From 8eb703edbeb5629bc513a0c7f9201465a617145f Mon Sep 17 00:00:00 2001 From: GuanFoxyier <1372851437@qq.com> Date: Thu, 23 May 2019 11:12:49 +0800 Subject: [PATCH 1/5] fix le --- src/you_get/extractors/le.py | 86 +++++++++++++++++++----------------- 1 file changed, 46 insertions(+), 40 deletions(-) diff --git a/src/you_get/extractors/le.py b/src/you_get/extractors/le.py index 940b9b35..af49c2dc 100644 --- a/src/you_get/extractors/le.py +++ b/src/you_get/extractors/le.py @@ -9,13 +9,16 @@ import base64, hashlib, urllib, time, re from ..common import * -#@DEPRECATED + +# @DEPRECATED def get_timestamp(): tn = random.random() url = 'http://api.letv.com/time?tn={}'.format(tn) result = get_content(url) return json.loads(result)['stime'] -#@DEPRECATED + + +# @DEPRECATED def get_key(t): for s in range(0, 8): e = 1 & t @@ -24,42 +27,40 @@ def get_key(t): t += e return t ^ 185025305 + def calcTimeKey(t): - ror = lambda val, r_bits, : ((val & (2**32-1)) >> r_bits%32) | (val << (32-(r_bits%32)) & (2**32-1)) + ror = lambda val, r_bits,: ((val & (2 ** 32 - 1)) >> r_bits % 32) | (val << (32 - (r_bits % 32)) & (2 ** 32 - 1)) magic = 185025305 return ror(t, magic % 17) ^ magic - #return ror(ror(t,773625421%13)^773625421,773625421%17) + # return ror(ror(t,773625421%13)^773625421,773625421%17) def decode(data): version = data[0:5] if version.lower() == b'vc_01': - #get real m3u8 + # get real m3u8 loc2 = data[5:] length = len(loc2) - loc4 = [0]*(2*length) + loc4 = [0] * (2 * length) for i in range(length): - loc4[2*i] = loc2[i] >> 4 - loc4[2*i+1]= loc2[i] & 15; - loc6 = loc4[len(loc4)-11:]+loc4[:len(loc4)-11] - loc7 = [0]*length + loc4[2 * i] = loc2[i] >> 4 + loc4[2 * i + 1] = loc2[i] & 15; + loc6 = loc4[len(loc4) - 11:] + loc4[:len(loc4) - 11] + loc7 = [0] * length for i in range(length): - loc7[i] = (loc6[2 * i] << 4) +loc6[2*i+1] + loc7[i] = (loc6[2 * i] << 4) + loc6[2 * i + 1] return ''.join([chr(i) for i in loc7]) else: # directly return - return data + return str(data) - - -def video_info(vid,**kwargs): - url = 'http://player-pc.le.com/mms/out/video/playJson?id={}&platid=1&splatid=101&format=1&tkey={}&domain=www.le.com®ion=cn&source=1000&accesyx=1'.format(vid,calcTimeKey(int(time.time()))) +def video_info(vid, **kwargs): + url = 'http://player-pc.le.com/mms/out/video/playJson?id={}&platid=1&splatid=105&format=1&tkey={}&domain=www.le.com®ion=cn&source=1000&accesyx=1'.format(vid, calcTimeKey(int(time.time()))) r = get_content(url, decoded=False) - info=json.loads(str(r,"utf-8")) + info = json.loads(str(r, "utf-8")) info = info['msgs'] - stream_id = None support_stream_id = info["playurl"]["dispatch"].keys() if "stream_id" in kwargs and kwargs["stream_id"].lower() in support_stream_id: @@ -70,27 +71,28 @@ def video_info(vid,**kwargs): elif "720p" in support_stream_id: stream_id = '720p' else: - stream_id =sorted(support_stream_id,key= lambda i: int(i[1:]))[-1] + stream_id = sorted(support_stream_id, key=lambda i: int(i[1:]))[-1] - url =info["playurl"]["domain"][0]+info["playurl"]["dispatch"][stream_id][0] + url = info["playurl"]["domain"][0] + info["playurl"]["dispatch"][stream_id][0] uuid = hashlib.sha1(url.encode('utf8')).hexdigest() + '_0' ext = info["playurl"]["dispatch"][stream_id][1].split('.')