def __init__(self):
self.url = 'https://my.cn.china.cn/manage.php?op=LoginShowNew'
self.browser = webdriver.Chrome()
self.wait = WebDriverWait(self.browser, 20)
self.email = ACCOUNT
self.password = PASSWORD
self.chaojiying = ChaojiyingClient(CJY_USERNAME, CJY_PASSWORD,
CJY_SOFT_ID)
def __init__(self):
self.url = 'https://kyfw.12306.cn/otn/resources/login.html'
# path是谷歌浏览器驱动的目录，如果已经将目录添加到系统变量，则不用设置此路径
path = r'F:\PycharmProjects\Python3爬虫\chromedriver.exe'
chrome_options = Options()
chrome_options.add_argument('--start-maximized')
self.browser = webdriver.Chrome(executable_path=path,
chrome_options=chrome_options)
self.wait = WebDriverWait(self.browser, 20)
self.username = USERNAME
self.password = PASSWORD
self.chaojiying = ChaojiyingClient(CHAOJIYING_USERNAME,
CHAOJIYING_PASSWORD,
CHAOJIYING_SOFT_ID)
def __init__(self):
self.login_url = "https://passport.bilibili.com/login"
caps = DesiredCapabilities().FIREFOX
firefox_options = Options()
firefox_options.headless = True
self.browser = webdriver.Firefox(
executable_path="/Users/chloeji/geckodriver",
capabilities=caps,
options=firefox_options)
self.driver_wait = WebDriverWait(self.browser, 60)
"""
设置超级鹰的用户名、密码以及软件 ID
"""
self.chaojiying = ChaojiyingClient(CHAOJIYING_USERNAME_,
CHAOJIYING_PASSWORD_,
CHAOJIYING_SOFT_ID_)
def parse_html(html):
# etree_html = etree.HTML(html)
screenshot = get_big_image()
screenshot.save('full_screen.png')
x1, y1, x2, y2 = get_position()
crop_image = screenshot.crop((x1, y1, x2, y2))
file_name = 'crop.png'
crop_image.save(file_name)
# 向超级鹰发送图片，获取该图片的验证码
chaojiying = ChaojiyingClient(username, password, '96001')
im = open(file_name, 'rb').read()
captha_str = chaojiying.PostPic(im, 1006)['pic_str']
# http: // bm.e21cn.com / log / reg.aspx 网站账户密码
username_code = 'carmack55'
password_code = '123456'
tel = '18511405897'
print(captha_str)
input_username = wait.until(
EC.presence_of_element_located((By.CSS_SELECTOR, 'input#username')))
input_password1 = wait.until(
EC.presence_of_element_located((By.CSS_SELECTOR, 'input#pwd')))
input_password2 = wait.until(
EC.presence_of_element_located((By.CSS_SELECTOR, 'input#pwd_Q')))
input_tel = wait.until(
EC.presence_of_element_located((By.CSS_SELECTOR, 'input#tel')))
input_check = wait.until(
EC.presence_of_element_located((By.CSS_SELECTOR, 'input#CheckCode')))
sublime = wait.until(
EC.element_to_be_clickable((By.CSS_SELECTOR, 'input#btn_login')))
input_username.send_keys(username_code)
input_password1.send_keys(password_code)
input_password2.send_keys(password_code)
input_tel.send_keys(tel)
input_check.send_keys(captha_str)
time.sleep(2)
sublime.click()
def get_captcha(browser, class_str):
"""
向超级鹰发送截下来的验证码图片，超级鹰返回验证码，得到图片验证码
:param browser: 浏览器对象
:param class_str: css选择器（定位网页中验证码节点元素）
:return: 验证码字符串
"""
full_screen_img = get_big_image(browser)
# 保存文件在当前文件夹下，文件名为mobile_login.png（完全可以不保存大图）
full_screen_img.save('mobile_login.png')
# 获取验证码左上角和右下角坐标
x1, y1, x2, y2 = get_captha_position(browser, class_str)
captha_img = full_screen_img.crop((x1, y1, x2, y2))
captha_img.save('mobile_captha.png')
# 根据具体情况修改账号、密码、和验证码类型代号
chaojiying = ChaojiyingClient('carmack', 'Vff635241', '96001')
im = open('mobile_captha.png', 'rb').read()
