def get_code(driver, location):
"""
返回验证码识别的内容
:param pic:
:return:
"""
pic_1 = temporary + os.sep + str(time.time()) + ".png"
# 1.先截图
driver.save_screenshot(pic_1)
# 2.把验证码图抠出来
ce = driver.find_element(*location)
left = ce.location['x']
top = ce.location['y']
right = ce.size['width'] + left
height = ce.size['height'] + top
# 3.保存抠的图
im = Image.open(pic_1)
img = im.crop((left, top, right, height))
pic_2 = temporary + os.sep + str(time.time()) + '.png'
img.save(pic_2)
cjy = Chaojiying_Client('18301085980', 'star000',
'909506') # 用户中心>>软件ID 生成一个替换 96001
im = open(pic_2, 'rb').read()
return cjy.PostPic(im, 1902)['pic_str']
def change_pwd(self, brower, wait):
brower.find_element_by_xpath('//a[text()="修改密码"]').click()
wait.until(
EC.presence_of_element_located(
(By.XPATH,
'//input[@name="oldpwd"]'))).send_keys(self.password)
if self.password == 'salesmind1800':
newpassword = '******'
else:
newpassword = '******'
wait.until(
EC.presence_of_element_located(
(By.XPATH,
'//input[@name="user_pwd"]'))).send_keys(newpassword)
wait.until(
EC.presence_of_element_located(
(By.XPATH, '//input[@data-nick="ok_new_password"]'
))).send_keys(newpassword)
while True:
imgelement = wait.until(
EC.presence_of_element_located(
(By.XPATH, '//img[@data-selector="ver-code"]')))
location = imgelement.location # 获取滑条x,y轴坐标
if location['x'] == 0:
return
brower.save_screenshot(BASE_DIR + '/' +
'liepin_.png') # 截取当前网页，该网页有我们需要的验证码
size = imgelement.size # 获取滑条的长宽
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(BASE_DIR + '/' + "liepin_.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.save(BASE_DIR + '/' + 'liepinyzm.png')
chaojiying = Chaojiying_Client('jackie1102', 'salesmind1800',
'1902')
im = open(BASE_DIR + '/' + 'liepinyzm.png', 'rb').read()
res = chaojiying.PostPic(im, 1902)
pic_str = res['pic_str']
os.remove(BASE_DIR + '/' + "liepin_.png")
os.remove(BASE_DIR + '/' + "liepinyzm.png")
inpt = brower.find_element_by_xpath('//input[@name="verifycode"]')
inpt.clear()
time.sleep(1)
inpt.send_keys(pic_str)
time.sleep(1)
brower.find_element_by_xpath('//button[@type="submit"]').click()
time.sleep(1)
try:
button = brower.find_element_by_xpath('//a[@data-name="ok"]')
if button:
chaojiying.ReportError(res['pic_id'])
button.click()
time.sleep(2)
imgelement.click()
except:
break
time.sleep(1)
return newpassword
def login(self):
self.driver.get('https://ehire.51job.com/')
js1 = "document.getElementsByClassName('headerBanner')[0].style.display='none'"
js2 = "document.getElementsByClassName('topHeader')[0].style.display='none'"
self.driver.execute_script(js1)
self.driver.execute_script(js2)
self.wait.until(EC.presence_of_element_located((By.XPATH, '//*[@id="txtMemberNameCN"]'))).send_keys(
self.vipname)
self.wait.until(EC.presence_of_element_located((By.XPATH, '//*[@id="txtUserNameCN"]'))).send_keys(self.username)
self.wait.until(EC.presence_of_element_located((By.XPATH, '//*[@id="txtPasswordCN"]'))).send_keys(self.password)
self.wait.until(EC.presence_of_element_located((By.XPATH, '//*[@id="btnBeginValidate"]'))).click()
while True:
time.sleep(1)
imgelement = self.driver.find_element_by_xpath('//*[@id="divValidateHtml"]/div') # 定位验证码
self.driver.save_screenshot('aa.png') # 截取当前网页，该网页有我们需要的验证码
location = imgelement.location # 获取验证码x,y轴坐标
print(location)
if location['x'] == 0:
