class TestSite(unittest.TestCase): def setUp(self): # Point the path to the tor-browser_en-US directory in your system tbpath = '/home/kdas/.local/tbb/tor-browser_en-US/' self.driver = TorBrowserDriver(tbpath, tbb_logfile_path='test.log') self.url = "https://check.torproject.org" def tearDown(self): # We want the browser to close at the end of each test. self.driver.close() def test_available(self): self.driver.load_url(self.url) # Find the element for success element = self.driver.find_element_by_class_name('on') self.assertEqual( str.strip(element.text), "Congratulations. This browser is configured to use Tor.") sleep(2) # So that we can see the page
# driver.add_cookie({'name': '1P_JAR', 'value': '2019-4-23-3'}) # driver.add_cookie({'name': 'DV', 'value': 'o1Nbl6B8jsZRELXrd6iumDQIQaWCpNYGGjFTFCYbPQAAAOB85pD-5LPtOQAAAOwZ_awmB2dqGAAAAAKrLPZJ7nerCgAAAA'}) # driver.add_cookie({'name': 'SIDCC', 'value': 'AN0-TYsIc9ao8HSl8ErVpCFrEf0JYQbOHu-ttenPp8mfKx-rY-Z6GPOJqgW0snerz0czS1As5w'}) # url = "https://check.torproject.org" url = "https://www.google.com/search?q=playoffs" headers = {} headers["User-agent"] = "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36" driver.load_url(url) # driver.context() # Find the element for success element = driver.find_element_by_class_name('LC20lb') print(element) sleep(2) # So that we can see the page driver.close() # class TestSite(unittest.TestCase): # def setUp(self): # # Point the path to the tor-browser_en-US directory in your system # tbpath = '/home/andrew/Desktop/tor-browser-linux64-8.0.8_en-US/tor-browser_en-US/' # self.driver = TorBrowserDriver(tbpath, tbb_logfile_path='test.log', tor_cfg=cm.USE_STEM) # self.url = "https://check.torproject.org" # def tearDown(self): # # We want the browser to close at the end of each test.
from tbselenium.tbdriver import TorBrowserDriver import pickle from bs4 import BeautifulSoup tbpath = "tor-browser_en-US" with open("oniontree-source.html", 'r') as f: data = f.read().replace('\n', '') driver = TorBrowserDriver(tbpath) # driver.load_url(website) soup = BeautifulSoup(data, 'html.parser') anchors = soup.find_all('a') l = map(lambda x: x.get("href"), anchors) potential_onions = [] for url in l: driver.load_url(url) e = driver.find_element_by_class_name("urls") onions = e.find_elements_by_tag_name("a") if len(onions) > 5: print("too many onions for {}. skipping".format(url)) for o in onions: print(o.get_attribute('href')) potential_onions.append(o.get_attribute('href')) pickle.save(potential_onions, 'onions.sav')