def main():
s = Server('/home/creature/browsermob/bin/browsermob-proxy', { 'port' : 1337})
s.start()
proxy = s.create_proxy({'port': 1338})
failcount = 0
d = tu.newProxytest(proxy)
proxy.new_har(options={'captureHeaders':False, 'captureContent': True})
if not deployOneTest(d):
failcount += 1
if not deleteTest(d):
failcount += 1
if not projectDeployTest(d):
failcount += 1
out = open('deploy.har', 'w')
out.write(str(proxy.har))
out.close()
# test all services from multiple projects showing up in services
if not multiDeployTest(d):
failcount += 1
# test that stopping services from services page removes them from project deployments
if not cleanupTest(d):
failcount += 1
tu.endtest(d)
s.stop()
sys.exit(failcount)
def proxy():
server = Server("/home/sergey/repositories/browsermob-proxy-2.1.4-bin/browsermob-proxy-2.1.4/bin/browsermob-proxy")
server.start()
proxy = server.create_proxy()
proxy.new_har(title='project_har')
yield proxy
server.stop()
def browser_and_proxy():
server = Server(config.BROWSERMOB_PATH)
server.start()
proxy = server.create_proxy()
proxy.new_har(options={'captureContent': True})
# Set up Chrome
option = webdriver.ChromeOptions()
option.add_argument('--proxy-server=%s' % proxy.proxy)
prefs = {"profile.managed_default_content_settings.images": 2}
option.add_experimental_option("prefs", prefs)
option.add_argument('--headless')
option.add_argument('--no-sandbox')
option.add_argument('--disable-gpu')
capabilities = DesiredCapabilities.CHROME.copy()
capabilities['acceptSslCerts'] = True
capabilities['acceptInsecureCerts'] = True
path = config.CHROME_PATH
browser = webdriver.Chrome(options=option,
desired_capabilities=capabilities,
executable_path=path)
try:
yield browser, proxy
finally:
browser.quit()
server.stop()
def locate(url, search_parameters=config.SEARCH_PARAMETERS):
server = Server(config.BROWSERMOB_PROXY)
server.start()
proxy = server.create_proxy()
options = Options()
options.headless = config.HEADLESS
profile = webdriver.FirefoxProfile(config.FIREFOX_PROFILE)
selenium_proxy = proxy.selenium_proxy()
profile.set_proxy(selenium_proxy)
browser = webdriver.Firefox(firefox_profile=profile, options=options)
proxy.new_har('source', options={'captureHeaders': True})
browser.get(url)
sleep(5)
browser.close()
server.stop()
streams = []
subtitles = []
for entry in proxy.har['log']['entries']:
for param in search_parameters:
request = {'method': entry['request']['method'], 'url': entry['request']['url'], 'headers': {x['name']: x['value'] for x in entry['request']['headers']}}
if param in entry['request']['url'].split('?')[0]:
if request not in streams:
streams.append(request)
elif '.vtt' in entry['request']['url'].split('?')[0] or '.srt' in entry['request']['url'].split('?')[0] or '.ass' in entry['request']['url'].split('?')[0]:
if request not in subtitles:
subtitles.append(request)
if os.path.exists(os.path.join(os.path.abspath(os.getcwd()), 'bmp.log')):
os.remove(os.path.join(os.path.abspath(os.getcwd()), 'bmp.log'))
if os.path.exists(os.path.join(os.path.abspath(os.getcwd()), 'geckodriver.log')):
os.remove(os.path.join(os.path.abspath(os.getcwd()), 'geckodriver.log'))
if os.path.exists(os.path.join(os.path.abspath(os.getcwd()), 'server.log')):
os.remove(os.path.join(os.path.abspath(os.getcwd()), 'server.log'))
return streams, subtitles
class ProxyDistributor:
browsermob_proxy_path = "/home/amerigo/PycharmProjects/Progetto/tesi/risorse/browsermob-proxy/bin/browsermob-proxy"
def __init__(self):
self.server = Server(self.browsermob_proxy_path)
self.actual_port = 9090
def get_new_proxy(self):
proxy = self.server.create_proxy({
'port': self.actual_port,
'captureHeaders': True,
'captureContent': True,
'captureBinaryContent': True
})
self.actual_port += 1
return proxy
def start(self):
if self.server is None:
self.server = Server(self.browsermob_proxy_path)
self.server.start()
def stop(self):
if self.server is not None:
self.server.stop()
def getAuthKey():
username = config['Users']['username']
password = config['Users']['password']
proxyServerAddress = config['config']['proxyserverpath']
# Creating Proxy server
server = Server(proxyServerAddress)
server.start()
proxy = server.create_proxy()
proxy.whitelist(regexp='*emofid.com*', status_code=123)
proxy.new_har(title="mofid",
options={
'captureContent': False,
'captureBinaryContent': False,
'captureHeaders': True
})
# Creating browser
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--ignore-certificate-errors')
chrome_options.add_argument("--proxy-server={0}".format(proxy.proxy))
browser = webdriver.Chrome(chrome_options=chrome_options)
url = "https://account.emofid.com/Login?returnUrl=%2Fconnect%2Fauthorize%2Fcallback%3Fclient_id%3Deasy2_client_pkce%26redirect_uri%3Dhttps%253A%252F%252Fd.easytrader.emofid.com%252Fauth-callback%26response_type%3Dcode%26scope%3Deasy2_api%2520openid%26state%3Df8ff796b1d994e0d8f6fa1f6e878f165%26code_challenge%3D7qf19ieakAg4BvrDkBTHbr5h7_A0BSvci7dtp-0ZUWY%26code_challenge_method%3DS256%26response_mode%3Dquery"
browser.get(url)
userFiled = browser.find_element_by_xpath('//*[@id="Username"]')
userFiled.clear()
userFiled.send_keys(username)
passwordFiled = browser.find_element_by_xpath('//*[@id="Password"]')
passwordFiled.clear()
passwordFiled.send_keys(password, Keys.RETURN)
element = WebDriverWait(browser, 10).until(
EC.presence_of_element_located(
(By.XPATH, "/html/body/app-root/d-release-notes/div/div/button")))
element.click()
try:
browser.find_element_by_xpath(
'//*[@id="root"]/main/div[2]/div[1]/ul[2]/li[1]/span/i').click()
except:
print('Error')
with open('data.json', 'w') as outfile:
json.dump(proxy.har, outfile)
server.stop()
tree = Tree(proxy.har)
authKey = ''
result = tree.execute(
"$.log.entries.request[@.url is 'https://d11.emofid.com/easy/api/account/checkuser'].headers"
)
for entry in result:
for e in entry:
if e['name'] == 'Authorization':
authKey = e["value"]
return authKey
def fetch_har_by_url(url, segments, index):
project_dir = os.path.dirname(__file__)
bpm_path = os.path.join(project_dir,
"browsermob-proxy-2.1.1/bin/browsermob-proxy")
server = Server(bpm_path)
server.start()
proxy = server.create_proxy()
profile = webdriver.FirefoxProfile()
profile.set_proxy(proxy.selenium_proxy())
driver = webdriver.Firefox(firefox_profile=profile,
executable_path=os.path.join(
os.path.dirname(__file__), _geckodriver))
proxy.new_har(url,
options={
'captureHeaders': True,
'captureContent': True,
'captureBinaryContent': True
})
proxy.wait_for_traffic_to_stop(2000, 10000)
driver.get(url)
har = proxy.har
server.stop()
driver.quit()
return har
class BrowserMobProxyTestCaseMixin(object):
def __init__(self, *args, **kwargs):
self.browsermob_server = None
self.browsermob_port = kwargs.pop('browsermob_port')
self.browsermob_script = kwargs.pop('browsermob_script')
def setUp(self):
options = {}
if self.browsermob_port:
options['port'] = self.browsermob_port
if not self.browsermob_script:
raise ValueError('Must specify --browsermob-script in order to '
'run browsermobproxy tests')
self.browsermob_server = Server(self.browsermob_script,
options=options)
self.browsermob_server.start()
def create_browsermob_proxy(self):
client = self.browsermob_server.create_proxy()
with self.marionette.using_context('chrome'):
self.marionette.execute_script("""
Services.prefs.setIntPref('network.proxy.type', 1);
Services.prefs.setCharPref('network.proxy.http', 'localhost');
Services.prefs.setIntPref('network.proxy.http_port', %(port)s);
Services.prefs.setCharPref('network.proxy.ssl', 'localhost');
Services.prefs.setIntPref('network.proxy.ssl_port', %(port)s);
""" % {"port": client.port})
return client
def tearDown(self):
if self.browsermob_server:
self.browsermob_server.stop()
self.browsermob_server = None
__del__ = tearDown
def proxy():
server = Server(os.path.join(os.path.dirname(__file__), 'browsermob-proxy-2.1.4/bin/browsermob-proxy'))
server.start()
proxy = server.create_proxy()
proxy.new_har(title='test_har')
yield proxy