[-1] url = url.replace('tss=0', 'tss=ios') - url+="&m3v=1&termid=1&format=1&hwtype=un&ostype=MacOS10.12.4&p1=1&p2=10&p3=-&expect=3&tn={}&vid={}&uuid={}&sign=letv".format(random.random(), vid, uuid) + url += "&m3v=1&termid=1&format=1&hwtype=un&ostype=MacOS10.12.4&p1=1&p2=10&p3=-&expect=3&tn={}&vid={}&uuid={}&sign=letv".format(random.random(), vid, uuid) - r2=get_content(url,decoded=False) - info2=json.loads(str(r2,"utf-8")) + r2 = get_content(url, decoded=False) + info2 = json.loads(str(r2, "utf-8")) # hold on ! more things to do # to decode m3u8 (encoded) suffix = '&r=' + str(int(time.time() * 1000)) + '&appid=500' - m3u8 = get_content(info2["location"]+suffix,decoded=False) + m3u8 = get_content(info2["location"] + suffix, decoded=False) m3u8_list = decode(m3u8) - urls = re.findall(r'^[^#][^\r]*',m3u8_list,re.MULTILINE) - return ext,urls + urls = re.findall(r'(http.*?)#', m3u8_list, re.MULTILINE) + return ext, urls -def letv_download_by_vid(vid,title, output_dir='.', merge=True, info_only=False,**kwargs): - ext , urls = video_info(vid,**kwargs) + +def letv_download_by_vid(vid, title, output_dir='.', merge=True, info_only=False, **kwargs): + ext, urls = video_info(vid, **kwargs) size = 0 for i in urls: _, _, tmp = url_info(i) @@ -100,27 +102,29 @@ def letv_download_by_vid(vid,title, output_dir='.', merge=True, info_only=False, if not info_only: download_urls(urls, title, ext, size, output_dir=output_dir, merge=merge) + def letvcloud_download_by_vu(vu, uu, title=None, output_dir='.', merge=True, info_only=False): - #ran = float('0.' + str(random.randint(0, 9999999999999999))) # For ver 2.1 - #str2Hash = 'cfflashformatjsonran{ran}uu{uu}ver2.2vu{vu}bie^#@(%27eib58'.format(vu = vu, uu = uu, ran = ran) #Magic!/ In ver 2.1 - argumet_dict ={'cf' : 'flash', 'format': 'json', 'ran': str(int(time.time())), 'uu': str(uu),'ver': '2.2', 'vu': str(vu), } - sign_key = '2f9d6924b33a165a6d8b5d3d42f4f987' #ALL YOUR BASE ARE BELONG TO US + # ran = float('0.' + str(random.randint(0, 9999999999999999))) # For ver 2.1 + # str2Hash = 'cfflashformatjsonran{ran}uu{uu}ver2.2vu{vu}bie^#@(%27eib58'.format(vu = vu, uu = uu, ran = ran) #Magic!/ In ver 2.1 + argumet_dict = {'cf': 'flash', 'format': 'json', 'ran': str(int(time.time())), 'uu': str(uu), 'ver': '2.2', 'vu': str(vu), } + sign_key = '2f9d6924b33a165a6d8b5d3d42f4f987' # ALL YOUR BASE ARE BELONG TO US str2Hash = ''.join([i + argumet_dict[i] for i in sorted(argumet_dict)]) + sign_key sign = hashlib.md5(str2Hash.encode('utf-8')).hexdigest() - request_info = urllib.request.Request('http://api.letvcloud.com/gpc.php?' + '&'.join([i + '=' + argumet_dict[i] for i in argumet_dict]) + '&sign={sign}'.format(sign = sign)) + request_info = urllib.request.Request('http://api.letvcloud.com/gpc.php?' + '&'.join([i + '=' + argumet_dict[i] for i in argumet_dict]) + '&sign={sign}'.format(sign=sign)) response = urllib.request.urlopen(request_info) data = response.read() info = json.loads(data.decode('utf-8')) type_available = [] for video_type in info['data']['video_info']['media']: type_available.append({'video_url': info['data']['video_info']['media'][video_type]['play_url']['main_url'], 