captha_str = chaojiying.PostPic(im, 1006)['pic_str']
return captha_str
class CrackTouClick():
def __init__(self):
self.url = 'https://kyfw.12306.cn/otn/resources/login.html'
# path是谷歌浏览器驱动的目录，如果已经将目录添加到系统变量，则不用设置此路径
path = r'F:\PycharmProjects\Python3爬虫\chromedriver.exe'
chrome_options = Options()
chrome_options.add_argument('--start-maximized')
self.browser = webdriver.Chrome(executable_path=path,
chrome_options=chrome_options)
self.wait = WebDriverWait(self.browser, 20)
self.username = USERNAME
self.password = PASSWORD
self.chaojiying = ChaojiyingClient(CHAOJIYING_USERNAME,
CHAOJIYING_PASSWORD,
CHAOJIYING_SOFT_ID)
def crack(self):
# 调用账号密码输入函数
self.get_input_element()
# 调用验证码图片剪裁函数
image = self.get_touclick_image()
bytes_array = BytesIO()
image.save(bytes_array, format='PNG')
# 利用超级鹰打码平台的 API PostPic() 方法把图片发送给超级鹰后台，发送的图像是字节流格式，返回的结果是一个JSON
result = self.chaojiying.PostPic(bytes_array.getvalue(),
CHAOJIYING_KIND)
print(result)
# 调用验证码坐标解析函数
locations = self.get_points(result)
# 调用模拟点击验证码函数
self.touch_click_words(locations)
# 调用模拟点击登录函数
self.login()
try:
# 查找是否出现用户的姓名，若出现表示登录成功
success = self.wait.until(
EC.text_to_be_present_in_element(
(By.CSS_SELECTOR, '.welcome-name'), '谭先生'))
print(success)
cc = self.browser.find_element(By.CSS_SELECTOR, '.welcome-name')
print('用户' + cc.text + '登录成功')
# 若没有出现表示登录失败，继续重试，超级鹰会返回本次识别的分值
except TimeoutException:
self.chaojiying.ReportError(result['pic_id'])
self.crack()
# 账号密码输入函数
def get_input_element(self):
# 登录页面发送请求
self.browser.get(self.url)
# 登录页面默认是扫码登录，所以首先要点击账号登录
login = self.wait.until(
EC.presence_of_element_located(
(By.CSS_SELECTOR, '.login-hd-account')))
login.click()
time.sleep(3)
# 查找到账号密码输入位置的元素
username = self.wait.until(
EC.presence_of_element_located(
(By.CSS_SELECTOR, 'input#J-userName')))
password = self.wait.until(
EC.presence_of_element_located(
(By.CSS_SELECTOR, 'input#J-password')))
# 输入账号密码
username.send_keys(self.username)
password.send_keys(self.password)
# 验证码图片剪裁函数
def get_touclick_image(self, name='12306.png'):
# 获取验证码的位置
element = self.wait.until(
EC.presence_of_element_located(
(By.CSS_SELECTOR, '.login-pwd-code')))
time.sleep(3)
location = element.location
size = element.size
top, bottom, left, right = location['y'], location['y'] + size[
'height'], location['x'], location['x'] + size['width']
# 先对整个页面截图
screenshot = self.browser.get_screenshot_as_png()
screenshot = Image.open(BytesIO(screenshot))
# 根据验证码坐标信息，剪裁出验证码图片
captcha = screenshot.crop((left, top, right, bottom))
captcha.save(name)
return captcha
# 验证码坐标解析函数，分析超级鹰返回的坐标
def get_points(self, captcha_result):
# 超级鹰识别结果以字符串形式返回，每个坐标都以|分隔
groups = captcha_result.get('pic_str').split('|')
# 将坐标信息变成列表的形式
locations = [[int(number) for number in group.split(',')]
for group in groups]
return locations
# 模拟点击验证码函数
def touch_click_words(self, locations):
element = self.wait.until(
EC.presence_of_element_located(
(By.CSS_SELECTOR, '.login-pwd-code')))
# 循环点击正确验证码的坐标
for location in locations:
print(location)
ActionChains(self.browser).move_to_element_with_offset(
element, location[0], location[1]).click().perform()
# 模拟点击登录函数
def login(self):
submit = self.wait.until(EC.element_to_be_clickable(
(By.ID, 'J-login')))
submit.click()
class CrackGeetest():