server.stop()
def save_web_page_stats_to_har(url, webdriver_name, save_to_file):
"""Generate the HAR archive from an URL with the Selenium webdriver
'webdriver_name', saving the HAR file to 'save_to_file'
"""
browsermob_server = Server(Config.browsermob_executable)
browsermob_server.start()
random_port = get_a_random_free_tcp_port()
proxy_conn = browsermob_server.create_proxy({"port": random_port})
driver = create_selenium_webdriver(webdriver_name, proxy_conn)
try:
proxy_conn.new_har(url, options={'captureHeaders': True})
driver.get(url)
har_json = json.dumps(proxy_conn.har, ensure_ascii=False,
indent=4, separators=(',', ': '))
# Save '.HAR' file
with io.open(save_to_file + '.har', mode='wt', buffering=1,
encoding='utf8', errors='backslashreplace',
newline=None) as output_har_f:
output_har_f.write(unicode(har_json))
# Save '.PROF' file with profiling report (timings, sizes, etc)
with io.open(save_to_file + '.prof', mode='wb', buffering=1,
newline=None) as prof_output:
report_har_dictionary(proxy_conn.har, prof_output)
finally:
proxy_conn.close()
browsermob_server.stop()
driver.quit()
def main(argv):
init()
parser = argparse.ArgumentParser()
parser.add_argument('-u', action='store', dest='start_url', help='Set page URL', required=True)
parser.add_argument('-c', action='store', dest='cookies_file', help='JSON file with cookies', required=False)
parser.add_argument('-w', action='store', dest='webdriver_type', help='Set WebDriver type (firefox or phantomjs, firebox by default)', default="firefox", required=False)
results = parser.parse_args()
start_url = results.start_url
cookies_file = results.cookies_file
webdriver_type = results.webdriver_type
allowed_domain = urlparse(start_url).netloc
browsermobproxy_path = get_browsermobproxy_path()
options = {
'port': 9090,
}
server = Server(browsermobproxy_path,options)
server.start()
proxy = server.create_proxy()
if webdriver_type == "phantomjs":
service_args = ['--proxy=localhost:9091','--proxy-type=http',]
driver = webdriver.PhantomJS(service_args=service_args)
driver.set_window_size(1440, 1024)
else:
profile = webdriver.FirefoxProfile()
profile.set_proxy(proxy.selenium_proxy())
driver = webdriver.Firefox(firefox_profile=profile)
proxy.new_har('woodpycker', options={'captureHeaders': True, 'captureContent': True})
driver.get(start_url)
if not cookies_file is None:
with open(cookies_file, 'rb') as fp:
cookies = json.load(fp)
for cookie in cookies:
driver.add_cookie(cookie)
driver.refresh()
links = driver.find_elements_by_tag_name('a')
lenl = len(links)
for i in range(0,lenl):
if links[i].is_displayed():
url = links[i].get_attribute('href')
text = links[i].get_attribute('text')
if url.find(allowed_domain) != -1:
links[i].click()
print "%s Clicked on the link '%s' with HREF '%s'" % (Fore.BLUE+"*"+Fore.RESET,Style.BRIGHT+text+Style.RESET_ALL,Style.BRIGHT+url+Style.RESET_ALL)
show_status_codes(proxy.har,allowed_domain)
driver.back()
driver.refresh()
links = driver.find_elements_by_tag_name('a')
driver.quit()
server.stop()
class testAuthBasic(unittest.TestCase):
def setUp(self):
self.server = Server(
r"C:\Users\user\Documents\ScrinShots\SeleniumLessons\basic_auth\browsermob-proxy\bin\browsermob-proxy"
)
self.server.start()
self.proxy = self.server.create_proxy()
self.profile = webdriver.FirefoxProfile()
self.profile.set_proxy(self.proxy.selenium_proxy())
self.driver = webdriver.Firefox(firefox_profile=self.profile)
self.driver.implicitly_wait(8)
self.driver.get("https://auth-demo.aerobatic.io/")
def tearDown(self):
self.server.stop()
self.driver.quit()
def test_search(self):
self.proxy.basic_authentication("auth-demo.aerobatic.io", "aerobatic",
"aerobatic")
self.driver.get("https://auth-demo.aerobatic.io/protected-standard/")
assert self.driver.find_element_by_css_selector(
"a.button-primary[href='/']")
def getToken():
server = Server(r'F:\browsermob-proxy-2.1.4\bin\browsermob-proxy.bat')
server.start()
proxy = server.create_proxy()
chrome_options = Options()
chrome_options.add_argument('--proxy-server={0}'.format(proxy.proxy))
driver = webdriver.Chrome(chrome_options=chrome_options)
base_url = "http://jzsc.mohurd.gov.cn/data/company/detail?id=C5C5C4C3C5C2C7C7C5C5C0C2C7CCC7C7C5C6"
proxy.new_har("douyin",
options={
'captureHeaders': True,
'captureContent': True
})
driver.get(base_url)
while '验证已过期，是否重新重新进行验证或停留在当前页面？' in driver.page_source:
driver.find_element_by_xpath(
'//*[@id="app"]/div/header/div[5]/div/div[3]/div/button[1]').click(
)
time.sleep(2.5)
driver.refresh()
time.sleep(3)
result = proxy.har
token = set()
for entry in result['log']['entries']:
_url = entry['request']['url']
if "api/webApi/dataservice/query/comp/caDetailList?qyId" in str(_url):
_response = entry['request']
_accessToken = entry['request']['headers'][4]['value']
if _accessToken != '':
token.add(_accessToken)
server.stop()
driver.quit()
return list(token)[0]
class GetWebPageHar:
proxy_path = "./browsermob-proxy-2.1.4/bin/browsermob-proxy"
def __init__(self):
self.server = Server(str(Path(self.proxy_path).absolute()))
self.server.start()
self.proxy = self.server.create_proxy()
def get_har(self, url, output_filename):
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument("--proxy-server={0}".format(
self.proxy.proxy))
chrome_options.add_argument("--ignore-certificate-errors")
chrome_options.add_argument("--incognito")
driver = webdriver.Chrome(chrome_options=chrome_options)
self.proxy.new_har("google")
driver.get(url)
time.sleep(10)
har_json = json.dumps(self.proxy.har, indent=4, ensure_ascii=False)
with open(output_filename, "w") as f:
f.write(har_json)
driver.quit()
def stop(self):
self.server.stop()
def CaptureNetworkTraffic(url, server_ip, headers, file_path):
'''
This function can be used to capture network traffic from the browser. Using this function we can capture header/cookies/http calls made from the browser
url - Page url
server_ip - remap host to for specific URL
headers - this is a dictionary of the headers to be set
file_path - File in which HAR gets stored
'''
port = {'port': 9090}
server = Server("G:\\browsermob\\bin\\browsermob-proxy",
port) #Path to the BrowserMobProxy
server.start()
proxy = server.create_proxy()
proxy.remap_hosts("www.example.com", server_ip)
proxy.remap_hosts("www.example1.com", server_ip)
proxy.remap_hosts("www.example2.com", server_ip)
proxy.headers(headers)
profile = webdriver.FirefoxProfile()
profile.set_proxy(proxy.selenium_proxy())
driver = webdriver.Firefox(firefox_profile=profile)
new = {'captureHeaders': 'True', 'captureContent': 'True'}
proxy.new_har("google", new)
driver.get(url)
proxy.har # returns a HAR JSON blob
server.stop()
driver.quit()
file1 = open(file_path, 'w')
json.dump(proxy.har, file1)
file1.close()
def reloadHeaderAndCookie():
killPortProcess(8090)
global browser
browsermob_path = '/usr/local/browsermob-proxy-2.1.4/bin/browsermob-proxy'
server = Server(browsermob_path, {'port': 8090})
server.start()
time.sleep(10)
proxy = server.create_proxy()
time.sleep(1)
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument("--proxy-server={0}".format(proxy.proxy))
browser = webdriver.Chrome(options=chrome_options)
url1 = "https://www.united.com/en/us"
url2 = "https://www.united.com/ual/en/US/flight-search/book-a-flight/results/awd?f=SFO&t=PVG&d=2021-11-07&tt=1&at=1&sc=7&px=1&taxng=1&newHP=True&idx=1"
options = {'captureHeaders': True, 'captureCookies': True}
proxy.new_har("united", options=options)
browser.get(url1)
time.sleep(5)
browser.get(url2)
print("click close button to get actual results")
time.sleep(5)
print("we now save all auths")
newH = proxy.har # returns a HAR JSON blob
with open('latestUnitedAuth.json', 'w') as outfile:
json.dump(newH, outfile)
time.sleep(10)
server.stop()
browser.quit()
def download_file(url, file_name):
server = Server('./browsermob-proxy') #Local path to BMP
server.start()
proxy = server.create_proxy(
) #Proxy is used to generate a HAR file containing the connection URLS that the MP3s are loaded from.
