Python html.get_content函数代码示例

    def prepare(self):
        info = VideoInfo(self.name)
        add_header("Referer", "http://www.bilibili.com")
        info.extra["referer"] = "http://www.bilibili.com"
        info.extra["ua"] = fake_headers['User-Agent']
        if not self.vid:
            html = get_content(self.url)
            self.vid = match1(html, 'cid=(\d+)', 'cid=\"(\d+)')
            info.title = match1(html, '<title>([^<]+)').split("_")[0].strip(u" 番剧 bilibili 哔哩哔哩弹幕视频网")
            if not self.vid:
                eid = match1(self.url, 'anime/v/(\d+)', 'play#(\d+)') or match1(html, 'anime/v/(\d+)')
                if eid:
                    Episode_info = json.loads(get_content('http://bangumi.bilibili.com/web_api/episode/{}.json'.format(eid)))['result']['currentEpisode']
                    self.vid = Episode_info['danmaku']
                    info.title = info.title + ' ' + Episode_info['indexTitle'] + '.  ' + Episode_info['longTitle']

        assert self.vid, "can't play this video: {}".format(self.url)
        for q in self.supported_stream_profile:
            sign_this = hashlib.md5(compact_bytes('cid={}&from=miniplay&player=1&quality={}{}'.format(self.vid, 3-self.supported_stream_profile.index(q), SECRETKEY_MINILOADER), 'utf-8')).hexdigest()
            api_url = 'http://interface.bilibili.com/playurl?cid={}&player=1&quality={}&from=miniplay&sign={}'.format(self.vid, 3-self.supported_stream_profile.index(q), sign_this)
            html = get_content(api_url)
            self.logger.debug("HTML> {}".format(html))
            urls, size, ext = parse_cid_playurl(html)
            if ext == 'hdmp4':
                ext = 'mp4'

            info.stream_types.append(self.profile_2_type[q])
            info.streams[self.profile_2_type[q]] = {'container': ext, 'video_profile': q, 'src' : urls, 'size': size}
        return info

    def prepare(self):
        info = VideoInfo(self.name, True)
        html = get_content(self.url)
        info.title = match1(html, '<title>([^<]+)').split('_')[0]

        data = json.loads(match1(html, 'channelOneInfo = ({.+?});'))
        tag_from = 'huomaoh5room'
        tn = str(int(time.time()))
        sign_context = data['stream'] + tag_from + tn + SECRETKEY
        token = hashlib.md5(compact_bytes(sign_context, 'utf-8')).hexdigest()

        params = { 'streamtype':'live',
                   'VideoIDS': data['stream'],
                   'time': tn,
                   'cdns' : '1',
                   'from': tag_from,
                   'token': token
                }
        content = get_content(self.live_base, data=compact_bytes(urlencode(params), 'utf-8'), charset='utf-8')
        stream_data = json.loads(content)

        assert stream_data["roomStatus"] == "1", "The live stream is not online! "
        for stream in stream_data["streamList"]:
            if stream['default'] == 1:
                defstream = stream['list']

        for stream in defstream:
            info.stream_types.append(stream['type'])
            info.streams[stream['type']] = {'container': 'flv', 'video_profile': self.stream_2_profile[stream['type']], 'src' : [stream['url']], 'size': float('inf')}

        info.stream_types = sorted(info.stream_types, key = self.supported_stream_types.index)
        return info

    def prepare(self):
        info = VideoInfo(self.name, True)
        if not self.vid:
            self.vid = match1(self.url, '/(\d+)')
        if not self.vid:
            html = get_content(self.url)
            self.vid = match1(html, '"room_id":(\d+)')

        #from upstream!!
        api_url = 'http://www.qie.tv/api/v1/room/{}'.format(self.vid)

        metadata = json.loads(get_content(api_url))
        assert metadata['error'] == 0, 'error {}: {}'.format(metadata['error'], metadata['data'])

        livedata = metadata['data']
        assert livedata['show_status'] == '1', 'error: live show is not on line!!'

