class CSohuCracker(object):
def __init__(self):
self._httpcli = HttpDownload()
self._format_vid = {
"normal": "norVid",
"high": "highVid",
"super": "superVid",
"original": "oriVid"
}
self._format_vid_linda = {
"normal": "nor",
"high": "hig",
"super": "sup"
}
self._url_action = "http://hot.vrs.sohu.com/vrs_flash.action?vid=%s"
self._url_real = "http://data.vod.itc.cn/?new=%s&mkey=%s&plat=17&prod=app"
self._url_action_linda = "http://m.tv.sohu.com/phone_playinfo?vid=%s&site=%s&appid=tv&plat=17&sver=1.0"
def get_action(self, vid, site=1):
try:
if site == 2:
resp = self._httpcli.get_data(self._url_action_linda %
(vid, site))
resp = resp.decode('gb2312').strip()
else:
resp = self._httpcli.get_data(self._url_action % vid)
if resp:
return json.loads(resp)
except Exception, e:
print e
print traceback.format_exc()
def __init__(self):
self._wkey_patterns = [re.compile('\'key\'\s+:\s+\'(\w+)\''), re.compile('_playKey = \'([a-zA-Z0-9+/=]+)\',')]
self._ua = 'Mozilla/5.0 (Linux; Android 4.4.2; GT-I9505 Build/JDQ39) AppleWebKit/537.36 (KHTML, like Gecko) Version/1.5 Chrome/28.0.1500.94 Mobile Safari/537.36'
self._xml_url = "http://www.wasu.cn/Api/getPlayInfoById/id/%s/datatype/xml"
self._enc_url = "http://www.wasu.cn/Api/getVideoUrl/id/%s/key/%s?url=%s"
self._httpcli = HttpDownload()
self._hdd = {'hd0':'normal', 'hd1':'high', 'hd2':'super'}
self._wasuc = CWasuConverter()
def __init__(self):
self._httpcli = HttpDownload()
self._url_action = "http://v.ku6.com/fetch.htm?t=getVideo4Player&vid=%s"
self._url_real = "http://data.vod.itc.cn/?new=%s&mkey=%s&plat=17&prod=app"
self._format = {
u"流 畅": "fluent",
u"标 清": "normal",
u"高 清": "high",
u"超 清": "super"
}
def __init__(self):
self._httpcli = HttpDownload()
self._format_map = {
'3gphd': 'normal',
'flv': 'normal',
'flvhd': 'high',
'mp4hd': 'high',
'mp4hd2': 'super',
'mp4hd3': 'original'
}
self.init()
class CV1Cracker(object):
def __init__(self):
self._httpcli = HttpDownload()
def crack(self, para):
result = {}
try:
url = self.convert_wurl_to_aurl(para['url'])
res = self._httpcli.get_data(url)
regex_express = 'source src=\"(.*\.(mp4))\"'
regex_pattern = re.compile(regex_express)
match_result = regex_pattern.search(res)
if match_result:
play_url = match_result.groups()[0]
format = "normal"
formats = []
formats.append(format)
segs = {}
seg = []
seg.append({"url": play_url, "duration": ""})
segs[format] = seg
if segs:
result["format"] = formats
result["seg"] = segs
result["type"] = ParseType.DIRECT
result["start"] = ""
result["end"] = ""
except Exception, e:
log.app_log.error(traceback.format_exc())
result = {'error': 1, 'code': ErrorCode.UNKNOWN_ERROR}
finally:
class CHunantvCracker(object):
def __init__(self):
self._api_url = 'http://mobile.api.hunantv.com/v5/video/getSource?appVersion=4.6.7&osType=android&videoId=%s'
self._httpcli = HttpDownload()
def crack(self, para):
result = {}
try:
if 'cont_id' in para:
video_id = cont_id = para['cont_id']
api_url = self._api_url % cont_id
resp = self._httpcli.get_data(api_url)
if resp:
segs = self.entrance_url_parse(resp)
if segs:
result['start'] = '"info":"'
result['end'] = '"'
result['seg'] = segs
result['format'] = segs.keys()
result['type'] = ParseType.CUSTOM
else:
result = {'error': 1, 'code': ErrorCode.PARSE_ERROR}
else:
result = {'error': 1, 'code': ErrorCode.NO_RESPONSE}
else:
result = {'error': 1, 'code': ErrorCode.PARAS_ERROR}