chrome_options = Options()
chrome_options.add_argument("--proxy-server={0}".format(
proxy.proxy)) #Configure chrome options
chrome_options.add_argument('--ignore-certificate-errors')
chrome_options.add_argument('--headless')
driver = webdriver.Chrome(executable_path='./chromedriver',
options=chrome_options)
proxy.new_har('filename')
driver.get(url)
save = proxy.har
server.stop()
driver.quit()
results = [entry['request']['url'] for entry in save['log']['entries']]
embedded_link = [
res for res in results if "https://embed.vhx.tv/videos" in res
][0]
subprocess.call([
"./youtube-dl", "-f"
"best[height=540]", "-o"
"{}.mp4".format(file_name), "--ignore-errors", embedded_link
])
def get_dependencies(url):
browsermobproxy_location = "browsermob-proxy/bin/browsermob-proxy"
clean_opened_processes()
server = Server(browsermobproxy_location)
server.start()
time.sleep(0.5)
proxy = server.create_proxy()
time.sleep(0.5)
options = Options()
options.headless = True
profile = webdriver.FirefoxProfile()
profile.set_proxy(proxy.selenium_proxy())
driver = webdriver.Firefox(options=options, firefox_profile=profile)
proxy.new_har("captured_elems")
driver.get(url)
time.sleep(3)
resources = [
elem["request"]["url"] for elem in proxy.har["log"]["entries"]
]
server.stop()
driver.quit()
resources = list(set(resources)) # eliminamos duplicados
return resources
def print_hi():
server = Server(r'D:\exchange_data\browsermob-proxy-2.1.4\bin\browsermob-proxy.bat')
server.start()
proxy = server.create_proxy()
# 设置driver options
chrome_options = Options()
chrome_options.add_argument('--proxy-server={0}'.format(proxy.proxy))
driver = webdriver.Chrome(chrome_options=chrome_options)
#
url = 'https://www.baidu.com/'
proxy.new_har('fund', options={'captureHeaders': True, 'captureContent': True})
driver.get(url)
result = proxy.har
print(result)
for entry in result['log']['entries']:
_url = entry['request']['url']
# 根据URL找到数据接口
# if "lsjz?callback=" in _url:
_response = entry['response']
_content = _response['content']['text']
# 获取接口返回内容
print(_content)
server.stop()
def CaptureNetworkTraffic(url,server_ip,headers,file_path):
'''
This function can be used to capture network traffic from the browser. Using this function we can capture header/cookies/http calls made from the browser
url - Page url
server_ip - remap host to for specific URL
headers - this is a dictionary of the headers to be set
file_path - File in which HAR gets stored
'''
port = {'port':9090}
server = Server("G:\\browsermob\\bin\\browsermob-proxy",port) #Path to the BrowserMobProxy
server.start()
proxy = server.create_proxy()
proxy.remap_hosts("www.example.com",server_ip)
proxy.remap_hosts("www.example1.com",server_ip)
proxy.remap_hosts("www.example2.com",server_ip)
proxy.headers(headers)
profile = webdriver.FirefoxProfile()
profile.set_proxy(proxy.selenium_proxy())
driver = webdriver.Firefox(firefox_profile=profile)
new = {'captureHeaders':'True','captureContent':'True'}
proxy.new_har("google",new)
driver.get(url)
proxy.har # returns a HAR JSON blob
server.stop()
driver.quit()
file1 = open(file_path,'w')
json.dump(proxy.har,file1)
file1.close()
def run(dep, arr, arr_date, num, china):
server = Server(path) # 设置服务器脚本路径
server.start()
tasks = []
semaphore = asyncio.Semaphore(num) # 限制并发量
i = 0
for date in arr_date:
for departureCity in dep:
for arrivalCity in arr:
if departureCity != arrivalCity:
if departureCity not in china or arrivalCity not in china:
url = search_url(departureCity, arrivalCity, date)
print(departureCity + "--" + arrivalCity +
"开始爬取数据..." + str(i))
i = i + 1
while True:
try:
c = get_request(url, server, semaphore,
departureCity, arrivalCity,
date)
task = asyncio.ensure_future(c)
task.add_done_callback(callback)
tasks.append(task)
break
except Exception as e:
print(e)
loop = asyncio.get_event_loop()
loop.run_until_complete(asyncio.wait(tasks))
loop.close()
print("server closed")
server.stop()
def __init__(self, browsermobDirectory, headless=False):
# Imports
print(
"New class reference, finding valid signature. This might take a minute."
)
from browsermobproxy import Server
import psutil
import json
import time
import json
from selenium import webdriver
from selenium.webdriver.firefox.options import Options
# Kills any browsermob-proxy
for proc in psutil.process_iter():
# check whether the process name matches
if proc.name() == "browsermob-proxy":
proc.kill()
dict = {'port': 8090}
server = Server(path=browsermobDirectory, options=dict)
# "browsermob-proxy/bin/browsermob-proxy"
server.start()
time.sleep(1)
proxy = server.create_proxy()
time.sleep(1)
# Creates FF profile
profile = webdriver.FirefoxProfile()
selenium_proxy = proxy.selenium_proxy()
profile.set_proxy(selenium_proxy)
options = Options()
if headless == True:
options.headless = True
driver = webdriver.Firefox(firefox_profile=profile, options=options)
# Records FF Har
proxy.new_har("list")
driver.get("https://www.tiktok.com/en/trending")
data = proxy.har
for element in data['log']['entries']:
if "https://m.tiktok.com/share/item/list?" in element['request'][
'url'] or "https://www.tiktok.com/share/item/list?" in element[
'request']['url']:
print("Found signature, continuing.")
self.signature = element['request']['queryString'][6]['value']
# Get Trending hashtags
hashtags = driver.find_elements_by_xpath(
'//h3[@class="_list_item_title"]/a')
hashtagArray = []
for hashtag in hashtags:
hashtagArray.append(hashtag.get_attribute('title'))
self.hashtag = hashtagArray
self.headless = headless
self.browsermobDirectory = browsermobDirectory
server.stop()
driver.quit()
def getVideoMp4Url():
conn = sqlite3.connect('sqlite.db')
cursor = conn.cursor()
sql = "select id,url,mp4url from video;"
cursor.execute(sql)
result = cursor.fetchall()
server = Server("/bin/browsermob-proxy-2.0-beta-6/bin/browsermob-proxy")
server.start()
proxy = server.create_proxy()
#
# # 设置浏览器
profile = webdriver.FirefoxProfile()
profile.set_preference("javascript.enabled", False)
profile.set_proxy(proxy.selenium_proxy())
driver = webdriver.Firefox(firefox_profile=profile)
driver.get(
"http://www.tongzhuo100.com/login/v/?url=http://www.tongzhuo100.com/")
# 输入账号密码
stu_id = driver.find_element_by_name("usr").send_keys("18500951888")
stu_pwd = driver.find_element_by_name("pwd")
stu_pwd.send_keys("tz4006345699")
# 登录
stu_pwd.send_keys(Keys.RETURN)
time.sleep(10)
##得到监控
# 得到网页源代码
for index in range(len(result)):
if result[index][2]:
print "aready update %s" % result[index][1]
else:
proxy.new_har("tongzhuo")
driver.get(result[index][1])
while True:
content = proxy.har # returns a HAR JSON blob
data = content['log']['entries']
getMp4 = False
for j in range(len(data)):
url = data[j]['request']['url']
if url.find("mp4") != -1:
getMp4 = True
sql = "update video set mp4url=\'%s\' where id=\'%s\';" % (
url, result[index][0])
print sql
cursor.execute(sql)
conn.commit()
break
if getMp4:
break
else:
time.sleep(3)
conn.commit()
conn.close()
server.stop()
driver.quit()
def main(argv):
del argv
global folder_path, max_thread
folder_path = os.path.abspath(FLAGS.download)
max_thread = FLAGS.threads
t1 = threading.Thread(target=threadMaster, name="master")
t1.start()
global over
try:
os.mkdir(folder_path)
except:
if not os.path.basename(folder_path) in os.listdir(
os.path.dirname(folder_path)):
print("Error!")
exit(0)
server = Server(FLAGS.mob)
server.start()
px = server.create_proxy()
co = webdriver.ChromeOptions()
co.add_argument("--proxy-server={}".format(px.proxy))
driver = webdriver.Chrome(FLAGS.chromedriver, chrome_options=co)
# cookie = get_cookies()
# if cookie == None:
# driver.get("https://www.saavn.com/login.php?action=login")
# else:
# driver.get("https://www.saavn.com")
# _ = [driver.add_cookie(x) for x in cookie]
with open(FLAGS.playlist, "r") as f:
playlist_link = f.readline()
driver.get(playlist_link)
songs = len(
driver.find_element_by_css_selector(
".track-list").find_elements_by_css_selector(".song-wrap"))
px.new_har("saavn")
final_req = {}
driver.execute_script(
"Content.playAllSongs(null,true,{},true,null)".format(str(0)))
_ = input("Press [Enter] when Ready")
for i in range(songs):
driver.execute_script(
"Content.playAllSongs(null,true,{},true,null)".format(str(i)))
time.sleep(2)
for ent in px.har["log"]["entries"]:
if re.search("\.mp3\?", ent["request"]["url"]):
if not final_req.get(ent["request"]["url"], None):
final_req[ent["request"]["url"]] = 1
with lock:
downList.append(ent["request"]["url"])
with lock:
over = True
url_list = list(set(filter(lambda x: re.search("\.mp3\?", x), final_req)))
t1.join()
#Cleaning Up
driver.close()
server.stop()
def get_signature_url(user_url):
try:
# 代理服务
server = Server(proxy_file)
server.start()
proxy = server.create_proxy()
options = webdriver.FirefoxOptions()
# options.add_argument("--headless")
options.add_argument("--proxy-server={0}".format(proxy.proxy))
options.add_argument('--disable-gpu')
options.add_argument('lang=zh_CN.UTF-8')
options.add_argument("user-agent=" + USER_AGENTS[0])
options.add_argument('accept=' + accept[0])
options.add_argument("accept-language=" + accept_language[0])
options.add_argument('accept-encoding="gzip, deflate, br"')
options.add_argument("upgrade-insecure-requests=1")
options.add_argument('cache-control="max-age=0"')
options.add_argument(
"Cookie='_ga=GA1.2.500940217.1582528192; _gid=GA1.2.1014623963.1583113987'"
)
options.add_argument("Host=www.iesdouyin.com")
# options.headless = True
# options.add_experimental_option('excludeSwitches', ['enable-automation']) # 爬虫关键字
driver = webdriver.Firefox(firefox_options=options,
executable_path=driver_path)
proxy.new_har("douyin",
options={
'captureHeaders': True,
'captureContent': True
})
logger.info("原始URL {}".format(url))
driver.get(user_url)
time.sleep(6)
result = proxy.har # 获取HAR
# print(result)
for entry in result['log']['entries']:
_url = entry['request']['url']
# print(_url)
# # 根据URL找到数据接口,这里要找的是 http://git.liuyanlin.cn/get_ht_list 这个接口
if "_signature" in _url:
logger.info("获取到用户第一个数据请求接口------>>>\n{}".format(_url))
return _url
# print(_url)
# _response = entry['response']
# _content = _response['content']
# 获取接口返回内容
# print(_content)
except Exception as e:
logger.exception(e)
pass
finally:
server.stop()
driver.quit()
def run():
# set up proxy
server = Server(
) # or add path to binary: 'Server(path="browsermob-proxy")'
server.start()
# 'useEcc' is needed to have decent response time with HTTPS
proxy = server.create_proxy({"useEcc": True})
# set up Geckodriver/Firefox
# # uncomment if you want to use Firefox
# profile = webdriver.FirefoxProfile()
# profile.set_proxy(proxy.selenium_proxy())
# driver = webdriver.Firefox(firefox_profile=profile)
# set up Chrome driver
options = webdriver.ChromeOptions()
options.add_argument("--proxy-server=%s" % proxy.proxy)
# options.add_argument("--headless") # uncomment if you want headless Chrome
capabilities = webdriver.DesiredCapabilities.CHROME.copy()
capabilities["acceptInsecureCerts"] = True
driver = webdriver.Chrome(options=options,
desired_capabilities=capabilities)
# start test case
driver.implicitly_wait(10)
test_case = "ga_demo_store_add_to_cart"
# 'captureContent' for POST requests
proxy.new_har(test_case, options={"captureContent": True})
driver.get("https://enhancedecommerce.appspot.com/")
sleep(2)
driver.find_element_by_id("homepage-9bdd2-1").click()
sleep(2)
driver.find_element_by_id("addToCart").click()
sleep(2)
# export har and close all
har = proxy.har
server.stop()
driver.quit()
# uncomment if you need to export the har
# with open(
# join(abspath(dirname(__file__)), test_case) + ".har", "w", encoding="utf8"
# ) as f:
# json.dump(har, f)
# check hits against tracking plan and print results
path = join(abspath(dirname(__file__)), "tracking_plan.json")
tracking_plan = gaunit.TrackingPlan.from_json(path)
r = gaunit.check_har(test_case, tracking_plan, har=har)
r.print_result(display_ok=True)
class BrowsermobProxy(object):
def __init__(self, browsermob_proxy_bat_location: str):
self.server = Server(browsermob_proxy_bat_location, {'port': 9394})
def get_proxy(self):
return self.server.create_proxy()
def start_server(self):
self.server.start()
def stop_server(self):
self.server.stop()
class HARCatcher(SeleniumWrapper):
def __init__(self,
url,
har_name,
browsermob_proxy_location,
selector_dictionary=None,
default_timeout=None,
firefox_binary=None,
highlight=False,
geckodriver="geckodriver"):
self.selector_dictionary = selector_dictionary
self.default_timeout = default_timeout if default_timeout is not None else 30
self.highlight = highlight
for proc in psutil.process_iter():
# check whether the process name matches
if proc.name() == "browsermob-proxy":
proc.kill()
options = {'port': 8090}
# self.server = Server(path="../tools/browsermob-proxy-2.1.4/bin/browsermob-proxy", options=dict)
self.server = Server(path=browsermob_proxy_location, options=options)
self.server.start()
time.sleep(1)
self.proxy = self.server.create_proxy()
time.sleep(1)
profile = webdriver.FirefoxProfile()
selenium_proxy = self.proxy.selenium_proxy()
profile.set_proxy(selenium_proxy)
self.driver = webdriver.Firefox(firefox_profile=profile,
firefox_binary=firefox_binary,
executable_path=geckodriver)
self.proxy.new_har(har_name)
self.driver.get(url)
def get_har(self):
"""
Returns the har file as a python dictionary.
