This commit is contained in:
dgtlmoon
2025-05-30 16:32:18 +02:00
parent e9d28b810a
commit 0d332dd519
4 changed files with 77 additions and 68 deletions
@@ -47,10 +47,6 @@
{{ render_field(form.requests.form.jitter_seconds, class="jitter_seconds") }}
<span class="pure-form-message-inline">Example - 3 seconds random jitter could trigger up to 3 seconds earlier or up to 3 seconds later</span>
</div>
<div class="pure-control-group">
{{ render_field(form.requests.form.workers) }}
<span class="pure-form-message-inline">Number of concurrent workers to process watches. More workers = faster processing but higher memory usage.</span>
</div>
<div class="pure-control-group">
{{ render_field(form.application.form.filter_failure_notification_threshold_attempts, class="filter_failure_notification_threshold_attempts") }}
<span class="pure-form-message-inline">After this many consecutive times that the CSS/xPath filter is missing, send a notification
@@ -139,6 +135,10 @@
{{ render_field(form.application.form.webdriver_delay) }}
</div>
</fieldset>
<div class="pure-control-group">
{{ render_field(form.requests.form.workers) }}
<span class="pure-form-message-inline">Number of concurrent workers to process watches. More workers = faster processing but higher memory usage.</span>
</div>
<div class="pure-control-group inline-radio">
{{ render_field(form.requests.form.default_ua) }}
<span class="pure-form-message-inline">
+1 -1
View File
@@ -68,7 +68,7 @@ class Fetcher():
return self.error
@abstractmethod
def run(self,
async def run(self,
url,
timeout,
request_headers,
@@ -310,15 +310,15 @@ class fetcher(Fetcher):
async def main(self, **kwargs):
await self.fetch_page(**kwargs)
def run(self, url, timeout, request_headers, request_body, request_method, ignore_status_codes=False,
async def run(self, url, timeout, request_headers, request_body, request_method, ignore_status_codes=False,
current_include_filters=None, is_binary=False, empty_pages_are_a_change=False):
#@todo make update_worker async which could run any of these content_fetchers within memory and time constraints
max_time = os.getenv('PUPPETEER_MAX_PROCESSING_TIMEOUT_SECONDS', 180)
max_time = int(os.getenv('PUPPETEER_MAX_PROCESSING_TIMEOUT_SECONDS', 180))
# This will work in 3.10 but not >= 3.11 because 3.11 wants tasks only
# Now we run this properly in async context since we're called from async worker
try:
asyncio.run(asyncio.wait_for(self.main(
await asyncio.wait_for(self.main(
url=url,
timeout=timeout,
request_headers=request_headers,
@@ -328,7 +328,7 @@ class fetcher(Fetcher):
current_include_filters=current_include_filters,
is_binary=is_binary,
empty_pages_are_a_change=empty_pages_are_a_change
), timeout=max_time))
), timeout=max_time)
except asyncio.TimeoutError:
raise(BrowserFetchTimedOut(msg=f"Browser connected but was unable to process the page in {max_time} seconds."))
@@ -47,7 +47,7 @@ class fetcher(Fetcher):
self.proxy_url = k.strip()
def run(self,
async def run(self,
url,
timeout,
request_headers,
@@ -58,77 +58,86 @@ class fetcher(Fetcher):
is_binary=False,
empty_pages_are_a_change=False):
from selenium.webdriver.chrome.options import Options as ChromeOptions
# request_body, request_method unused for now, until some magic in the future happens.
import asyncio
# Wrap the entire selenium operation in a thread executor
def _run_sync():
from selenium.webdriver.chrome.options import Options as ChromeOptions
# request_body, request_method unused for now, until some magic in the future happens.
options = ChromeOptions()
options = ChromeOptions()
# Load Chrome options from env
CHROME_OPTIONS = [
line.strip()
for line in os.getenv("CHROME_OPTIONS", "").strip().splitlines()
if line.strip()
]
# Load Chrome options from env
CHROME_OPTIONS = [
line.strip()
for line in os.getenv("CHROME_OPTIONS", "").strip().splitlines()
if line.strip()
]
for opt in CHROME_OPTIONS:
options.add_argument(opt)
for opt in CHROME_OPTIONS:
options.add_argument(opt)