return
size = imgelement.size # 获取验证码的长宽
print(size['width'])
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("aa.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.save('frame4.png')
chaojiying = Chaojiying_Client('jackie1102', 'salesmind1800', '9004')
im = open('frame4.png', 'rb').read()
while True:
try:
res = chaojiying.PostPic(im, 9004)
except Exception as E:
print(E)
time.sleep(2)
continue
break
content = res['pic_str'].split('|')
loc_list = []
for i in content:
loc = i.split(',')
loc_list.append(loc)
action = ActionChains(self.driver)
for loca in loc_list:
action.move_to_element_with_offset(imgelement, int(loca[0]), int(loca[1])).click()
action.pause(1)
action.perform()
time.sleep(1)
self.wait.until(EC.presence_of_element_located((By.LINK_TEXT, '验 证'))).click()
time.sleep(1)
success = self.driver.find_element_by_xpath('//*[@id="btnEndValidate"]').text
if success == '验证通过':
break
else:
chaojiying.ReportError(res['pic_id'])
time.sleep(3)
self.driver.find_element_by_xpath('//*[@id="Login_btnLoginCN"]').click()
def __init__(self):
"""
初始化
"""
self.url = URL
self.browser = webdriver.Chrome()
self.wait = WebDriverWait(self.browser, TIME_OUT)
# 简书登录账号、密码
self.email = EMAIL
self.password = PASSWORD
# 创建超级鹰Client对象
self.chaojiying = Chaojiying_Client(CHAIJIYING_USERNAME, CHAOJIYING_PASSWORD, CHAIJIYING_SOFT_ID)
def yzm1(self):
while True:
# 定位滑条
imgelement1 = self.wait.until(
EC.presence_of_element_located(
(By.XPATH, '//*[@id="nc_1__scale_text"]')))
self.driver.save_screenshot('qichacha.png') # 截取当前网页，该网页有我们需要的验证码
location = imgelement1.location # 获取滑条x,y轴坐标
size1 = imgelement1.size # 获取滑条的长宽
# 定位验证码
try:
imgelement2 = self.driver.find_element_by_xpath(
'//*[@id="nc_1_clickCaptcha"]')
except:
return
size2 = imgelement2.size # 获取验证码的长宽
rangle = (int(location['x']), int(location['y']),
int(location['x'] + size1['width']),
int(location['y'] + size1['height'] + size2['height'])
) # 写成我们需要截取的位置坐标
i = Image.open("qichacha.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.save('qichachayzm.png')
chaojiying = Chaojiying_Client('jackie1102', 'salesmind1800',
'9101')
im = open('qichachayzm.png', 'rb').read()
res = chaojiying.PostPic(im, 9101)
content = res['pic_str']
loca = content.split(',')
action = ActionChains(self.driver)
action.move_to_element_with_offset(imgelement1, int(loca[0]),
int(loca[1]))
action.click()
action.perform()
time.sleep(1)
try:
text = self.driver.find_element_by_xpath(
'//*[@id="nc_1__scale_text"]/span/b').text
if text == '验证通过':
break
except Exception:
# print('验证失败')
chaojiying.ReportError(res['pic_id'])
time.sleep(1)
try:
self.driver.find_element_by_xpath('//*[@id="verify"]').click()
time.sleep(1)
except:
pass
def yzm2(self):
while True:
imgelement = self.wait.until(
EC.presence_of_element_located(
(By.XPATH, '//*[@id="nc_1__imgCaptcha_img"]/img')))
location = imgelement.location # 获取滑条x,y轴坐标
if location['x'] == 0:
return
self.driver.save_screenshot('qichacha.png') # 截取当前网页，该网页有我们需要的验证码
size = imgelement.size # 获取滑条的长宽
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("qichacha.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.save('qichachayzm.png')
chaojiying = Chaojiying_Client('jackie1102', 'salesmind1800',
'1902')
im = open('qichachayzm.png', 'rb').read()
res = chaojiying.PostPic(im, 1902)
