Python根据文件URL将文件转为Base64字符串

from flask import flask, request, jsonify
import requests
import base64
import logging
import os
from logging.handlers import timedrotatingfilehandler
from datetime import datetime
import mimetypes
 
app = flask(__name__)
 
# 配置日志目录
log_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'logs')
if not os.path.exists(log_dir):
    os.makedirs(log_dir)
 
# 按年月日构建日志文件路径
current_date = datetime.now().strftime('%y%m%d')
log_file = os.path.join(log_dir, f'file-to-base64-{current_date}.log')
 
# 配置日志
logging.basicconfig(
    level=logging.info,
    format='%(asctime)s - %(levelname)s - %(message)s',
    handlers=[
        logging.streamhandler(),
        timedrotatingfilehandler(
            log_file,
            when='midnight',
            interval=1,
            backupcount=30,
            encoding='utf-8'
        )
    ]
)
 
# 输入：{fileurl:xxx} 输出：{fileext:文件类型,len:字符串长度,str:base64字符串}
@app.route('/file-to-base64', methods=['post'])
def file_to_base64():
    """根据文件url(本地路径或网络路径)将文件转换为base64字符串"""
    # 每次请求时打印日志，分割
    logging.info("-----------------------------------------------------------------------------------------------------------------")
    # 1.获取请求头中的 authorization 字段（可选）
    authorization = request.headers.get('authorization')
    if authorization != 'dpvnrntrqhhmxdfgooea':
        logging.warning(f"authorization 字段验证失败: {authorization}")
        return jsonify({"error": "authorization verification failed"}), 401    
    # 2.获取请求参数
    data = request.json
    if not data or 'file_url' not in data:
        logging.warning("请求参数缺失")
        return jsonify({"error": "file_url is required"}), 400
    # 3. 开始处理文件转换
    file_url = data['file_url']
    logging.info(f"开始处理文件转换，url: {file_url}")
    
    try:
 
        # 3.1 读取本地文件或网络文件
        if file_url.startswith('file://') or os.path.exists(file_url):
            # 3.1.1 处理本地文件
            if file_url.startswith('file://'):
                file_path = file_url[7:]
            else:
                file_path = file_url
                
            with open(file_path, 'rb') as f:
                file_bytes = f.read()
            content_type = mimetypes.guess_type(file_path)[0] or 'application/octet-stream'
        else:
            # 3.1.2 处理网络文件
            # 问题：httpsconnectionpool(host='xx.xx.xx.xx', port=443): max retries exceeded with url
            # 解决方法：添加 verify=false 忽略证书验证
            response = requests.get(file_url, verify=false)
            response.raise_for_status()
            file_bytes = response.content
            content_type = response.headers.get('content-type', '')
 
        # 3.2 通过content-type判断文件类型
        file_extension = get_file_extension_from_content_type(content_type)
        # 3.3 将文件转换为base64字符串
        base64_encoded = base64.b64encode(file_bytes).decode('utf-8')
        # 3.4 添加mime类型前缀返回（可选）
        if content_type:
            base64_encoded = f"data:{content_type};base64,{base64_encoded}"
        # 3.5 记录转换结果
        logging.info(f"转换成功！文件类型：{file_extension}，base64字符串长度: {len(base64_encoded)}")
        return jsonify({
            "fileext":file_extension,
            "len":len(base64_encoded),
            "str": base64_encoded
        })
    # 4. 异常处理
    except requests.requestexception as e:
        logging.error(f"请求url: {file_url}时出错: {e}")
        return jsonify({"error": str(e)}), 500
    except exception as e:
        logging.error(f"请求url: {file_url}转换发生未知错误: {e}")
        return jsonify({"error": "internal server error"}), 500
 
def get_file_extension_from_content_type(content_type):
    """根据content-type获取文件扩展名"""
    # 去除字符集信息，只保留mime类型部分
    mime_type = content_type.split(';')[0].strip().lower()
    mime_to_extension = {
        # 图片类型
        'image/jpeg': 'jpg',
        'image/png': 'png',
        'image/gif': 'gif',
        'image/bmp': 'bmp',
        'image/webp': 'webp',
        'image/svg+xml': 'svg',
        
        # 音频类型
        'audio/wav': 'wav',
        'audio/mpeg': 'mp3',
        'audio/ogg': 'ogg',
        'audio/webm': 'weba',
        
        # 视频类型
        'video/mp4': 'mp4',
        'video/webm': 'webm',
        'video/ogg': 'ogv',
        
        # 文档类型
        'application/pdf': 'pdf',
        'application/msword': 'doc',
        'application/vnd.openxmlformats-officedocument.wordprocessingml.document': 'docx',
        'application/vnd.ms-excel': 'xls',
        'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet': 'xlsx',
        'application/vnd.ms-powerpoint': 'ppt',
        'application/vnd.openxmlformats-officedocument.presentationml.presentation': 'pptx',
        
        # 文本类型
        'text/plain': 'txt',
        'text/html': 'html',
        'text/css': 'css',
        'text/javascript': 'js',
        'application/javascript': 'js',
        'application/json': 'json',
        'application/xml': 'xml',
        
        # 压缩文件
        'application/zip': 'zip',
        'application/x-rar-compressed': 'rar',
        'application/x-tar': 'tar',
        'application/x-gzip': 'gz',
        
        # 其他常见类型
        'application/octet-stream': 'bin',
        'application/x-shockwave-flash': 'swf',
        'application/x-font-ttf': 'ttf',
        'application/x-font-woff': 'woff',
        'application/x-font-woff2': 'woff2'
    }
    return mime_to_extension.get(mime_type, 'unknown')
 
if __name__ == "__main__":
    app.run(host='0.0.0.0', port=5000)

cd /usr/ai/codes/fileutil
# 运行
python3 filetobase64.py
 
# 后台运行
nohup python3 filetobase64.py > /dev/null 2>&1 &
 
# 查看进程
ps -ef | grep filetobase64.py

curl --location --request post 'http://127.0.0.1:5000/file-to-base64' \
--header 'authorization: dpvnrntrqhhmxdfgooea' \
--header 'content-type: application/json' \
--data-raw '{"file_url":"https://lf-flow-web-cdn.doubao.com/obj/flow-doubao/samantha/logo-icon-white-bg.png"}'

{
  "fileext": "txt",
  "len": 131,
  "str": "data:text/plain;base64,5lil6l295zyw5z2a77yadqpodhrwczovl2nvzgvsb2fklmdpdgh1yi5jb20vbgfuz2dlbml1cy9kawz5l3ppcc9yzwzzl2hlywrzl21haw4="
}

{
  "error": "file_url is required"
}
 
{
    "errmsg": "invalid url 'none': no scheme supplied. perhaps you meant https://none?"
}