【浅记】使用seleniumwire滑动极兔滑块
直接上代码
import asyncio
import gzip
import os
import time
import requests
import cv2
import numpy
from random import randint
from selenium.webdriver.common.by import By
from seleniumwire import webdriver
from selenium.webdriver.common.action_chains import ActionChains
def show_image(img_array, name='img', resize_flag=False):
"""展示图片"""
maxheight = 540
maxwidth = 960
scalex = maxwidth / img_array.shape[1]
scaley = maxheight / img_array.shape[0]
scale = min(scalex, scaley)
if resize_flag and scale < 1:
img_array = cv2.resize(img_array, (0, 0), fx=scale, fy=scale)
cv2.imshow(name, img_array)
cv2.waitkey(0)
cv2.destroywindow(name)
def make_threshold(img):
"""全局阈值
将图片二值化,去除噪点,让其黑白分明"""
x = numpy.ones(img.shape, numpy.uint8) * 255
y = img - x
result, thresh = cv2.threshold(y, 127, 255, cv2.thresh_binary_inv)
# 将二值化后的结果返回
return thresh
def move_slider(website, slider, track, **kwargs):
"""将滑块移动到终点位置
:param website: selenium页面对象
:param slider: selenium页面中滑块元素对象
:param track: 到终点所需的距离
"""
name = kwargs.get('name', '滑块')
try:
if track[0] > 200:
return track[0]
# 点击滑块元素并拖拽
ActionChains(website).click_and_hold(slider).perform()
time.sleep(0.15)
for i in track:
# 随机上下浮动鼠标
ActionChains(website).move_by_offset(xoffset=i, yoffset=randint(-2, 2)).perform()
# 释放元素
time.sleep(0.2)
ActionChains(website).release(slider).perform()
time.sleep(0.5)
# 随机拿开鼠标
# ActionChains(website).move_by_offset(xoffset=randint(200, 300), yoffset=randint(200, 300)).perform()
print(f'[网页] 拖拽 {name}')
return True
except Exception as e:
print(f'[网页] 拖拽 {name} 失败 {e}')
class computedistance:
"""获取需要滑动的距离
将验证码背景大图和需要滑动的小图进行处理,先在大图中找到相似的小图位置,再获取对应的像素偏移量"""
def __init__(self, background_path: str, image_to_move: str, offset_top_px: int, show_img=False):
"""
:param background_path: 验证码背景大图
:param image_to_move: 需要滑动的小图
:param offset_top_px: 小图距离在大图上的顶部边距(像素偏移量)
:param show_img: 是否展示图片
"""
self.background_img = cv2.imread(background_path)
self.offset_px = offset_top_px
self.show_img = show_img
small_img_data = cv2.imread(image_to_move, cv2.imread_unchanged)
# 得到一个改变维度为50的乘以值
scalex = 50 / small_img_data.shape[1]
# 使用最近邻插值法缩放，让xy乘以scalex，得到缩放后shape为50x50的图片
self.tpl_img = cv2.resize(small_img_data, (0, 0), fx=scalex, fy=scalex)
self.background_cutting = None
def show(self, img):
if self.show_img:
show_image(img)
def tpl_op(self):
# 将小图转换为灰色
tpl_gray = cv2.cvtcolor(self.tpl_img, cv2.color_bgr2gray)
h, w = tpl_gray.shape
# 将背景图转换为灰色
# background_gray = cv2.cvtcolor(self.background_img, cv2.color_bgr2gray)
background_gray = cv2.cvtcolor(self.background_cutting, cv2.color_bgr2gray)
# 得到二值化后的小图
threshold_img = make_threshold(tpl_gray)
# 将小图与大图进行模板匹配,找到所对应的位置
result = cv2.matchtemplate(background_gray, threshold_img, cv2.tm_ccoeff_normed)
min_val, max_val, min_loc, max_loc = cv2.minmaxloc(result)
# 左上角位置
top_left = (max_loc[0] - 5, max_loc[1] + self.offset_px)
# 右下角位置
bottom_right = (top_left[0] + w, top_left[1] + h)
# 在源颜色大图中画出小图需要移动到的终点位置
"""rectangle(图片源数据, 左上角, 右下角, 颜色, 画笔厚度)"""
