我正在尝试使CAPTCHA自动化,为此我也编写了python代码。现在,我陷入了困境,即无法通过创建自定义库在Robot Framework中调用它。
from PIL import Image
import string
import json
import os
import time
import pytesseract
import cv2
import numpy as np
import re
from tesserocr import PyTessBaseAPI,PSM, OEM
import time
import logging
captcha_url = "http://www.mca.gov.in/mcafoportal/getCapchaImage.do"
regex = re.compile(r'[\n\r\t ]')#special char plus space
def get_captcha2(session):
res = session.get(captcha_url, timeout = 10)
with open("a.jpg", "wb") as f: f.write(res.content)
img = Image.open("a.jpg")
captcha = pytesseract.image_to_string(img, config='--psm 8 --oem 0 -c tessedit_char_whitelist=abcdefghijklmnopqrstuvwxyz')
logging.info("cap: %s"%captcha)
while not (captcha.islower() and captcha.isalpha() and len(captcha) in [6,7]):
time.sleep(.05)
res = session.get(captcha_url)
with open("a.jpg", "wb") as f: f.write(res.content)
img = Image.open("a.jpg")
captcha = pytesseract.image_to_string(img, config='--psm 8')
logging.info("cap: %s"%captcha)
return captcha
def get_captcha(req):
api = PyTessBaseAPI(psm=PSM.SINGLE_WORD, oem = 0)
api.SetVariable("tessedit_char_whitelist", "abcdefghijklmnopqrstuvwxyz")
res = req.get(captcha_url, timeout = 10)
#with open("a.jpg", "wb") as f: f.write(res.content)
clean_captcha_image(api, res.content)
captcha = regex.sub("", api.GetUTF8Text())
conf = api.MeanTextConf()
cnt = 0
while (len(captcha) not in [6,7] or conf<=70) and cnt<=3:
res = req.get(captcha_url, timeout = 10)
clean_captcha_image(api, res.content)
captcha = regex.sub("", api.GetUTF8Text())
conf = api.MeanTextConf()
cnt += 1
return captcha
def break_point(arr):
for i,n in arr:
if n:
break
return i
def convert_numpy_ipl(trimmed):
h,w = trimmed.shape
c = 1
iplimage = cv.CreateImageHeader((w,h), cv.IPL_DEPTH_8U, c)
cv.SetData(iplimage, trimmed.tostring(),trimmed.dtype.itemsize * c * (w))
return iplimage
def clean_captcha_image(api, c_content):
try:
arr = np.fromstring(c_content, np.uint8)
image = cv2.imdecode(arr,0)
th = cv2.threshold(image,50,255,cv2.THRESH_BINARY|cv2.THRESH_OTSU)[1]
iplimage = Image.fromarray(th)
api.SetImage(iplimage)
except Exception as e:
print("Unexpected error on clean ",e)
def parse_captcha(filename):
return pytesseract.image_to_string(Image.open(filename))
if __name__ == "__main__":
import requests
session = requests.Session()
session.headers = {"User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.87 Safari/537.36"}
get_captcha2(session)
我尝试使用Robot Framework自动执行相同操作,但由于会话超时而失败。当我尝试下载图像时,验证码已更改。
请按照以下步骤从机器人文件中获取调用的功能,
步骤1:使用以下函数创建python文件:C:\ Users \ kgurupra \ pyfirst.py
def message(msg):
print ('your message is ' + msg)
return True
第2步:确保PYTHONPATH中的.py文件非常重要
第3步:如下所述创建您的机器人文件,
*** Settings ***
Library String
Library Collections
Library Selenium2Library
**Library pyfirst.py**
*** Test Cases ***
Case1
message "hello"
步骤4:您应该看到如下所示的输出,
(rf1) C:\Users\kgurupra>robot rbpy.robot
==============================================================================
Rbpy
==============================================================================
Case1 | PASS |
------------------------------------------------------------------------------
Rbpy | PASS |
1 critical test, 1 passed, 0 failed
1 test total, 1 passed, 0 failed
==============================================================================
Output: C:\Users\kgurupra\output.xml
Log: C:\Users\kgurupra\log.html
Report: C:\Users\kgurupra\report.html
版权声明:本文内容由阿里云实名注册用户自发贡献,版权归原作者所有,阿里云开发者社区不拥有其著作权,亦不承担相应法律责任。具体规则请查看《阿里云开发者社区用户服务协议》和《阿里云开发者社区知识产权保护指引》。如果您发现本社区中有涉嫌抄袭的内容,填写侵权投诉表单进行举报,一经查实,本社区将立刻删除涉嫌侵权内容。