:return: har file as dict
"""
return self.proxy.har
def deinit(self):
self.server.stop()
try:
self.driver.quit()
except:
print(
"The driver couldn't be properly closed for an unknown reason."
)
class CreateHar(object):
"""create HTTP archive file"""
def __init__(self, mob_path,email,password):
"""initial setup"""
self.browser_mob = mob_path
self.server = self.driver = self.proxy = None
self.email = email
self.password = password
@staticmethod
def __store_into_file(title, result):
"""store result"""
har_file = open(title + '.har', 'w')
har_file.write(str(result))
har_file.close()
def __start_server(self):
"""prepare and start server"""
self.server = Server(self.browser_mob)
self.server.start()
self.proxy = self.server.create_proxy()
def __start_driver(self):
"""prepare and start driver"""
profile = webdriver.FirefoxProfile()
profile.set_proxy(self.proxy.selenium_proxy())
self.driver = webdriver.Firefox(firefox_profile=profile)
def start_all(self):
"""start server and driver"""
self.__start_server()
self.__start_driver()
def create_har(self, title, url):
"""start request and parse response"""
self.proxy.new_har(ref=title,options={'captureHeaders': True,'captureCookie':True})
# self.proxy.new_har(title)
self.proxy.remap_hosts(address="https://unite.nike.com/login?appVersion=833&experienceVersion=833")
self.driver.get(url)
self.driver.find_element_by_xpath('.//*[@name="emailAddress"]').send_keys(self.email)
self.driver.find_element_by_xpath('.//*[@name="password"]').send_keys(self.password)
self.driver.find_element_by_xpath('.//*[@value="SIGN IN"]').click()
time.sleep(14)
result = json.dumps(self.proxy.har, ensure_ascii=False)
self.__store_into_file(title, result)
def stop_all(self):
"""stop server and driver"""
self.server.stop()
self.driver.quit()
class HTTPTracing(object):
"""create HTTP archive file"""
def __init__(self, url):
"""initial setup"""
self.browser_mob = path
self.server = self.driver = self.proxy = None
self.traffic_for_domain = []
self.url = url
def __start_server(self):
"""prepare and start server"""
self.server = Server(self.browser_mob)
self.server.start()
self.proxy = self.server.create_proxy()
def __enter__(self):
self.__start_server()
self.driver = webdriver.Firefox(proxy=self.proxy.selenium_proxy())
self.driver.implicitly_wait(10)
self.driver.get(self.url)
self.proxy.new_har(self.url,
options={
'captureHeaders': True,
'captureCookies': True
})
return self
@property
def entries(self):
return self.proxy.har["log"]["entries"]
def wait_change_entry(self, url, duration=2):
num_loops = duration / 0.1
count = 0
har = self.proxy.har
entry = har["log"]["entries"]
while count <= num_loops and not self.url_in_entry(url):
time.sleep(0.1)
count += 1
return self.f_entries
def url_in_entry(self, base_url):
self.f_entries = list(
filter(lambda x: base_url in x["request"]["url"], self.entries))
return self.f_entries
def __exit__(self, exc_type, exc_val, exc_tb):
"""stop server and driver"""
self.server.stop()
self.driver.quit()
def getStreamFile(linkToFilm):
#print("WAITING FOR PROXY")
#proxyThread.join()
#print("DONE WAITING")
#proxy = proxyContainer["proxy"]
#server = proxyContainer["server"]
server = Server(r"c:\Users\Alex\Documents\GitHub\Hackathon_MEGOGO_2018\getStreamFile\browsermob-proxy\bin\browsermob-proxy")
server.start()
proxy = server.create_proxy()
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument("--proxy-server={0}".format(proxy.proxy))
chrome_options.add_argument("headless")
browser = webdriver.Chrome(chrome_options=chrome_options)
proxy.new_har("defaultName")
browser.get(linkToFilm)
element = 0
try:
# that's for serials
element = browser.find_element_by_xpath('//*[@id="episode-code"]/iframe')
except NoSuchElementException:
# and that's for movies
element = browser.find_element_by_xpath('//*[@id="basplayer_hd"]/iframe')
element.click()
element.click() # double-click to ensure that video will load
i = 0
while True:
print("wait...")
time.sleep(0.1)
i = i + 0.1
for elem in proxy.har['log']['entries']:
if "request" in elem.keys():
if "queryString" in elem['request'].keys():
if len(elem['request']['queryString']) > 0 and elem['request']['queryString'][0]['name'] == "tok":
if "m3u8" in elem['request']['url']:
browser.quit()
server.stop()
return elem['request']['url']
if i > 20:
print("Error in getting requests. Restart the app.") # TODO: restart browser() in case requests won't load
class RequestLog(object):
def __init__(self,
har_name,
blacklist=[],
har_options={
'captureHeaders': True,
'captureContent': True
}):
import os
#har_options = {}
browsermob_exe = os.environ[
'BROWSERMOB'] if 'BROWSERMOB' in os.environ else 'D:/browsermob-proxy-2.1.4/bin/browsermob-proxy'
self.server = Server(browsermob_exe)
self.server.start()
#raise
#self.server = RemoteServer(host='111.230.223.37',port=62421)
self.proxy = self.server.create_proxy(
{'httpProxy': '111.230.223.37:24342'})
self.proxy.new_har(har_name, options=har_options)
for host, code in blacklist:
self.setBlackList(host, code)
def setBlackList(self, host, code):
self.proxy.blacklist(host, code)
def setOptions(self, options):
options.add_argument('--proxy-server={0}'.format(self.proxy.proxy))
def getHar(self):
return self.proxy.har
def getEntries(self):
return self.proxy.har['log']['entries']
def close(self):
try:
if self.server != None:
self.server.stop()
except:
pass
if self.proxy != None:
self.proxy.close()
def __enter__(self):
return self
def __exit__(self, exc_type, exc_val, exc_tb):
self.close()
def run(departureCity, arrivalCity, date, num):
server = Server(path) # 设置服务器脚本路径
server.start()
tasks = []
semaphore = asyncio.Semaphore(num) # 限制并发量
url = search_url(departureCity, arrivalCity, date)
print(departureCity + "--" + arrivalCity + "开始爬取数据...")
c = get_request(url, server, semaphore, departureCity, arrivalCity, date)
task = asyncio.ensure_future(c)
task.add_done_callback(callback)
tasks.append(task)
loop = asyncio.get_event_loop()
loop.run_until_complete(asyncio.wait(tasks))
print("server closed")
server.stop()
def main():
init()
if len(sys.argv) >= 2:
start_url = sys.argv[1]
else:
print "You must specify page URL!"
