How to Search Twitter (X) Videos via API

import os, requests

HEADERS = {"X-API-Key": os.environ["TWITTERAPI_IO_KEY"]}
BASE = "https://api.twitterapi.io"

def search_videos(topic: str, min_faves: int = 20, max_pages: int = 10) -> list:
    query = f"{topic} filter:videos lang:en min_faves:{min_faves} -filter:retweets"
    tweets, cursor = [], None
    for _ in range(max_pages):
        params = {"query": query}
        if cursor: params["cursor"] = cursor
        r = requests.get(f"{BASE}/twitter/tweet/advanced_search", headers=HEADERS, params=params, timeout=15)
        r.raise_for_status()
        resp = r.json()
        tweets.extend(resp.get("tweets", []))
        cursor = resp.get("next_cursor")
        if not cursor: break
    return tweets

# High-signal AI news videos with 50+ engagement
vids = search_videos("OpenAI OR Anthropic OR GPT", min_faves=50)
print(f"{len(vids):,} video tweets found")

# Access video URLs from extendedEntities.media (highest-bitrate MP4 variant)
for t in vids[:5]:
    media = (t.get("extendedEntities") or {}).get("media", [])
    for m in media:
        if m.get("type") in ("video", "animated_gif"):
            mp4s = [v for v in (m.get("video_info") or {}).get("variants", []) if v.get("content_type") == "video/mp4"]
            best = max(mp4s, key=lambda v: v.get("bitrate", 0), default={})
            print(f"  @{t.get('author', {}).get('userName')}: {best.get('url', 'no-url')}")

# Cost per twitterapi.io/pricing: len(vids) × $0.00015

# 30-day bulk video pull for a topic — window-sliced pattern.
import os, requests, json
from datetime import date, timedelta
from pathlib import Path

HEADERS = {"X-API-Key": os.environ["TWITTERAPI_IO_KEY"]}
BASE = "https://api.twitterapi.io"
OUT = Path("video_corpus.jsonl")

def pull_day(topic: str, d: date) -> int:
    query = f"{topic} filter:videos lang:en min_faves:10 -filter:retweets since:{d} until:{d + timedelta(days=1)}"
    n, cursor = 0, None
    with open(OUT, "a") as f:
        for _ in range(50):
            params = {"query": query}
            if cursor: params["cursor"] = cursor
            r = requests.get(f"{BASE}/twitter/tweet/advanced_search", headers=HEADERS, params=params, timeout=15)
            r.raise_for_status()
            resp = r.json()
            for t in resp.get("tweets", []):
                f.write(json.dumps(t) + "\n"); n += 1
            cursor = resp.get("next_cursor")
            if not cursor: break
    return n

TOPIC = "climate change"
END = date.today()
START = END - timedelta(days=30)

d = START
total = 0
while d < END:
    n = pull_day(TOPIC, d)
    print(f"  {d}: {n:,} video tweets")
    total += n
    d += timedelta(days=1)

print(f"\n30d total: {total:,} video tweets")
print(f"Cost per twitterapi.io/pricing: {total} × $0.00015 = ${total * 0.00015:.2f}")