Python PhantomJS.get方法代码示例

# 需要导入模块: from selenium.webdriver import PhantomJS [as 别名]
# 或者: from selenium.webdriver.PhantomJS import get [as 别名]
def generate_image(structure):
    image_path = os.path.join(mkdtemp(), 'okc.png')
    html_path = os.path.join(
        os.path.dirname(os.path.realpath(__file__)),
        'okc.html',
    )
    url = 'file://{}'.format(html_path)
    driver = PhantomJS(service_log_path=mkstemp()[1])
    driver.set_window_size(2000, 500)
    driver.get(url)
    driver.execute_script('setText({});'.format(json.dumps(structure)))

    if random() > 0.4:
        driver.execute_script('hideForm();')
    elif random() > 0.5:
        driver.execute_script('uncheckForm();')

    driver.set_window_size(*driver.execute_script('return getSize();'))
    driver.save_screenshot(image_path)

    # twitter's gonna make our beautiful screenshot a jpeg unless we make it
    # think that we're using transparency for a reason, so,,
    img = Image.open(image_path)
    origin = img.getpixel((0, 0))
    new_origin = origin[:3] + (254,)
    img.putpixel((0, 0), new_origin)
    img.save(image_path)

    subprocess.check_call(['optipng', '-quiet', image_path])

    return image_path

# 需要导入模块: from selenium.webdriver import PhantomJS [as 别名]
# 或者: from selenium.webdriver.PhantomJS import get [as 别名]
    def selenium(self, webdriverOption=0):
        """
        # 调用浏览器下载，适用于任何情形
        :return:
        """
        if not self.url[:4] == "http":
            return None

        driver = None
        if webdriverOption == 0:
            from selenium.webdriver import PhantomJS

            driver = PhantomJS()
        elif webdriverOption == 1:
            from selenium.webdriver import Chrome

            driver = Chrome()
        elif webdriverOption == 2:
            from selenium.webdriver import Firefox

            driver = Firefox()

        if not driver:
            print(u"-->DownLoader->Selenium driver初始化出错，请检查运行环境或webdriverOption选项")

        driver.get(self.url)
        src = driver.page_source
        driver.quit()
        self.pageSource = src
        return src

# 需要导入模块: from selenium.webdriver import PhantomJS [as 别名]
# 或者: from selenium.webdriver.PhantomJS import get [as 别名]
class SeleniumTestCase(LiveServerTestCase):
    def _pre_setup(self):
        super(SeleniumTestCase, self)._pre_setup()
        self.driver = PhantomJS()

    def _post_teardown(self):
        self.driver.quit()
        super(SeleniumTestCase, self)._post_teardown()

    def login(self, username='user', password='password', url='login'):
        """
        Login to the server and be authenticated
        """
        self.open(reverse(url))
        self.driver.find_element_by_id("id_username").clear()
        self.driver.find_element_by_id("id_username").send_keys(username)
        self.driver.find_element_by_id("id_password").clear()
        self.driver.find_element_by_id("id_password").send_keys(password)
        self.driver.find_element_by_id("submit-id-login").click()

    def open(self, url):
        self.driver.get("%s%s" %(self.live_server_url, url))

    def is_element_present(self, how, what):
        try:
            self.driver.find_element(by=how, value=what)
        except NoSuchElementException, e:
            return False
        return True

# 需要导入模块: from selenium.webdriver import PhantomJS [as 别名]
# 或者: from selenium.webdriver.PhantomJS import get [as 别名]
    def _init_robot(self, id):
        robot = WDriver()
        logging.debug("initialize")
        self.robots.update({str(id): robot})
        logging.debug("get facebook.com")
        robot.get('http://fb.com')

        logging.debug("login")
        robot.find_element_by_name('email').send_keys('[email protected]')
        robot.find_element_by_name('pass').send_keys('2855930022040')
        robot.find_element_by_name('pass').send_keys(Keys.RETURN)

        for index in range(len(self.remain_ids)):
            self.lock.acquire()
            user_id = self.remain_ids.pop()
            self.lock.release()
            try:
                self.get_name_for_id(robot, user_id)
            except:
                logging.debug("error while updating record with id=%s" % str(user_id))
                self.error_ids.add(user_id)
            else:
                self.done_ids.add(user_id)
        robot.close()
        return

# 需要导入模块: from selenium.webdriver import PhantomJS [as 别名]
# 或者: from selenium.webdriver.PhantomJS import get [as 别名]
def export(plot, filename, width=800, height=600):
    """
    Export plot to file.