# 1. proxy_config /Proxy(proxy_config) selenium object is REALLY unreliable
# 2. selenium-wire cant be used because the websocket version conflicts with pypeteer-ng
# 3. selenium only allows ONE runner at a time by default!
# 4. driver must use quit() or it will continue to block/hold the selenium process!!
# 1. proxy_config /Proxy(proxy_config) selenium object is REALLY unreliable
# 2. selenium-wire cant be used because the websocket version conflicts with pypeteer-ng
# 3. selenium only allows ONE runner at a time by default!
# 4. driver must use quit() or it will continue to block/hold the selenium process!!
if self.proxy_url:
options.add_argument(f'--proxy-server={self.proxy_url}')
if self.proxy_url:
options.add_argument(f'--proxy-server={self.proxy_url}')
from selenium.webdriver.remote.remote_connection import RemoteConnection
from selenium.webdriver.remote.webdriver import WebDriver as RemoteWebDriver
driver = None
try:
# Create the RemoteConnection and set timeout (e.g., 30 seconds)
remote_connection = RemoteConnection(
self.browser_connection_url,
)
remote_connection.set_timeout(30) # seconds
from selenium.webdriver.remote.remote_connection import RemoteConnection
from selenium.webdriver.remote.webdriver import WebDriver as RemoteWebDriver
driver = None
try:
# Create the RemoteConnection and set timeout (e.g., 30 seconds)
remote_connection = RemoteConnection(
self.browser_connection_url,
)
remote_connection.set_timeout(30) # seconds
# Now create the driver with the RemoteConnection
driver = RemoteWebDriver(
command_executor=remote_connection,
options=options
)
# Now create the driver with the RemoteConnection
driver = RemoteWebDriver(
command_executor=remote_connection,
options=options
)
driver.set_page_load_timeout(int(os.getenv("WEBDRIVER_PAGELOAD_TIMEOUT", 45)))
except Exception as e:
if driver:
driver.quit()
raise e
driver.set_page_load_timeout(int(os.getenv("WEBDRIVER_PAGELOAD_TIMEOUT", 45)))
except Exception as e:
if driver:
driver.quit()
raise e
try:
driver.get(url)
try:
driver.get(url)
if not "--window-size" in os.getenv("CHROME_OPTIONS", ""):
driver.set_window_size(1280, 1024)
if not "--window-size" in os.getenv("CHROME_OPTIONS", ""):
driver.set_window_size(1280, 1024)
driver.implicitly_wait(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)))
if self.webdriver_js_execute_code is not None:
driver.execute_script(self.webdriver_js_execute_code)
# Selenium doesn't automatically wait for actions as good as Playwright, so wait again
driver.implicitly_wait(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)))
# @todo - how to check this? is it possible?
self.status_code = 200
# @todo somehow we should try to get this working for WebDriver
# raise EmptyReply(url=url, status_code=r.status_code)
if self.webdriver_js_execute_code is not None:
driver.execute_script(self.webdriver_js_execute_code)
# Selenium doesn't automatically wait for actions as good as Playwright, so wait again
driver.implicitly_wait(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)))
# @todo - how to check this? is it possible?
self.status_code = 200
# @todo somehow we should try to get this working for WebDriver
# raise EmptyReply(url=url, status_code=r.status_code)
# @todo - dom wait loaded?
import time
time.sleep(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay)
self.content = driver.page_source
self.headers = {}
self.screenshot = driver.get_screenshot_as_png()
except Exception as e:
driver.quit()
raise e
# @todo - dom wait loaded?
time.sleep(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay)
self.content = driver.page_source
self.headers = {}
self.screenshot = driver.get_screenshot_as_png()
except Exception as e:
driver.quit()
raise e
driver.quit()
# Run the selenium operations in a thread pool to avoid blocking the event loop
loop = asyncio.get_event_loop()
await loop.run_in_executor(None, _run_sync)