Python PhantomJS.find_element_by_id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 find_element_by_id [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 find_element_by_id [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 find_element_by_id [as 别名]
	def __init__(self, browser: webdriver.PhantomJS, click_to_display_id: str):
		self._browser = browser
		self.click_to_display_id = click_to_display_id
		self.click_to_display_element = browser.find_element_by_id(click_to_display_id)

# 需要导入模块: from selenium.webdriver import PhantomJS [as 别名]
# 或者: from selenium.webdriver.PhantomJS import find_element_by_id [as 别名]
    school_info = wd.find_elements_by_class_name('school-info__item')
    for s in school_info:
        inner_html = sub(r'<.*?>|\n', ' ', s.get_attribute('innerHTML'))
        inner_html = sub(r'\s+', ' ', inner_html).strip()
        if 'grades' in inner_html.lower():
            min_grade, max_grade = inner_html.split(' ')[-1].split('-')
            if min_grade.lower() == 'pk':
                min_grade = -1
            elif min_grade.lower() == 'k':
                min_grade = 0
            n_grades = int(max_grade) - int(min_grade) + 1
        elif 'students' in inner_html.lower():
            n_students = int(sub(r'[^0-9]', '', inner_html.split(' ')[-1]))
    students_per_grade = float(n_students) / float(n_grades)

    staff_info = wd.find_element_by_id('TeachersStaff').find_elements_by_class_name('rating-container__score-item')
    teacher_info = sub(r'<.*?>|\n', ' ', staff_info[0].get_attribute('innerHTML'))
    teacher_info = sub(r'\s+', ' ', teacher_info).strip()
    counsel_info = sub(r'<.*?>|\n', ' ', staff_info[1].get_attribute('innerHTML'))
    counsel_info = sub(r'\s+', ' ', counsel_info).strip()
    t_to_s_school = int(sub(r'.*?(\d+) :1.*', r'\1', teacher_info))
    c_to_s_school = int(sub(r'.*?(\d+) :1.*', r'\1', counsel_info))

    columns = ['indicator', 'subject', 'category', 'school_score', 'state_average']
    df = DataFrame(columns=columns)
    ind = 0

    for indicator in indicators:
        elem = wd.find_element_by_id(indicator)
        buttons = elem.find_elements_by_class_name('sub-nav-item')
        for b in buttons:

# 需要导入模块: from selenium.webdriver import PhantomJS [as 别名]
# 或者: from selenium.webdriver.PhantomJS import find_element_by_id [as 别名]
class WeixinPhantomjs(Base):
    all_uids = {docs['uid'] for docs in in_collection.find({}, {'uid': 1}) if 'uid' in docs}

    def __init__(self):
        self.start_page = START_PAGE
        self.end_page = END_PAGE
        self.weixin_url = REFER_FIRST

        # self.driver = Firefox()
        if hasattr(config, 'PHANTOMJS_PATH'):
            self.driver = PhantomJS(executable_path=getattr(config, 'PHANTOMJS_PATH'))
        else:
            self.driver = PhantomJS()

    def open_weixin_browser(self, word):
        try:
            self.driver.get(self.weixin_url)
            self.driver.set_page_load_timeout(3)

            self.driver.find_element_by_id('upquery').send_keys(word)
            self.driver.find_element_by_class_name('swz').click()
            time.sleep(3)

            urls_uids = self.extract_urls_uids(word=word)
            Article(urls_uids=urls_uids, word=word).extract()
        except Exception as e:
            storage_word.append([word, 0])
            self.logger.info('Open weixin error: type <{}>, mag <{}>'.format(e.__class__, e))
            self.close_browser()
            return True
        return False

    def get_total_pages_to_word(self):
        pages = []
        page_id_css = 'pagebar_container'

        try:
            e = self.driver.find_element_by_id(page_id_css)
            for _p in e.text.split():
                _p = _p.strip()

                if not _p.isdigit():
                    return DEFAULT_PAGES if DEFAULT_PAGES <= pages[-1] else pages[-1]
                else:
                    pages.append(int(_p))
            return 1
        except (NoSuchElementException, NoSuchWindowException, TypeError, IndexError):
            pass
        return 1

    def extract_urls_uids(self, word):
        urls_uids = []
        timestamp = [_t.get_attribute('t') for _t in self.driver.find_elements_by_css_selector('div.s-p')]
        urls_tits = [(t.get_attribute('href'), self.trim(t.text))
                     for t in self.driver.find_elements_by_css_selector('h4 a')]

        if len(urls_tits) != len(timestamp):
            return urls_uids

        for index, url_tit in enumerate(urls_tits):
            try:
                uid = self.md5(timestamp[index] + url_tit[1] + word)

                if uid not in self.__class__.all_uids:
                    self.__class__.all_uids.add(uid)
                    urls_uids.append({'url': url_tit[0], 'uid': uid})
            except (TypeError, IndexError):
                pass
        return urls_uids

