DriveServices.py 文件源码

def crawlListPage(self):
        self.openPage("http://hotels.ctrip.com/hotel/nanjing12#ctm_ref=hod_hp_sb_lst")
        self.driver.implicitly_wait(10)
        # ??????
        loopNum = 0
        # ?????????????False???????????
        ifHandle = False
        # ??????
        pageNum = 140
        while(pageNum>=1):
            # ?????1
            loopNum = loopNum + 1
            # ????90%?
            # js="var q=document.documentElement.scrollTop=9600"
            # self.driver.execute_script(js)
            self.driver.find_element_by_tag_name("body").send_keys(Keys.END)
            self.driver.find_element_by_tag_name("body").send_keys(Keys.PAGE_UP)
            # ??????“???”???????????????
            if u"??" in self.driver.page_source:
                # ????????????
                if ifHandle==False:
                    self.__crawllianjie(self.driver.page_source)
                    print u"???????%d"%len(self.listPageInfo)
                    ifHandle = True
                # ??????
                try:
                    if u"???" in self.driver.page_source:
                        self.driver.find_element_by_partial_link_text(u"???").click()
                        #self.driver.find_element_by_xpath("//a[@class='c_down']").click()
                        pageNum = pageNum - 1
                        # ???????????
                        ifHandle = False
                        # ?????????
                        loopNum = 0
                        time.sleep(random.uniform(3, 6))
                        print u"???" +  str(pageNum)
                except:
                    print "error happen at clicking of nextpage"
            # ??????????????????????
            if loopNum != 0:
                # ????????????????15??????????????????????????
                if loopNum < 15:
                    time.sleep(3)
                    continue
                else:
                    break
        return False if pageNum > 1 else True

    # ??????