pull/1943/head
dgtlmoon 1 year ago
parent 858b66efb4
commit 7477ce11d6

@ -712,7 +712,7 @@ def changedetection_app(config=None, datastore_o=None):
system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
is_html_webdriver = False
if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver':
if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver' or watch.get('fetch_backend', '').startswith('extra_browser_'):
is_html_webdriver = True
# Only works reliably with Playwright
@ -975,7 +975,7 @@ def changedetection_app(config=None, datastore_o=None):
system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
is_html_webdriver = False
if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver':
if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver' or watch.get('fetch_backend', '').startswith('extra_browser_'):
is_html_webdriver = True
password_enabled_and_share_is_off = False
@ -1029,7 +1029,7 @@ def changedetection_app(config=None, datastore_o=None):
is_html_webdriver = False
if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver':
if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver' or watch.get('fetch_backend', '').startswith('extra_browser_'):
is_html_webdriver = True
# Never requested successfully, but we detected a fetch error

@ -96,6 +96,7 @@ class Fetcher():
content = None
error = None
fetcher_description = "No description"
browser_connection_url = None
headers = {}
status_code = None
webdriver_js_execute_code = None
@ -251,14 +252,17 @@ class base_html_playwright(Fetcher):
proxy = None
def __init__(self, proxy_override=None):
def __init__(self, proxy_override=None, browser_connection_url=None):
super().__init__()
# .strip('"') is going to save someone a lot of time when they accidently wrap the env value
self.browser_type = os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').strip('"')
self.command_executor = os.getenv(
"PLAYWRIGHT_DRIVER_URL",
'ws://playwright-chrome:3000'
).strip('"')
self.browser_connection_url = browser_connection_url
if not browser_connection_url:
self.browser_connection_url = os.getenv(
"PLAYWRIGHT_DRIVER_URL",
'ws://playwright-chrome:3000'
).strip('"')
# If any proxy settings are enabled, then we should setup the proxy object
proxy_args = {}
@ -444,7 +448,7 @@ class base_html_playwright(Fetcher):
# Seemed to cause a connection Exception even tho I can see it connect
# self.browser = browser_type.connect(self.command_executor, timeout=timeout*1000)
# 60,000 connection timeout only
browser = browser_type.connect_over_cdp(self.command_executor, timeout=60000)
browser = browser_type.connect_over_cdp(self.browser_connection_url, timeout=60000)
# SOCKS5 with authentication is not supported (yet)
# https://github.com/microsoft/playwright/issues/10567
@ -504,7 +508,11 @@ class base_html_playwright(Fetcher):
self.status_code = response.status
if self.status_code != 200 and not ignore_status_codes:
raise Non200ErrorCodeReceived(url=url, status_code=self.status_code)
screenshot=self.page.screenshot(type='jpeg', full_page=True,
quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, screenshot=screenshot)
if len(self.page.content().strip()) == 0:
context.close()
@ -555,8 +563,6 @@ class base_html_webdriver(Fetcher):
else:
fetcher_description = "WebDriver Chrome/Javascript"
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 = ['proxyType', 'ftpProxy', 'httpProxy', 'noProxy',
@ -564,12 +570,13 @@ class base_html_webdriver(Fetcher):
'socksProxy', 'socksVersion', 'socksUsername', 'socksPassword']
proxy = None
def __init__(self, proxy_override=None):
def __init__(self, proxy_override=None, browser_connection_url=None):
super().__init__()
from selenium.webdriver.common.proxy import Proxy as SeleniumProxy
# .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 not self.browser_connection_url:
self.browser_connection_url = 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 = {}
@ -611,7 +618,7 @@ class base_html_webdriver(Fetcher):
options.proxy = self.proxy
self.driver = webdriver.Remote(
command_executor=self.command_executor,
command_executor=self.browser_connection_url,
options=options)
try:
@ -666,9 +673,10 @@ class base_html_webdriver(Fetcher):
class html_requests(Fetcher):
fetcher_description = "Basic fast Plaintext/HTTP Client"
def __init__(self, proxy_override=None):
def __init__(self, proxy_override=None, browser_connection_url=None):
super().__init__()
self.proxy_override = proxy_override
# browser_connection_url is none because its always 'launched locally'
def run(self,
url,

@ -168,7 +168,9 @@ class ValidateContentFetcherIsReady(object):
def __call__(self, form, field):
import urllib3.exceptions
from changedetectionio import content_fetcher
return
# AttributeError: module 'changedetectionio.content_fetcher' has no attribute 'extra_browser_unlocked<>ASDF213r123r'
# Better would be a radiohandler that keeps a reference to each class
if field.data is not None and field.data != 'system':
klass = getattr(content_fetcher, field.data)

@ -40,6 +40,18 @@ class difference_detection_processor():
if not prefer_fetch_backend or prefer_fetch_backend == 'system':
prefer_fetch_backend = self.datastore.data['settings']['application'].get('fetch_backend')
# In the case that the preferred fetcher was a browser config with custom connection URL..
# @todo - on save watch, if its extra_browser_ then it should be obvious it will use playwright (like if its requests now..)
browser_connection_url = None
if prefer_fetch_backend.startswith('extra_browser_'):
(t, key) = prefer_fetch_backend.split('extra_browser_')
connection = list(
filter(lambda s: (s['browser_name'] == key), self.datastore.data['settings']['requests'].get('extra_browsers', [])))
if connection:
prefer_fetch_backend = 'base_html_playwright'
browser_connection_url = connection[0].get('browser_connection_url')
# Grab the right kind of 'fetcher', (playwright, requests, etc)
if hasattr(content_fetcher, prefer_fetch_backend):
fetcher_obj = getattr(content_fetcher, prefer_fetch_backend)
@ -54,8 +66,9 @@ class difference_detection_processor():
print(f"Using proxy Key: {preferred_proxy_id} as Proxy URL {proxy_url}")
# Now call the fetcher (playwright/requests/etc) with arguments that only a fetcher would need.
# When browser_connection_url is None, it method should default to working out whats the best defaults (os env vars etc)
self.fetcher = fetcher_obj(proxy_override=proxy_url,
#browser_url_extra/configurable browser url=...
browser_connection_url=browser_connection_url
)
if self.watch.has_browser_steps:

@ -104,8 +104,9 @@
{% if watch.get_fetch_backend == "html_webdriver"
or ( watch.get_fetch_backend == "system" and system_default_fetcher == 'html_webdriver' )
or "extra_browser_" in watch.get_fetch_backend
%}
<img class="status-icon" src="{{url_for('static_content', group='images', filename='Google-Chrome-icon.png')}}" title="Using a chrome browser" >
<img class="status-icon" src="{{url_for('static_content', group='images', filename='Google-Chrome-icon.png')}}" title="Using a Chrome browser" >
{% endif %}
{%if watch.is_pdf %}<img class="status-icon" src="{{url_for('static_content', group='images', filename='pdf-icon.svg')}}" title="Converting PDF to text" >{% endif %}

Loading…
Cancel
Save