score", 0),
"hook_score": results.get("hook_score", {}).get("score", 0),
})
time.sleep(1)
# 6. Send all scores to Mave for comparative ranking
scores_block = "\n".join(
f"- {a['brand']}: \"{a['title']}\" — clarity {a['message_clarity']}/100, "
f"emotion {a['emotional_impact']}/100, attribution {a['brand_attribution']}/100, "
f"hook {a['hook_score']}/100, views {a['views']:,}"
for a in all_analyses
)
ranking = requests.post(f"{MV_BASE}/mave/chat", headers=MV_H, json={
"message": f"""Rank these competitor YouTube ads in a competitive showdown.
SCORES:
{scores_block}
For each brand:
1. Overall rank and composite score
2. Biggest creative strength
3. Most exploitable weakness
4. How our brand could beat them (specific creative recommendation)
End with: which competitor is the biggest creative threat and why.""",
}).json()
print("COMPETITOR AD ANALYSIS SHOWDOWN")
print("=" * 60)
for a in sorted(all_analyses, key=lambda x: -x["emotional_impact"]):
print(f" {a['brand']:<12} {a['title'][:35]:<38} "
f"Clarity:{a['message_clarity']:>3} Emotion:{a['emotional_impact']:>3} "
f"Hook:{a['hook_score']:>3}")
print("\n" + ranking.get("content", "")[:1500])
