python：一个代理流量监控的媒体文件下载脚本

前言

一个mitmproxy代理服务应用，作用是监听系统流量，并自动下载可能的video媒体文件到本地。

如果你没有安装mitmproxy或没有做完准备工作，请参考我的这篇文章：

文件架构目录

源码

python 复制代码

import os
import time
import threading
import requests
from mitmproxy import http

SAME_DOWNLOADS = []

# 设置代理
proxies = {
    'http': 'http://127.0.0.1:9099',
    'https': 'http://127.0.0.1:9099'
}


def go_download(url, save_path):
    if url in SAME_DOWNLOADS:
        return
    SAME_DOWNLOADS.append(url)
    r = requests.get(url, proxies=proxies, verify=False)
    with open(save_path, 'wb') as f:
        f.write(r.content)
    print(save_path, 'saved')


# 定义资源类型分类函数
def classify_resource(flow: http.HTTPFlow):
    url = flow.request.url
    content_type = flow.response.headers.get('Content-Type', '')

    # 媒体资源
    if any(ext in url for ext in ['.mp4', '.avi', '.mov', '.mkv', '.mp3', '.wav']):
        extensions = ['.mp4', '.avi', '.mov', '.mkv', '.mp3', '.wav']
        for ext in extensions:
            if ext in url:
                filename = str(int(time.time()) * 1000) + ext
                print(filename, 'downloading')
                a = threading.Thread(target=go_download, args=(url, os.path.join('save/video', filename)))
                a.start()
                break

        return '媒体资源'
    elif 'video/' in content_type or 'audio/' in content_type:
        filename = str(int(time.time()) * 1000) + '.' + content_type.split('/')[-1]
        print(filename, 'downloading')
        a = threading.Thread(target=go_download, args=(url, os.path.join('save/video', filename)))
        a.start()
        return '媒体资源'

    # 图片资源
    if any(ext in url for ext in ['.jpg', '.jpeg', '.png', '.gif', '.bmp']):
        return '图片资源'
    elif 'image/' in content_type:
        return '图片资源'

    # 页面资源
    if 'text/html' in content_type:
        return '页面资源'

    # CSS 资源
    if any(ext in url for ext in ['.css']):
        return 'CSS 资源'
    elif 'text/css' in content_type:
        return 'CSS 资源'

    # JS 资源
    if any(ext in url for ext in ['.js']):
        return 'JS 资源'
    elif 'application/javascript' in content_type:
        return 'JS 资源'

    # API 接口资源
    if '/api/' in url.lower() or 'application/json' in content_type:
        return 'API 接口资源'

    return '其他资源'


# 请求处理函数
def response(flow: http.HTTPFlow) -> None:
    if flow.response:
        resource_type = classify_resource(flow)
        print(f"URL: {flow.request.url}")
        print(f"Resource Type: {resource_type}")
        print("-" * 50)
        # 将资源类型添加到请求的注释中
        flow.request.comment = resource_type

运行指令：

python 复制代码

mitmdump -s simply_run.py -p 9099

结果展示：