        info.title = livedata['room_name']
        info.artist = livedata['nickname']

        base_url = livedata['rtmp_url']

        if 'hls_url' in livedata:
            info.stream_types.append('BD')
            info.streams['BD'] = {'container': 'm3u8', 'video_profile': u'原画', 'src' : [livedata['hls_url']], 'size': float('inf')}

        mutli_stream = livedata['rtmp_multi_bitrate']
        for i in self.mutli_bitrate:
            if i in mutli_stream:
                info.stream_types.append(self.bitrate_2_type[i])
                info.streams[self.bitrate_2_type[i]] = {'container': 'flv', 'video_profile': self.bitrate_2_profile[i], 'src' : [base_url + '/' + mutli_stream[i]], 'size': float('inf')}
        return info

    def parser_list(self, url):
        add_header("Referer", "http://music.163.com/")
        vid =  match1(url, 'id=(.*)')
        if "album" in url:
           api_url = "http://music.163.com/api/album/{}?id={}&csrf_token=".format(vid, vid)
           listdata = json.loads(get_content(api_url))
           playlist = listdata['album']['songs']
        elif "playlist" in url:
           api_url = "http://music.163.com/api/playlist/detail?id={}&csrf_token=".format(vid)
           listdata = json.loads(get_content(api_url))
           playlist = listdata['result']['tracks']
        elif "toplist" in url:
           api_url = "http://music.163.com/api/playlist/detail?id={}&csrf_token=".format(vid)
           listdata = json.loads(get_content(api_url))
           playlist = listdata['result']['tracks']
        elif "artist" in url:
           api_url = "http://music.163.com/api/artist/{}?id={}&csrf_token=".format(vid, vid)
           listdata = json.loads(get_content(api_url))
           playlist = listdata['hotSongs']

        info_list = []
        for music in playlist:
            info = VideoInfo(self.name)
            info.title = music['name']
            info.artist = music['artists'][0]['name']
            self.mp3_host = music['mp3Url'][8]
            for st in self.supported_stream_types:
                if st in music and music[st]:
                    info.stream_types.append(st)
                    self.song_date[st] = music[st]
            self.extract_song(info)
            info_list.append(info)
        return info_list

    def prepare(self):
        info = VideoInfo(self.name)
        if not self.vid:
            self.vid = match1(self.url, '/show(?:/channel)?/([^\./]+)',
                                        '/media/([^\./]+)')
        if not self.vid:
            html = get_content(self.url)
            self.vid = match1(html, 's[cm]id ?= ?[\'"]([^\'"]+)[\'"]')
        assert self.vid, "No VID match!"

        data = json.loads(get_content('https://n.miaopai.com/api/aj_media/info.json?smid={}'.format(self.vid)))
        if 'status' in data:
            if data['status'] != 200:
                data = json.loads(get_content('http://api.miaopai.com/m/v2_channel.json?fillType=259&scid={}&vend=miaopai'.format(self.vid)))

            assert data['status'] == 200, data['msg']

            data = data['result']
            info.title = data['ext']['t'] or self.name + '_' + self.vid
            url = data['stream']['base']
            ext = data['stream']['and']
        else:
            assert data['code'] == 200, data['msg']

            data = data['data']
            info.title = data['description'] or self.name + '_' + self.vid
            url = data['meta_data'][0]['play_urls']['m']
            _, ext, _ = url_info(url)

        info.stream_types.append('current')
        info.streams['current'] = {'container': ext or 'mp4', 'src': [url], 'size' : 0}
        return info

    def prepare(self):
        info = VideoInfo(self.name)
        if self.url and not self.vid:
            self.vid = match1(self.url, 'http://www.mgtv.com/b/\d+/(\d+).html')
            if self.vid is None:
                html = get_content(self.url)
                self.vid = match1(html, 'vid=(\d+)', 'vid=\"(\d+)', 'vid: (\d+)')

        api_url = 'http://pcweb.api.mgtv.com/player/video?video_id={}'.format(self.vid)
        meta = json.loads(get_content(api_url))

        assert meta['code'] == 200, '[failed] status: {}, msg: {}'.format(meta['status'],meta['msg'])
        assert meta['data'], '[Failed] Video not found.'

