提取pcap文件中的请求部分的数据

from scapy.all import rdpcap  # 读pcap
import re
import sys
from urllib.request import unquote  # url解码


def extract(src):
    packets = rdpcap(str(src))
    print(repr(packets))
    for data in packets:
        res = repr(data)

        # host
        host = re.findall('Host: (.*?)\\\\r\\\\n', res)
        if len(host) > 0:
            for host_i in host:
                if '\\' not in host_i:
                    all_host.append(host_i)

        # 应用名别名
        com_name = re.findall('(com\..*?)\\\\r', res)
        if len(com_name) > 0:
            for com_name_i in com_name:
                if ('\\' or 'com.cn' or 'com.org') not in com_name_i:
                    if '&' not in com_name_i:
                        all_com_name.append(com_name_i)
                    else:
                        com_name_i = com_name_i.split('&')[0]
                        all_com_name.append(com_name_i)

        # url
        url = re.findall('GET (.*?) HTTP|POST (.*?) HTTP|PUT (.*?) HTTP', res)
        if len(url) > 0:
            for url_i in url:
                for url_o in url_i:
                    if url_o != '' and ''.join(url_o.split(' ')) != '/':
                        all_url.append(unquote(url_o))

        # cookie
        cookie = re.findall('\\\\r\\\\nCookie: (.*?)\\\\r\\\\n', res)
        if len(cookie) > 0:
            for cookie_i in cookie:
                all_cookie.append(unquote(cookie_i))


def all_host_to():
    # host
    print('*' * 50 + 'Host' + '*' * 50)
    for all in list(set(all_host)):
        print(all)


def all_name_to():
    # name
    print('*' * 50 + 'Name' + '*' * 50)
    for all in list(set(all_com_name)):
        print(all)


def all_url_to():
    # url
    print('*' * 50 + 'URL' + '*' * 50)
    for all in list(set(all_url)):
        print(all)

def all_cookie_to():
    # url
    print('*' * 50 + 'Cookie' + '*' * 50)
    for all in list(set(all_cookie)):
        print(all)


def all_ls_to():
    # 全部数据
    all_ls = all_host + all_com_name
    print('*' * 50 + '全部' + '*' * 50)
    for all in list(set(all_ls)):
        print(all)


def main(src):
    extract(src)
    all_host_to()
    all_name_to()
    all_url_to()
    all_cookie_to()
    # all_ls_to()


if __name__ == '__main__':
    all_host = []
    all_com_name = []
    all_url = []
    all_cookie = []
    # main(sys.argv[1])
    main(r'C:\Users\Administrator\Desktop\已完成\未识别应用列表\特征\360儿童卫士.pcap')