pic_str = res['pic_str']
os.remove("qichacha.png")
os.remove("qichachayzm.png")
inpt = self.driver.find_element_by_xpath(
'//*[@id="nc_1_captcha_input"]')
inpt.clear()
time.sleep(1)
inpt.send_keys(pic_str)
time.sleep(1)
self.driver.find_element_by_xpath(
'//*[@id="nc_1_scale_submit"]/span').click()
time.sleep(1)
try:
txt = self.driver.find_element_by_xpath(
'//*[@id="nc_1__captcha_img_text"]/span').text
if txt:
chaojiying.ReportError(res['pic_id'])
time.sleep(2)
except:
break
time.sleep(1)
try:
self.driver.find_element_by_xpath('//*[@id="verify"]').click()
time.sleep(1)
except:
pass
from lxml import etree
import base64
from utils import rsa
from utils.chaojiying import Chaojiying_Client
import private
from base import Request
import re
chaojiying = Chaojiying_Client(private.CODE_USERNAME, private.CODE_PASSWORD, private.CODE_NUMBER)
class YiLogin(Request):
'''
直接通过模拟易班登录方式进行登录
'''
def __init__(self, username, password):
self.headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.120 Safari/537.36',
}
self.headers2 = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.120 Safari/537.36',
'X-Requested-With': 'XMLHttpRequest',
}
self.username = username
self.password = password
def login(self):
cookies, public_key = self.access()
# 进行加密
password = self._encrypt(self.password, public_key)
class Crack_Jianshu(object):
def __init__(self):
"""
初始化
"""
self.url = URL
self.browser = webdriver.Chrome()
self.wait = WebDriverWait(self.browser, TIME_OUT)
# 简书登录账号、密码
self.email = EMAIL
self.password = PASSWORD
# 创建超级鹰Client对象
self.chaojiying = Chaojiying_Client(CHAIJIYING_USERNAME, CHAOJIYING_PASSWORD, CHAIJIYING_SOFT_ID)
def __del__(self):
"""
gc机制关闭浏览器
"""
self.browser.close()
def open(self):
"""
打开简书网页版登录界面输入邮箱账号、密码
:return: None
"""
self.browser.get(self.url)
# 邮箱
email = self.wait.until(EC.presence_of_element_located((By.ID, 'session_email_or_mobile_number')))
# 密码
password = self.wait.until(EC.presence_of_element_located((By.ID, 'session_password')))
# 输入邮箱
email.clear()
email.send_keys(self.email)
sleep(2)
# 输入密码
password.clear()
password.send_keys(self.password)
sleep(2)
def get_submit_btn(self):
"""
获取登录按钮
:return: button
"""
button = self.wait.until(EC.element_to_be_clickable((By.ID, 'sign-in-form-submit-btn')))
return button
def get_touclick_element(self):
"""
获取验证码图片对象
:return: 图片对象
"""
element = self.wait.until(EC.presence_of_element_located((By.CLASS_NAME, 'geetest_item_img')))
return element
def get_code_position(self):
"""
获取验证码位置
:return: 验证码位置列表
"""
element = self.get_touclick_element()
sleep(3)
# 相对位置
location = element.location
# 宽高度
size = element.size
# 坐标值
top, bottom, left, right = location['y'], location['y'] + size['height'], location['x'], location['x'] + size['width']
# 验证码左上角和右下角坐标
return [left, top, right, bottom]
def get_screenshot(self):
"""
获取网页截图
:return: 截图对象
"""
screenshot = self.browser.get_screenshot_as_png()
screenshot = Image.open(BytesIO(screenshot))
return screenshot
def get_touclick_image(self, name='captcha.png'):
"""
获取验证码图片
:return: 图片对象
"""
left, top, right, bottom = self.get_code_position()
print('验证码位置：', left, top, right, bottom)
# 获取网页截图的Image对象
screenshot = self.get_screenshot()
# 获取验证码的Image对象
jianshu_code = screenshot.crop((left, top, right, bottom))
# 存储
jianshu_code.save(name)
return jianshu_code
