课堂直播视频-爬虫-3

  上回说到，我就差一个参数就可以获取视频了，第二天，我一步步看一步步找，终于我感觉好像问题出在flash上，我从请求中从来没获取到上次播放位置，而每次刷新都会从原来位置上播放，这样目光一下瞄准swf文件。

 

  一堆乱码，只能先下载保存一个这样的文件了。

  

headers = {
    "authority": "p.bokecc.com",
    "accept-encoding": "gzip, deflate",
    "accept-language": "zh-CN,zh;q=0.9",
    # "Cache-Control": "no-cache",
    "if-modified-since": "Tue, 10 Jul 2018 06:19:51 GMT",
    "if-none-match": "5b445007-8c0e",
    # "Connection": "keep-alive",
    # "Cookie": "Hm_lvt_2c32a112d0d1558c3e63c2f90cd57477=1595775774,1595860124,1596264790; Hm_lpvt_2c32a112d0d1558c3e63c2f90cd57477=1596294515",
    # "Pragma": "no-cache",
    # "Host": "tzb.feelmoore.com",
    "sec-fetch-dest": "embed",
    "sec-fetch-mode": "no-cors",
    "sec-fetch-site": "cross-site",
    "path": "/flash/player.swf?vid=CCB1C8D79776B6469C33DC5901307461&siteid=0C728A4805962911&playerid=A8E5C78ED3BA6213&playertype=1&autoStart=true&mediatype=1",
    "Referer": "http://www.kuaxue.com/Weixin/ClassUrl/shandong2/id/9867.shtml",
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36"
    # "
}
url ="https://p.bokecc.com/flash/player.swf?vid=CCB1C8D79776B6469C33DC5901307461&siteid=0C728A4805962911&playerid=A8E5C78ED3BA6213&playertype=1&autoStart=true&mediatype=1"
resp = requests.get(url, headers=headers)
print(resp.status_code)
with open('1.swf', 'wb') as f:
    f.write(resp.content)

　　一通度娘，网上说swf文件需要反编译，又一通度娘，终于找到了一个大杀器，---jpexs-decompiler。下载安装，将刚才下载好的swf文件导入。

    全局搜索一下rnd ，我去终于找到了，一看，无语了，随机数。。。。。

    这下终于搞定了下载flv吧。

def get_real_url(uu, uid, vid, pid, id):
    try:
        headers = {
            "authority": "p.bokecc.com",
            "accept-encoding": "gzip, deflate, br",
            "accept-language": "zh-CN,zh;q=0.9",
            "cache-control": "no-cache",
            "pragma": "no-cache",
            "sec-fetch-dest": "empty",
            "sec-fetch-mode": "no-cors",
            "sec-fetch-site": "cross-site",
            "x-requested-with": "ShockwaveFlash/32.0.0.403",
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36",
            "path": "/servlet/playinfo?uid=" + uid + "&vid=" + vid + "&lid=&pid=" + pid + "&pt=1&pm=spark&ci=&isp=%2D1&m=1&pp=false&d=ktzb%2Efeelmoore%2Ecom&fv=WIN%2032%2C0%2C0%2C403&uu=" + uu + "&mediatype=1&vc=null&version=20140214&rnd=3156",
            "Referer": 'http://www.kuaxue.com/Weixin/ClassUrl/shandong2/id/' + str(id) + '.shtml'
        }
        url = "https://p.bokecc.com/servlet/playinfo?uid=" + uid + "&vid=" + vid + "&lid=&pid=" + pid + "&pt=1&pm=spark&ci=&isp=%2D1&m=1&pp=false&d=ktzb%2Efeelmoore%2Ecom&fv=WIN%2032%2C0%2C0%2C403&uu=" + uu + "&mediatype=1&vc=null&version=20140214&rnd=3156"
        print(url)
        data = requests.get(url,
                            headers=headers).text
        soup = BeautifulSoup(data, 'lxml')
        # print(soup)
        # img = soup.get('response')
        res = soup.find_all("response")[0]
        upid = re.findall(r'<upid>(.+?)</upid>', str(res))
        if upid != []:
            temp = res.find_all("video")[0].find_all("quality")
            return str(temp[len(temp) - 1].find_all("copy")[0]["playurl"]) + "&upid=" + upid[0] + "&pt=0&pi=1"
        else:
            return ""
    except:
        print(vid+"获取playinfo失败")
        return ""

def download(url, id, save_home,name):
    try:
        headers = {
            #     "Accept: */*
            "Accept-Encoding": "gzip, deflate",
            "Accept-Language": "zh-CN,zh;q=0.9",
            "Cache-Control": "no-cache",
            "Connection": "keep-alive",
            "Pragma": "no-cache",
            "Host": url.replace("http://", "").split(".com")[0] + ".com",
            # "path": url.replace("http://", "").split(".com")[1],
            "Referer": "http://ktzb.feelmoore.com/LivingClassroom/index.html?isbn=" + str(id),
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36"
            # "
        }
        resp = requests.get(url, headers=headers)
        #
        with open(save_home+name + '.flv', 'wb') as f:
            f.write(resp.content)
    except:
        print(name+"下载视频失败")
uu = "474A2CC1946AEBAA0B83195A8F5ED539EB85CB9F"
uid = '0C728A4805962911'
pid = 'A8E5C78ED3BA6213'
for file in os.listdir("data/"):
    with open("data/"+file, encoding='utf8') as data_json:
        data_json = json.load(data_json)
    list_data = str(data_json['data']).replace("[", '').replace("]", '').split("},")
    result = []
    for element in list_data:
        try:
            result.append(json.loads(element + "}"))
        except:
            result.append(json.loads(element))
    for element in result:
        vid =element['ccid']
        id=element['id']
        print(id)
        flv_url = get_real_url(uu,uid, vid, pid, id)
        download(flv_url, id, "flv/", element['title'])