import re
import os
import base64
#import ast
from urllib import parse
from datetime import datetime
import cv2
import random
import requests
import time
import redis
from scrapy import Selector
from selenium import webdriver
from selenium.webdriver import ActionChains
from PIL import Image
domain = "http://www.91jf.com/"
domain_log = "http://www.91jf.com/default.php?url=member&act=memberinfo"
#IMAGE_URL = "http://www.91jf.com/default.php?act=code"
chrome_options = webdriver.ChromeOptions()
path = r'D:project_91jiafangwanchromedriver.exe'
browser = webdriver.Chrome(executable_path=path, chrome_options=chrome_options)
def get_captcha(filename):
"""
访问验证码解析API，解析图片验证码
:param filename:
:return:
"""
CAPTCHA_PATH = 'http://192.168.3.9:8888/captcha'
with open(filename, "rb") as f:
image_base64 = base64.b64encode(f.read())
payload = {'image': image_base64}
while True:
response = requests.request("POST", CAPTCHA_PATH, data=payload)
if response.status_code == 200:
if response.json().get('code') == 200:
return response.json().get('text')
else:
print(response.json().get('err'))
return '1234'
else:
print('验证码网络无法访问，请确认网络情况')
time.sleep(10)
def log_in():
browser.get(domain_log)
browser.maximize_window()
slider = browser.find_element_by_xpath("//img[@onclick='show_user_login()']")
ActionChains(browser).click(slider).perform()
ActionChains(browser).release().perform()
#IMAGE_URL = "http://www.91jf.com/default.php?act=code"
# 截取当前网页并放到D盘下命名为printscreen，该网页有我们需要的验证码
browser.save_screenshot('./image/printscreen.png')
img_ele = browser.find_element_by_xpath("//img[@src='default.php?act=code']")
location = img_ele.location # 获取验证码x,y轴坐标
size = img_ele.size # 获取验证码的长宽
rangle = (int(location['x']), int(location['y']), int(location['x'] + size['width']),
int(location['y'] + size['height'])) # 写成我们需要截取的位置坐标
i = Image.open("./image/printscreen.png") # 打开截图
frame4 = i.crop(rangle) # 使用Image的crop函数，从截图中再次截取我们需要的区域
frame4 = frame4.convert('RGB')
frame4.save('./image/save.jpg') # 保存我们接下来的验证码图片 进行打码
username = "18206275210"
password = "czx0711."
username_ele = browser.find_element_by_xpath("//input[@name='username']")
password_ele = browser.find_element_by_xpath("//input[@name='password']")
username_ele.send_keys(username)
password_ele.send_keys(password)
time.sleep(2)
#request_download(IMAGE_URL)
image = cv2.imread('./image/save.jpg')
cv2.imshow("image",image)
cv2.waitKey(0)
pic = get_captcha('./image/save.jpg')
pic_ele = browser.find_element_by_xpath("//input[@name='t_code']")
pic_ele.send_keys(pic)
time.sleep(2)
slider = browser.find_element_by_xpath("//div[@class='login_but']")
ActionChains(browser).click(slider).perform()
ActionChains(browser).release().perform()
def request_download(IMAGE_URL):
os.makedirs('./image/', exist_ok=True)
import requests
r = requests.get(IMAGE_URL)
with open('./image/img'+ '0' + '.jpg', 'wb') as f:
f.write(r.content)
'''
for i in range(1000):
request_download(str(i))
time.sleep(random.randint(1,4))
'''
log_in()
'''
image = cv2.imread('./image/img0.jpg')
cv2.imshow("image",image)
cv2.waitKey(0)
'''