except Exception, e:
log.app_log.error(traceback.format_exc())
result = {'error': 1, 'code': ErrorCode.UNKNOWN_ERROR}
finally:
def __init__(self):
self._httpcli = HttpDownload()
self._format_vid = {
"normal": "norVid",
"high": "highVid",
"super": "superVid",
"original": "oriVid"
}
self._format_vid_linda = {
"normal": "nor",
"high": "hig",
"super": "sup"
}
self._url_action = "http://hot.vrs.sohu.com/vrs_flash.action?vid=%s"
self._url_real = "http://data.vod.itc.cn/?new=%s&mkey=%s&plat=17&prod=app"
self._url_action_linda = "http://m.tv.sohu.com/phone_playinfo?vid=%s&site=%s&appid=tv&plat=17&sver=1.0"
def __init__(self):
self._ctx = PyV8.JSContext()
self._ctx.enter()
self._httpcli = HttpDownload()
#load js
self._js = ""
base_dir = os.path.abspath(".")
filename = base_dir + "/js/youku.js"
jsfile = open(filename)
#jsfile = open('/tmp/crack_server/cracker/youku.js')
try:
self._js = jsfile.read()
finally:
jsfile.close()
self._func = self._ctx.eval(self._js)
def __init__(self):
self.last_update_time = None
self.isDomain = True
self.pname = 'MPlayer'
self._letvc = CLetvConverter()
self._httpcli = HttpDownload(with_cookie=True)
self.set_pyv8()
class CBilibiliCracker(object):
def __init__(self):
self._httpcli = HttpDownload()
self._format_map = {1: 'normal', 2: 'high', 3: 'super'}
def build_url(self, cid, quality):
# 老接口，用不了了
# url = 'http://interface.bilibili.com/playurl?appkey=f3bb208b3d081dc8&cid=%s&quality=%s' % (cid, quality)
# return url
appkey = "85eb6835b0a1034e"
secretkey = "2ad42749773c441109bdc0191257a664"
m1 = md5.new()
md5_str = "appkey=%s&cid=%s&quality=%s%s" % (appkey, cid, quality, secretkey)
m1.update(md5_str)
sign = m1.hexdigest()
url = "http://interface.bilibili.com/playurl?appkey=%s&cid=%s&quality=%s&sign=%s" % (appkey, cid, quality, sign)
return url
def crack(self, para):
result = {}
try:
cid = para['cid']
segs = {}
formats = []
# 有bug，默认三种清晰度都有，其实可能会遇到没有的
for i in self._format_map.keys():
url = self.build_url(cid, i)
resp = self._httpcli.get_data(url, timeout=5)
if resp:
doc = etree.fromstring(resp)
seg = []
for node in doc.xpath("//video/durl"):
length_sel = node.xpath('./length/text()')
if length_sel:
duration = length_sel[0]
url_sel = node.xpath('./url/text()')
if url_sel:
play_url = url_sel[0]
if play_url:
seg.append({"url":play_url, "duration": str(int(duration) /1000 if duration else '')})
segs[self._format_map[i]] = seg
formats.append(self._format_map[i])
if segs:
result["format"] = formats
result["seg"] = segs
result["type"] = ParseType.DIRECT
result["start"] = ""
result["end"] = ""
except Exception, e:
log.app_log.error(traceback.format_exc())
result = {'error': 1, 'code': ErrorCode.NO_RESPONSE}
finally:
class CWasuCracker(object):
def __init__(self):
self._wkey_patterns = [re.compile('\'key\'\s+:\s+\'(\w+)\''), re.compile('_playKey = \'([a-zA-Z0-9+/=]+)\',')]
self._ua = 'Mozilla/5.0 (Linux; Android 4.4.2; GT-I9505 Build/JDQ39) AppleWebKit/537.36 (KHTML, like Gecko) Version/1.5 Chrome/28.0.1500.94 Mobile Safari/537.36'
self._xml_url = "http://www.wasu.cn/Api/getPlayInfoById/id/%s/datatype/xml"
self._enc_url = "http://www.wasu.cn/Api/getVideoUrl/id/%s/key/%s?url=%s"
self._httpcli = HttpDownload()
self._hdd = {'hd0':'normal', 'hd1':'high', 'hd2':'super'}
self._wasuc = CWasuConverter()
def crack(self, para):
result = {}
try:
wid = para.get('wid')
url = para.get('url')
os = para.get('os')
