From f5aa767ef1d6e1c1867179f07fafdaa46437180d Mon Sep 17 00:00:00 2001
From: Luoyger <739052349@qq.com>
Date: Thu, 27 Apr 2023 12:48:43 +0800
Subject: [PATCH] add --no-sandbox for chrome in url_selenium (#3589)

without --no-sandbox param, load documents from url by selenium in
chrome occured error below:

```Traceback (most recent call last):
  File "/data//playgroud/try_langchain.py", line 343, in <module>
    langchain_doc_loader()
  File "/data//playgroud/try_langchain.py", line 67, in langchain_doc_loader
    documents = loader.load()
  File "/install/anaconda3-env/envs/python3.10/lib/python3.10/site-packages/langchain/document_loaders/url_selenium.py", line 102, in load
    driver = self._get_driver()
  File "/install/anaconda3-env/envs/python3.10/lib/python3.10/site-packages/langchain/document_loaders/url_selenium.py", line 76, in _get_driver
    return Chrome(options=chrome_options)
  File "/install/anaconda3-env/envs/python3.10/lib/python3.10/site-packages/selenium/webdriver/chrome/webdriver.py", line 80, in __init__
    super().__init__(
  File "/install/anaconda3-env/envs/python3.10/lib/python3.10/site-packages/selenium/webdriver/chromium/webdriver.py", line 104, in __init__
    super().__init__(
  File "/install/anaconda3-env/envs/python3.10/lib/python3.10/site-packages/selenium/webdriver/remote/webdriver.py", line 286, in __init__
    self.start_session(capabilities, browser_profile)
  File "/install/anaconda3-env/envs/python3.10/lib/python3.10/site-packages/selenium/webdriver/remote/webdriver.py", line 378, in start_session
    response = self.execute(Command.NEW_SESSION, parameters)
  File "/install/anaconda3-env/envs/python3.10/lib/python3.10/site-packages/selenium/webdriver/remote/webdriver.py", line 440, in execute
    self.error_handler.check_response(response)
  File "/install/anaconda3-env/envs/python3.10/lib/python3.10/site-packages/selenium/webdriver/remote/errorhandler.py", line 245, in check_response
    raise exception_class(message, screen, stacktrace)
selenium.common.exceptions.WebDriverException: Message: unknown error: Chrome failed to start: exited abnormally.
  (unknown error: DevToolsActivePort file doesn't exist)
  (The process started from chrome location /usr/bin/google-chrome is no longer running, so ChromeDriver is assuming that Chrome has crashed.)
Stacktrace:
#0 0x55cf8da1bfe3 <unknown>
#1 0x55cf8d75ad36 <unknown>
#2 0x55cf8d783b20 <unknown>
#3 0x55cf8d77fa9b <unknown>
#4 0x55cf8d7c1af7 <unknown>
#5 0x55cf8d7c111f <unknown>
#6 0x55cf8d7b8693 <unknown>
#7 0x55cf8d78b03a <unknown>
#8 0x55cf8d78c17e <unknown>
#9 0x55cf8d9dddbd <unknown>
#10 0x55cf8d9e1c6c <unknown>
#11 0x55cf8d9eb4b0 <unknown>
#12 0x55cf8d9e2d63 <unknown>
#13 0x55cf8d9b5c35 <unknown>
#14 0x55cf8da06138 <unknown>
#15 0x55cf8da062c7 <unknown>
#16 0x55cf8da14093 <unknown>
#17 0x7f3da31a72de start_thread
```

add option `chrome_options.add_argument("--no-sandbox")` for chrome.
---
 langchain/document_loaders/url_selenium.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/langchain/document_loaders/url_selenium.py b/langchain/document_loaders/url_selenium.py
index d061d1aebe7a9..339d5ec4b8d9d 100644
--- a/langchain/document_loaders/url_selenium.py
+++ b/langchain/document_loaders/url_selenium.py
@@ -71,6 +71,7 @@ def _get_driver(self) -> Union["Chrome", "Firefox"]:
             chrome_options = ChromeOptions()
             if self.headless:
                 chrome_options.add_argument("--headless")
+                chrome_options.add_argument("--no-sandbox")
             if self.executable_path is None:
                 return Chrome(options=chrome_options)
             return Chrome(executable_path=self.executable_path, options=chrome_options)