def get_points(self, captcha_result):
"""
解析超级鹰识别结果
:param captcha_result: 识别结果
:return: 转化结果
"""
# 获取pic_str的values
groups = captcha_result.get('pic_str').split('|')
# 将 字符串坐标值 转换为 整数型的坐标值
locations = [[int(number) for number in group.split(',')] for group in groups]
return locations
def touch_click_words(self, locations):
"""
点击验证图片
:param locations: 点击位置
:return: None
"""
cnt = 1
for location in locations:
print('坐标点{}: {}'.format(cnt,location))
ActionChains(self.browser).move_to_element_with_offset(self.get_touclick_element(),location[0], location[1]).click().perform()
cnt = cnt + 1
sleep(1)
def get_verifi_button(self):
"""
确认按钮
:return: None
"""
submit = self.wait.until(EC.presence_of_element_located((By.XPATH, '//*[@class="geetest_commit_tip"]')))
submit.click()
def get_article_info(self):
pass
def connect_db(self):
pass
def save_to_db(self):
pass
def crack_login(self):
"""
登录
:return: None
"""
# 打开简书登录界面
self.open()
# 点击登录按钮
button = self.get_submit_btn()
button.click()
# 获取验证码图片
image = self.get_touclick_image()
bytes_array = BytesIO()
# 存储为字节流格式
image.save(bytes_array, format='PNG')
# 识别验证码
result = self.chaojiying.PostPic(bytes_array.getvalue(), CHAOJIYING_KIND)
print("\n超级鹰识别结果：{}\n".format(result))
locations = self.get_points(result)
self.touch_click_words(locations)
sleep(3)
# 点击确认按钮
self.get_verifi_button()
# 通过获取"Logo"判断是否登录成功
sleep(5)
success = self.wait.until(EC.presence_of_element_located((By.CLASS_NAME, 'logo')))
if success:
print('\nSuccessful login!\n')
# 失败重试
if not success:
print("-" * 50)
self.crack_login()
def check_yzm(self):
"""
验证码处理：
1·捕获验证码，对当前页面进行截屏
2·定位验证码图片位置，并从截屏中提取
3·调用打码平台，破解验证码，返回验证码参数
4·对验证码参数进一步处理，并模拟人工操作破解验证码
5·验证是否破解成功，否则发送验证失败api
:return:
"""
while True:
try:
imgelement = self.driver.find_element_by_xpath('//*[@id="divValidateHtml"]/div') # 定位验证码
self.driver.save_screenshot('aa.png') # 截取当前网页，该网页有我们需要的验证码
location = imgelement.location # 获取验证码x,y轴坐标
if location['x'] == 0:
return
size = imgelement.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("aa.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.save('frame4.png')
chaojiying = Chaojiying_Client('jackie1102', 'salesmind1800', '9004')
im = open('frame4.png', 'rb').read()
while True:
try:
res = chaojiying.PostPic(im, 9004)
except Exception as E:
print(E)
time.sleep(2)
continue
break
content = res['pic_str'].split('|')
print(res)
loc_list = []
for i in content:
loc = i.split(',')
loc_list.append(loc)
action = ActionChains(self.driver)
for loca in loc_list:
action.move_to_element_with_offset(imgelement, int(loca[0]), int(loca[1])).click()
action.pause(1)
action.perform()
time.sleep(1)
self.wait.until(EC.presence_of_element_located((By.LINK_TEXT, '验 证'))).click()
time.sleep(1)
self.driver.refresh()
imgelement = self.driver.find_element_by_xpath('//*[@id="divValidateHtml"]/div') # 定位验证码
print(imgelement, '111111')
self.driver.save_screenshot('d://aa.png') # 截取当前网页，该网页有我们需要的验证码
location = imgelement.location # 获取验证码x,y轴坐标
print(location)
if location['x'] == 0:
print('验证成功')
else:
print('验证失败')
chaojiying.ReportError(res['pic_id'])
time.sleep(3)
except:
print('没有出现验证码')
break
def login(self):
chrome_options = Options()
chrome_options.add_argument('window-size=1920x2000') # 指定浏览器分辨率
chrome_options.add_argument('--disable-gpu') # 谷歌文档提到需要加上这个属性来规避bug