sys.exit()
allowed_domain = urlparse(start_url).netloc
browsermobproxy_path = "/usr/local/opt/browsermobproxy/bin/browsermob-proxy"
options = {
'port': 9090,
}
server = Server(browsermobproxy_path,options)
server.start()
proxy = server.create_proxy()
profile = webdriver.FirefoxProfile()
profile.set_proxy(proxy.selenium_proxy())
driver = webdriver.Firefox(firefox_profile=profile)
driver.get(start_url)
links = driver.find_elements_by_tag_name('a')
lenl = len(links)
for i in range(0,lenl):
if links[i].is_displayed():
url = links[i].get_attribute('href')
text = links[i].get_attribute('text')
if url.find(allowed_domain) != -1:
proxy.new_har('demo')
links[i].click()
print "%s Clicked on the link '%s' with HREF '%s'" % (Fore.BLUE+"*"+Fore.RESET,Style.BRIGHT+text+Style.RESET_ALL,Style.BRIGHT+url+Style.RESET_ALL)
show_status_codes(proxy.har,allowed_domain)
driver.back()
driver.refresh()
links = driver.find_elements_by_tag_name('a')
driver.quit()
server.stop()
class CreateHar(object):
"""create HTTP archive file"""
def __init__(self, mob_path):
"""initial setup"""
self.browser_mob = mob_path
self.server = self.driver = self.proxy = None
@staticmethod
def __store_into_file(title, result):
"""store result"""
har_file = open(title + '.har', 'w')
har_file.write(str(result))
har_file.close()
def __start_server(self):
"""prepare and start server"""
self.server = Server(self.browser_mob)
self.server.start()
self.proxy = self.server.create_proxy()
def __start_driver(self):
"""prepare and start driver"""
profile = webdriver.FirefoxProfile()
profile.set_proxy(self.proxy.selenium_proxy())
self.driver = webdriver.Firefox(firefox_profile=profile)
def start_all(self):
"""start server and driver"""
self.__start_server()
self.__start_driver()
def create_har(self, title, url):
"""start request and parse response"""
self.proxy.new_har(title)
self.driver.get(url)
result = json.dumps(self.proxy.har, ensure_ascii=False)
self.__store_into_file(title, result)
def stop_all(self):
"""stop server and driver"""
self.server.stop()
self.driver.quit()
def fetch(url, config, output_directory, fetchEngine="browsermobproxy+selenium", browser="firefox"):
if fetchEngine in ("phantomjs", "ph"):
data = subprocess.check_output( config['fetchEngines']['phantomjs_command'].replace("$url", url), shell=True )
elif fetchEngine in ("browsermobproxy+selenium", "bs"):
from browsermobproxy import Server
from selenium import webdriver
server = Server(config['fetchEngines']['browsermobproxy_binary'])
server.start()
proxy = server.create_proxy()
if browser in ("firefox", "ff"):
profile = webdriver.FirefoxProfile()
profile.set_proxy(proxy.selenium_proxy())
driver = webdriver.Firefox(firefox_profile=profile)
else:
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument("--proxy-server={0}".format(proxy.proxy))
driver = webdriver.Chrome(chrome_options = chrome_options)
proxy.new_har(url, options={'captureHeaders': True})
driver.get(url)
data = json.dumps(proxy.har, ensure_ascii=False)
server.stop()
driver.quit()
else:
sys.exit("Unrecognized engine.")
if (data):
fileName = output_directory + "/" + url.replace("http://", "").replace("https://", "") + "_" + strftime("%Y-%m-%d_%H:%M:%S", gmtime()) + ".har"
f = open(fileName, "w")
f.write(data.encode("utf8"))
f.close()
return fileName
else:
return None
class ad_driver():
_driver = None
_server = None
_proxy = None
def __init__(self, path_to_batch, browser="chrome"):
""" start browsermob proxy """
self._server = Server(path_to_batch)
self._server.start()
self._proxy = self._server.create_proxy()
""" Init browser profile """
if browser is "chrome":
PROXY = "localhost:%s" % self._proxy.port # IP:PORT or HOST:PORT
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--proxy-server=%s' % PROXY)
self._driver = webdriver.Chrome(chrome_options=chrome_options)
elif browser is "ff":
profile = webdriver.FirefoxProfile()
driver = webdriver.Firefox(firefox_profile=profile, proxy=proxy)
else:
print "Please set 'browser' variable to any of the value \n 'chrome', 'ff' !"
self._driver.maximize_window()
self._driver.implicitly_wait(20)
def execute(self, test):
self._proxy.new_har(test["name"])
self._driver.get(_test_data_dir + os.sep + test['file'])
time.sleep(2)
callToTestMethod = getattr(test_steps, test["name"])
callToTestMethod(self._driver)
har = self._proxy.har
requests = har['log']['entries']
return requests
def quit(self):
self._server.stop()
self._driver.quit()
class Proxy(object):
proxy = None
proxy_server = None
test_id = None
def __init__(self, test_id):
self.test_id = test_id
self.start_proxy()
def start_proxy(self):
self.proxy_server = Server(config.proxy_bin)
self.proxy_server.start()
self.proxy = self.proxy_server.create_proxy()
if config.blacklist:
self.set_blacklist(config.blacklist)
self.proxy.new_har(self.test_id)
logger.debug('Browsermob proxy started.')
return self
def stop_proxy(self):
filename = '{}.har'.format(self.test_id)
with open(filename, 'w') as harfile:
json.dump(self.proxy.har, harfile)
data = json.dumps(self.proxy.har, ensure_ascii=False)
self.proxy_server.stop()
self.proxy = None
self.proxy_server = None
logger.debug('Browsermob proxy stopped. HAR created: {}'
.format(filename))
def set_blacklist(self, domain_list):
for domain in domain_list:
self.proxy.blacklist("^https?://([a-z0-9-]+[.])*{}*.*"
.format(domain), 404)
logger.debug("Proxy blacklist set.")
def get_blacklist(self):
return requests.get('{}{}/blacklist'
.format(config.proxy_api, self.proxy.port))
class BrowserMobProxyTestCaseMixin(object):
def __init__(self, *args, **kwargs):
self.browsermob_server = None
self.browsermob_port = kwargs.pop('browsermob_port')
self.browsermob_script = kwargs.pop('browsermob_script')
def setUp(self):
options = {}
if self.browsermob_port:
options['port'] = self.browsermob_port
if not self.browsermob_script:
raise ValueError('Must specify --browsermob-script in order to '
'run browsermobproxy tests')
self.browsermob_server = Server(
self.browsermob_script, options=options)
self.browsermob_server.start()
def create_browsermob_proxy(self):
client = self.browsermob_server.create_proxy()
with self.marionette.using_context('chrome'):
self.marionette.execute_script("""
Components.utils.import("resource://gre/modules/Preferences.jsm");
Preferences.set("network.proxy.type", 1);
Preferences.set("network.proxy.http", "localhost");
Preferences.set("network.proxy.http_port", {port});
Preferences.set("network.proxy.ssl", "localhost");
Preferences.set("network.proxy.ssl_port", {port});
""".format(port=client.port))
return client
def tearDown(self):
if self.browsermob_server:
self.browsermob_server.stop()
self.browsermob_server = None
__del__ = tearDown
def create_hars(urls, browsermob_dir, run_cached):
for url in urls:
print 'starting browsermob proxy'
server = Server('{}/bin/browsermob-proxy'.format(browsermob_dir))
server.start()
proxy = server.create_proxy()
profile = webdriver.FirefoxProfile()
profile.set_proxy(proxy.selenium_proxy())
driver = webdriver.Firefox(firefox_profile=profile)
url_slug = slugify(url)
proxy.new_har(url_slug)
print 'loading page: {}'.format(url)
driver.get(url)
har_name = '{}-{}.har'.format(url_slug, time.time())
print 'saving HAR file: {}'.format(har_name)
save_har(har_name, proxy.har)
if run_cached:
url_slug = '{}-cached'.format(slugify(url))
proxy.new_har(url_slug)
print 'loading cached page: {}'.format(url)
driver.get(url)
har_name = '{}-{}.har'.format(url_slug, time.time())
print 'saving HAR file: {}'.format(har_name)
save_har(har_name, proxy.har)
driver.quit()
print 'stopping browsermob proxy'
server.stop()
class BrowserMobProxyTestCaseMixin(object):
def __init__(self, *args, **kwargs):
self.browsermob_server = None
self.browsermob_port = kwargs.pop('browsermob_port')
self.browsermob_script = kwargs.pop('browsermob_script')
def setUp(self):
options = {}
if self.browsermob_port:
options['port'] = self.browsermob_port
if not self.browsermob_script:
raise ValueError('Must specify --browsermob-script in order to '
'run browsermobproxy tests')
self.browsermob_server = Server(
self.browsermob_script, options=options)
self.browsermob_server.start()
def create_browsermob_proxy(self):
client = self.browsermob_server.create_proxy()
with self.marionette.using_context('chrome'):
self.marionette.execute_script("""
Services.prefs.setIntPref('network.proxy.type', 1);
Services.prefs.setCharPref('network.proxy.http', 'localhost');
Services.prefs.setIntPref('network.proxy.http_port', %(port)s);
Services.prefs.setCharPref('network.proxy.ssl', 'localhost');
Services.prefs.setIntPref('network.proxy.ssl_port', %(port)s);
""" % {"port": client.port})
return client
def tearDown(self):
if self.browsermob_server:
self.browsermob_server.stop()
self.browsermob_server = None
__del__ = tearDown
def run_webdriver(self, start_url, port, config, download_dir):
global useragent
global referer
urllib3_logger = logging.getLogger('urllib3')
urllib3_logger.setLevel(logging.DEBUG)
logging.info("Starting WebRunner")
firefox_profile = None
server = None
proxy = None
har = None
if config.referer:
referer = config.referer
else:
referer = 'http://www.google.com/search?q={}+&oq={}&oe=utf-8&rls=org.mozilla:en-US:official&client=firefox-a&channel=fflb&gws_rd=cr'.format(
config.url, config.url)
if config.useragent:
useragent = config.useragent
else:
useragent = 'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:24.0) Gecko/20100101 Firefox/24.0'
logging.debug("Running with UserAgent: {}".format(useragent))
