如何通过 API 在 public platform 上寻找 AI Influencer

https://api.twexapi.io/twitter/search-user/{keyword}/{target_count}

curl --request GET \
  --url 'https://api.twexapi.io/twitter/search-user/AI%20founder/50' \
  --header 'Authorization: Bearer <token>'

1{
2  "code": 200,
3  "msg": "success",
4  "data": [
5    {
6      "id": "1717001045992251392",
7      "name": "Example AI Founder",
8      "screen_name": "example_ai",
9      "description": "Building AI agents for support teams",
10      "followers_count": 42000,
11      "listed_count": 310,
12      "is_verified": true,
13      "is_blue_verified": true,
14      "verified_type": "blue"
15    }
16  ]
17}

1import os
2from typing import Any
3from urllib.parse import quote
4
5import requests
6
7TOKEN = os.environ["TWEXAPI_BEARER_TOKEN"]
8BASE_URL = "https://api.twexapi.io/twitter/search-user"
9
10def search_users(keyword: str, *, target_count: int = 50) -> list[dict[str, Any]]:
11    encoded_keyword = quote(keyword)
12    url = f"{BASE_URL}/{encoded_keyword}/{target_count}"
13
14    response = requests.get(
15        url,
16        headers={"Authorization": f"Bearer {TOKEN}"},
17        timeout=30,
18    )
19    response.raise_for_status()
20    return response.json().get("data", [])
21
22if __name__ == "__main__":
23    users = search_users("AI founder", target_count=25)
24    for user in users[:10]:
25        print(
26            user.get("screen_name"),
27            user.get("followers_count"),
28            user.get("description"),
29        )

1from typing import Any
2
3AI_TERMS = [
4    "ai",
5    "artificial intelligence",
6    "llm",
7    "agent",
8    "agents",
9    "machine learning",
10    "ml",
11    "copilot",
12]
13
14def text_contains_ai_signal(text: str) -> bool:
15    lowered = text.lower()
16    return any(term in lowered for term in AI_TERMS)
17
18def to_candidate_row(user: dict[str, Any], keyword: str) -> dict[str, Any]:
19    description = user.get("description") or ""
20    followers_count = user.get("followers_count") or 0
21    listed_count = user.get("listed_count") or 0
22
23    return {
24        "keyword": keyword,
25        "user_id": user.get("id"),
26        "screen_name": user.get("screen_name"),
27        "name": user.get("name"),
28        "description": description,
29        "location": user.get("location"),
30        "followers_count": followers_count,
31        "listed_count": listed_count,
32        "is_verified": user.get("is_verified") is True,
33        "is_blue_verified": user.get("is_blue_verified") is True,
34        "verified_type": user.get("verified_type"),
35        "profile_match": text_contains_ai_signal(description),
36        "profile_url": f"https://x.com/{user.get('screen_name')}",
37        "raw": user,
38    }

1import math
2
3def candidate_score(row: dict[str, Any]) -> float:
4    score = 0.0
5
6    if row["profile_match"]:
7        score += 40
8    if row["is_verified"]:
9        score += 10
10    if row["is_blue_verified"]:
11        score += 5
12    if row["verified_type"] in {"business", "government"}:
13        score += 10
14
15    followers = row["followers_count"] or 0
16    listed = row["listed_count"] or 0
17    score += min(math.log10(followers + 1) * 10, 45)
18    score += min(math.log10(listed + 1) * 6, 20)
19
20    return round(score, 2)
21
22keywords = [
23    "AI founder",
24    "LLM engineer",
25    "AI agents",
26    "AI product manager",
27]
28
29candidates = []
30seen_user_ids = set()
31
32for keyword in keywords:
33    for user in search_users(keyword, target_count=50):
34        user_id = user.get("id")
35        if not user_id or user_id in seen_user_ids:
36            continue
37        seen_user_ids.add(user_id)
38
39        row = to_candidate_row(user, keyword)
40        row["score"] = candidate_score(row)
41        candidates.append(row)
42
43candidates.sort(key=lambda row: row["score"], reverse=True)
44
45for row in candidates[:25]:
46    print(row["score"], row["screen_name"], row["followers_count"], row["profile_url"])

1import csv
2import json
3from datetime import datetime, timezone
4from pathlib import Path
5
6timestamp = datetime.now(timezone.utc).isoformat()
7csv_path = Path("ai-influencer-candidates.csv")
8jsonl_path = Path("ai-influencer-candidates.raw.jsonl")
9
10fieldnames = [
11    "score",
12    "keyword",
13    "screen_name",
14    "name",
15    "description",
16    "location",
17    "followers_count",
18    "listed_count",
19    "is_verified",
20    "is_blue_verified",
21    "verified_type",
22    "profile_url",
23]
24
25with csv_path.open("w", newline="", encoding="utf-8") as f:
26    writer = csv.DictWriter(f, fieldnames=fieldnames)
27    writer.writeheader()
28    for row in candidates:
29        writer.writerow({field: row.get(field) for field in fieldnames})
30
31with jsonl_path.open("w", encoding="utf-8") as f:
32    for row in candidates:
33        f.write(json.dumps({
34            "fetched_at": timestamp,
35            "candidate": row,
36        }, ensure_ascii=False) + "\n")
37
38print(f"Saved {len(candidates)} candidates")