        data = meta['data']

        info.title = data['info']['title']
        domain = data['stream_domain'][0]
        for lstream in data['stream']:
            if lstream['url']:
                url = json.loads(get_content(domain + lstream['url']))['info']
                info.streams[self.profile_2_types[lstream['name']]] = {'container': 'm3u8', 'video_profile': lstream['name'], 'src' : [url]}
                info.stream_types.append(self.profile_2_types[lstream['name']])
        info.stream_types= sorted(info.stream_types, key = self.supported_stream_types.index)
        return info

    def prepare(self):
        info = VideoInfo(self.name, True)
        html = get_content(self.url)
        info.title = match1(html, '<title>([^<]+)').split('_')[0]

        video_name = match1(html, 'getFlash\("[0-9]+","([^"]+)')
        params = { 'streamtype':'live',
                   'VideoIDS': video_name,
                   'cdns' : '1'
                }
        form = urlencode(params)
        content = get_content(self.live_base,data=compact_bytes(form, 'utf-8'),charset = 'utf-8')
        stream_data = json.loads(content)

        assert stream_data["roomStatus"] == "1", "The live stream is not online! "
        for stream in stream_data["streamList"]:
            if stream['default'] == 1:
                defstream = stream['list']

        for stream in defstream:
            info.stream_types.append(stream['type'])
            info.streams[stream['type']] = {'container': 'flv', 'video_profile': self.stream_2_profile[stream['type']], 'src' : [stream['url']], 'size': float('inf')}

        info.stream_types = sorted(info.stream_types, key = self.supported_stream_types.index)
        return info

    def prepare(self):
        info = VideoInfo(self.name, True)

        if not self.vid:
            html = get_content(self.url)
            room = match1(html, 'var $ROOM = ([^;]+)')
            self.vid = match1(html, '"room_id.?":(\d+)')
            info.title = json.loads("{\"room_name\" : \"" + match1(html, '"room_name.?":"([^"]+)') + "\"}")['room_name']
            info.artist = json.loads("{\"name\" : \"" + match1(html, '"owner_name.?":"([^"]+)') + "\"}")['name']
        api_url = 'https://www.douyu.com/lapi/live/getPlay/{}'.format(self.vid)
        tt = str(int(time.time() / 60))
        rnd_md5 = hashlib.md5(str(random.random()).encode('utf8'))
        did = rnd_md5.hexdigest().upper()
        to_sign = ''.join([self.vid, did, API_KEY, tt])
        sign = stupidMD5(to_sign)
        for stream in self.stream_ids:
            rate = self.stream_id_2_rate[stream]
            params = {"ver" : VER, "sign" : sign, "did" : did, "rate" : rate, "tt" : tt, "cdn" : "ws"}
            form = urlencode(params)
            html_content = get_content(api_url, data=compact_bytes(form, 'utf-8'))
            live_data = json.loads(html_content)
            assert live_data["error"] == 0, "live show is offline"
            live_data = live_data["data"]
            real_url = '/'.join([live_data['rtmp_url'], live_data['rtmp_live']])

            info.stream_types.append(stream)
            info.streams[stream] = {'container': 'flv', 'video_profile': self.id_2_profile[stream], 'src' : [real_url], 'size': float('inf')}

        return info

    def prepare(self):
        info = VideoInfo(self.name, True)
        if not self.vid:
            self.vid = match1(self.url, 'channel=([\d]+)')

        live_data = json.loads(get_content('http://api.live.letv.com/v1/channel/letv/100/1001/{}'.format(self.vid)))['data']

        info.title = self.name + " " + live_data['channelName']

        stream_data = live_data['streams']

        for s in stream_data:
            stream_id = self.stream_2_id[s['rateType']]
            stream_profile = self.stream_2_profile[s['rateType']]
            if not stream_id in info.stream_types:
                info.stream_types.append(stream_id)
                date = datetime.datetime.now()
                streamUrl = s['streamUrl'] + '&format=1&expect=2&termid=1&hwtype=un&platid=10&splatid=1001&playid=1sign=live_web&&ostype={}&p1=1&p2=10&p3=-&vkit={}&station={}&tm={}'.format(platform.platform(), date.strftime("%Y%m%d"), self.vid, int(time.time()))
                data = json.loads(get_content(streamUrl))
                nodelist = data['nodelist']
                for node in nodelist:
                    src = node['location']
                    try:
                        get_content(src)
                        info.streams[stream_id] = {'container': 'm3u8', 'video_profile': stream_profile, 'size' : float('inf'), 'src' : [src]}
                    except:
                        continue
                    break
        info.stream_types = sorted(info.stream_types, key = self.stream_ids.index)
        return info

    def prepare(self):

        if not self.vid:
            self.vid = match1(self.url, r'http://www.le.com/ptv/vplay/(\d+).html', '#record/(\d+)')