logging.debug("Running with Referer: {}".format(referer))
logging.debug("Checking URL: {}".format(config.url))
server = Server("lib/browsermob/bin/browsermob-proxy", {'port': port})
server.start()
proxy = server.create_proxy()
proxy.headers({'User-Agent': useragent, 'Accept-Encoding': "", 'Connection': 'Close'})
request_js = (
'var referer = request.getProxyRequest().getField("Referer");'
'addReferer(request);'
'function addReferer(r){'
'if (! referer ) {'
'r.addRequestHeader("Referer","' + referer + '");'
'}'
'return;'
'}')
proxy.request_interceptor(request_js)
if config.firefoxprofile:
firefox_profile = FirefoxProfile(profile_directory=config.firefoxprofile)
else:
firefox_profile = FirefoxProfile()
logging.debug("Using profile {}".format(firefox_profile.path))
firefox_profile.set_preference("security.OCSP.enabled", 0)
firefox_profile.set_preference("browser.download.folderList", 2)
firefox_profile.set_preference("browser.download.manager.showWhenStarting", False)
firefox_profile.set_preference("browser.download.dir", download_dir)
firefox_profile.set_preference("browser.helperApps.neverAsk.saveToDisk",
"application/x-xpinstall;application/x-zip;application/x-zip-compressed;application/octet-stream;application/zip;application/pdf;appl\
ication/msword;text/plain;application/octet")
firefox_profile.set_preference("browser.helperApps.alwaysAsk.force", False)
firefox_profile.set_preference("browser.download.manager.showWhenStarting", False)
firefox_profile.set_preference("network.proxy.type", 1)
firefox_profile.set_proxy(proxy.selenium_proxy())
try:
webdriver = WebDriver(firefox_profile)
proxy.new_har(start_url.hostname,
options={"captureHeaders": "true", "captureContent": "true", "captureBinaryContent": "true"})
self.analyse_page(webdriver, start_url)
har = proxy.har
logging.info("Stopping WebRunner")
proxy.close()
server.stop()
webdriver.quit()
har = Har(har)
except Exception, e:
logging.error(e)
proxy.close()
webdriver.quit()
server.stop()
class performance(object):
#create performance data
def __init__(self, mob_path):
#initialize
from datetime import datetime
print "%s: Go "%(datetime.now())
self.browser_mob = mob_path
self.server = self.driver = self.proxy = None
@staticmethod
def __store_into_file(args,title, result):
#store data collected into file
if 'path' in args:
har_file = open(args['path']+'/'+title + '.json', 'w')
else:
har_file = open(title + '.json', 'w')
har_file.write(str(result))
har_file.close()
def __start_server(self):
#prepare and start server
self.server = Server(self.browser_mob)
self.server.start()
self.proxy = self.server.create_proxy()
def __start_driver(self,args):
#prepare and start driver
#chromedriver
if args['browser'] == 'chrome':
print "Browser: Chrome"
print "URL: {0}".format(args['url'])
chromedriver = os.getenv("CHROMEDRIVER_PATH", "/chromedriver")
os.environ["webdriver.chrome.driver"] = chromedriver
url = urlparse.urlparse (self.proxy.proxy).path
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument("--proxy-server={0}".format(url))
chrome_options.add_argument("--no-sandbox")
self.driver = webdriver.Chrome(chromedriver,chrome_options = chrome_options)
#firefox
if args['browser'] == 'firefox':
print "Browser: Firefox"
profile = webdriver.FirefoxProfile()
profile.set_proxy(self.proxy.selenium_proxy())
self.driver = webdriver.Firefox(firefox_profile=profile)
def start_all(self,args):
#start server and driver
self.__start_server()
self.__start_driver(args)
def create_har(self,args):
#start request and parse response
self.proxy.new_har(args['url'], options={'captureHeaders': True})
self.driver.get(args['url'])
result = json.dumps(self.proxy.har, ensure_ascii=False)
self.__store_into_file(args,'har', result)
performance = json.dumps(self.driver.execute_script("return window.performance"), ensure_ascii=False)
self.__store_into_file(args,'perf', performance)
def stop_all(self):
#stop server and driver
from datetime import datetime
print "%s: Finish"%(datetime.now())
self.server.stop()
self.driver.quit()
from browsermobproxy import Server
server = Server("/root/Desktop/browsermob-proxy-2.1.0-beta-4/bin/browsermob-proxy")
server.start()
proxy = server.create_proxy()
from selenium import webdriver
profile = webdriver.FirefoxProfile()
profile.set_proxy(proxy.selenium_proxy())
driver = webdriver.Firefox(firefox_profile=profile)
proxy.new_har("google")
driver.get("http://www.google.co.uk")
test = proxy.har # returns a HAR JSON blob
print test
server.stop()
driver.quit()
class HarProfiler:
def __init__(self, config, url, login_first=False):
self.url = url
self.login_first = login_first
self.login_user = config.get('login_user')
self.login_password = config.get('login_password')
self.browsermob_dir = config['browsermob_dir']
self.har_dir = config['har_dir']
self.label_prefix = config['label_prefix'] or ''
self.run_cached = config['run_cached']
self.virtual_display = config['virtual_display']
self.virtual_display_size_x = config['virtual_display_size_x']
self.virtual_display_size_y = config['virtual_display_size_y']
self.label = '{}{}'.format(self.label_prefix, self.slugify(url))
self.cached_label = '{}-cached'.format(self.label)
epoch = time.time()
self.har_name = '{}-{}.har'.format(self.label, epoch)
self.cached_har_name = '{}-{}.har'.format(self.cached_label, epoch)
def __enter__(self):
if self.virtual_display:
log.info('starting virtual display')
self.display = Display(visible=0, size=(
self.virtual_display_size_x,
self.virtual_display_size_y
))
self.display.start()
log.info('starting browsermob proxy')
self.server = Server('{}/bin/browsermob-proxy'.format(
self.browsermob_dir)
)
self.server.start()
return self
def __exit__(self, type, value, traceback):
log.info('stopping browsermob proxy')
self.server.stop()
if self.virtual_display:
log.info('stopping virtual display')
self.display.stop()
def _make_proxied_webdriver(self):
proxy = self.server.create_proxy()
profile = webdriver.FirefoxProfile()
profile.set_proxy(proxy.selenium_proxy())
driver = webdriver.Firefox(firefox_profile=profile)
return (driver, proxy)
def _save_har(self, har, cached=False):
if not os.path.isdir(self.har_dir):
os.makedirs(self.har_dir)
if not cached:
har_name = self.har_name
elif cached:
har_name = self.cached_har_name
log.info('saving HAR file: {}'.format(har_name))
with open(os.path.join(self.har_dir, har_name), 'w') as f:
json.dump(har, f, indent=2, ensure_ascii=False)
def _login(self, driver):
log.info('logging in...')
error_msg = 'must specify login credentials in yaml config file'
if self.login_user is None:
raise RuntimeError(error_msg)
if self.login_password is None:
raise RuntimeError(error_msg)
driver.get('https://courses.edx.org/login')
# handle both old and new style logins
try:
email_field = driver.find_element_by_id('email')
password_field = driver.find_element_by_id('password')
except NoSuchElementException:
email_field = driver.find_element_by_id('login-email')
password_field = driver.find_element_by_id('login-password')
email_field.send_keys(self.login_user)
password_field.send_keys(self.login_password)
password_field.submit()
def _add_page_event_timings(self, driver, har):
jscript = textwrap.dedent("""
var performance = window.performance || {};
var timings = performance.timing || {};
return timings;
""")
timings = driver.execute_script(jscript)
har['log']['pages'][0]['pageTimings']['onContentLoad'] = (
timings['domContentLoadedEventEnd'] - timings['navigationStart']
)
har['log']['pages'][0]['pageTimings']['onLoad'] = (
timings['loadEventEnd'] - timings['navigationStart']
)
return har
def load_page(self):
try:
driver, proxy = self._make_proxied_webdriver()
if self.login_first:
self._login(driver)
proxy.new_har(self.label)
log.info('loading page: {}'.format(self.url))
driver.get(self.url)
har = self._add_page_event_timings(driver, proxy.har)
self._save_har(har)
if self.run_cached:
proxy.new_har(self.cached_label)
log.info('loading cached page: {}'.format(self.url))
driver.get(self.url)
har = self._add_page_event_timings(driver, proxy.har)
self._save_har(har, cached=True)
except Exception:
raise
finally:
driver.quit()
def slugify(self, text):
pattern = re.compile(r'[^a-z0-9]+')
slug = '-'.join(word for word in pattern.split(text.lower()) if word)
return slug
class HarProfiler:
def __init__(self, config, url):
self.har_dir = config['har_dir']
self.browsermob_dir = config['browsermob_dir']
self.label_prefix = config['label_prefix'] or ''
self.virtual_display = config['virtual_display']
self.virtual_display_size_x = config['virtual_display_size_x']
self.virtual_display_size_y = config['virtual_display_size_y']
self.label = '{}{}'.format(
self.label_prefix,
format(self.slugify(url))
)
self.cached_label = '{}-cached'.format(self.label)
epoch = time.time()
self.har_name = '{}-{}.har'.format(self.label, epoch)
self.cached_har_name = '{}-{}.har'.format(self.cached_label, epoch)
def __enter__(self):
log.info('starting virtual display')
if self.virtual_display:
self.display = Display(visible=0, size=(
self.virtual_display_size_x,
self.virtual_display_size_y
))
self.display.start()
log.info('starting browsermob proxy')
self.server = Server('{}/bin/browsermob-proxy'.format(
self.browsermob_dir)
)
self.server.start()
return self
def __exit__(self, type, value, traceback):
log.info('stopping browsermob proxy')
self.server.stop()
log.info('stopping virtual display')
self.display.stop()
def _make_proxied_webdriver(self):
