Question

def get_main_page_url(urlparameter, strDestPath, strMD5):

    url = 'https://www.hybrid-analysis.com'

    session = requests.Session()

    # getting csrf value
    response = session.get(url)
    soup = bs4.BeautifulSoup(response.content)
    form = soup.form
    csrf = form.find('input', attrs = {'name':'query'})
##    csrf1 = form.find('input', attrs ={'name': 'search'}).get('value')

    # logging in
    data = {
        'query' : strMD5,
        'name' : csrf
    }

    response = session.post(urlparameter, data = data)
    soup = bs4.BeautifulSoup(response.content)
    print(soup)
    data = get_mal_page_urls(soup)
    links = []
    for link in data:
        if len(link) > 20:
            link = base_url + link
            links.append(link)
    isDownloaded = True
    for link in links:
        if (isDownloaded):
            response = session.get(link)
            soup = bs4.BeautifulSoup(response.content)
            if(None != soup.find('section', id='file').find('table')('tr')[-1].a):
                link = soup.find('section', id='file').find('table')('tr')[-1].a.get('href')
                link = base_url + link
                isDownloaded =False
                webFile = session.get(link)
##                filename =link.split('/')[-2]
                filename = strDestPath + strMD5
                localFile = open(filename, 'wb')
                localFile.write(webFile.content)
                webFile.close()
                localFile.close()
                print(filename+" file written successfully")

def main():
    arg1 = sys.argv[1]
    arg2 = sys.argv[2]

    url = 'https://www.hybrid-analysis.com/search/'
    get_main_page_url(url, arg1, arg2)

我之前为其他网站发布了相同的问题，但

malwr.com

网站上有一个用于搜索的crftoken 在这里，我想搜索给网址中提到的网站的MD5并下载文件在这里，我无法在搜索框中发布MD5，无法进入下一页，我可以找到下载链接，然后可以下载文件

没有crftoken在表单标签中搜索

0 个答案: