spider/EasySpider
1
0
Fork 0
mirror of https://github.com/NaiboWang/EasySpider.git synced 2025-04-20 10:05:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update MyChrome

Browse Source
This commit is contained in:
naibo 2023-11-09 16:25:49 +08:00
parent a90b679673
commit c749107a6a
13 changed files with 29 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.temp_to_pub/EasySpider_windows_x64/execution_instances/115.json Normal file
View File

File diff suppressed because one or more lines are too long

1
.temp_to_pub/EasySpider_windows_x64/execution_instances/116.json Normal file
View File

File diff suppressed because one or more lines are too long

1
.temp_to_pub/EasySpider_windows_x64/execution_instances/117.json Normal file
View File

File diff suppressed because one or more lines are too long

1
.temp_to_pub/EasySpider_windows_x64/execution_instances/118.json Normal file
View File

File diff suppressed because one or more lines are too long

1
.temp_to_pub/EasySpider_windows_x64/execution_instances/119.json Normal file
View File

File diff suppressed because one or more lines are too long

1
.temp_to_pub/EasySpider_windows_x64/execution_instances/120.json Normal file
View File

File diff suppressed because one or more lines are too long

1
.temp_to_pub/EasySpider_windows_x64/execution_instances/121.json Normal file
View File

File diff suppressed because one or more lines are too long

1
.temp_to_pub/EasySpider_windows_x64/execution_instances/122.json Normal file
View File

File diff suppressed because one or more lines are too long

2
.temp_to_pub/EasySpider_windows_x64/tasks/212.json
View File

File diff suppressed because one or more lines are too long

1
.temp_to_pub/EasySpider_windows_x64/tasks/234.json Normal file
View File

File diff suppressed because one or more lines are too long

2
ExecuteStage/.vscode/launch.json vendored
View File

@ -12,7 +12,7 @@
"justMyCode": false, "justMyCode": false,
// "args": ["--id", "[7]", "--read_type", "remote", "--headless", "0"] // "args": ["--id", "[7]", "--read_type", "remote", "--headless", "0"]
// "args": ["--id", "[9]", "--read_type", "remote", "--headless", "0", "--saved_file_name", "YOUTUBE"] // "args": ["--id", "[9]", "--read_type", "remote", "--headless", "0", "--saved_file_name", "YOUTUBE"]
"args": ["--id", "[112]", "--headless", "0", "--user_data", "0", "--keyboard", "0"] "args": ["--id", "[119]", "--headless", "0", "--user_data", "0", "--keyboard", "0"]
} }
] ]
} }

24
ExecuteStage/myChrome.py
View File

@ -37,19 +37,21 @@ class MyChrome(webdriver.Chrome):
except Exception as e: except Exception as e:
print(e) print(e)
find_element = False find_element = False
# 遍历所有的 iframe 并点击里面的元素 # 遍历所有的 iframe 并查找里面的元素
for iframe in iframes: for iframe in iframes:
# 切换到 iframe # 切换到 iframe
super().switch_to.default_content() super().switch_to.default_content()
super().switch_to.frame(iframe) super().switch_to.frame(iframe)
self.iframe_env = True self.iframe_env = True
try: try:
# 在 iframe 中查找并点击元素 # 在 iframe 中查找元素
# 在这个例子中，我们查找 XPath 为 '//div[1]' 的元素 # 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) element = super().find_element(by=by, value=value)
find_element = True find_element = True
except NoSuchElementException as e: except NoSuchElementException as e:
print(f"No such element found in the iframe: {str(e)}") print(f"No such element found in the iframe: {str(e)}")
except Exception as e:
print(f"Exception: {str(e)}")
# 完成操作后切回主文档 # 完成操作后切回主文档
# super().switch_to.default_content() # super().switch_to.default_content()
if find_element: if find_element:
@ -68,14 +70,14 @@ class MyChrome(webdriver.Chrome):
# 获取所有的 iframe # 获取所有的 iframe
iframes = super().find_elements(By.CSS_SELECTOR, "iframe") iframes = super().find_elements(By.CSS_SELECTOR, "iframe")
find_element = False find_element = False
# 遍历所有的 iframe 并点击里面的元素 # 遍历所有的 iframe 并找到里面的元素
for iframe in iframes: for iframe in iframes:
# 切换到 iframe # 切换到 iframe
try: try:
super().switch_to.default_content() super().switch_to.default_content()
super().switch_to.frame(iframe) super().switch_to.frame(iframe)
self.iframe_env = True self.iframe_env = True
# 在 iframe 中查找并点击元素 # 在 iframe 中查找元素
# 在这个例子中，我们查找 XPath 为 '//div[1]' 的元素 # 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) elements = super().find_elements(by=by, value=value)
if len(elements) > 0: if len(elements) > 0:
@ -86,6 +88,8 @@ class MyChrome(webdriver.Chrome):
return elements return elements
except NoSuchElementException as e: except NoSuchElementException as e:
print(f"No such element found in the iframe: {str(e)}") print(f"No such element found in the iframe: {str(e)}")
except Exception as e:
print(f"Exception: {str(e)}")
if not find_element: if not find_element:
raise NoSuchElementException raise NoSuchElementException
else: else:
@ -117,19 +121,21 @@ if sys.platform != "darwin":
except Exception as e: except Exception as e:
print(e) print(e)
find_element = False find_element = False
# 遍历所有的 iframe 并点击里面的元素 # 遍历所有的 iframe 并找到里面的元素
for iframe in iframes: for iframe in iframes:
# 切换到 iframe # 切换到 iframe
super().switch_to.default_content() super().switch_to.default_content()
super().switch_to.frame(iframe) super().switch_to.frame(iframe)
self.iframe_env = True self.iframe_env = True
try: try:
# 在 iframe 中查找并点击元素 # 在 iframe 中查找元素
# 在这个例子中，我们查找 XPath 为 '//div[1]' 的元素 # 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) element = super().find_element(by=by, value=value)
find_element = True find_element = True
except NoSuchElementException as e: except NoSuchElementException as e:
print(f"No such element found in the iframe: {str(e)}") print(f"No such element found in the iframe: {str(e)}")
except Exception as e:
print(f"Exception: {str(e)}")
# 完成操作后切回主文档 # 完成操作后切回主文档
# super().switch_to.default_content() # super().switch_to.default_content()
if find_element: if find_element:
@ -148,14 +154,14 @@ if sys.platform != "darwin":
# 获取所有的 iframe # 获取所有的 iframe
iframes = super().find_elements(By.CSS_SELECTOR, "iframe") iframes = super().find_elements(By.CSS_SELECTOR, "iframe")
find_element = False find_element = False
# 遍历所有的 iframe 并点击里面的元素 # 遍历所有的 iframe 并查找里面的元素
for iframe in iframes: for iframe in iframes:
# 切换到 iframe # 切换到 iframe
try: try:
super().switch_to.default_content() super().switch_to.default_content()
super().switch_to.frame(iframe) super().switch_to.frame(iframe)
self.iframe_env = True self.iframe_env = True
# 在 iframe 中查找并点击元素 # 在 iframe 中查找元素
# 在这个例子中，我们查找 XPath 为 '//div[1]' 的元素 # 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) elements = super().find_elements(by=by, value=value)
if len(elements) > 0: if len(elements) > 0:
@ -166,6 +172,8 @@ if sys.platform != "darwin":
return elements return elements
except NoSuchElementException as e: except NoSuchElementException as e:
print(f"No such element found in the iframe: {str(e)}") print(f"No such element found in the iframe: {str(e)}")
except Exception as e:
print(f"Exception: {str(e)}")
if not find_element: if not find_element:
raise NoSuchElementException raise NoSuchElementException
else: else:

4
Readme.md
View File

@ -1,8 +1,8 @@
<!-- ## 请您Star/Please Star ## 请您Star/Please Star
如果您觉得此工具不错，请轻轻点击此页面右上角**Star**按钮增加项目曝光度，谢谢！软件完全免费（商用除外），只求大家Star和宣传给其他需要的朋友，谢谢！ 如果您觉得此工具不错，请轻轻点击此页面右上角**Star**按钮增加项目曝光度，谢谢！软件完全免费（商用除外），只求大家Star和宣传给其他需要的朋友，谢谢！
If you think this tool is good, please gently click the **Star** button in the upper right corner at this page to increase the project exposure, thank you! The software is completely free (except for commercial use), only ask everyone to Star and promote it to other friends in need, thank you! --> If you think this tool is good, please gently click the **Star** button in the upper right corner at this page to increase the project exposure, thank you! The software is completely free (except for commercial use), only ask everyone to Star and promote it to other friends in need, thank you!
# 易采集/EasySpider: Visual Code-Free Web Crawler # 易采集/EasySpider: Visual Code-Free Web Crawler