proxy = self.server.create_proxy()
profile = webdriver.FirefoxProfile()
profile.set_proxy(proxy.selenium_proxy())
driver = webdriver.Firefox(firefox_profile=profile)
return (driver, proxy)
def _save_har(self, har, cached=False):
if not os.path.isdir(self.har_dir):
os.makedirs(self.har_dir)
if not cached:
har_name = self.har_name
elif cached:
har_name = self.cached_har_name
log.info('saving HAR file: {}'.format(har_name))
with open(os.path.join(self.har_dir, har_name), 'w' ) as f:
json.dump(har, f, indent=2, ensure_ascii=False)
def load_page(self, url, run_cached=True):
driver, proxy = self._make_proxied_webdriver()
proxy.new_har(self.label)
log.info('loading page: {}'.format(url))
driver.get(url)
self._save_har(proxy.har)
if run_cached:
proxy.new_har(self.cached_label)
log.info('loading cached page: {}'.format(url))
driver.get(url)
self._save_har(proxy.har, cached=True)
driver.quit()
def slugify(self, text):
pattern = re.compile(r'[^a-z0-9]+')
slug = '-'.join(word for word in pattern.split(text.lower()) if word)
return slug
class Browser:
def __init__(self, chromedriverPath, browsermobPath, harfilePath, cookies=None):
self.harfilePath = harfilePath
self.server = Server(browsermobPath)
self.server.start()
self.proxy = self.server.create_proxy()
os.environ["webdriver.chrome.driver"] = chromedriverPath
url = urlparse (self.proxy.proxy).path
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument("--proxy-server={0}".format(url))
self.driver = webdriver.Chrome(chromedriverPath,chrome_options =chrome_options)
if cookies:
print("Loading cookies from "+str(cookies))
with open(cookies, 'r') as cookieFile:
cookieJson = json.loads(cookieFile.read())
for cookie in cookieJson:
self.driver.add_cookie(cookie)
def get(self, url, timeout=20):
print(url)
self.proxy.new_har(url, {"captureContent":True})
try:
self.driver.set_page_load_timeout(timeout)
self.driver.get(url)
self.driver.execute_script("window.scrollTo(0, document.body.scrollHeight/5);")
time.sleep(.5) #wait for the page to load
self.driver.execute_script("window.scrollTo(0, document.body.scrollHeight/4);")
time.sleep(.5) #wait for the page to load
self.driver.execute_script("window.scrollTo(0, document.body.scrollHeight/3);")
time.sleep(.5) #wait for the page to load
self.driver.execute_script("window.scrollTo(0, document.body.scrollHeight/2);")
time.sleep(.5) #wait for the page to load
self.driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
time.sleep(4) #wait for the page to load
except TimeoutException:
print("Timeout")
self.driver.find_element_by_tag_name("body").send_keys(Keys.CONTROL+Keys.ESCAPE)
try:
source = self.driver.page_source
result = json.dumps(self.proxy.har, ensure_ascii=False)
with open(self.harfilePath+"/"+str(int(time.time()*1000.0))+".har", "w") as harfile:
harfile.write(result)
return source
except TimeoutException:
print("Retrying, with a timeout of "+str(timeout+5))
return self.get(url, timeout=timeout+5)
def close(self):
try:
self.server.stop()
except Exception:
print("Warning: Error stopping server")
pass
try:
self.driver.quit()
except Exception:
print("Warning: Error stopping driver")
pass
class BrowserMobLibrary():
ROBOT_LIBRARY_SCOPE = 'GLOBAL'
ROBOT_LIBRARY_VERSION = VERSION
def __init__(self):
self.isServerStarted = False
self.activeProxy = None
self.server = None
self.proxies = []
def _proxy(self):
if self.activeProxy is None:
raise Exception("No proxy has been created")
return self.activeProxy
def start_browsermob(self, browsermob_path):
self.server = Server(browsermob_path)
self.server.start()
self.isServerStarted = True
def stop_browsermob(self):
self.server.stop()
self.server = None
self.isServerStarted = False
def create_proxy(self):
self.activeProxy = self.server.create_proxy
self.proxies.append(self.activeProxy)
return self.server.create_proxy()
def close_proxy(self, proxy):
self.proxies.remove(proxy)
proxy.close()
def close_active_proxy(self):
self.close_proxy(self.activeProxy)
def set_active_proxy(self, proxy):
self.activeProxy = proxy
def get_active_proxy(self):
return self.activeProxy
def get_all_proxies(self):
return self.proxies
def close_all_proxies(self):
for proxy in self.proxies:
proxy.close()
def capture_traffic(self, reference=None, **options):
return self._proxy().new_har(reference, options)
def get_captured_traffic(self):
return self._proxy().har
def set_capture_reference(self, reference=None):
return self._proxy().new_page(reference)
def ignore_all_traffic_matching(self, regexp, status_code):
return self._proxy().blacklist(regexp, status_code)
def only_capture_traffic_matching(self, regexp, status_code):
return self._proxy().whitelist(regexp, status_code)
def use_basic_authentication(self, domain, username, password):
return self._proxy().basic_authentication(domain, username, password)
def set_headers(self, headers, ):
return self._proxy().headers(headers)
def set_response_interceptor(self, js, ):
return self._proxy().response_interceptor(js)
def set_request_interceptor(self, js, ):
return self._proxy().request_interceptor(js)
def set_bandwith_limits(self, **options):
return self._proxy().limits(options)
def set_proxy_timeouts(self, **options):
return self._proxy().timeouts(options)
def remap_hosts(self, address, ip_address):
return self._proxy().remap_hosts(address, ip_address)
def wait_for_traffic_to_stop(self, quiet_period, timeout):
return self._proxy().wait_for_traffic_to_stop(quiet_period, timeout)
def clear_proxy_dns_cache(self):
return self._proxy().clear_dns_cache()
def rewrite_url(self, match, replace):
return self._proxy().rewrite_url(match, replace)
def retrieve_har():
print "Retrieving .har file using generated url..."
har_name_ex = har_name + ".har"
complete_har_path = os.path.join(har_save_path, har_name_ex)
# Magic starts here:
server = Server(path)
server.start()
proxy = server.create_proxy()
profile = webdriver.FirefoxProfile(ff_profile)
profile.set_proxy(proxy.selenium_proxy())
driver = webdriver.Firefox(firefox_profile=profile)
# Broken script to load the page in Google Chrome instead of Mozilla Firefox
"""
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument("--proxy-server={0}".format(proxy.proxy))
driver = webdriver.Chrome(chrome_options = chrome_options)
"""
proxy.new_har(har_name, options={'captureHeaders': True})
driver.get(url)
#Trying to click 'vplayer'
try:
driver.switch_to.frame(0) # Clicking the video automagically
jwplayer = driver.find_element_by_name('vplayer')
jwplayer.click()
#And if that somehow doesn't work
except Exception:
print "Couldn't click player!"
print "Trying again in 5 seconds..."
time.sleep(5)
#Try it again...
try:
driver.switch_to.frame(0) # Clicking the video automagically (again)
jwplayer = driver.find_element_by_name('vplayer')
jwplayer.click()
#And if that doesn't work either
except Exception:
print "Not able to click the video player"
#Stop the server and the driver
server.stop()
driver.quit()
time.sleep(3)
sys.exit()
time.sleep(1)
#Exporting the wanted .har file
result = json.dumps(proxy.har, ensure_ascii=False, indent=4) # indent=4 puts the .har file on seperated lines
#And write it to an automatically created file
har_file = open(complete_har_path,'w')
har_file.write(str(result))
har_file.close()
#Stop the server and the driver
server.stop()
driver.quit()
def run_webdriver(self, start_url, port, config, download_dir):
"""
Run Selenium WebDriver
"""
useragent = None
referer = None
webdriver = None
urllib3_logger = logging.getLogger('urllib3')
urllib3_logger.setLevel(logging.DEBUG)
self.logger.info("Starting WebRunner")
firefox_profile = None
server = None
proxy = None
har = None
if config.referer:
referer = config.referer
else:
referer = 'http://www.google.com/search?q={}+&oq={}&oe=utf-8&rls=org.mozilla:en-US:official&client=firefox-a&channel=fflb&gws_rd=cr'.format(
config.url, config.url)
if config.useragent:
useragent = config.useragent
else:
useragent = 'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:24.0) Gecko/20100101 Firefox/24.0'
self.logger.debug("Running with UserAgent: {}".format(useragent))
self.logger.debug("Running with Referer: {}".format(referer))
self.logger.debug("Checking URL: {}".format(config.url))
server = Server("lib/browsermob/bin/browsermob-proxy", {'port': port})
server.start()
proxy = server.create_proxy()
proxy.headers({'User-Agent': useragent, 'Accept-Encoding': "", 'Connection': 'Close'})
request_js = (
'var referer = request.getProxyRequest().getField("Referer");'
'addReferer(request);'
'function addReferer(r){'
'if (! referer ) {'
'r.addRequestHeader("Referer","' + referer + '");'
'}'
'return;'
'}')
proxy.request_interceptor(request_js)
from types import NoneType
if config.firefoxprofile is not None and os.path.isdir(config.firefoxprofile):
self.logger.debug("Using existing firefox profile")
firefox_profile = FirefoxProfile(profile_directory=config.firefoxprofile)
else:
firefox_profile = FirefoxProfile()
self.logger.debug("Using profile {}".format(firefox_profile.path))
firefox_profile.set_preference("security.OCSP.enabled", 0)
firefox_profile.set_preference("browser.download.folderList", 2)
firefox_profile.set_preference("browser.download.manager.showWhenStarting", False)
firefox_profile.set_preference("browser.download.dir", download_dir)
firefox_profile.set_preference("browser.helperApps.neverAsk.saveToDisk",
"application/x-xpinstall;application/x-zip;application/x-zip-compressed;application/octet-stream;application/zip;application/pdf;application/msword;text/plain;application/octet")