    Args:
        plot (quorra.Plot): Quorra plot object to export.
        width (int): Width for plot (pixels).
        height (int): Height for plot (pixels).
        filename (str): Filename to export to.
    """
    global _phantom, __templates__, __cwd__
    if _phantom is None:
        from selenium.webdriver import PhantomJS
        _phantom = PhantomJS(service_log_path=os.path.devnull)
    tmpl = os.path.join(__templates__, 'export.html')
    exp = os.path.join(__cwd__, '.' + str(uuid.uuid1()) + '.html')
    try:
        with open(tmpl, 'r') as fi, open(exp, 'w') as fo:
            dat = fi.read()
            dat = dat.replace('var plot = undefined;', 'var plot = {};'.format(str(plot)))
            dat = dat.replace('width: 800px;', 'width: {}px;'.format(width))
            dat = dat.replace('height: 500px;', 'height: {}px;'.format(height))
            fo.write(dat)
        _phantom.get('file://' + exp)
        _phantom.save_screenshot(filename.replace('.png', '') + '.png')
    finally:
        if os.path.exists(exp):
            os.remove(exp)
    return

# 需要导入模块: from selenium.webdriver import PhantomJS [as 别名]
# 或者: from selenium.webdriver.PhantomJS import get [as 别名]
class Crawler:
    def __init__(self, timeout=20, phantomjs_cfg_file='python-utils/config/phantomjs_cfg.json', use_cfg_file=False, proxy_pool_server='http://127.0.0.1:15110'):
        self.timeout = timeout
        if use_cfg_file:
            phantomjs_service_args = ['--config={}'.format(phantomjs_cfg_file)]
        else:
            _, proxy_type, proxy, proxy_auth = get_proxy(proxy_pool_server)
            phantomjs_service_args = [
                '--proxy-type={}'.format(proxy_type),
                '--proxy={}'.format(proxy),
                '--proxy-auth={}'.format(proxy_auth),
            ]

        self.driver = PhantomJS(
            desired_capabilities=self.new_desired_capabilities(),
            service_args=phantomjs_service_args)
        self.check_client_info()

    def __enter__(self):
        return self

    def __exit__(self, exc_type, exc_value, traceback):
        self.close()

    def close(self):
        self.driver.quit()

    @contextmanager
    def wait_for_page_load(self, old_element):
        yield
        WebDriverWait(self.driver, self.timeout).until(EC.staleness_of(old_element))

    def new_desired_capabilities(self, user_agent=default_ua):
        desired_capabilities = DesiredCapabilities.PHANTOMJS.copy()
        if not user_agent:
            user_agent = ua.random
        desired_capabilities["phantomjs.page.settings.userAgent"] = user_agent
        return desired_capabilities

    def check_client_info(self):
        url='http://www.whoishostingthis.com/tools/user-agent/'
        self.driver.get(url)
        ip_addr = get_xpath_element(self.driver, '//*[@id="user-agent"]/div[2]/span').text.strip()
        user_agent = get_xpath_element(self.driver, '//*[@id="user-agent"]/div[1]').text.strip()
        logger.info('IP: {}, User-Agent: {}'.format(ip_addr, user_agent))
        if self.wrong_ip(ip_addr):
            logger.error('Proxy not set correctly!')
            sys.exit(-1)

    def wrong_ip(self, ip_addr):
        if ip_addr.startswith('166.111.') or ip_addr.startswith('59.66.') or ip_addr.startswith('101.5.') or ip_addr.startswith('101.6.'):
            return True
        else:
            return False

# 需要导入模块: from selenium.webdriver import PhantomJS [as 别名]
# 或者: from selenium.webdriver.PhantomJS import get [as 别名]
def main(argv=sys.argv[1:]):
    parser = argparse.ArgumentParser()
    parser.add_argument('--url', default='http://127.0.0.1:8000/static/index.html')
    args = parser.parse_args(argv)

    url = args.url

    browser = WebDriver()
    browser.get(url)
    tags = browser.find_elements_by_css_selector('li')
    for tag in tags:
        print(tag.text)
    browser.close()

# 需要导入模块: from selenium.webdriver import PhantomJS [as 别名]
# 或者: from selenium.webdriver.PhantomJS import get [as 别名]
 def onegoogolePR(self, url):
     '''返回单个PR'''
     prUrl = 'http://pr.chinaz.com'  # 谷歌PR查询地址
     driver = PhantomJS()
     driver.get(prUrl)
     driver.find_element_by_id('PRAddress').send_keys(url)
     driver.find_element_by_class_name('search-write-btn').click()
     try:
         imgsrc = driver.find_element_by_css_selector('span#pr>img').get_attribute('src')
         pr = search(r'\d', imgsrc).group()
     except:
         pr = '暂无数据'
     driver.quit()
     return pr