chrome_options.add_argument('--hide-scrollbars') # 隐藏滚动条, 应对一些特殊页面
chrome_options.add_argument(
'--headless') # 浏览器不提供可视化页面. linux下如果系统不支持可视化不加这条会启动失败
# brower = webdriver.Chrome(chrome_options=chrome_options)
brower = webdriver.Chrome()
brower.maximize_window()
wait = WebDriverWait(brower, 10)
brower.get('https://passport.liepin.com/e/account')
url1 = brower.current_url
while True:
yz_error = False
newpassword = None
if self.sign == 0:
wait.until(
EC.presence_of_element_located((
By.XPATH,
'//*[@id="user-reglpt"]/div[1]/div[2]/div/div[1]/ul/li[2]'
))).click()
user = wait.until(
EC.presence_of_element_located((
By.XPATH,
'//section[@data-selector="PC"]//input[@name="user_login"]'
)))
user.clear()
for item in self.username:
user.send_keys(item)
time.sleep(random.uniform(0.3, 0.6))
time.sleep(1)
pwd = wait.until(
EC.presence_of_element_located((
By.XPATH,
'//section[@data-selector="PC"]//input[@name="user_pwd"]'
)))
pwd.clear()
for item in self.password:
pwd.send_keys(item)
time.sleep(random.uniform(0.3, 0.6))
time.sleep(1)
wait.until(
EC.presence_of_element_located(
(By.XPATH, '//*[@id="verify-button"]'))).click()
while True:
if self.sign == 0:
imgelement = brower.find_element_by_xpath(
'//*[@id="captcha"]/iframe') # 定位验证码
location = imgelement.location # 获取验证码x,y轴坐标
if location['x'] == 0:
return
brower.save_screenshot(
'liepin.png') # 截取当前网页，该网页有我们需要的验证码
size = imgelement.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('liepin.png') # 打开截图
frame = 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
frame.save('liepinframe.png')
chaojiying = Chaojiying_Client('jackie1102',
'salesmind1800', '9004')
im = open('liepinframe.png', 'rb').read()
while True:
try:
res = chaojiying.PostPic(im, 9004)
except Exception as E:
time.sleep(2)
continue
break
os.remove('liepin.png')
os.remove('liepinframe.png')
content = res['pic_str'].split('|')
loc_list = []
for i in content:
loc = i.split(',')
loc_list.append(loc)
action = ActionChains(brower)
for loca in loc_list:
action.move_to_element_with_offset(
imgelement, int(loca[0]),
int(loca[1])).click()
action.move_to_element_with_offset(
imgelement, 210, 245).click()
action.perform()
time.sleep(5)
url2 = brower.current_url
for i in range(2):
if url1 != url2:
try:
node = brower.find_element_by_xpath(
'//h1[text()="账号登录异常"]')
if node:
newpassword = self.change_pwd(
brower, wait)
brower.find_element_by_xpath(
'//*[text()="立即登录"]').click()
break
except:
break
else:
time.sleep(3)
else:
yz_error = True
break
else:
break
if yz_error:
continue
if newpassword:
self.password = newpassword
task = SpiderTask.objects.get_one_task(id=self.task_id)
data = json.loads(task.param)
data["password"] = newpassword
task.param = json.dumps(data)
task.save()
continue
cookie = [
item["name"] + "=" + item["value"]
for item in brower.get_cookies()
]
cookiestr = '; '.join(item for item in cookie)
print(cookiestr)
self.headers = {
'User-Agent':
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36',
'Cookie': cookiestr,
'X-Requested-With': 'XMLHttpRequest',
'Referer':
'https://lpt.liepin.com/cvsearch/showcondition/',
'Host': 'lpt.liepin.com',
'Origin': 'https://lpt.liepin.com'
}
brower.quit()
break
else:
break
def yzm(self):
"""
浏览器模拟登陆处理验证码
:return:
"""
driver = self.login()
driver.get('https://antirobot.tianyancha.com/captcha/verify?')
