Re #267 - Pass settings for the proxy setup for webdriver (#326)

* Re #267 - Pass HTTP_PROXY as the proxy setup for webdriver
* Update README.md

README.md

@@ -136,24 +136,9 @@ When you enable a `json:` filter, you can even automatically extract and parse e
 
 `json:$.price` would give `23.50`, or you can extract the whole structure
 
-### Proxy
+### Proxy configuration
 
-A proxy for ChangeDetection.io can be configured by setting environment the 
-`HTTP_PROXY`, `HTTPS_PROXY` variables, examples are also in the `docker-compose.yml`
-
-`NO_PROXY` exclude list can be specified by following `"localhost,192.168.0.0/24"`
-
-as `docker run` with `-e`
-
-```
-docker run -d --restart always -e HTTPS_PROXY="socks5h://10.10.1.10:1080" -p "127.0.0.1:5000:5000" -v datastore-volume:/datastore --name changedetection.io dgtlmoon/changedetection.io
-```
-
-With `docker-compose`, see the `Proxy support example` in <a href="https://github.com/dgtlmoon/changedetection.io/blob/master/docker-compose.yml">docker-compose.yml</a>.
-
-For more information see https://docs.python-requests.org/en/master/user/advanced/#proxies
-
-This proxy support also extends to the notifications https://github.com/caronc/apprise/issues/387#issuecomment-841718867
+See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration
 
 ### RaspberriPi support?
 

changedetectionio/content_fetcher.py

@@ -3,6 +3,7 @@ import time
 from abc import ABC, abstractmethod
 from selenium import webdriver
 from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
+from selenium.webdriver.common.proxy import Proxy as SeleniumProxy
 from selenium.common.exceptions import WebDriverException
 import urllib3.exceptions
 
@@ -65,15 +66,34 @@ class html_webdriver(Fetcher):
 
     command_executor = ''
 
+    # Configs for Proxy setup
+    # In the ENV vars, is prefixed with "webdriver_", so it is for example "webdriver_sslProxy"
+    selenium_proxy_settings_mappings = ['ftpProxy', 'httpProxy', 'noProxy',
+                                        'proxyAutoconfigUrl', 'sslProxy', 'autodetect',
+                                        'socksProxy', 'socksUsername', 'socksPassword']
+    proxy=None
+
     def __init__(self):
-        self.command_executor = os.getenv("WEBDRIVER_URL", 'http://browser-chrome:4444/wd/hub')
+        # .strip('"') is going to save someone a lot of time when they accidently wrap the env value
+        self.command_executor = os.getenv("WEBDRIVER_URL", 'http://browser-chrome:4444/wd/hub').strip('"')
+
+        # If any proxy settings are enabled, then we should setup the proxy object
+        proxy_args = {}
+        for k in self.selenium_proxy_settings_mappings:
+            v = os.getenv('webdriver_' + k, False)
+            if v:
+                proxy_args[k] = v.strip('"')
+
+        if proxy_args:
+            self.proxy = SeleniumProxy(raw=proxy_args)
 
     def run(self, url, timeout, request_headers):
 
         # check env for WEBDRIVER_URL
         driver = webdriver.Remote(
             command_executor=self.command_executor,
-            desired_capabilities=DesiredCapabilities.CHROME)
+            desired_capabilities=DesiredCapabilities.CHROME,
+            proxy=self.proxy)
 
         try:
             driver.get(url)

changedetectionio/forms.py

@@ -106,10 +106,12 @@ class ValidateContentFetcherIsReady(object):
             except urllib3.exceptions.MaxRetryError as e:
                 driver_url = some_object.command_executor
                 message = field.gettext('Content fetcher \'%s\' did not respond.' % (field.data))
-                message += '<br/>'+field.gettext('Be sure that the selenium/webdriver runner is running and accessible via network from this container/host.')
+                message += '<br/>' + field.gettext(
+                    'Be sure that the selenium/webdriver runner is running and accessible via network from this container/host.')
                 message += '<br/>' + field.gettext('Did you follow the instructions in the wiki?')
                 message += '<br/><br/>' + field.gettext('WebDriver Host: %s' % (driver_url))
                 message += '<br/><a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">Go here for more information</a>'
+                message += '<br/>'+field.gettext('Content fetcher did not respond properly, unable to use it.\n %s' % (str(e)))
 
                 raise ValidationError(message)
 

docker-compose.yml

@@ -13,13 +13,23 @@ services:
 
   #      - PUID=1000
   #      - PGID=1000
-  #       # Alternative WebDriver/selenium URL, do not use "'s or 's!
+  #
+  #       Alternative WebDriver/selenium URL, do not use "'s or 's!
   #      - WEBDRIVER_URL=http://browser-chrome:4444/wd/hub
-  #        Proxy support example.
+  #
+  #       WebDriver proxy settings webdriver_ftpProxy, webdriver_httpProxy, webdriver_noProxy,
+  #                                webdriver_proxyAutoconfigUrl, webdriver_sslProxy, webdriver_autodetect,
+  #                                webdriver_socksProxy, webdriver_socksUsername, webdriver_socksPassword
+  #
+  #             https://selenium-python.readthedocs.io/api.html#module-selenium.webdriver.common.proxy
+  #
+  #        Plain requsts - proxy support example.
   #      - HTTP_PROXY=socks5h://10.10.1.10:1080
   #      - HTTPS_PROXY=socks5h://10.10.1.10:1080
+  #
   #        An exclude list (useful for notification URLs above) can be specified by with
   #      - NO_PROXY="localhost,192.168.0.0/24"
+  #
   #        Base URL of your changedetection.io install (Added to the notification alert)
   #      - BASE_URL=https://mysite.com