    @property
    def is_forbidden(self):
        css_id = 'seccodeForm'

        try:
            if self.driver.find_element_by_id(css_id):
                return True
        except NoSuchElementException:
            pass
        return False

    def appear_element(self, by):
        try:
            # Have `click` function to specified element
            tag = WebDriverWait(self.driver, 20).until(lambda driver: driver.find_element_by_id(by))
            tag.click()
            return True
        except (TimeoutException, NoSuchWindowException, NoSuchElementException):
            pass
        return False

    def crawl_single(self, word=None, go=0):
        is_go = True
        go_page = int(go)
        next_page_css = 'sogou_page_%s'

        is_break = self.open_weixin_browser(word)
        pages = self.get_total_pages_to_word()

        for page in range(self.start_page + 1, (pages or self.end_page) + 1):
#.........这里部分代码省略.........

# 需要导入模块: from selenium.webdriver import PhantomJS [as 别名]
# 或者: from selenium.webdriver.PhantomJS import find_element_by_id [as 别名]
class WeixinPhantomjs(Base):
    def __init__(self):
        self.start_page = START_PAGE
        self.end_page = END_PAGE
        self.weixin_url = REFER_FIRST

        # self.driver = Firefox()
        if hasattr(config, 'PHANTOMJS_PATH'):
            self.driver = PhantomJS(executable_path=getattr(config, 'PHANTOMJS_PATH'))
        else:
            self.driver = PhantomJS()

        self.client = MongoClient(HOST, PORT)
        self.collection = self.client[DB][COLLECTION]
        self.all_uids = self.uids

    def open_weixin_browser(self, word):
        try:
            self.driver.get(self.weixin_url)
            self.driver.set_page_load_timeout(3)

            self.driver.find_element_by_id('upquery').send_keys(word)
            self.driver.find_element_by_class_name('swz').click()
            time.sleep(3)

            urls_uids = self.extract_urls_uids(word=word)
            Article(urls_uids=urls_uids, word=word).extract()
        except Exception as e:
            storage_word.append([word, 0])
            self.logger.info('Open weixin error: type <{}>, mag <{}>'.format(e.__class__, e))
            self.close_browser()
            return True
        return False

    def get_total_pages_to_word(self):
        pages = []
        page_id_css = 'pagebar_container'

        try:
            e = self.driver.find_element_by_id(page_id_css)
            for _p in e.text.split():
                _p = _p.strip()

                if not _p.isdigit():
                    return DEFAULT_PAGES if DEFAULT_PAGES <= pages[-1] else pages[-1]
                else:
                    pages.append(int(_p))
            return 1
        except (NoSuchElementException, NoSuchWindowException, TypeError, IndexError):
            pass
        return 1

    def get_query_words(self, word):
        query_words = []

        for docs in self.collection.find({}, {'rel': 1, 'conp': 1}).sort([('_id', 1)]):
            w = docs['conp']

            if w not in query_words:
                query_words.append(w)

            for item in docs['rel']:
                if item not in query_words:
                    query_words.append(item)

        self.client.close()

        return self.query_index(query_words, word)

    @property
    def uids(self):
        return {docs['uid'] for docs in in_collection.find({}, {'uid': 1}) if 'uid' in docs}

    def extract_urls_uids(self, word):
        urls_uids = []
        timestamp = [_t.get_attribute('t') for _t in self.driver.find_elements_by_css_selector('div.s-p')]
        urls_tits = [(t.get_attribute('href'), self.trim(t.text))
                     for t in self.driver.find_elements_by_css_selector('h4 a')]

        if len(urls_tits) != len(timestamp):
            return urls_uids

        for index, url_tit in enumerate(urls_tits):
            try:
                uid = self.md5(timestamp[index] + url_tit[1] + word)

                if uid not in self.all_uids:
                    self.all_uids.add(uid)
                    urls_uids.append({'url': url_tit[0], 'uid': uid})
            except (TypeError, IndexError):
                pass
        return urls_uids

    @staticmethod
    def query_index(words, cut_word):
        temp_words = words[START_INDEX:END_INDEX]

        try:
            index = temp_words.index(cut_word)
            return temp_words[index:], index + START_INDEX
#.........这里部分代码省略.........