time.sleep(2)
while True:
try:
imgelement = self.driver.find_element_by_xpath(
'//div[@class="new-box94"]') # 定位验证码
self.driver.save_screenshot(
'tianyancha.png') # 截取当前网页，该网页有我们需要的验证码
location = imgelement.location # 获取验证码x,y轴坐标
if location['x'] == 0:
return
size = imgelement.size # 获取验证码的长宽
# print(size['width'])
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("tianyancha.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.save('frame_tyc.png')
chaojiying = Chaojiying_Client('jackie1102', 'salesmind1800',
'9004')
im = open('frame_tyc.png', 'rb').read()
while True:
try:
res = chaojiying.PostPic(im, 9004)
except Exception as E:
# print(E)
continue
break
content = res['pic_str'].split('|')
loc_list = []
for i in content:
loc = i.split(',')
loc_list.append(loc)
action = ActionChains(self.driver)
for loca in loc_list:
action.move_to_element_with_offset(imgelement,
int(loca[0]),
int(loca[1])).click()
action.perform()
time.sleep(1)
self.wait.until(
EC.presence_of_element_located(
(By.XPATH, '//*[@id="submitie"]'))).click()
time.sleep(1)
self.driver.refresh()
imgelement = self.driver.find_element_by_xpath(
'//div[@class="new-box94"]') # 定位验证码
location = imgelement.location # 获取验证码x,y轴坐标
if location['x'] == 0:
# print('验证成功')
break
else:
# print('验证失败')
chaojiying.ReportError(res['pic_id'])
except Exception:
break
driver.quit()
def login(self):
"""
登录网站
:return:
"""
chrome_options = Options()
chrome_options.add_argument('window-size=1920x1500') # 指定浏览器分辨率
chrome_options.add_argument('--disable-gpu') # 谷歌文档提到需要加上这个属性来规避bug
chrome_options.add_argument('--hide-scrollbars') # 隐藏滚动条, 应对一些特殊页面
chrome_options.add_argument(
'--headless') # 浏览器不提供可视化页面. linux下如果系统不支持可视化不加这条会启动失败
# driver = webdriver.Chrome()
driver = webdriver.Chrome(chrome_options=chrome_options)
driver.maximize_window()
wait = WebDriverWait(driver, 5)
driver.get('https://ehire.51job.com/')
time.sleep(1)
while True:
wait.until(
EC.presence_of_element_located(
(By.XPATH,
'//*[@id="txtMemberNameCN"]'))).send_keys(self.vipname)
wait.until(
EC.presence_of_element_located(
(By.XPATH,
'//*[@id="txtUserNameCN"]'))).send_keys(self.username)
wait.until(
EC.presence_of_element_located(
(By.XPATH,
'//*[@id="txtPasswordCN"]'))).send_keys(self.password)
wait.until(
EC.presence_of_element_located(
(By.XPATH, '//*[@id="btnBeginValidate"]'))).click()
time.sleep(1)
while True:
imgelement = driver.find_element_by_xpath(
'//*[@id="divValidateHtml"]/div') # 定位验证码
location = imgelement.location # 获取验证码x,y轴坐标
if location['x'] == 0:
return
driver.save_screenshot(BASE_DIR + '/' + self.table_name +
'_job.png') # 截取当前网页，该网页有我们需要的验证码
size = imgelement.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(BASE_DIR + '/' + self.table_name +
'_job.png') # 打开截图
frame = 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
frame.save(BASE_DIR + '/' + self.table_name + 'frame.png')
chaojiying = Chaojiying_Client('jackie1102', 'salesmind1800',
'9004')
im = open(BASE_DIR + '/' + self.table_name + 'frame.png',
'rb').read()
while True:
