python 常见的反爬虫策略

import hashlib
print(hashlib.md5('python'.encode()).hexdigest())

import base64

#python中base64的加密
print(base64.b64encode('python'.encode()).decode())
#python中base64的解密
print(base64.b64decode('Y2hpbmE='.encode()).decode())

import requests

url = "gushiwen.org"

session = requests.Session()

text = session.get(url).text

# 解析响应，找到验证码的图片地址，
# 下载验证码图片，保存
with open('code.jpg', 'wb')as f:
  f.write('验证码的url地址'.encode())

code = input('验证码是: ')

login_url = "login.com"

data = {
  "username": 'xx',
  "password": 'xx',
  "code": code
}
requests.post(url, data=data)

import json
import requests
import base64
from io import BytesIO
from PIL import Image
from sys import version_info


def base64_api(uname, pwd, img):
  img = img.convert('RGB')
  buffered = BytesIO()
  img.save(buffered, format="JPEG")
  if version_info.major >= 3:
    b64 = str(base64.b64encode(buffered.getvalue()), encoding='utf-8')
  else:
    b64 = str(base64.b64encode(buffered.getvalue()))
  data = {"username": uname, "password": pwd, "image": b64}
  result = json.loads(requests.post("http://api.ttshitu.com/base64", json=data).text)
  if result['success']:
    return result["data"]["result"]
  else:
    return result["message"]
  return ""


def request_captcha(uname, pwd, img_path):
  img_path = img_path # 待验证的验证码路径
  img = Image.open(img_path)
  result = base64_api(uname, pwd, img)
  # 传入账号 密码 和图片
  print(result)

img_path = '图片路径'

from captcha_api import request_captcha

ret = request_captcha("账号", "密码", img_path)