        #normal process
        info_url = 'http://api.le.com/mms/out/video/playJson?id={}&platid=1&splatid=101&format=1&tkey={}&domain=www.le.com'.format(self.vid, calcTimeKey(int(time.time())))
        r = get_content(info_url)
        info=json.loads(r)

        self.title = info['playurl']['title']
        available_stream_id = info["playurl"]["dispatch"].keys()
        for stream in self.supported_stream_types:
            if stream in available_stream_id:
                s_url =info["playurl"]["domain"][0]+info["playurl"]["dispatch"][stream][0]
                s_url+="&ctv=pc&m3v=1&termid=1&format=1&hwtype=un&ostype=Linux&tag=le&sign=le&expect=3&tn={}&pay=0&iscpn=f9051&rateid={}".format(random.random(),stream)
                r2=get_content(s_url)
                info2=json.loads(r2)

                # hold on ! more things to do
                # to decode m3u8 (encoded)
                m3u8 = get_content(info2["location"], charset = 'ignore')
                m3u8_list = decode(m3u8)
                self.streams[stream] = {'container': 'm3u8', 'video_profile': stream, 'size' : 0}
                import tempfile
                self.streams[stream]['tmp'] = tempfile.NamedTemporaryFile(mode='w+t', suffix='.m3u8')
                self.streams[stream]['tmp'].write(m3u8_list)
                self.streams[stream]['src'] = [self.streams[stream]['tmp'].name]
                self.streams[stream]['tmp'].flush()
                self.stream_types.append(stream)

    def prepare(self):
        info = VideoInfo(self.name, True)
        ID = match1(self.url, "/(\d+)")
        api1_data = json.loads(get_content("{}?id={}".format(api1_url, ID)))
        self.vid = api1_data["data"]["room_id"]
        api2_data = json.loads(get_content("{}?room_id={}&from=room".format(api2_url, self.vid)))
        info.title = api2_data["data"]["title"]
        assert api2_data["data"]["live_status"] == 1, u"主播正在觅食......"

        def get_live_info(q=0):
            data = json.loads(get_content("{}?player=1&cid={}&quality={}&otype=json".format(api_url, self.vid, q)))

            assert data["code"] == 0, data["msg"]

            data = data["data"]
            urls = [random.choice(data["durl"])["url"]]
            qlt = data['current_quality']
            aqlts = [int(x) for x in data['accept_quality']]
            size = float('inf')
            ext = 'flv'
            prf = self.supported_stream_profile[4 - qlt]
            st = self.profile_2_type[prf]
            if urls and st not in info.streams:
                info.stream_types.append(st)
                info.streams[st] = {'container': ext, 'video_profile': prf, 'src' : urls, 'size': size}

            if q == 0:
                aqlts.remove(qlt)
                for aqlt in aqlts:
                    get_live_info(aqlt)

        get_live_info()
        return info

    def prepare(self):
        info = VideoInfo(self.name)
        stream_temp = {'1080p': None , '1300': None, '1000':None , '720p': None, '350': None }
        self.__STREAM_TEMP__.append(stream_temp)
        if not self.vid:
            self.vid = match1(self.url, r'http://www.le.com/ptv/vplay/(\d+).html', '#record/(\d+)')

        #normal process
        info_url = 'http://api.le.com/mms/out/video/playJson?id={}&platid=1&splatid=101&format=1&tkey={}&domain=www.le.com'.format(self.vid, calcTimeKey(int(time.time())))
        r = get_content(info_url)
        data=json.loads(r)

        info.title = data['playurl']['title']
        available_stream_id = sorted(list(data["playurl"]["dispatch"].keys()), key = self.supported_stream_types.index)
        for stream in available_stream_id:
            s_url =data["playurl"]["domain"][0]+data["playurl"]["dispatch"][stream][0]
            s_url+="&ctv=pc&m3v=1&termid=1&format=1&hwtype=un&ostype=Linux&tag=le&sign=le&expect=3&tn={}&pay=0&iscpn=f9051&rateid={}".format(random.random(),stream)
            r2=get_content(s_url)
            data2=json.loads(r2)

