Python爬虫多次请求后被要求验证码的应对策略

Python

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

23

24

25

26

27

28

29

30

31

32

33

34

35

36

37

38

39

40

41

42

43

44

45

46

47

48

49

50

51

52

53

54

55

import requests

import time

import random

import pytesseract

from PIL import Image

from io import BytesIO

# 配置

captcha_url = "http://example.com/captcha.jpg"

target_url = "http://example.com/data"

headers = {

"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3",

"Referer": "http://example.com"

}

# 代理信息

proxyHost = "www.16yun.cn"

proxyPort = "5445"

proxyUser = "16QMSOML"

proxyPass = "280651"

# 构造代理字典

proxies = {

"http": f"http://{proxyUser}:{proxyPass}@{proxyHost}:{proxyPort}",

"https": f"http://{proxyUser}:{proxyPass}@{proxyHost}:{proxyPort}"

}

def fetch_captcha():

# 使用代理请求验证码图片

response = requests.get(captcha_url, headers=headers, proxies=proxies)

image = Image.open(BytesIO(response.content))

captcha_text = pytesseract.image_to_string(image)

return captcha_text

def fetch_data_with_captcha(captcha_text):

data = {

"captcha": captcha_text

}

# 使用代理发送请求

response = requests.post(target_url, headers=headers, data=data, proxies=proxies)

return response

def main():

while True:

captcha_text = fetch_captcha()

response = fetch_data_with_captcha(captcha_text)

if response.status_code == 200:

print("数据获取成功：", response.text)

break

else:

print("验证码错误或请求失败，重新尝试...")

time.sleep(random.uniform(1, 3))  # 随机停留1到3秒

if __name__ == "__main__":

main()