渗透测试-----请求响应 (爬虫)

一   http请求方式连接网站数据

statusCode.py
import requests

#在路径中直接添加get方式获取路径和状态码

url='https://www.baidu.com/get'

response=requests.get(url)

print(response)

print(response.status_code)

#无参数的get获取状态码方式

url='http://www.jd.com'

r=requests.get(url=url)

print(r.status_code)

print(r.url)

#有参数的get获取状态码方式

url='https://login.taobao.com/member/login.jhtml'

#字典格式

payload={

'spm':'a21bo.2017.754894437.1.5af911d9IUfLcO',

    'f':'top',

    'redirectURL':'https%3A%2F%2Fwww.taobao.com%2F'

}

#请求方式get路径和参数

r=requests.get(url=url,params=payload)

print(r)

print(r.url)

print(r.status_code)

print(r.content)

print(r.text)

result=r.content

if str(result).find('succ'):

print('admin:admin'+'succeeful')

#请求的post方式 带参数的请求

url='https://i.taobao.com/my_taobao.htm'

params={

"spm":"a21bo.2017.754894437.3.5af911d9j6H5ku",

    "ad_id":"",

    "cm_id":"",

    "pm_id":"1501036000a02c5c3739"

}

r=requests.post(url=url,params=params)

print(r)

print(r.request)

print(r.status_code)

print(r.url)

print(r.text)

print(type(r.text))

if r.text.find('succ'):

print("successful")

url='http://www.baidu.com'

r=requests.get(url)

#得到网站请求头

r1=r.request.headers

print(r1)

#定义user-agent的值 可以改变固定值

url="http://www.jd.com"

headers={

"User-Agent":"my-sql"

}

r=requests.get(url=url,headers=headers)

print(r.request.headers)

控制台运行结果如下：

     <class 'str'>

successful

{'User-Agent': 'python-requests/2.23.0', 'Accept-Encoding': 'gzip, deflate', 'Accept': '*/*', 'Connection': 'keep-alive'}

{'User-Agent': 'my-sql', 'Accept-Encoding': 'gzip, deflate', 'Accept': '*/*', 'Connection': 'keep-alive'}

二  **  不同的http请求的不同结果

url='https://www.tmall.com/'

r=requests.get(url,params={

"ali_trackid":"2:mm_26632258_3504122_55934697:1600051047_178_2071692865",

    "clk1":"4e5c8f90d4dfbc090f056171fea55794",

    "upsid":"4e5c8f90d4dfbc090f056171fea55794",

    "bxsign":"tbk16000510475478276d5e30e98700bd0143d2d468075d8"

})

print(r.status_code)

print(r.headers)

print(r.request.headers)

print(r.encoding)

print(r.url)

#此时cookies是空目录 

print(r.cookies)

#当https的时候cookies为有数据状态    ]>

url="https://www.baidu.com"

r=requests.get(url)

print(r.cookies)

控制台输出结果

200

{'Server': 'Tengine', 'Content-Type': 'text/html; charset=utf-8', 'Transfer-Encoding': 'chunked', 'Connection': 'keep-alive', 'Vary': 'Accept-Encoding, Accept-Encoding, Origin, Ali-Detector-Type, X-Host, Accept-Encoding', 'Date': 'Mon, 14 Sep 2020 02:57:39 GMT', 'x-server-id': '28c3d6b2523ca52cb704b8b5dcd97677d231532c71c47d1b0f87559eae61f07c8bb00e660f25c2b1', 'realpath': 'page/portal/act/fp', 'Cache-Control': 'max-age=0, s-maxage=116', 'ETag': 'W/"36e89-v0m9Q3I/yOxHAam8+4z7Cz3ZtiI"', 'x-readtime': '85', 'x-via': 'cn2460.l1, bcache8.cn2460, l2cn859.l2, cache17.l2cn859, wormholesource011088033031.center.na61', 'EagleEye-TraceId': '7beb211c16000522590061050e', 'Strict-Transport-Security': 'max-age=0, max-age=31536000', 'Timing-Allow-Origin': '*, *', 'Ali-Swift-Global-Savetime': '1600052259', 'Via': 'cache17.l2cn859[176,200-0,C], cache35.l2cn859[15,0], bcache2.cn2583[0,200-0,H], bcache4.cn2583[1,0]', 'Age': '99', 'X-Cache': 'HIT TCP_MEM_HIT dirn:-2:-2', 'X-Swift-SaveTime': 'Mon, 14 Sep 2020 02:57:39 GMT', 'X-Swift-CacheTime': '116', 'EagleId': '3cdd499816000523589496905e', 'Content-Encoding': 'gzip'}

{'User-Agent': 'python-requests/2.23.0', 'Accept-Encoding': 'gzip, deflate', 'Accept': '*/*', 'Connection': 'keep-alive'}

utf-8

https://www.tmall.com/?ali_trackid=2%3Amm_26632258_3504122_55934697%3A1600051047_178_2071692865&clk1=4e5c8f90d4dfbc090f056171fea55794&upsid=4e5c8f90d4dfbc090f056171fea55794&bxsign=tbk16000510475478276d5e30e98700bd0143d2d468075d8

<RequestsCookieJar[]>

<RequestsCookieJar[<Cookie BDORZ=27315 for .baidu.com/>]>