def __init__(self):
self.url = 'https://my.cn.china.cn/manage.php?op=LoginShowNew'
self.browser = webdriver.Chrome()
self.wait = WebDriverWait(self.browser, 20)
self.email = ACCOUNT
self.password = PASSWORD
self.chaojiying = ChaojiyingClient(CJY_USERNAME, CJY_PASSWORD,
CJY_SOFT_ID)
def __del__(self):
self.browser.close()
def open_image(self, path):
f = open(path, mode='rb')
img = f.read()
f.close()
return img
def get_geetest_button(self):
"""
获取初始验证按钮
:return:
"""
button = self.wait.until(
EC.element_to_be_clickable((By.CLASS_NAME, 'geetest_radar_tip')))
return button
def get_position(self):
"""
获取验证码位置
:return: 验证码位置元组
"""
img = self.wait.until(
EC.presence_of_element_located((By.ID, 'showCaptcha')))
time.sleep(2)
location = img.location
size = img.size
top, bottom, left, right = location['y'], location['y'] + size[
'height'], location['x'], location['x'] + size['width']
return (top, bottom, left, right)
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_slider(self):
"""
获取滑块
:return: 滑块对象
"""
slider = self.wait.until(
EC.element_to_be_clickable(
(By.CLASS_NAME, 'geetest_slider_button')))
return slider
def get_geetest_image(self, name='captcha.png'):
"""
获取验证码图片
:return: 图片对象
"""
top, bottom, left, right = self.get_position()
print('验证码位置', top, bottom, left, right)
screenshot = self.get_screenshot()
captcha = screenshot.crop((left, top, right, bottom))
captcha.save(name)
return captcha
def open(self):
"""
打开网页输入用户名密码
:return: None
"""
# 打开浏览器登陆页面
self.browser.get(self.url)
# 获取账号输入框
email = self.wait.until(
EC.presence_of_element_located((By.ID, 'userName')))
# 获取密码输入框
password = self.wait.until(
EC.presence_of_element_located((By.ID, 'userPassword')))
# 输入账号
email.send_keys(self.email)
# 输入密码
password.send_keys(self.password)
# 获取验证码输入框
img = self.wait.until(
EC.presence_of_element_located((By.ID, 'verifystr')))
# 获取验证码
self.get_geetest_image(name="login.png")
time.sleep(0.1)
image = self.open_image("login.png")
img_num = self.chaojiying.PostPic(image, 1902).get("pic_str")
# 输入验证码
img.send_keys(img_num)
# 获取登陆按钮
submit = self.wait.until(EC.presence_of_element_located(
(By.ID, 'btn')))
submit.click()
time.sleep(10)
def get_gap(self, image1, image2):
"""
获取缺口偏移量
:param image1: 不带缺口图片
:param image2: 带缺口图片
:return:
"""
left = 60
for i in range(left, image1.size[0]):
for j in range(image1.size[1]):
if not self.is_pixel_equal(image1, image2, i, j):
left = i
return left
return left
def is_pixel_equal(self, image1, image2, x, y):
"""
判断两个像素是否相同
:param image1: 图片1
:param image2: 图片2
:param x: 位置x
:param y: 位置y
:return: 像素是否相同
"""
# 取两个图片的像素点
pixel1 = image1.load()[x, y]
pixel2 = image2.load()[x, y]
threshold = 60
if abs(pixel1[0] - pixel2[0]) < threshold and abs(
pixel1[1] - pixel2[1]) < threshold and abs(
pixel1[2] - pixel2[2]) < threshold:
return True
else:
return False
def get_track(self, distance):
"""
根据偏移量获取移动轨迹
:param distance: 偏移量
:return: 移动轨迹
"""
# 移动轨迹
track = []
# 当前位移
current = 0
# 减速阈值
mid = distance * 4 / 5
# 计算间隔
t = 0.2
# 初速度
v = 0
while current < distance:
if current < mid:
# 加速度为正2
a = 2
else:
# 加速度为负3
a = -3
# 初速度v0
v0 = v
# 当前速度v = v0 + at
v = v0 + a * t
# 移动距离x = v0t + 1/2 * a * t^2
move = v0 * t + 1 / 2 * a * t * t