# 需要导入模块: from selenium.webdriver import PhantomJS [as 别名]
# 或者: from selenium.webdriver.PhantomJS import get [as 别名]
def catalog_url(url='http://www.meitun.com/'):
    # catalog_url is AJAX,use phantomJS
    driver = PhantomJS()
    driver.get(url)
    driver.maximize_window()
    mov_ele = driver.find_element_by_css_selector('.nav>ul>li:nth-child(1)')
    # the mouse move to the lazy layout element,and perform
    ActionChains(driver).move_to_element(mov_ele).perform()
    time.sleep(3)
    response = driver.page_source
    driver.quit()
    # use pyquery parser the page source,more quickly
    d = pq(response)
    return map(lambda x: 'http:' + pq(x).attr('href'), d.find('.cg-pdts a'))

# 需要导入模块: from selenium.webdriver import PhantomJS [as 别名]
# 或者: from selenium.webdriver.PhantomJS import get [as 别名]
class AdvertisementAdvancedViewTests(LiveServerTestCase):
    def setUp(self):
        self.driver = PhantomJS()

        self.user = User.objects.create_user('admin', '[email protected]', 'pass')
        self.user.save()

        self.provider = Provider(
            name='provider',
            user=self.user,
        )
        self.provider.save()

        self.provider_adverts = mommy.make(Advertisement, _quantity=20, provider=self.provider)

    def tearDown(self):
        self.driver.quit()

    def open(self, url):
        self.driver.get("%s%s" % (self.live_server_url, url))

    def test_side_ad_display(self):
        """
        Test that the side ads display properly
        """
        self.open(reverse('advertisements.views.side_ads'))

        self.assertEqual(len(self.driver.find_elements_by_xpath("//a")), 4)

        self.driver.find_element_by_xpath("//a[1]/img")
        self.driver.find_element_by_xpath("//a[2]/img")
        self.driver.find_element_by_xpath("//a[3]/img")
        self.driver.find_element_by_xpath("//a[4]/img")

        self.assertNotEqual(self.driver.find_element_by_xpath("//a[1]").get_attribute("href"), '')
        self.assertNotEqual(self.driver.find_element_by_xpath("//a[2]").get_attribute("href"), '')
        self.assertNotEqual(self.driver.find_element_by_xpath("//a[3]").get_attribute("href"), '')
        self.assertNotEqual(self.driver.find_element_by_xpath("//a[4]").get_attribute("href"), '')

    def test_top_ad_display(self):
        """
        Test that the top ad displays properly
        """
        self.open(reverse('advertisements.views.top_ad'))

        self.assertEqual(len(self.driver.find_elements_by_xpath("//a")), 1)
        self.driver.find_element_by_xpath("//a/img")
        self.assertNotEqual(self.driver.find_element_by_xpath("//a").get_attribute("href"), '')

# 需要导入模块: from selenium.webdriver import PhantomJS [as 别名]
# 或者: from selenium.webdriver.PhantomJS import get [as 别名]
class Premiumgeneratorlink(object):
	def __init__(self, url):
		self.url = url
		self.browser = PhantomJS()

	def get_link(self):
		try:
			self.browser.get('http://premiumgeneratorlink.com/')
			self.browser.find_element_by_name('link').send_keys(self.url)
			self.browser.find_element_by_xpath('//a[@class="input"]').click()
			wdw = WebDriverWait(self.browser, 10)
			wdw.until(EC.element_to_be_clickable((By.ID, 'check'))).click()
			wdw.until(EC.element_to_be_clickable((By.ID, 'generate'))).click()
			link = wdw.until(EC.visibility_of_element_located((By.XPATH, '//form[@class="center"]'))).get_attribute('action')
		except (WebDriverException, NoSuchElementException, TimeoutException):
			return False
		finally:
			self.browser.quit()
		return link

