sparphantor.py 文件源码

python
阅读 28 收藏 0 点赞 0 评论 0

项目:sparphantor 作者: antitree 项目源码 文件源码
def _init_browser(self):
        ''' Setup selenium browser. Uses default path location
        if none is specified. Returns browser object or
        None if it fails.'''
        # User Agent
        uas = [
            "Mozilla/5.0 (Windows NT 6.1; rv:31.0) Gecko/20100101 Firefox/31.0",
            "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.135 Safari/537.36",
            "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:37.0) Gecko/20100101 Firefox/37.0",
            "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.135 Safari/537.36",
            "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.90 Safari/537.36",
            ]
        ua = random.choice(uas)

        ## PhantomJS Binary files
        phantoms = config.PHANTOM_PATH
        phantompath = random.choice(phantoms)

        # Custom user agent
        dc = dict(DesiredCapabilities.PHANTOMJS)
        dc["phantomjs.page.settings.userAgent"] = ua
        #dc["pages.settings.XSSAuditEnabled"] = "true"

        try:
            browser = webdriver.PhantomJS(
                phantompath,
                service_args=self.service_args,
                desired_capabilities=dc
            )
        except WebDriverException as err:
            logging.error("Could not create browser. Check path")
            logging.error(err)
            return None
        except:
            logging.error("Major problem with webdriver. "
                          "Could be related to performance."
                          "Decrease the number of threads.")
            return None
        browser.set_page_load_timeout(45)

        ## DELETED GOOD STUFF ##
        return browser
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