'video_quality': int(info['data']['video_info']['media'][video_type]['play_url']['vtype'])}) - urls = [base64.b64decode(sorted(type_available, key = lambda x:x['video_quality'])[-1]['video_url']).decode("utf-8")] + urls = [base64.b64decode(sorted(type_available, key=lambda x: x['video_quality'])[-1]['video_url']).decode("utf-8")] size = urls_size(urls) ext = 'mp4' print_info(site_info, title, ext, size) if not info_only: download_urls(urls, title, ext, size, output_dir=output_dir, merge=merge) + def letvcloud_download(url, output_dir='.', merge=True, info_only=False): qs = parse.urlparse(url).query vu = match1(qs, r'vu=([\w]+)') @@ -128,7 +132,8 @@ def letvcloud_download(url, output_dir='.', merge=True, info_only=False): title = "LETV-%s" % vu letvcloud_download_by_vu(vu, uu, title=title, output_dir=output_dir, merge=merge, info_only=info_only) -def letv_download(url, output_dir='.', merge=True, info_only=False ,**kwargs): + +def letv_download(url, output_dir='.', merge=True, info_only=False, **kwargs): url = url_locations([url])[0] if re.match(r'http://yuntv.letv.com/', url): letvcloud_download(url, output_dir=output_dir, merge=merge, info_only=info_only) @@ -136,14 +141,15 @@ def letv_download(url, output_dir='.', merge=True, info_only=False ,**kwargs): html = get_content(url) vid = match1(url, r'video/(\d+)\.html') title = match1(html, r'

([^<]+)

') - letv_download_by_vid(vid, title=title, output_dir=output_dir, merge=merge, info_only=info_only,**kwargs) + letv_download_by_vid(vid, title=title, output_dir=output_dir, merge=merge, info_only=info_only, **kwargs) else: html = get_content(url) vid = match1(url, r'http://www.letv.com/ptv/vplay/(\d+).html') or \ - match1(url, r'http://www.le.com/ptv/vplay/(\d+).html') or \ - match1(html, r'vid="(\d+)"') - title = match1(html,r'name="irTitle" content="(.*?)"') - letv_download_by_vid(vid, title=title, output_dir=output_dir, merge=merge, info_only=info_only,**kwargs) + match1(url, r'http://www.le.com/ptv/vplay/(\d+).html') or \ + match1(html, r'vid="(\d+)"') + title = match1(html, r'name="irTitle" content="(.*?)"') + letv_download_by_vid(vid, title=title, output_dir=output_dir, merge=merge, info_only=info_only, **kwargs) + site_info = "Le.com" download = letv_download From 5e5d2540d5bcff8f1e88427b7147ce3d255e5818 Mon Sep 17 00:00:00 2001 From: GuanFoxyier <1372851437@qq.com> Date: Fri, 24 May 2019 14:33:17 +0800 Subject: [PATCH 2/5] fix sohu --- src/you_get/extractors/sohu.py | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/src/you_get/extractors/sohu.py b/src/you_get/extractors/sohu.py index 607bf44c..63971bc3 100644 --- a/src/you_get/extractors/sohu.py +++ b/src/you_get/extractors/sohu.py @@ -15,11 +15,13 @@ Changelog: new api ''' + def real_url(fileName, key, ch): url = "https://data.vod.itc.cn/ip?new=" + fileName + "&num=1&key=" + key + "&ch=" + ch + "&pt=1&pg=2&prod=h5n" return json.loads(get_html(url))['servers'][0]['url'] -def sohu_download(url, output_dir = '.', merge = True, info_only = False, extractor_proxy=None, **kwargs): + +def sohu_download(url, output_dir='.', merge=True, info_only=False, extractor_proxy=None, **kwargs): if