firefox_profile.set_preference("browser.helperApps.alwaysAsk.force", False)
firefox_profile.set_preference("browser.download.manager.showWhenStarting", False)
firefox_profile.set_preference("security.mixed_content.block_active_content", False)
firefox_profile.set_preference("security.mixed_content.block_display_content", False)
firefox_profile.set_preference("extensions.blocklist.enabled", False)
firefox_profile.set_preference("network.proxy.type", 1)
firefox_profile.set_proxy(proxy.selenium_proxy())
firefox_profile.set_preference("webdriver.log.file", "/tmp/ff.log")
firefox_profile.set_preference("webdriver.log.driver", "DEBUG")
firefox_profile.set_preference("browser.newtabpage.enhanced", False)
firefox_profile.set_preference("browser.newtabpage.enabled", False)
firefox_profile.set_preference("browser.newtabpage.directory.ping", "")
firefox_profile.set_preference("browser.newtabpage.directory.source", "")
firefox_profile.set_preference("browser.search.geoip.url", "")
try:
self.xvfb.start()
capabilities = DesiredCapabilities.FIREFOX
capabilities['loggingPrefs'] = {'browser':'ALL'}
if os.path.exists("{}/firefox".format(firefox_profile.path)):
binary = FirefoxBinary("{}/firefox".format(firefox_profile.path))
else:
binary = FirefoxBinary("/usr/bin/firefox")
webdriver = WebDriver(capabilities=capabilities, firefox_profile=firefox_profile, firefox_binary=binary)
proxy.new_har(start_url.hostname,
options={"captureHeaders": "true", "captureContent": "true", "captureBinaryContent": "true"})
self.analyse_page(webdriver, start_url)
for entry in webdriver.get_log('browser'):
self.logger.info("Firefox: {}".format(entry))
har = proxy.har
self.logger.info("Stopping WebRunner")
proxy.close()
server.stop()
webdriver.quit()
har = Har(har)
except Exception, e:
self.logger.error(e)
proxy.close()
if webdriver:
webdriver.quit()
self.xvfb.stop()
server.stop()
class WebTrafficGenerator:
def __init__(self,args):
self.browser_mob_proxy_location = os.environ.get("BROWSERMOBPROXY_BIN")
if not self.browser_mob_proxy_location:
self.browser_mob_proxy_location = "./browsermob-proxy/bin/browsermob-proxy"
# Parse arguments
self.urls_file = args['in_file']
self.out_stats_folder = args['out_folder']
self.timeout = args['timeout']
self.save_headers = args['headers']
self.max_interval = args['max_interval']
self.browsers_num = args['browsers']
self.max_requests = args['limit_urls']
self.no_sleep = args['no_sleep']
self.no_https = args['no_https']
def run(self):
# create temporary directory for downloads
self.temp_dir = tempfile.TemporaryDirectory()
try:
# Read URLs and time
self.urls=[]
self.thinking_times=[]
visit_timestamps=[]
with open(self.urls_file ,"r") as f:
history = f.read().splitlines()
for line in history:
entry = line.split()
if not (entry[1].lower().startswith("file://") or
(entry[1].lower().startswith("http://") and
(entry[1].lower().startswith("10.",7) or
entry[1].lower().startswith("192.168.",7))) or
(entry[1].lower().startswith("https://") and
(entry[1].lower().startswith("10.",8) or
entry[1].lower().startswith("192.168.",8)))):
# convert timestamp in seconds
visit_timestamps.append(float(entry[0])/1000000)
if (not self.no_https or not entry[1].lower().startswith("https://")):
self.urls.append(entry[1])
if not self.max_requests:
self.max_requests = len(self.urls)
visit_timestamps.sort()
for i in range(1, len(visit_timestamps)):
think_time=(visit_timestamps[i]-visit_timestamps[i-1])
if think_time<=self.max_interval:
self.thinking_times.append(think_time)
self.cdf, self.inverse_cdf, self.cdf_samples = compute_cdf(self.thinking_times)
print ("Number of URLs: "+str(len(self.urls)))
# Create or clean statistics folder
if not os.path.exists(self.out_stats_folder):
os.makedirs(self.out_stats_folder)
else:
for file in os.listdir(self.out_stats_folder):
file_path = os.path.join(self.out_stats_folder, file)
if os.path.isfile(file_path):
os.remove(file_path)
# Plot history statistics
self.plot_thinking_time_cdf()
#self.plot_thinking_time_inverse_cdf()
# Start Proxy
self.server = Server(self.browser_mob_proxy_location)
self.server.start()
# start queues
self.urls_queue = Queue()
self.hars_queue = Queue()
# start Barrier (for coordinating proxy server restart)
self.barrier = Barrier(self.browsers_num, action = self.restart_proxy_server)
try:
self.workers = [Browser(i, self.server,
self.urls_queue, self.hars_queue,
self.barrier,
self.timeout, self.save_headers,
self.temp_dir.name)
for i in range(self.browsers_num)]
for w in self.workers:
w.start()
number_of_requests = 0
# Start requesting pages
for url in self.urls:
if number_of_requests==self.max_requests:
break
self.urls_queue.put(url)
number_of_requests += 1
if not self.no_sleep:
time.sleep(self.get_thinking_time())
for w in self.workers:
self.urls_queue.put(None)
self.hars = []
for w in self.workers:
browser_hars = self.hars_queue.get()
self.hars.extend(browser_hars)
# write HAR file
with open(os.path.join(self.out_stats_folder,"HARs.json"),"w") as f:
json.dump(self.hars,f)
# Gather statistics
self.stats = {
"totalTime":[],
"blocked":[],
"dns":[],
"connect":[],
"send":[],
"wait":[],
"receive":[],
"ssl":[]
}
for har in self.hars:
if har["log"]["totalTime"]!=-1:
self.stats["totalTime"].append(har["log"]["totalTime"])
for entry in har["log"]["entries"]:
if (not self.no_https or not entry["request"]["url"].lower().startswith("https://")):
# Queuing
if entry["timings"]["blocked"]!=-1:
self.stats["blocked"].append(entry["timings"]["blocked"])
# DNS resolution
if entry["timings"]["dns"]!=-1:
self.stats["dns"].append(entry["timings"]["dns"])
# TCP Connection
if entry["timings"]["connect"]!=-1:
self.stats["connect"].append(entry["timings"]["connect"])
# HTTP Request send
if entry["timings"]["send"]!=-1:
self.stats["send"].append(entry["timings"]["send"])
# Wait the server
if entry["timings"]["wait"]!=-1:
self.stats["wait"].append(entry["timings"]["wait"])
# HTTP Response receive
if entry["timings"]["receive"]!=-1:
self.stats["receive"].append(entry["timings"]["receive"])
if entry["timings"]["ssl"]!=-1:
self.stats["ssl"].append(entry["timings"]["ssl"])
# Save statistics
self.plot_stats()
for w in self.workers:
w.join()
except KeyboardInterrupt:
pass
finally:
self.urls_queue.close()
self.hars_queue.close()
self.server.stop()
except Exception as e:
print("Exception: " + str(e))
import traceback
traceback.print_exc()
finally:
self.temp_dir.cleanup()
def restart_proxy_server(self):
try:
self.server.stop()
except Exception as e:
print("Failed to stop proxy server. Exception: " + str(e))
# Start Proxy
self.server = Server(self.browser_mob_proxy_location)
self.server.start()
print("Proxy server restarted")
def plot_thinking_time_cdf(self):
x = np.linspace(min(self.thinking_times), max(self.thinking_times), num=10000, endpoint=True)
# Plot the cdf
fig = plt.figure()
axes = fig.add_subplot(111)
axes.plot(x, self.cdf(x))
axes.set_ylim((0,1))
axes.set_xlabel("Seconds")
axes.set_ylabel("CDF")
axes.set_title("Thinking time")
axes.grid(True)
fig.savefig(os.path.join(self.out_stats_folder,"thinking_time_cdf.png"))
def plot_thinking_time_inverse_cdf(self):
x = np.linspace(min(self.cdf_samples), max(self.cdf_samples), num=10000, endpoint=True)
# Plot the cdf
fig = plt.figure()
axes = fig.add_subplot(111)
axes.plot(x, self.inverse_cdf(x))
axes.set_xlim((0,1))
axes.set_ylabel("Seconds")
axes.set_xlabel("CDF")
axes.set_title("Thinking time")
axes.grid(True)
fig.savefig(os.path.join(self.out_stats_folder,"thinking_time_inverse_cdf.png"))
def get_thinking_time(self):
rand=random.uniform(min(self.cdf_samples),max(self.cdf_samples))
time = float(self.inverse_cdf(rand))
return time
def plot_stats(self):
fig_total = plt.figure()
axes_total = fig_total.add_subplot(111)
fig_timings = plt.figure()
axes_timings = fig_timings.add_subplot(1,1,1)
fig_timings_log = plt.figure()
axes_timings_log = fig_timings_log.add_subplot(1,1,1)
for key in self.stats:
if len(set(self.stats[key]))>1:
cdf = compute_cdf(self.stats[key])
x = np.linspace(min(self.stats[key]), max(self.stats[key]), num=10000, endpoint=True)
# Plot the cdf
if key=="totalTime":
axes_total.plot(x/1000, cdf[0](x), label=key)
else:
axes_timings.plot(x, cdf[0](x), label=key)
# zero is not valid with log axes
if min(self.stats[key])==0:
non_zero_min = find_non_zero_min(self.stats[key])
if non_zero_min == 0:
continue
x = np.linspace(non_zero_min, max(self.stats[key]), num=10000, endpoint=True)
axes_timings_log.plot(x, cdf[0](x), label=key)
axes_total.set_ylim((0,1))
axes_total.set_xlabel("Seconds")
axes_total.set_ylabel("CDF")
axes_total.set_title("Page load time")
axes_total.grid(True)
fig_total.savefig(os.path.join(self.out_stats_folder,"page_load_cdf.png"))
axes_timings.set_ylim((0,1))
axes_timings.set_xlabel("Milliseconds")
axes_timings.set_ylabel("CDF")
axes_timings.set_title("Single resource timings")
axes_timings.grid(True)
axes_timings.legend(loc='best')
axes_timings_log.set_ylim((0,1))
axes_timings_log.set_xlabel("Milliseconds")
axes_timings_log.set_ylabel("CDF")
axes_timings_log.set_xscale("log")
axes_timings_log.set_title("Single resource timings")
axes_timings_log.grid(True, which="both", axis="x")
axes_timings_log.grid(True, which="major", axis="y")
axes_timings_log.legend(loc='best')
fig_timings.savefig(os.path.join(self.out_stats_folder,"timings_cdf.png"))
fig_timings_log.savefig(os.path.join(self.out_stats_folder,"timings_cdf_log.png"))
