Esempio n. 1
0
def get_raw_meta_texts(url):
    print('running Chrome...')
    c = Chrome()
    c.get(url)
    _scroll_to_the_bottom_google_image_search(c)
    print('exacting by xpath...')
    elements = c.xpath_lxml('//*[@class = "rg_meta notranslate"]')
    raw_meta_texts = list(map(lambda x: x.text_content(), elements))
    c.quit()
    return raw_meta_texts
Esempio n. 2
0
def test_access():
    url = "https://b2b-ch.infomart.co.jp/company/search/list.page?1942&chi=23&cha=13"
    from selenium.webdriver import ActionChains
    from selenium.webdriver.common.keys import Keys
    c = Chrome()
    actions = ActionChains(c)
    c.get(url)
    links = c.find_elements_by_xpath("//a[@id='lnkCompanyName']")
    main_tab = c.current_window_handle
    for link in links:
        actions.key_down(Keys.CONTROL).click(link).key_up(
            Keys.CONTROL).perform()
        while True:
            try:
                c.switch_tab(index=1)
                xpath_ = "//div[@class='co-detail-tbl-row']"
                rows = c.find_elements_by_xpath(xpath_)
                if len(rows) == 0:
                    raise

                text = c.find_element_by_xpath("//div[@class='main-area']")
                print(text.text)

                # tab.close()
                c.close()
                # len_ = len(c.window_handles)
                # while True:
                #     c.close_tab()
                #     if len(c.window_handles) == 1:
                #         break
                c.switch_to_window(main_tab)
            except (Exception, ) as e:
                print(e)
            else:
                break
    c.quit()