try:
res = chaojiying.PostPic(im, 9004)
except Exception as E:
time.sleep(2)
continue
break
os.remove(BASE_DIR + '/' + self.table_name + '_job.png')
os.remove(BASE_DIR + '/' + self.table_name + 'frame.png')
content = res['pic_str'].split('|')
loc_list = []
for i in content:
loc = i.split(',')
loc_list.append(loc)
action = ActionChains(driver)
for loca in loc_list:
action.move_to_element_with_offset(imgelement,
int(loca[0]),
int(loca[1])).click()
action.perform()
time.sleep(1)
wait.until(
EC.presence_of_element_located(
(By.LINK_TEXT, '验 证'))).click()
time.sleep(1)
success = driver.find_element_by_xpath(
'//*[@id="btnEndValidate"]').text
if success == '验证通过':
break
else:
chaojiying.ReportError(res['pic_id'])
time.sleep(3)
driver.find_element_by_xpath('//*[@id="Login_btnLoginCN"]').click()
try:
wait.until(
EC.presence_of_element_located(
(By.XPATH, '//a[text()="强制下线"]'))).click()
time.sleep(2)
url = driver.current_url
if 'Navigate.aspx?' in url:
break
else:
continue
except:
break
time.sleep(5)
cookie = [
item["name"] + "=" + item["value"]
for item in driver.get_cookies()
]
cookiestr = '; '.join(item for item in cookie)
print(cookiestr)
driver.quit()
return cookiestr
def login(self):
"""
登录网站
:return:
"""
options = webdriver.FirefoxOptions()
options.add_argument('-headless')
options.add_argument('--disable-gpu')
driver = webdriver.Firefox(firefox_options=options)
# driver = webdriver.Firefox()
driver.maximize_window()
wait = WebDriverWait(driver, 5)
driver.get('https://passport.zhaopin.com/org/login')
time.sleep(2)
wait.until(
EC.presence_of_element_located(
(By.XPATH, '//*[@id="loginName"]'))).send_keys(self.username)
time.sleep(2)
wait.until(
EC.presence_of_element_located(
(By.XPATH, '//*[@id="password"]'))).send_keys(self.password)
time.sleep(2)
while True:
wait.until(
EC.presence_of_element_located(
(By.XPATH, '//*[@id="loginbutton"]'))).click()
time.sleep(2)
imgelement = wait.until(
EC.presence_of_element_located(
(By.XPATH, '//div[@class="geetest_head"]'))) # 定位验证码
location1 = imgelement.location # 获取验证码x,y轴坐标
if location1['x'] == 0:
continue
else:
break
while True:
imgelement1 = wait.until(
EC.presence_of_element_located(
(By.XPATH, '//div[@class="geetest_head"]'))) # 定位验证码
imgelement2 = wait.until(
EC.presence_of_element_located(
(By.XPATH, '//div[@class="geetest_table_box"]'))) # 定位验证码
location1 = imgelement1.location # 获取验证码x,y轴坐标
if location1['x'] == 0:
break
driver.save_screenshot('aa.png') # 截取当前网页，该网页有我们需要的验证码
size1 = imgelement1.size # 获取验证码的长宽
size2 = imgelement2.size # 获取验证码的长宽
rangle = (int(location1['x']), int(location1['y']),
int(location1['x'] + size1['width']),
int(location1['y'] + size1['height'] + size2['height'])
) # 写成我们需要截取的位置坐标
i = Image.open("aa.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.save('frame4.png')
chaojiying = Chaojiying_Client('jackie1102', 'salesmind1800',
'9004')
im = open('frame4.png', 'rb').read()
res = chaojiying.PostPic(im, 9004)
content = res['pic_str'].split('|')
print(res)
loc_list = []
