如何通过 API 采集 Cerfia 的 X 数据

curl --request GET \
  --url https://api.twexapi.io/twitter/CerfiaFR/about \
  --header 'Authorization: Bearer <token>'

curl --request POST \
  --url https://api.twexapi.io/twitter/CerfiaFR/timeline/page \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "count": 20
  }'

{
  "code": 200,
  "msg": "success",
  "data": [],
  "has_next_page": true,
  "next_cursor": "DAAHCgAB...",
  "requested_count": 20,
  "effective_count": 20,
  "parsed_count": 20
}

1import os
2from typing import Any
3
4import requests
5
6TOKEN = os.environ["TWEXAPI_BEARER_TOKEN"]
7SCREEN_NAME = "CerfiaFR"
8BASE_URL = "https://api.twexapi.io"
9
10def headers() -> dict[str, str]:
11    return {"Authorization": f"Bearer {TOKEN}", "Content-Type": "application/json"}
12
13def get_profile(screen_name: str) -> dict[str, Any] | None:
14    response = requests.get(
15        f"{BASE_URL}/twitter/{screen_name}/about",
16        headers=headers(),
17        timeout=30,
18    )
19    response.raise_for_status()
20    return response.json().get("data")
21
22def get_timeline_page(
23    screen_name: str,
24    *,
25    count: int = 20,
26    next_cursor: str | None = None,
27) -> dict[str, Any]:
28    payload: dict[str, Any] = {"count": count}
29    if next_cursor:
30        payload["next_cursor"] = next_cursor
31
32    response = requests.post(
33        f"{BASE_URL}/twitter/{screen_name}/timeline/page",
34        headers=headers(),
35        json=payload,
36        timeout=30,
37    )
38    response.raise_for_status()
39    return response.json()
40
41def normalize_post(post: dict[str, Any]) -> dict[str, Any]:
42    tweet_id = post.get("tweet_id") or post.get("id")
43    return {
44        "tweet_id": tweet_id,
45        "created_at": post.get("created_at_datetime") or post.get("created_at"),
46        "text": post.get("full_text") or post.get("text") or "",
47        "favorite_count": post.get("favorite_count") or 0,
48        "retweet_count": post.get("retweet_count") or 0,
49        "reply_count": post.get("reply_count") or 0,
50        "quote_count": post.get("quote_count") or 0,
51        "url": f"https://x.com/i/status/{tweet_id}",
52    }
53
54def collect_timeline(screen_name: str, max_pages: int = 3) -> list[dict[str, Any]]:
55    rows: list[dict[str, Any]] = []
56    cursor = None
57
58    for _ in range(max_pages):
59        page = get_timeline_page(screen_name, count=20, next_cursor=cursor)
60        rows.extend(normalize_post(post) for post in page.get("data", []))
61
62        if not page.get("has_next_page"):
63            break
64        cursor = page.get("next_cursor")
65        if not cursor:
66            break
67
68    return rows
69
70if __name__ == "__main__":
71    profile = get_profile(SCREEN_NAME)
72    posts = collect_timeline(SCREEN_NAME, max_pages=2)
73    print(profile.get("screen_name") if profile else SCREEN_NAME, len(posts))

curl --request POST \
  --url https://api.twexapi.io/twitter/advanced_search/page \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "searchTerms": ["from:CerfiaFR climate"],
    "sortBy": "Latest"
  }'