Python——12306图片验证码

本次爬虫，我们来模拟一下12306的验证码验证
                         

本次练习用到的模块：

• requests
• re
• base64
• urllib3

第一步，按F12查看验证码图片的信息：

提取URL：https://kyfw.12306.cn/passport/captcha/captcha-image64 （后面的参数不要）
提取requests的params参数内容：

第二步，先获取验证码的图片：

#coding=utf-8
import requests
import re
import urllib3
import base64

headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36"}
params = {
    "login_site": " E",
    "module": "login",
    "rand": "sjrand",
    "1556350688384": "",
    "callback": "jQuery1910650727092213933_1556350657738",
    "_":" 1556350657741"
}

# 1. 创建
session对象, 设置相关信息
session = requests.Session()
session.headers = headers
session.params = params

# 2. 发送请求, 是session不用管cookies
resp = session.get(url="https://kyfw.12306.cn/passport/captcha/captcha-image64", verify=False)

# 3. 数据处理
b64_image = re.findall(r'{"image":"(.*?)",', resp.text, re.S)[0]
image_data = base64.b64decode(b64_image)
with open(r"ca.jpg", "wb") as f:
    f.write(image_data)

第三步，坐标处理：

这是用来获取坐标的函数：

def position_count(args):
    """
    1 2 3 4
    5 6 7 8
    :param args:
    :return:
    """
    position_dict = {
        '1': '49,50',
        '2': '106,50',
        '3': '174,50',
        '4': '240,50',
        '5': '50,121',
        '6': '120,120',
        '7': '174,123',
        '8': '240,125',
    }
    position_data = []
    for i in args:
        position_data.append(position_dict.get(i))
    return ','.join(position_data)

在这里，我们要设置第二个params参数，传给检验验证码的url

# 4. 坐标整理
input_data = input("enter:") # 第几张图就输入几，空格分开
pic_num = input_data.split()  
pix_num = position_count(pic_num)
params = {
    "callback": "jQuery191014934245692777215_1556354228848",
    "answer": pix_num,  # answer是验证码的坐标
    "rand": "sjrand",
    "login_site": "E",
    "_": "1556354228850",
}

第四步，发送check：

这里的URL是检验验证码的URL，不是生成验证码的URL（可手动验证一次获取）

# 5. 发送check
session.params = params
resp = session.get(url="https://kyfw.12306.cn/passport/captcha/captcha-check", verify=False)
print(resp.text)

结果：

代码整合：

#coding=utf-8
import requests
import re
import urllib3
import base64

# requests关闭证书验证会警告，加上这个可以关闭警告
urllib3.disable_warnings()  
# 模拟点击验证图片
def position_count(args):
    """
    1 2 3 4
    5 6 7 8
    :param args:
    :return:
    """
    # 这是图片的坐标，模拟点击用
    position_dict = {
        '1': '49,50',
        '2': '106,50',
        '3': '174,50',
        '4': '240,50',
        '5': '50,121',
        '6': '120,120',
        '7': '174,123',
        '8': '240,125',
    }
    position_data = []
    for i in args:
        position_data.append(position_dict.get(i))
    return ','.join(position_data)



headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36"}
params = {
    "login_site": " E",
    "module": "login",
    "rand": "sjrand",
    "1556350688384": "",
    "callback": "jQuery1910650727092213933_1556350657738",
    "_":" 1556350657741"
}

# 1. 创建session对象, 设置相关信息
session = requests.Session()
session.headers = headers
session.params = params

# 2. 发送请求, 是session不用管cookies
resp = session.get(url="https://kyfw.12306.cn/passport/captcha/captcha-image64", verify=False)

# 3. 数据处理
b64_image = re.findall(r'{"image":"(.*?)",', resp.text, re.S)[0]
image_data = base64.b64decode(b64_image)
with open(r"ca.jpg", "wb") as f:
    f.write(image_data)

# 4. 坐标整理
input_data = input("enter:")
pic_num = input_data.split()
pix_num = position_count(pic_num)
params = {
    "callback": "jQuery191014934245692777215_1556354228848",
    "answer": pix_num,
    "rand": "sjrand",
    "login_site": "E",
    "_": "1556354228850",
}

# 5. 发送check
session.params = params
resp = session.get(url="https://kyfw.12306.cn/passport/captcha/captcha-check", verify=False)
print(resp.text)

END
您的支持，是我前进的动力！