Python Firefox.find_element_by_class_name方法代码示例

# 需要导入模块: from selenium.webdriver import Firefox [as 别名]
# 或者: from selenium.webdriver.Firefox import find_element_by_class_name [as 别名]
class WebDriver(object):
    def __init__(self, name):
        self.webdriver = Firefox()
        self.name = name

    def get_village(self, name):
        village = Village.objects.get(name=name)
        return village

    def enter_site(self, url):
        self.webdriver.get(url)
        return self.webdriver.current_url

    def get_total_stores(self):
        result = self.webdriver.find_element_by_class_name('total')
        return result.text

    def move_down_page(self):
        total_pages = self.get_total_stores()
        total = int(total_pages)
        for i in xrange(total):
            self.webdriver.find_element_by_class_name('maisConteudo').click()

    def create_stores(self):
        village = self.get_village(self.name)
        stores = self.webdriver.find_element_by_class_name('col2-1')
        StoresTxt.objects.create(village=village, content=stores)

    def run(self):
        if self.name:
            village = self.get_village(self.name)
            self.enter_site(village.url)
            self.move_down_page()
            self.create_stores()

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

# 需要导入模块: from selenium.webdriver import Firefox [as 别名]
# 或者: from selenium.webdriver.Firefox import find_element_by_class_name [as 别名]
def open_browser(self):
    # Open Firefox to charter using Selenium
    browser = Firefox()
    browser.get('https://www.charter.com/browse/content/new-channel-lineup')

    # Click the "choose state" menu using Selenium
    wait = WebDriverWait('browser', 20)
    button = browser.find_element_by_css_selector('.drop-down-current')
    button.click()

    # # Identify all states in the list, read as text using Selenium
    list_item = browser.find_element_by_class_name('drop-down-list')
    states = list_item.text
    # print states

    # sel_st = raw_input('Type in 2 letter st abbreviation: ')
    def prompt(self)

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

        self.driver = Firefox()

        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()
            self.driver.implicitly_wait(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 pages[-1]
                else:
                    pages.append(int(_p))
            return 1
        except (NoSuchElementException, NoSuchWindowException, TypeError, IndexError):
            pass

    def get_query_words(self):
        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 query_words

    @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):
        try:
            index = words.index(cut_word)
            return index
        except ValueError:
            pass
        return 0

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

#.........这里部分代码省略.........

# 需要导入模块: from selenium.webdriver import Firefox [as 别名]
# 或者: from selenium.webdriver.Firefox import find_element_by_class_name [as 别名]
from selenium.webdriver import Firefox
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC

from pygeocoder import Geocoder
import pygmaps
from bs4 import BeautifulSoup



browser = Firefox()
browser.get('https://www.charter.com/browse/content/new-channel-lineup')
wait = WebDriverWait('browser', 20)
button = browser.find_element_by_css_selector('.drop-down-current')
button.click()
list_item = browser.find_element_by_class_name('drop-down-list')
# states = list_item.text
# print states


while True:
    st_prompt = raw_input("Enter 2 letter state abbreviation: ")
    find_st = browser.find_element_by_link_text(st_prompt.upper())
    sel_st = find_st.text + ', USA'
    print sel_st
    find_st.click() # click to sel state
    sleep(1)
    try:
        list_region = WebDriverWait(browser, 02).until(EC.visibility_of((By.ID, "select-region")))
        # list_region = browser.find_element_by_xpath('//*[@id="select-region"]/div[2]') # find Choose Region button
        list_region.click()

# 需要导入模块: from selenium.webdriver import Firefox [as 别名]
# 或者: from selenium.webdriver.Firefox import find_element_by_class_name [as 别名]
class TestMaxlifeFeature(object):
    """
    Checks if the maxlife feature is working
    """

    def setup_class(self):
        """
        Setup: Open a mozilla browser, login
        """
        self.browser = Firefox()
        self.browser.get('http://localhost:5000/')
        token = self.browser.find_element_by_name("token")
        password = "foo"
        # login
        token.send_keys(password)
        token.send_keys(Keys.ENTER)
        time.sleep(.1)
        try:
            self.browser.find_element_by_xpath("//input[@value='Logout']")
        except NoSuchElementException:
            raise ValueError("Can't login!!! Create a user 'foo' with the permissions"
                             "'read' and 'write' in your PERMISSIONS in the config")

    def teardown_class(self):
        """
        Tear down: Close the browser
        """
        self.browser.quit()

    def test_unit_input_exists(self):
        unit_input = self.browser.find_element_by_name("maxlife-unit")
        assert unit_input is not None
        value_input = self.browser.find_element_by_name("maxlife-value")
        assert value_input is not None

    def fill_form(self):
        paste_input = self.browser.find_element_by_id("formupload")
        paste_input.send_keys("This is test")
        filename_input = self.browser.find_element_by_id("filename")
        filename_input.send_keys("test.txt")
        contenttype_input = self.browser.find_element_by_id("contenttype")
        contenttype_input.send_keys("text/plain")
        contenttype_input.send_keys(Keys.ENTER)

    def delete_current_file(self):
        self.browser.find_element_by_id("del-btn").click()
        time.sleep(.2)
        self.browser.find_element_by_class_name("btn-primary").click()

    def test_paste_keep_forever(self):
        self.browser.find_element_by_xpath("//select[@name='maxlife-unit']/option[@value='forever']").click()
        value_input = self.browser.find_element_by_name("maxlife-value")
        value_input.clear()
        value_input.send_keys(1)
        self.fill_form()
        assert "max life" not in self.browser.find_element_by_tag_name("body").text.lower()
        self.delete_current_file()

    def test_paste_keep_minutes(self):
        self.browser.find_element_by_xpath("//select[@name='maxlife-unit']/option[@value='minutes']").click()
        value_input = self.browser.find_element_by_name("maxlife-value")
        value_input.clear()
        value_input.send_keys(1)
        self.fill_form()
        assert "max time" in self.browser.find_element_by_tag_name("body").text.lower()
        self.delete_current_file()

