python爬蟲- requests、httpx、aiohttp、scrapy突破ja3指紋識別

requests

from requests.adapters import HTTPAdapter
from requests.packages.urllib3.util.ssl_ import create_urllib3_context
import requests
import random
ORIGIN_CIPHERS = ('ECDH+AESGCM:DH+AESGCM:ECDH+AES256:DH+AES256:ECDH+AES128:DH+AES:ECDH+HIGH:'
                  'DH+HIGH:ECDH+3DES:DH+3DES:RSA+AESGCM:RSA+AES:RSA+HIGH:RSA+3DES')


class DESAdapter(HTTPAdapter):
    def __init__(self, *args, **kwargs):
        """
        A TransportAdapter that re-enables 3DES support in Requests.
        """
        CIPHERS = ORIGIN_CIPHERS.split(':')
        random.shuffle(CIPHERS)
        CIPHERS = ':'.join(CIPHERS)
        self.CIPHERS = CIPHERS + ':!aNULL:!eNULL:!MD5'
        super().__init__(*args, **kwargs)

    def init_poolmanager(self, *args, **kwargs):
        context = create_urllib3_context(ciphers=self.CIPHERS)
        kwargs['ssl_context'] = context
        return super(DESAdapter, self).init_poolmanager(*args, **kwargs)

    def proxy_manager_for(self, *args, **kwargs):
        context = create_urllib3_context(ciphers=self.CIPHERS)
        kwargs['ssl_context'] = context
        return super(DESAdapter, self).proxy_manager_for(*args, **kwargs)

headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.131 Safari/537.36 Edg/92.0.902.67'}
s = requests.Session()
s.headers.update(headers)

for _ in range(5):
    s.mount('https://ja3er.com', DESAdapter())
    resp = s.get('https://ja3er.com/json').json()
    print(resp)

 

來源:點我

aiohttp

import random
import ssl
import asyncio
import aiohttp

# ssl._create_default_https_context = ssl._create_unverified_context


ORIGIN_CIPHERS = ('ECDH+AESGCM:DH+AESGCM:ECDH+AES256:DH+AES256:ECDH+AES128:DH+AES:ECDH+HIGH:'
                  'DH+HIGH:ECDH+3DES:DH+3DES:RSA+AESGCM:RSA+AES:RSA+HIGH:RSA+3DES')


class SSLFactory:
    def __init__(self):
        self.ciphers = ORIGIN_CIPHERS.split(":")

    def __call__(self) -> ssl.SSLContext:
        random.shuffle(self.ciphers)
        ciphers = ":".join(self.ciphers)
        ciphers = ciphers + ":!aNULL:!eNULL:!MD5"
        context = ssl.create_default_context()
        context.set_ciphers(ciphers)
        return context


sslgen = SSLFactory()
async def main():
    async with aiohttp.ClientSession() as session:
        for _ in range(5):
            async with session.get("https://ja3er.com/json", headers={}, ssl=sslgen()) as resp:
                data = await resp.json()
                print(data)

asyncio.get_event_loop().run_until_complete(main()) # 專爲win準備的寫法

  

來源:點我,且這裏面也有scrapy相關的ja3指紋修改

 

httpx

異步模式:

import httpx
import asyncio
import random
import ssl

ORIGIN_CIPHERS = ('ECDH+AESGCM:DH+AESGCM:ECDH+AES256:DH+AES256:ECDH+AES128:DH+AES:ECDH+HIGH:'
                  'DH+HIGH:ECDH+3DES:DH+3DES:RSA+AESGCM:RSA+AES:RSA+HIGH:RSA+3DES')


class SSLFactory:
    def __init__(self):
        self.ciphers = ORIGIN_CIPHERS.split(":")

    def __call__(self) -> ssl.SSLContext:
        random.shuffle(self.ciphers)
        ciphers = ":".join(self.ciphers)
        ciphers = ciphers + ":!aNULL:!eNULL:!MD5"
        context = ssl.create_default_context()
        context.set_ciphers(ciphers)
        return context


sslgen = SSLFactory()
async def main():
    async with httpx.AsyncClient(verify=sslgen()) as client:
        resp = await client.get('https://ja3er.com/json')
        result = resp.json()
        print(result)


asyncio.run(main())

  

同步模式:

import httpx
import asyncio
import random
import ssl

ORIGIN_CIPHERS = ('ECDH+AESGCM:DH+AESGCM:ECDH+AES256:DH+AES256:ECDH+AES128:DH+AES:ECDH+HIGH:'
                  'DH+HIGH:ECDH+3DES:DH+3DES:RSA+AESGCM:RSA+AES:RSA+HIGH:RSA+3DES')


class SSLFactory:
    def __init__(self):
        self.ciphers = ORIGIN_CIPHERS.split(":")

    def __call__(self) -> ssl.SSLContext:
        random.shuffle(self.ciphers)
        ciphers = ":".join(self.ciphers)
        ciphers = ciphers + ":!aNULL:!eNULL:!MD5"
        context = ssl.create_default_context()
        context.set_ciphers(ciphers)
        return context


sslgen = SSLFactory()
with httpx.Client(headers={}, http2=True, verify=sslgen()) as client:
    response = client.get('https://ja3er.com/json')
    print(response.text)

  

 

發表評論
所有評論
還沒有人評論,想成為第一個評論的人麼? 請在上方評論欄輸入並且點擊發布.
相關文章