GetUserFansId.py 文件源码

def getSoup(start, stop):

    try:
        for number in range(start, stop+1):

            url = 'http://space.bilibili.com/'+str(number)+'/#!/'
            # url = 'http://space.bilibili.com/122879/#!/'

            # "http://http://space.bilibili.com/122879/#!/"
            dcap = dict(DesiredCapabilities.PHANTOMJS)
            dcap["phantomjs.page.settings.userAgent"] = (
                "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:50.0) Gecko/20100101 Firefox/50.0"
            )
            dcap["phantomjs.page.settings.loadImages"] = False  #??????????
            # executable_path='D:\\Chrome\\phantomjs-2.1.1-windows\\phantomjs-2.1.1-windows\\bin\\phantomjs.exe',
            driver = webdriver.PhantomJS(desired_capabilities=dcap)
            driver.get(url)
            content = driver.page_source  # ??????
            # print(content)
            driver.close()
            soup = BeautifulSoup(content, 'lxml')
            username= getInfo(soup) # ?????
            uid = number # number??uid

            get_fans_uid = GetFansUid.GetFansUid(number)
            fansuid, fansnumber = get_fans_uid.get_uids()  # ????id?????
            print(uid, username, fansnumber)

            saveData(uid, username, fansnumber, fansuid)# ?????
    except Exception:
        print("get page error")
        return getSoup(number + 1, stop+1)


# ????