re.match(r'http://share.vrs.sohu.com', url): vid = r1('id=(\d+)', url) else: @@ -31,12 +33,12 @@ def sohu_download(url, output_dir = '.', merge = True, info_only = False, extrac if extractor_proxy: set_proxy(tuple(extractor_proxy.split(":"))) info = json.loads(get_decoded_html('http://hot.vrs.sohu.com/vrs_flash.action?vid=%s' % vid)) - for qtyp in ["oriVid","superVid","highVid" ,"norVid","relativeId"]: + for qtyp in ["oriVid", "superVid", "highVid", "norVid", "relativeId"]: if 'data' in info: hqvid = info['data'][qtyp] else: hqvid = info[qtyp] - if hqvid != 0 and hqvid != vid : + if hqvid != 0 and hqvid != vid: info = json.loads(get_decoded_html('http://hot.vrs.sohu.com/vrs_flash.action?vid=%s' % hqvid)) if not 'allot' in info: continue @@ -63,14 +65,15 @@ def sohu_download(url, output_dir = '.', merge = True, info_only = False, extrac urls = [] data = info['data'] title = data['tvName'] - size = sum(map(int,data['clipsBytes'])) + size = sum(map(int, data['clipsBytes'])) assert len(data['clipsURL']) == len(data['clipsBytes']) == len(data['su']) for fileName, key in zip(data['su'], data['ck']): urls.append(real_url(fileName, key, data['ch'])) print_info(site_info, title, 'mp4', size) if not info_only: - download_urls(urls, title, 'mp4', size, output_dir, refer = url, merge = merge) + download_urls(urls, title, 'mp4', size, output_dir, refer=url, merge=merge) + site_info = "Sohu.com" download = sohu_download From 8c41765d1364fe77900cdbcb8e9ebf99757b625f Mon Sep 17 00:00:00 2001 From: GuanFoxyier <1372851437@qq.com> Date: Fri, 24 May 2019 14:35:49 +0800 Subject: [PATCH 3/5] fix sohu --- src/you_get/extractors/sohu.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/src/you_get/extractors/sohu.py b/src/you_get/extractors/sohu.py index 63971bc3..a1afc126 100644 --- a/src/you_get/extractors/sohu.py +++ b/src/you_get/extractors/sohu.py @@ -29,10 +29,10 @@ def sohu_download(url, output_dir='.', merge=True, info_only=False, extractor_pr vid = r1(r'\Wvid\s*[\:=]\s*[\'"]?(\d+)[\'"]?', html) assert vid - if re.match(r'http[s]://tv.sohu.com/', url): - if extractor_proxy: - set_proxy(tuple(extractor_proxy.split(":"))) - info = json.loads(get_decoded_html('http://hot.vrs.sohu.com/vrs_flash.action?vid=%s' % vid)) + if extractor_proxy: + set_proxy(tuple(extractor_proxy.split(":"))) + info = json.loads(get_decoded_html('http://hot.vrs.sohu.com/vrs_flash.action?vid=%s' % vid)) + if info and info.get("data", ""): for qtyp in ["oriVid", "superVid", "highVid", "norVid", "relativeId"]: if 'data' in info: hqvid = info['data'][qtyp] From 1758cd0ae99b15047cef9f4ca4ba0bce18866ccd Mon Sep 17 00:00:00 2001 From: Mort Yao Date: Tue, 11 Jun 2019 15:56:46 +0200 Subject: [PATCH 4/5] [youtube] signature -> sig (fix #2711) --- src/you_get/extractors/youtube.py | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/src/you_get/extractors/youtube.py b/src/you_get/extractors/youtube.py index 0629035b..eea31503 100644 --- a/src/you_get/extractors/youtube.py +++ b/src/you_get/extractors/youtube.py @@ -216,6 +216,7 @@ class YouTube(VideoExtractor): self.html5player = 'https://www.youtube.com' + ytplayer_config['assets']['js'] # Workaround: get_video_info returns bad s. Why? stream_list = ytplayer_config['args']['url_encoded_fmt_stream_map'].split(',') + #stream_list = ytplayer_config['args']['adaptive_fmts'].split(',') except: stream_list = video_info['url_encoded_fmt_stream_map'][0].split(',') if re.search('([^"]*/base\.js)"', video_page): @@ -306,7 +307,8 @@ class YouTube(VideoExtractor): 'url': metadata['url'][0], 'sig': metadata['sig'][0] if 'sig' in metadata else None, 's': metadata['s'][0] if 's' in metadata else None, - 'quality': metadata['quality'][0], + 'quality': metadata['quality'][0] if 'quality' in metadata else None, + #'quality': metadata['quality_label'][0] if 'quality_label' in metadata else None, 'type': metadata['type'][0], 'mime': metadata['type'][0].split(';')[0], 'container': mime_to_container(metadata['type'][0].split(';')[0]), @@ -433,13 +435,13 @@ class YouTube(VideoExtractor): dash_mp4_a_url = stream['url'] if 's' in stream: sig = self.__class__.decipher(self.js, stream['s']) - dash_mp4_a_url += '&signature={}'.format(sig) + dash_mp4_a_url += '&sig={}'.format(sig) dash_mp4_a_size = stream['clen'] elif stream['type'].startswith('audio/webm'): dash_webm_a_url = stream['url'] if 's' in stream: sig = self.__class__.decipher(self.js, stream['s']) - dash_webm_a_url += '&signature={}'.format(sig) + dash_webm_a_url += '&sig={}'.format(sig) dash_webm_a_size = stream['clen'] for stream in streams: # video if 'size' in stream: @@ -448,7 +450,7 @@ class YouTube(VideoExtractor): dash_url = stream['url'] if 's' in stream: sig = self.__class__.decipher(self.js, stream['s']) - dash_url += '&signature={}'.format(sig) + dash_url += '&sig={}'.format(sig) dash_size = stream['clen'] itag = stream['itag'] dash_urls = self.__class__.chunk_by_range(dash_url, int(dash_size)) @@ -467,7 +469,7 @@ class YouTube(VideoExtractor): dash_url = stream['url'] if 's' in stream: sig = self.__class__.decipher(self.js, stream['s']) - dash_url += '&signature={}'.format(sig) + dash_url += '&sig={}'.format(sig) dash_size = stream['clen'] itag = stream['itag'] audio_url = None @@ -510,13 +512,13 @@ class YouTube(VideoExtractor): src = self.streams[stream_id]['url'] if self.streams[stream_id]['sig'] is not None: sig = self.streams[stream_id]['sig'] - src += '&signature={}'.format(sig) + src += '&sig={}'.format(sig) elif self.streams[stream_id]['s'] is not None: if not hasattr(self, 'js'): self.js = get_content(self.html5player) s = self.streams[stream_id]['s'] sig = self.__class__.decipher(self.js, s) - src += '&signature={}'.format(sig) + src += '&sig={}'.format(sig) self.streams[stream_id]['src'] = [src] self.streams[stream_id]['size'] = urls_size(self.streams[stream_id]['src']) From 2496decf24a8c8228137fdaf2391bcc6f74a9207 Mon Sep 17 00:00:00 2001 From: Mort Yao Date: Tue, 11 Jun 2019 16:02:36 +0200 Subject: [PATCH 5/5] version 0.4.1314 --- src/you_get/version.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/you_get/version.py b/src/you_get/version.py index 654732ce..a31efa48 100644 --- a/src/you_get/version.py +++ b/src/you_get/version.py @@ -1,4 +1,4 @@ #!/usr/bin/env python script_name = 'you-get' -__version__ = '0.4.1302' +__version__ = '0.4.1314'