Access Chrome's network tab (e.g. XHR requests) with Selenium

selenium_xhr_requests_via_performance_logging.py

#
# This small example shows you how to access JS-based requests via Selenium
# Like this, one can access raw data for scraping, 
# for example on many JS-intensive/React-based websites
#

from time import sleep

from selenium import webdriver
from selenium.webdriver import DesiredCapabilities

# make chrome log requests
capabilities = DesiredCapabilities.CHROME
capabilities["loggingPrefs"] = {"performance": "ALL"}  # newer: goog:loggingPrefs
driver = webdriver.Chrome(
    desired_capabilities=capabilities, executable_path="./chromedriver"
)

# fetch a site that does xhr requests
driver.get("https://sitewithajaxorsomething.com")
sleep(5)  # wait for the requests to take place

# extract requests from logs
logs_raw = driver.get_log("performance")
logs = [json.loads(lr["message"])["message"] for lr in logs_raw]

def log_filter(log_):
    return (
        # is an actual response
        log_["method"] == "Network.responseReceived"
        # and json
        and "json" in log_["params"]["response"]["mimeType"]
    )

for log in filter(log_filter, logs):
    request_id = log["params"]["requestId"]
    resp_url = log["params"]["response"]["url"]
    print(f"Caught {resp_url}")
    print(driver.execute_cdp_cmd("Network.getResponseBody", {"requestId": request_id}))

Hello
Is there a way to use this with selenium Grid ? (remote)

With selnium grid I can catch the request but never the response

options = webdriver.ChromeOptions()
    options.add_argument('--ignore-ssl-errors=yes')
    options.add_argument('--ignore-certificate-errors')
    options.add_experimental_option('w3c', True)
    # Try to catch XHR response
    options.set_capability(
        "goog:loggingPrefs", {"performance": "ALL"}
)

driver = webdriver.Remote(
  command_executor='http://'+GRID_HOST+'/wd/hub',
  options=options,
)

driver.get("https://www.mywebsite.com/")

searchbox = driver.find_element(By.ID, "searchbox")
searchbox.send_keys("type something in the searchbox")

logs_raw = driver.get_log("performance")

for log in filter(log_filter, requests):
  request_id = log["params"]["requestId"]
  resp_url = log["params"]["response"]["url"]
  if 'aj_recherche' in resp_url:
   response = driver.execute_cdp_cmd("Network.getResponseBody", {"requestId": request_id})

I can then log every request associated to searchbox (ajax)
But never the JSON response (I can find it in the Chrome dev console)

Any idea ?

Hello Is there a way to use this with selenium Grid ? (remote)

With selnium grid I can catch the request but never the response

options = webdriver.ChromeOptions()
    options.add_argument('--ignore-ssl-errors=yes')
    options.add_argument('--ignore-certificate-errors')
    options.add_experimental_option('w3c', True)
    # Try to catch XHR response
    options.set_capability(
        "goog:loggingPrefs", {"performance": "ALL"}
)

driver = webdriver.Remote(
  command_executor='http://'+GRID_HOST+'/wd/hub',
  options=options,
)

driver.get("https://www.mywebsite.com/")

searchbox = driver.find_element(By.ID, "searchbox")
searchbox.send_keys("type something in the searchbox")

logs_raw = driver.get_log("performance")

for log in filter(log_filter, requests):
  request_id = log["params"]["requestId"]
  resp_url = log["params"]["response"]["url"]
  if 'aj_recherche' in resp_url:
   response = driver.execute_cdp_cmd("Network.getResponseBody", {"requestId": request_id})

I can then log every request associated to searchbox (ajax) But never the JSON response (I can find it in the Chrome dev console)

Any idea ?

@ofostier Yes! Took me some time to figure out but starting from Selenium 4.16.0 you should replace response = driver.execute_cdp_cmd("Network.getResponseBody", {"requestId": request_id}) with:

response = driver.execute(
                        driver_command="executeCdpCommand",
                        params={
                            "cmd": "Network.getResponseBody",
                            "params": {"requestId": request_id},
                                         },
                    )
body = response["value"]["body"]

source: get_browser_request_body(driver: WebDriver, request_id: str) answer from Borys Oliinyk.
Also consider what @nathan-fiscaletti mentioned about avoiding error -32000. In my case it happens for responses captured from previous sessions where I cleared session and local storage but was still using te same webdriver Remote() instance

It's better to listen for the Network.loadingFinished event before calling driver.execute_cdp_cmd("Network.getResponseBody", {"requestId": request_id}) to prevent this issue