for i in content:
loc = i.split(',')
loc_list.append(loc)
action = ActionChains(driver)
loc1 = loc_list[0]
try:
x = int(loc1[0])
except Exception as E:
print(E)
chaojiying.ReportError(res['pic_id'])
continue
for loca in loc_list:
action.move_to_element_with_offset(imgelement1, int(loca[0]),
int(loca[1])).click()
action.pause(random.uniform(1, 2))
action.perform()
time.sleep(1)
wait.until(
EC.presence_of_element_located(
(By.XPATH, '//a[@class="geetest_commit"]'))).click()
time.sleep(2)
try:
imgelement = wait.until(
EC.presence_of_element_located(
(By.XPATH, '//div[@class="geetest_widget"]')))
location = imgelement.location
if location['x'] == 0:
break
else:
chaojiying.ReportError(res['pic_id'])
time.sleep(1)
continue
except:
break
try:
input_phone = driver.find_element_by_xpath('//*[@id="vmobile"]')
pc = PhoneCode()
phone = pc.get_phone()
input_phone.send_keys(phone)
driver.find_element_by_xpath(
'//a[@class="verify_code_btn"]').click()
while True:
imgelement1 = wait.until(
EC.presence_of_element_located(
(By.XPATH, '//div[@class="geetest_head"]'))) # 定位验证码
imgelement2 = wait.until(
EC.presence_of_element_located(
(By.XPATH,
'//div[@class="geetest_table_box"]'))) # 定位验证码
driver.save_screenshot('aa.png') # 截取当前网页，该网页有我们需要的验证码
location1 = imgelement1.location # 获取验证码x,y轴坐标
print(location1)
if location1['x'] == 0:
break
size1 = imgelement1.size # 获取验证码的长宽
size2 = imgelement2.size # 获取验证码的长宽
print(size1['width'])
rangle = (int(location1['x']), int(location1['y']),
int(location1['x'] + size1['width']),
int(location1['y'] + size1['height'] +
size2['height'])) # 写成我们需要截取的位置坐标
i = Image.open("aa.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.save('frame4.png')
chaojiying = Chaojiying_Client('jackie1102', 'salesmind1800',
'9004')
im = open('frame4.png', 'rb').read()
res = chaojiying.PostPic(im, 9004)
content = res['pic_str'].split('|')
print(res)
loc_list = []
for i in content:
loc = i.split(',')
loc_list.append(loc)
action = ActionChains(driver)
loc1 = loc_list[0]
try:
x = int(loc1[0])
except Exception as E:
print(E)
chaojiying.ReportError(res['pic_id'])
continue
for loca in loc_list:
action.move_to_element_with_offset(imgelement1,
int(loca[0]),
int(loca[1])).click()
action.pause(random.uniform(1, 2))
action.perform()
time.sleep(1)
wait.until(
EC.presence_of_element_located(
(By.XPATH, '//a[@class="geetest_commit"]'))).click()
time.sleep(2)
try:
imgelement = wait.until(
EC.presence_of_element_located(
(By.XPATH, '//div[@class="geetest_widget"]')))
location = imgelement.location
if location['x'] == 0:
break
else:
chaojiying.ReportError(res['pic_id'])
time.sleep(1)
continue
except:
break
code = pc.get_code(phone)
input_code = driver.find_element_by_xpath('//*[@id="verifyCode"]')
input_code.send_keys(code)
driver.find_element_by_xpath('//*[@id="confirm_btn"]').click()
except:
pass
time.sleep(5)
cookie = [
item["name"] + "=" + item["value"]
for item in driver.get_cookies()
]
cookiestr = '; '.join(item for item in cookie)
print(cookiestr)
driver.quit()
return cookiestr