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

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

        self.login()

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

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

    def login(self):
        self.open(settings.LOGIN_URL)
        self.driver.find_element_by_id("id_username").send_keys("admin")
        self.driver.find_element_by_id("id_password").send_keys("password")
        self.driver.find_element_by_css_selector("button.btn.btn-default").click()

        self.assertEqual(
            self.driver.current_url,
            self.live_server_url + reverse('advertisements.views.view_provider_statistics', args=[self.provider.pk]),
        )

    def test_can_login(self):
        """
        Test that the user can login
        """
        pass

    def test_provider_page_has_all_data(self):
        """
        Test that the provider statistics page has all the correct data
        """
        self.open(reverse('advertisements.views.view_provider_statistics', args=[self.provider.pk]))

        self.assertEqual("Open Ads", self.driver.title)
        self.assertIn(
            "{0} advertisements".format(self.provider.name),
            self.driver.find_element_by_css_selector("h1.page-header").text
        )
        self.assertIn(
            "{0} advertisements in rotation".format(20),
            self.driver.find_element_by_css_selector("h1.page-header").text
        )

    def test_advertisement_page_has_all_data(self):
        """
        Test that the advertisement page has all the correct data
        """

        for advert in self.provider_adverts:
            self.open(reverse('advertisements.views.view_advert_statistics', args=[advert.pk]))

            self.assertIn(
                "ID number: {0}".format(advert.pk),
                self.driver.find_element_by_css_selector("h1.page-header").text,
            )
            self.driver.find_element_by_css_selector("img")
            self.assertEqual("Active", self.driver.find_element_by_xpath("//td[2]/span").text)
            self.assertEqual(advert.url, self.driver.find_element_by_link_text(advert.url).text)
            self.driver.find_element_by_link_text("Edit URL").click()
            self.assertEqual(advert.url, self.driver.find_element_by_id("id_url").get_attribute("value"))

# 需要导入模块: from selenium.webdriver import PhantomJS [as 别名]
# 或者: from selenium.webdriver.PhantomJS import find_element_by_id [as 别名]
def get_url_files(retail, invoice_doc_type, invoice_id, invoice_date, invoice_amount):
    retail_invoice_url = RETAIL_INVOICE_URL[retail]

    driver = PhantomJS()
    driver.get(retail_invoice_url)

    # 1 Set doc_type 'select'
    try:
        select_doc_type = Select(driver.find_element_by_name('txtTipoDte'))
        value = RETAIL_INVOICE_DOC_TYPES[retail][invoice_doc_type]['value']
        select_doc_type.select_by_value(value)
        # name = RETAIL_INVOICE_DOC_TYPES[retail][invoice_doc_type]['name']
        # select_doc_type.select_by_visible_text(name)
    except Exception:
        print 'ERROR: set doc_type select as Boleta'
        driver.save_screenshot('screen.png')
        return '', ''

    time.sleep(5)

    # 2 Get recaptcha img url
    try:
        recaptcha_img = driver.find_element_by_id('recaptcha_challenge_image')
        recaptcha_img_url = recaptcha_img.get_attribute('src')
    except Exception:
        print 'ERROR: get recaptcha image url'
        driver.save_screenshot('screen.png')
        return '', ''

    # 3 Solve recaptcha
    v = VisionApi()
    recaptcha_value = v.detect_text_from_url(recaptcha_img_url)

    if recaptcha_value is None:
        print 'ERROR: solving recaptcha image'
        driver.save_screenshot('screen.png')
        return '', ''

    # 4 Fill form
    script = u"""
        document.getElementsByName('txtFolio')[0].value = '{invoice_id}';
        document.getElementsByName('txtFechaEmision')[0].value = '{invoice_date}';
        document.getElementsByName('txtMontoTotal')[0].value = '{invoice_amount}';
        document.getElementsByName('recaptcha_response_field')[0].value = '{recaptcha_value}';
    """.format(
        invoice_id=invoice_id,
        invoice_date=invoice_date,
        invoice_amount=invoice_amount,
        recaptcha_value=recaptcha_value,
    )
    driver.execute_script(script)

    # 5 Submit form
    try:
        driver.find_element_by_name('frmDatos').submit()
    except Exception:
        print 'ERROR: submitting form'
        driver.save_screenshot('screen.png')
        return '', ''

    # 6 Get url files
    try:
        xml_a_tag = driver.find_element_by_xpath('//*[@id="Tabla_01"]/tbody/tr[1]/td[2]/p/a[2]')
        pdf_a_tag = driver.find_element_by_xpath('//*[@id="Tabla_01"]/tbody/tr[1]/td[2]/p/a[1]')

        xml_url = xml_a_tag.get_attribute('href')
        pdf_url = pdf_a_tag.get_attribute('href')
    except Exception:
        print 'ERROR: getting url files'
        driver.save_screenshot('screen.png')
        return '', ''

    # 8 Delete driver session
    driver.close()
    driver.quit()

    return xml_url, pdf_url