by-agent-for-agent/scripts/twitter_pro_dl.py

# /// script
# requires-python = ">=3.12"
# dependencies = [
#     "httpx",
# ]
# ///
import httpx
import os
import sys
import re

def download_twitter_media(url, output_dir="downloads"):
    if not os.path.exists(output_dir):
        os.makedirs(output_dir)

    # 提取推文 ID
    match = re.search(r'status/(\d+)', url)
    if not match:
        print("❌ 无法提取推文 ID")
        return
    tweet_id = match.group(1)

    print(f"🚀 正在分析推文 {tweet_id}...")

    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
        "Referer": "https://twitter.com/",
    }

    try:
        # 使用 Syndication API，这是推特用于渲染嵌入卡片的接口，不需要登录
        syndication_url = f"https://cdn.syndication.twimg.com/tweet-result?id={tweet_id}&lang=en"
        
        with httpx.Client(headers=headers, timeout=20.0) as client:
            response = client.get(syndication_url)
            if response.status_code != 200:
                print(f"❌ 接口请求失败 ({response.status_code})，推文可能不可见。")
                return
            
            data = response.json()
            media_list = data.get("mediaDetails", [])
            
            if not media_list:
                print("❌ 未在推文中发现多媒体资源。")
                return

            print(f"📸 发现 {len(media_list)} 个媒体资源，准备下载...")

            for i, media in enumerate(media_list):
                media_url = ""
                # 如果是视频/GIF
                if media.get("type") == "video" or media.get("type") == "animated_gif":
                    variants = media.get("video_info", {}).get("variants", [])
                    # 找比特率最高（画质最好）的 mp4
                    mp4_variants = [v for v in variants if v.get("content_type") == "video/mp4"]
                    if mp4_variants:
                        best_variant = max(mp4_variants, key=lambda v: v.get("bitrate", 0))
                        media_url = best_variant.get("url")
                # 如果是图片
                else:
                    media_url = media.get("media_url_https")
                    if media_url:
                        media_url += "?name=orig" # 获取最高原图画质

                if media_url:
                    ext = "mp4" if "video" in media.get("type", "") else "jpg"
                    if "format=" in media_url:
                        ext_match = re.search(r'format=([a-z]+)', media_url)
                        if ext_match: ext = ext_match.group(1)

                    save_path = os.path.join(output_dir, f"twitter_{tweet_id}_{i}.{ext}")
                    print(f"📥 正在下载: {media_url}")
                    
                    img_res = client.get(media_url)
                    if img_res.status_code == 200:
                        with open(save_path, "wb") as f:
                            f.write(img_res.content)
                        print(f"✅ 保存成功: {save_path}")

    except Exception as e:
        print(f"💥 运行异常: {e}")

if __name__ == "__main__":
    if len(sys.argv) < 2:
        print("用法: uv run scripts/twitter_pro_dl.py <twitter_url>")
    else:
        download_twitter_media(sys.argv[1])