# 当前位移
current += move
# 加入轨迹
track.append(round(move))
return track
def move_to_gap(self, slider, track):
"""
拖动滑块到缺口处
:param slider: 滑块
:param track: 轨迹
:return:
"""
ActionChains(self.browser).click_and_hold(slider).perform()
for x in track:
ActionChains(self.browser).move_by_offset(xoffset=x,
yoffset=0).perform()
time.sleep(0.5)
ActionChains(self.browser).release().perform()
def login(self):
"""
登录
:return: None
"""
submit = self.wait.until(
EC.element_to_be_clickable((By.CLASS_NAME, 'login-btn')))
submit.click()
time.sleep(3)
print('登录成功')
def crack(self):
# 输入用户名密码
# self.open()
# home = self.browser.find_element_by_xpath("//div[@class='brand']/a")
# # 执行js访问主页
# self.browser.execute_script("arguments[0].click();", home)
url = 'https://cn.china.cn/'
self.browser.get(url)
# time.sleep(10)
# 获取搜索框搜索
self.wait.until(EC.element_to_be_clickable(
(By.ID, 'keyinput'))).send_keys("智能设备")
# 找到公司搜索
button = self.browser.find_element_by_xpath(
"//ul[@class='serch-items']/li[2]")
# 执行js搜索公司
self.browser.execute_script("arguments[0].click();", button)
time.sleep(1)
provinces = self.browser.find_elements_by_xpath(
"//div[@class='branlist-view']/ul/li/a")
n = len(provinces) - 1
print(provinces)
for i in range(n):
provinces = self.browser.find_elements_by_xpath(
"//div[@class='branlist-view']/ul/li/a")
provinces[n - i].click()
cities = self.browser.find_elements_by_xpath(
"//div[contains(@class,'ctg-mod-brancate')][2]//ul/li/a")
cn = len(cities) - 1
print(cities)
for j in range(cn):
cities = self.browser.find_elements_by_xpath(
"//div[contains(@class,'ctg-mod-brancate')][2]//ul/li/a")
cities[cn - j].click()
print(self.browser.current_url)
companies = self.browser.find_elements_by_xpath(
"//div[@class='corpinfo']/h3/a")
cpn = len(companies) - 1
# 访问公司主页
for i in range(cpn):
companies = self.browser.find_elements_by_xpath(
"//div[@class='corpinfo']/h3/a")
companies[i].click()
print(self.browser.current_url)
self.browser.back()
time.sleep(1)
self.browser.find_element_by_class_name("rollPage").click()
time.sleep(1)
companies = self.browser.find_elements_by_xpath(
"//div[@class='corpinfo']/h3/a")
cpn = len(companies) - 1
# 访问公司主页
for i in range(cpn):
companies = self.browser.find_elements_by_xpath(
"//div[@class='corpinfo']/h3/a")
companies[i].click()
print(self.browser.current_url)
self.browser.back()
time.sleep(1)
class Bilibili:
def __init__(self):
self.login_url = "https://passport.bilibili.com/login"
caps = DesiredCapabilities().FIREFOX
firefox_options = Options()
firefox_options.headless = True
self.browser = webdriver.Firefox(
executable_path="/Users/chloeji/geckodriver",
capabilities=caps,
options=firefox_options)
self.driver_wait = WebDriverWait(self.browser, 60)
"""
设置超级鹰的用户名、密码以及软件 ID
"""
self.chaojiying = ChaojiyingClient(CHAOJIYING_USERNAME_,
CHAOJIYING_PASSWORD_,
CHAOJIYING_SOFT_ID_)
def send_infos(self, username, password):
self.browser.get(self.login_url)
username_sender = self.driver_wait.until(
EC.presence_of_element_located(
(By.XPATH, "//*[@id='login-username']")))
username_sender.send_keys(username)
password_sender = self.driver_wait.until(
EC.presence_of_element_located(
(By.XPATH, "//*[@id='login-passwd']")))
password_sender.send_keys(password)