cv2.rectangle(self.background_img, top_left, bottom_right, (0, 0, 255), 2)
if self.show_img:
show_image(self.background_img)
return top_left
def cutting_background(self):
"""切割图片的上下边框"""
height = self.tpl_img.shape[0]
# 将大图中上下多余部分去除,如: background_img[40:110, :]
self.background_cutting = self.background_img[self.offset_px - 10: self.offset_px + height + 10, :]
def run(self):
# 如果小图的长度与大图的长度一致则不用将大图进行切割,可以将self.cutting_background()注释掉
self.cutting_background()
return self.tpl_op()
def identify_gap(bg, tp):
'''
bg: 背景图片
tp: 缺口图片
out:输出图片
'''
# 读取背景图片和缺口图片
bg_img = cv2.imread(bg) # 背景图片
tp_img = cv2.imread(tp) # 缺口图片
# 识别图片边缘
bg_edge = cv2.Canny(bg_img, 100, 200)
tp_edge = cv2.Canny(tp_img, 100, 200)
# 转换图片格式
bg_pic = cv2.cvtColor(bg_edge, cv2.COLOR_GRAY2RGB)
tp_pic = cv2.cvtColor(tp_edge, cv2.COLOR_GRAY2RGB)
# 缺口匹配
res = cv2.matchTemplate(bg_pic, tp_pic, cv2.TM_CCOEFF_NORMED)
min_val, max_val, min_loc, max_loc = cv2.minMaxLoc(res) # 寻找最优匹配
# 绘制方框
# th, tw = tp_pic.shape[:2]
tl = max_loc # 左上角点的坐标
# br = (tl[0] + tw, tl[1] + th) # 右下角点的坐标
# cv2.rectangle(bg_img, tl, br, (0, 0, 255), 2) # 绘制矩形
# cv2.imwrite(out, bg_img) # 保存在本地
print(tl[0])
# 返回缺口的X坐标
return tl[0]
class SliderMove(object):
def __init__(self):
self.url = 'https://www.jtexpress.com.cn/service.html?indexIpt=JT5125611716695'
# self.process_folder = os.path.join(os.path.expanduser('~'), "desktop", "today_news")
self.process_folder = ''
self.background_path = './bg.jpg'
self.small_path = './tp.jpg'
self.small_px = 0
self.xpath = {}
self.browser = None
self.bg_path = None
self.tp_path = None
def check_file_exist(self):
"""检查流程目录是否存在"""
if not os.path.isdir(self.process_folder):
os.mkdir(self.process_folder)
def start_browser(self):
"""启动浏览器"""
chrome_options = webdriver.ChromeOptions()
# chrome_options.add_argument('--headless')
chrome_options.add_argument(
"user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36")
chrome_options.add_argument('--no-sandbox')
chrome_options.add_argument('--disable-gpu')
chrome_options.add_argument('--disable-dev-shm-usage')
chrome_options.add_argument(f"--ignore-ssl-errors")
chrome_options.add_argument(f"--ignore-certificate-errors")
# chrome_options.add_argument(f"blink-settings=imagesEnabled=false")
chrome_options.add_argument(f"disable-infobars")
chrome_options.add_experimental_option('excludeSwitches', ['enable-automation'])
self.browser = webdriver.Chrome(options=chrome_options,
executable_path='C:\Program Files\Google\Chrome\Application\chromedriver.exe')
# self.browser = webdriver.Chrome(options=chrome_options,
# executable_path='/usr/bin/chromedriver')
self.browser.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {
"source": """Object.defineProperty(navigator, 'webdriver', { get: () => undefined });"""})
self.browser.maximize_window()
def close_browser(self):
self.browser.close()
self.browser.quit()
def wait_element_loaded(self, xpath: str, timeout=10, close_browser=True):
"""等待页面元素加载完成
:param xpath: xpath表达式
:param timeout: 最长等待超时时间
:param close_browser: 元素等待超时后是否关闭浏览器
