visit.py 文件源码

python
阅读 18 收藏 0 点赞 0 评论 0

项目:webfp-crawler-phantomjs 作者: pankajb64 项目源码 文件源码
def get_multitab(self):
        """Open two tab, use one to load a background site and the other to
        load the real site."""
        PAUSE_BETWEEN_TAB_OPENINGS = 0.5
        ut.timeout(cm.HARD_VISIT_TIMEOUT)  # set timeout to kill running procs
        # load a blank page - a page is needed to send keys to the browser
        self.tb_driver.get(BAREBONE_HOME_PAGE)
        self.sniffer.start_capture(self.pcap_path,
                                   'tcp and not host %s and not host %s'
                                   % (VBOX_GATEWAY_IP, LOCALHOST_IP))

        time.sleep(cm.PAUSE_BETWEEN_INSTANCES)
        try:
            self.tb_driver.set_page_load_timeout(cm.SOFT_VISIT_TIMEOUT)
        except:
            wl_log.info("Exception setting a timeout {}".format(self.page_url))

        wl_log.info("Crawling URL: {} with {} in the background".
                    format(self.page_url, self.bg_site))

        body = self.tb_driver.find_element_by_tag_name("body")
        body.send_keys(Keys.CONTROL + 't')  # open a new tab
        # now that the focus is on the address bar, load the background
        # site by "typing" it to the address bar and "pressing" ENTER (\n)
        # simulated by send_keys function
        body.send_keys('%s\n' % self.bg_site)

        # the delay between the loading of background and real sites
        time.sleep(PAUSE_BETWEEN_TAB_OPENINGS)

        body = self.tb_driver.find_element_by_tag_name("body")
        body.send_keys(Keys.CONTROL + 't')  # open a new tab

        t1 = time.time()
        self.tb_driver.get(self.page_url)  # load the real site in the 2nd tab

        page_load_time = time.time() - t1
        wl_log.info("{} loaded in {} sec"
                    .format(self.page_url, page_load_time))
        time.sleep(cm.WAIT_IN_SITE)
        if self.capture_screen:
            self.take_screenshot()
        self.cleanup_visit()
评论列表
文章目录


问题


面经


文章

微信
公众号

扫码关注公众号