    @pytest.mark.slow
    def test_file_gets_deleted(self):
        self.browser.find_element_by_xpath("//select[@name='maxlife-unit']/option[@value='minutes']").click()
        value_input = self.browser.find_element_by_name("maxlife-value")
        value_input.clear()
        value_input.send_keys(1)
        self.fill_form()
        time.sleep(61)
        self.browser.find_element_by_id("inline-btn").click()
        assert "not found" in self.browser.find_element_by_tag_name("body").text.lower()

# 需要导入模块: from selenium.webdriver import Firefox [as 别名]
# 或者: from selenium.webdriver.Firefox import find_element_by_class_name [as 别名]

#.........这里部分代码省略.........
        except:
            property_data['beds'] = 'N/A';print('beds not found')
        try:
            property_data['baths'] = self.soup.find('div', attrs={'data-rf-test-id': 'abp-baths'}).find(
                'div').get_text()
        except:
            property_data['baths'] = 'N/A';print('baths not found')
        try:
            property_data['sqFt'] = self.soup.find('div', attrs={'data-rf-test-id': 'abp-sqFt'}).find('span', attrs={
                'class': 'main-font statsValue'}).get_text()
        except:
            property_data['sqFt'] = 'N/A';print('sqFt not found')
        try:
            property_data['price_per_sqFt'] = self.soup.find('div', attrs={'data-rf-test-id': 'abp-sqFt'}).find('div',
                                                                                                                attrs={
                                                                                                                    "data-rf-test-id": "abp-priceperft"}).get_text()
        except:
            property_data['price_per_sqFt'] = 'N/A';print('price_per_sqFt not found')
        try:
            property_data['year_built'] = self.soup.find('span', attrs={"data-rf-test-id": "abp-yearBuilt"}).find(
                'span', attrs={'class': 'value'}).get_text()
        except:
            property_data['year_built'] = 'N/A';print('year_built not found')
        try:
            property_data['days_on_redfin'] = self.soup.find('span',
                                                             attrs={"data-rf-test-id": "abp-daysOnRedfin"}).find('span',
                                                                                                                 attrs={
                                                                                                                     'class': 'value'}).get_text()
        except:
            property_data['days_on_redfin'] = 'N/A';print('days_on_redfin not found')
        try:
            property_data['status'] = self.soup.find('span', attrs={"data-rf-test-id": "abp-status"}).find('span',
                                                                                                           attrs={
                                                                                                               'class': 'value'}).get_text()
        except:
            property_data['status'] = 'N/A';print('status not found')

        property_data['summary'] = self.soup.find('div', attrs={'class': 'remarks'}).get_text()
        for row in self.soup.find('div', attrs={'class': 'more-info-div'}).find_all('tr'):
            cells = row.find_all('td')
            property_data[cells[0].get_text().strip()] = cells[1].get_text().strip()

        # use loops to maintain data structure ina dict
        property_data['property_details'] = OrderedDict()
        for category in self.soup.find('div', attrs={'class': 'amenities-container'}).children:
            key = category.contents[0].get_text().strip()
            property_data['property_details'][key] = OrderedDict()
            for row in category.contents[1].find_all('div', attrs={'class': 'amenity-group'}):
                key2 = row.find('h4').get_text()
                property_data['property_details'][key][key2] = []
                for row2 in row.find_all('li'):
                    property_data['property_details'][key][key2].append(row2.get_text())

        property_data['propert_history'] = []
        for row in self.soup.find_all('tr', attrs={'id': reg_property_history_row}):
            data_cells = row.find_all('td')
            history_data_row = OrderedDict()
            history_data_row['date'] = data_cells[0].get_text()
            history_data_row['event & source'] = data_cells[1].get_text()
            history_data_row['price'] = data_cells[2].get_text()
            history_data_row['appreciation'] = data_cells[3].get_text()
            property_data['propert_history'].append(history_data_row)

        property_data['url'] = 'https://www.redfin.com' + property_url
        self.output_data.append(property_data)
        return property_data

    def use_browser(self):
        self.use_selenium = True
        firefox_profile = FirefoxProfile()
        #  might as well turn off images since we don't need them
        if self.use_proxies:
            #  if use proxies is true load firefox with proxies
            firefox_profile.set_preference("permissions.default.image", 2)
            proxy_host, proxy_port = choice(self.proxies).split(':')
            firefox_profile.set_preference("network.proxy.type", 1)
            firefox_profile.set_preference("network.proxy.http", proxy_host)
            firefox_profile.set_preference("network.proxy.http_port", int(proxy_port))
            firefox_profile.set_preference("network.proxy.ssl", proxy_host)
            firefox_profile.set_preference("network.proxy.ssl_port", int(proxy_port))
        self.driver = Firefox(firefox_profile)
        self.driver.implicitly_wait(2)

    def get_page_selenium(self, page_url):
        self.driver.get(page_url)
        self.selenium_bypass_captcha()
        return self.driver.page_source

    def selenium_bypass_captcha(self):
        #  basic code for handling captcha
        #  this requires the user to actually solve the captcha and then continue
        try:
            self.driver.switch_to_frame(self.driver.find_element_by_xpath('//iframe[@title="recaptcha widget"]'))
            self.driver.find_element_by_class_name('recaptcha-checkbox-checkmark').click()
            print('solve captcha ( pop up only ) and press enter to continue')
            raw_input()
            self.driver.switch_to_default_content()
            self.driver.find_element_by_id('submit').click()
        except Exception as e:
            pass