def get_verify_button(self):
button = self.driver_wait.until(
EC.presence_of_element_located(
(By.XPATH, "//a[@class='btn btn-login']")))
pprint(button.text)
sleep(3)
return button
def get_verify_elements(self):
self.driver_wait.until(
EC.presence_of_element_located(
(By.CLASS_NAME, "geetest_item_img")))
sleep(2)
element = self.driver_wait.until(
EC.presence_of_element_located(
(By.CLASS_NAME, "geetest_table_box")))
logger.info("成功获取验证码节点。")
return element
def get_verify_pos(self):
element = self.get_verify_elements()
sleep(2)
location = element.location
print(location)
size = element.size
print(size)
top, buttom, left, right = \
location["y"] * 2, \
(location["y"] + size["height"]) * 2, \
location["x"] * 2, \
(location["x"] + size["width"]) * 2
return top, buttom, left, right
def get_screenshoot(self):
# http://allselenium.info/taking-screenshot-using-python-selenium-webdriver/
screenshoot = self.browser.get_screenshot_as_png()
screenshoot = Image.open(io.BytesIO(screenshoot))
sleep(5)
screenshoot.save("screenshoot.png")
return screenshoot
def get_verify_image(self, name="need_to_verified.png"):
top, buttom, left, right = self.get_verify_pos()
logger.info(f"验证码位置：{top, buttom, left, right}")
screenshoot = self.get_screenshoot()
verification_area = screenshoot.crop((left, top, right, buttom))
verification_area.save(name)
return verification_area
def get_points(self, verify_result):
groups = verify_result.get("pic_str").split("|")
try:
locations = [[int(number) for number in group.split(",")]
for group in groups]
except ValueError:
locations = [[int(float(number)) for number in group.split(",")]
for group in groups]
return locations
# geckodriver browser issue with viewpoint
def touch_click_words(self, locations):
for location in locations:
print(location)
X_OFFSET = location[0]
Y_OFFSET = location[1]
try:
ActionChains(self.browser).\
move_to_element_with_offset(self.get_verify_elements(),
X_OFFSET, Y_OFFSET).\
click().\
perform()
sleep(3)
except MoveTargetOutOfBoundsException:
self.browser.execute_script(
'window.scrollTo(0, " + str(self.get_verify_elements())");'
)
except Exception:
pprint(traceback.format_exc())
def touch_click_verify(self):
button = self.driver_wait.until(
EC.element_to_be_clickable((By.CLASS_NAME, "geetest_commit")))
button.click()
def login(self):
submit = self.driver_wait.until(
EC.element_to_be_clickable((By.CLASS_NAME, "btn btn-login")))
submit.click()
sleep(10)
logger.info("登录成功。")
def crack(self, user, pswd):
# self.browser.execute_script("document.body.style.transform='scale(0.9)';")
self.browser.set_window_size(1024, 768)
self.send_infos(user, pswd)
button = self.get_verify_button()
button.click()
# 开始识别码
image = self.get_verify_image()
bytes_array = io.BytesIO()
image.save(bytes_array, "PNG")
sleep(10)
result = self.chaojiying.PostPic(bytes_array.getvalue(),
CHAOJIYING_KIND)
pprint(result)
locations = self.get_points(result)
self.touch_click_words(locations)
self.touch_click_verify()
sleep(3)
try:
success = self.driver_wait.until(
EC.text_to_be_present_in_element(
(By.CLASS_NAME, "bilifont bili-icon_dingdao_zhuzhan"),
"主站"))
pprint(success)
except Exception as e:
logger.warn("登录失败。", e)
finally:
self.browser.quit()