GetBilibiliUser_Oracle.py 文件源码

def getSoup(start, stop):
    try:
        for number in range(start, stop+1):
            url = 'http://space.bilibili.com/'+str(number)+'/#!/'
            # "http://space.bilibili.com/1643718/#!/"
            # "http://space.bilibili.com/902915/#!/"
            # "http://space.bilibili.com/1/#!/"
            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  #??????????
            # phantomjs.exe???G:\Anaconda3\phantomjs\bin
            driver = webdriver.PhantomJS(executable_path='G:\\Anaconda3\\phantomjs\\bin\\phantomjs.exe',
                                         desired_capabilities=dcap)
            driver.get(url)
            # time.sleep(1)  # ?????????????
            content = driver.page_source  # ??????
            # print(content)
            driver.close()
            driver.quit()
            soup = BeautifulSoup(content, 'lxml')
            getInfo(soup)
    except Exception:
        pass


# ????