aurl = self.get_aurl(url, os)
wkey = self.get_wkey(aurl)
xurl = self._xml_url % wid
sxml = self._httpcli.get_data(xurl)
xml = etree.fromstring(sxml)
segs_new = {}
format_new = []
segs_old = {}
format_old = []
for ele in xml.iter('mp4', 'video'):
if ele.tag == 'mp4':
for hd in ele.iter('hd0', 'hd1', 'hd2'):
ft = self.get_format(hd.tag)
b64url = hd.text
encurl = self.get_encurl(wid, wkey, b64url)
if not encurl or re.match('http:.*.mp4', encurl):
continue
try:
decurl = self.get_decurl(encurl)
if decurl:
decurl += "?version=SWFPlayer_V.4.1.0&vid=%s" %wid
except Exception, e:
continue
segs_new[ft] = [{'url':decurl, 'duration':''}]
format_new.append(ft)
elif ele.tag == 'video':
b64url = ele.text
encurl = self.get_encurl(wid, wkey, b64url)
if not encurl or re.match('http:.*.mp4', encurl):
continue
try:
decurl = self.get_decurl(encurl)
if decurl:
decurl += "?version=SWFPlayer_V.4.1.0&vid=%s" %wid
except Exception, e:
continue
ft = self.get_format(self.get_hd(xml.xpath("//bitrate/text()")[0]))
segs_old[ft] = [{'url':decurl, 'duration':''}]
format_old.append(ft)
def __init__(self):
self.letvc = CLetvConverter()
self.qqc = CQqConverter()
self.hunantvc = CHunantvConverter()
self.ykc = CYoukuConverter()
self.iqiyic = CIqiyiConverter()
self.sohuc = CSohuConverter()
self.pptvc = CPptvConverter()
self.wasuc = CWasuConverter()
self.dy1905c = C1905Converter()
self._httpcli = HttpDownload()
class C17173Cracker(object):
def __init__(self):
self._httpcli = HttpDownload()
self._format_map = {1: "normal", 2: "high", 4: "super"}
def get_detail(self, video_id):
result = None
current = int(time.time() * 1000)
url = "http://v.17173.com/api/video/vInfo/id/%s?t=%s" % (video_id,
current)
resp = self._httpcli.get_data(url)
if resp:
details = json.loads(resp)
if details['success'] == 1:
result = details['data']['splitInfo']
return result
def crack(self, para):
result = {}
try:
video_id = para['videoId']
details = self.get_detail(video_id)
formats = []
segs = {}
for detail in details:
format_17173 = detail['def']
format = self._format_map[format_17173]
if not format:
log.app_log.error("unknown format: %s" % (format_17173))
formats.append(format)
segs[format] = []
infos = detail['info']
for info in infos:
duration = info['duration']
url = info['url'][0]
segs[format].append({'url': url, 'duration': duration})
if segs:
result["format"] = formats
result["seg"] = segs
result["type"] = ParseType.DIRECT
result["start"] = ""
result["end"] = ""
except Exception, e:
log.app_log.error(traceback.format_exc())
result = {'error': 1, 'code': ErrorCode.NO_RESPONSE}
finally:
class C56Cracker(object):
def __init__(self):
self._httpcli = HttpDownload(with_cookie=True)
self._url_action = "http://m.tv.sohu.com/phone_playinfo?vid=%s&site=2"
self._url_list = "http://data.vod.itc.cn/cdnList?%s&vid=%s_2&prod=flash&rb=1"
self._ua = "Mozilla/5.0 (Linux; Android 4.3; Nexus 10 Build/JSS15Q) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2307.2 Safari/537.36"
self._formats = {"hig": "high", "nor": "normal", "sup": "super"}
def get_action(self, vid):
try:
resp = self._httpcli.get_data(self._url_action % vid, ua=self._ua)
if resp:
#return resp
return json.loads(resp.decode().encode('utf8'))
except Exception, e:
print traceback.format_exc()
def __init__(self):
#self._ctx = PyV8.JSContext()
#self._ctx.enter()
#load js
self._js = ""
base_dir = os.path.abspath(".")