:return: boolean
"""
now_time = int(time.time())
while int(time.time()) - now_time < timeout:
# noinspection pybroadexception
try:
# element = self.browser.find_element_by_xpath(xpath)
element = self.browser.find_element(by=By.CLASS_NAME, value=xpath)
if element:
return True
time.sleep(1)
except Exception:
pass
else:
if close_browser:
self.close_browser()
# print("查找页面元素失败，如果不存在网络问题请尝试修改xpath表达式")
return False
def process_main(self):
"""处理页面内容"""
self.browser.get(self.url)
tp = ''
bg = ''
for request in self.browser.requests:
if request.response:
# print(request.path)
if 'hycdn' in request.path:
if 'PNG' in str(request.response.body):
tp = request.response.body
else:
bg = request.response.body
self.bg_path = f'./bg_{os.getpid()}.jpg'
self.tp_path = f'./tp_{os.getpid()}.jpg'
with open(self.bg_path, 'wb')as f1:
f1.write(bg)
with open(self.tp_path, 'wb')as f2:
f2.write(tp)
for i in range(2):
print('重试第%d次' % (i))
# small_img = self.browser.find_element_by_xpath(self.xpath['slideBlock'])
# small_img = self.browser.find_element_by_xpath('//img[@id="slideBlock"]')
# 获取小图片距离背景图顶部的像素距离
# self.small_px = small_img.value_of_css_property("top").replace("px", "").split(".")[0]
# print(self.small_px)
time.sleep(0.5)
# 如果没滑动成功则刷新页面重试
if not self.process_slider():
self.browser.refresh()
continue
else:
break
@staticmethod
def handle_distance(distance):
"""将直线距离转为缓慢的轨迹"""
import random
slow_distance = []
while sum(slow_distance) <= distance:
slow_distance.append(random.randint(-2, 50))
if sum(slow_distance) != distance:
slow_distance.append(distance - sum(slow_distance))
return slow_distance
def process_slider(self):
"""处理滑块验证码"""
# distance_obj = computedistance(self.background_path, self.small_path, int(self.small_px), show_img=False)
# 获取移动所需的距离
# distance = distance_obj.run()
distance = identify_gap(self.bg_path, self.tp_path)
# track = self.handle_distance(distance[0])
track = self.handle_distance(distance // 2 - 10)
track.extend([-10, -5, -1])
# slider_element = self.browser.find_element_by_xpath(self.xpath['tcaptcha_drag_thumb'])
iframe = self.browser.find_element(by=By.ID, value='tcaptcha_iframe')
self.browser.switch_to.frame(iframe)
slider_element = self.browser.find_element(By.ID, "tcaptcha_drag_thumb")
move_slider(self.browser, slider_element, track)
time.sleep(1)
# 如果滑动完成则返回true
# if not self.wait_element_loaded(self.xpath['waybillStatusMain'], timeout=2, close_browser=False):
if not self.wait_element_loaded('waybillStatusMain', timeout=2, close_browser=False):
return False
else:
for request in self.browser.requests:
if request.response:
# print(request.path)
if 'trackingCustomerByWaybillNo' in request.path:
print(request.path)
# print(request.response.body.decode('utf8'))
print(gzip.decompress(request.response.body).decode("utf-8"))
return True
def run(self):
# self.check_file_exist()
self.start_browser()
self.process_main()
self.close_browser()
os.remove(self.tp_path)
os.remove(self.bg_path)
if __name__ == '__main__':
api_task = SliderMove()
api_task.run()