            # hold on ! more things to do
            # to decode m3u8 (encoded)
            m3u8 = get_content(data2["location"], charset = 'ignore')
            m3u8_list = decode(m3u8)
            stream_id = self.stream_2_id[stream]
            info.streams[stream_id] = {'container': 'm3u8', 'video_profile': self.stream_2_profile[stream], 'size' : 0}
            stream_temp[stream] = compact_tempfile(mode='w+t', suffix='.m3u8')
            stream_temp[stream].write(m3u8_list)
            info.streams[stream_id]['src'] = [stream_temp[stream].name]
            stream_temp[stream].flush()
            info.stream_types.append(stream_id)
        return info

    def prepare(self):
        html = get_content(self.url)
        title = match1(html, u'<title>(.+?)丨嘀哩嘀哩</title>')
        source_url = match1(html, r'var sourceUrl\s?=\s?"(.+?)"', r'var Url\s?=\s?"(.+?)"')
        
        # First type, bangumi
        # http://www.dilidili.wang/watch3/72766/ or
        # http://www.dilidili.wang/watch3/52919/
        if source_url:
            ext = source_url.split('?')[0].split('.')[-1]
        
            # Dilidili hosts this video itself
            if ext in ('mp4', 'flv', 'f4v', 'm3u', 'm3u8'):
                self.build_videoinfo(title, ext, source_url)
        
            # It is an embedded video from other websites
            else:
                self.video_info['url'] = source_url
                self.video_info['title'] = title

        # Second type, user-uploaded videos
        # http://www.dilidili.wang/huiyuan/76983/
        else:
            player_url = match1(html, r'<iframe src="(.+?)"')
            html = get_content(player_url)
            video_url = match1(html, r'var main = "(.+?)"')
            video_url_full = '/'.join(player_url.split('/')[0:3]) + video_url
            ext = video_url.split('?')[0].split('.')[-1]
            self.build_videoinfo(title, ext, video_url_full)

    def prepare(self):
        info = VideoInfo(self.name)
        if not self.vid:
            html = get_content(self.url)
            self.vid = match1(html, 'video_id:\'([^\']+)') or match1(self.url, '#(\d+)')

        assert self.vid, "can't get vid"

        api_url = 'http://s.video.sina.com.cn/video/h5play?video_id={}'.format(self.vid)
        data = json.loads(get_content(api_url))['data']
        info.title = data['title']
        for t in ['mp4', '3gp', 'flv']:
            if t in data['videos']:
                video_info = data['videos'][t]
                break

        for profile in video_info:
            if not profile in info.stream_types:
                v = video_info[profile]
                tp = v['type']
                url = v['file_api']+'?vid='+v['file_id']
                r_url = get_realurl(url)
                info.stream_types.append(profile)
                info.streams[profile] = {'container': tp, 'video_profile': profile, 'src': [r_url], 'size' : 0}
        return info

    def prepare(self):
        info = VideoInfo(self.name, True)
        html = get_content(self.url)
        t_a = match1(html, '"keywords" content="([^"]+)')
        info.title = t_a.split(',')[0]
        info.artist = t_a.split(',')[1]

        replay_url = match1(html, '"m3u8":"([^"]+)')
        if replay_url:
            replay_url = replay_url.replace('\/','/')
            info.live = False
            info.stream_types.append('current')
            info.streams['current'] = {'container': 'm3u8', 'video_profile': 'current', 'src' : [replay_url], 'size': float('inf')}
            return info

        self.vid = match1(html, '"sn":"([^"]+)')
        channel = match1(html, '"channel":"([^"]+)')
        api_url = 'http://g2.live.360.cn/liveplay?stype=flv&channel={}&bid=huajiao&sn={}&sid={}&_rate=xd&ts={}&r={}&_ostype=flash&_delay=0&_sign=null&_ver=13'.format(channel, self.vid, SID, time.time(),random.random())
        encoded_json = get_content(api_url)
        decoded_json = base64.decodestring(compact_bytes(encoded_json[0:3]+ encoded_json[6:], 'utf-8')).decode('utf-8')
        video_data = json.loads(decoded_json)
        live_url = video_data['main']
        info.live = True
        info.stream_types.append('current')
        info.streams['current'] = {'container': 'flv', 'video_profile': 'current', 'src' : [live_url], 'size': float('inf')}
        return info