New Version Pre-Release

.temp_to_pub/EasySpider_windows_x64/Code/easyspider_executestage.py

@@ -41,7 +41,7 @@
 from PIL import Image
 # import uuid
 from threading import Thread, Event
-from myChrome import MyChrome
+from myChrome import MyChrome, MyUCChrome
 from utils import check_pause, download_image, get_output_code, isnull, myMySQL, new_line, write_to_csv, write_to_excel
 desired_capabilities = DesiredCapabilities.CHROME
 desired_capabilities["pageLoadStrategy"] = "none"
@@ -1473,7 +1473,7 @@ def getData(self, para, loopElement, isInLoop=True, parentPath="", index=0):
  browser_t = MyChrome(
  options=options, chrome_options=option, executable_path=driver_path)
  elif cloudflare == 1:
- browser_t = uc.Chrome(
+ browser_t = MyUCChrome(
  options=options, chrome_options=option, executable_path=driver_path)
  print("Pass Cloudflare Mode")
  print("过Cloudflare验证模式")

.temp_to_pub/EasySpider_windows_x64/Code/myChrome.py

@@ -1,5 +1,3 @@
-
-
 from selenium.webdriver.chrome.options import Options
 from selenium.webdriver.common.keys import Keys
 from selenium.webdriver.common.action_chains import ActionChains
@@ -14,10 +12,12 @@
 from selenium.webdriver.support.ui import Select
 from selenium.webdriver import ActionChains
 from selenium.webdriver.common.by import By
+import undetected_chromedriver as uc
 desired_capabilities = DesiredCapabilities.CHROME
 desired_capabilities["pageLoadStrategy"] = "none"
 
 
+
 class MyChrome(webdriver.Chrome):
 
  def __init__(self, *args, **kwargs):
@@ -89,3 +89,77 @@ def find_elements(self, by=By.ID, value=None, iframe=False):
  raise NoSuchElementException
  else:
  return super().find_elements(by=by, value=value)
+
+
+class MyUCChrome(uc.Chrome):
+
+ def __init__(self, *args, **kwargs):
+ self.iframe_env = False # 现在的环境是root还是iframe
+ super().__init__(*args, **kwargs) # 调用父类的 __init__
+
+ def find_element(self, by=By.ID, value=None, iframe=False):
+ # 在这里改变查找元素的行为
+ if self.iframe_env:
+ super().switch_to.default_content()
+ self.iframe_env = False
+ if iframe:
+ # 获取所有的 iframe
+ try:
+ iframes = super().find_elements(By.CSS_SELECTOR, "iframe")
+ except Exception as e:
+ print(e)
+ find_element = False
+ # 遍历所有的 iframe 并点击里面的元素
+ for iframe in iframes:
+ # 切换到 iframe
+ super().switch_to.default_content()
+ super().switch_to.frame(iframe)
+ self.iframe_env = True
+ try:
+ # 在 iframe 中查找并点击元素
+ # 在这个例子中，我们查找 XPath 为 '//div[1]' 的元素
+ element = super().find_element(by=by, value=value)
+ find_element = True
+ except:
+ print("No such element found in the iframe")
+ # 完成操作后切回主文档
+ # super().switch_to.default_content()
+ if find_element:
+ return element
+ if not find_element:
+ raise NoSuchElementException
+ else:
+ return super().find_element(by=by, value=value)
+
+ def find_elements(self, by=By.ID, value=None, iframe=False):
+ # 在这里改变查找元素的行为
+ if self.iframe_env:
+ super().switch_to.default_content()
+ self.iframe_env = False
+ if iframe:
+ # 获取所有的 iframe
+ iframes = super().find_elements(By.CSS_SELECTOR, "iframe")
+ find_element = False
+ # 遍历所有的 iframe 并点击里面的元素
+ for iframe in iframes:
+ # 切换到 iframe
+ try:
+ super().switch_to.default_content()
+ super().switch_to.frame(iframe)
+ self.iframe_env = True
+ # 在 iframe 中查找并点击元素
+ # 在这个例子中，我们查找 XPath 为 '//div[1]' 的元素
+ elements = super().find_elements(by=by, value=value)
+ if len(elements) > 0:
+ find_element = True
+ # 完成操作后切回主文档
+ # super().switch_to.default_content()
+ if find_element:
+ return elements
+ except:
+ print("No such element found in the iframe")
+ if not find_element:
+ raise NoSuchElementException
+ else:
+ return super().find_elements(by=by, value=value)
+