# 需要导入模块: from selenium.webdriver import PhantomJS [as 别名]
# 或者: from selenium.webdriver.PhantomJS import get [as 别名]
 def on_start_again(self, url):
     driver = PhantomJS()
     driver.get(url)
     time.sleep(2)
     driver.maximize_window()
     t = driver.find_element_by_css_selector('.page-txt').text
     res_t = []
     if t:
         t = int(t.split('/')[1][:-1]) - 1  # get the page count
         # the count of page turning should be i-1
         while t:
             t -= 1
             move_ele = driver.find_element_by_css_selector('#next')
             ActionChains(driver).move_to_element(move_ele).click()
             time.sleep(1)
             res_t.append(driver.page_source)
     driver.quit()
     for item in res_t:
         self.step_first(item)

# 需要导入模块: from selenium.webdriver import PhantomJS [as 别名]
# 或者: from selenium.webdriver.PhantomJS import get [as 别名]
class Leecherus(object):
	def __init__(self, url):
		self.url = url
		self.browser = PhantomJS()

	def get_link(self):
		try:
			self.browser.get('http://leecher.us')
			wdw = WebDriverWait(self.browser, 10)
			wdw.until(EC.visibility_of_element_located((By.NAME, 'link'))).send_keys(self.url)
			wdw.until(EC.element_to_be_clickable((By.XPATH, '//button[@class="subscribe"]'))).click()
			wdw.until(EC.element_to_be_clickable((By.XPATH, '//input[@class="subscribe"]'))).click()
			self.browser.switch_to_window(self.browser.window_handles[1])
			onclick = wdw.until(EC.element_to_be_clickable((By.ID, 'get_link'))).get_attribute('onclick')
		except (WebDriverException, NoSuchElementException, TimeoutException, IndexError):
			return False
		finally:
			self.browser.quit()
		m = re.search("'(http://[^']+)'", onclick)
		return m.group(1) if m else False

# 需要导入模块: from selenium.webdriver import PhantomJS [as 别名]
# 或者: from selenium.webdriver.PhantomJS import get [as 别名]
 def post(self):
     id = request.values['page']
     page = Page.objects.get_or_404(id=id)
     # html = requests.get(page.baseurl).text
     screenshot = None
     try:
         phantom = PhantomJS(desired_capabilities={'acceptSslCerts': True},
                             service_args=['--web-security=false',
                                           '--ssl-protocol=any',
                                           '--ignore-ssl-errors=true'], port=8888)
         phantom.set_window_size(1024, 768)
         phantom.get(page.baseurl)
         html = phantom.page_source
         screenshot = phantom.get_screenshot_as_png()
         phantom.close()
     except Exception as ex:
         html = "error when i snap your page ... %s" % ex
         snap = Snap(html, datetime.datetime.now(), screenshot).save()
         page.update(push__snaps=snap)
     snap = Snap(html, datetime.datetime.now(), screenshot).save()
     page.update(push__snaps=snap)
     return jsonify({'id': "%s" % snap.id})

# 需要导入模块: from selenium.webdriver import PhantomJS [as 别名]
# 或者: from selenium.webdriver.PhantomJS import get [as 别名]
def render(gist_id, commit):
    block_url = 'http://bl.ocks.org/' + gist_id
    d3_block_rec = {'gist_id': gist_id}
    try:
        driver = PhantomJS()
        driver.get(block_url)
        time.sleep(RENDER_DELAY)  # let it render
        fullpage_im = Image.open(BytesIO(driver.get_screenshot_as_png()))
        fimb = BytesIO()
        fullpage_im.save(fimb, 'png')
        d3_block_rec['fullpage_base64'] = base64.b64encode(fimb.getvalue())
        d3_block_rec['block_url'] = driver.current_url
    except Exception as e:
        # we got nothing
        with LittlePGer('dbname=' + DB_NAME, commit=commit) as pg:
            d3_block_rec['error'] = str(e)
            pg.insert('d3_block', values=d3_block_rec)
        exit(10)

    try:
        f = driver.find_element_by_xpath('//iframe')
        x, y = int(f.location['x']), int(f.location['y'])
        w, h = x + int(f.size['width']), y + int(f.size['height'])
        block_im = fullpage_im.crop((x, y, w, h))
        bimb = BytesIO()
        block_im.save(bimb, 'png')
        d3_block_rec['block_base64'] = base64.b64encode(bimb.getvalue())
        d3_block_rec['block_size'] = list(block_im.size)
    except Exception as e:
        # at least we got the fullpage im, save it
        with LittlePGer('dbname=' + DB_NAME, commit=commit) as pg:
            d3_block_rec['error'] = str(e)
            pg.insert('d3_block', values=d3_block_rec)
        exit(11)

    # all good, save everything
    with LittlePGer('dbname=' + DB_NAME, commit=commit) as pg:
        pg.insert('d3_block', values=d3_block_rec)