filename = base_dir + "/js/iqiyi.js"
#filename = base_dir + "/js/test.js"
self._phantomjs_cmd = "/home/wangchao/phantomjs-2.1.1-linux-x86_64/bin/phantomjs ./phantomjs/iqiyi.js %s %s"
jsfile = open(filename)
try:
self._js = jsfile.read()
finally:
jsfile.close()
#self._func = self._ctx.eval(self._js)
self._iqiyivc = CIqiyiConverter()
self._httpcli = HttpDownload()
class CKu6Cracker(object):
def __init__(self):
self._httpcli = HttpDownload()
self._url_action = "http://v.ku6.com/fetch.htm?t=getVideo4Player&vid=%s"
self._url_real = "http://data.vod.itc.cn/?new=%s&mkey=%s&plat=17&prod=app"
self._format = {
u"流 畅": "fluent",
u"标 清": "normal",
u"高 清": "high",
u"超 清": "super"
}
def get_action(self, vid):
try:
resp = self._httpcli.get_data(self._url_action % vid, timeout=5)
if resp:
return json.loads(resp)
except Exception, e:
log.app_log.error(traceback.format_exc())
def __init__(self, host, port, timeout):
self._did = "02fcd60b280ca68dee0d0d8cb30be840"
self._api_key = "qwer3as2jin4fdsa"
self._format_map = {
"normal": "3gphd",
"high": {
"flv": "flv",
"mp4": "mp4"
},
"super": "hd2"
}
self._details = {}
self._redis = RedisMgr(cs.redis_ip, cs.redis_port, cs.redis_pwd)
self._httpcli = HttpDownload()
tmp_timeout = int(timeout / 1000)
if tmp_timeout > 1:
self._timeout = tmp_timeout
else:
self._timeout = 1
def __init__(self):
self._httpcli = HttpDownload()
self._format_map = {1: "normal", 2: "high", 4: "super"}
def __init__(self, *args, **kwargs):
self.b2f = {1: 'fluent', 2: 'high', 4: 'super', 5: 'original'}
# self.salt = "6ab6d0280511493ba85594779759d4ed"
self._redis = RedisMgr(cs.redis_ip, cs.redis_port, cs.redis_pwd)
self._httpcli = HttpDownload()
class CPptvCracker(object):
def __init__(self):
self._api_url = "http://web-play.pptv.com/webplay3-0-%s.xml?version=4&type=web.fpp"
self._real_url = "http://%s/%s/%s?fpp.ver=1.3.0.19&k=%s&type=web.fpp"
self._all_format = ['fluent', 'high', 'super', 'original']
#self._all_format = ['fluent', 'high', 'super', 'original', 'original_high']
self._httpcli = HttpDownload()
def crack(self, para):
result = {}
result['seg'] = {}
format_list = result['format'] = []
try:
pptv_id = para.get('pptv_id', '')
if pptv_id:
api_url = self._api_url % pptv_id
resp = self._httpcli.get_data(api_url)
if resp:
doc = etree.fromstring(resp)
files = doc.xpath(
"//file/item[@rid and @bitrate and @height and @width and @ft]"
)
file_num = len(files)
for f in files:
df = f.attrib
rid = df.get('rid')
bitrate = df.get('bitrate')
ft = int(df.get('ft'))
if ft >= len(self._all_format):
continue
format = self._all_format[ft]
ipl = doc.xpath("//dt[@ft=%s]/sh" % ft)
ip = ipl[
0].text if ipl else "vod.pplive.com.cust.footprint.net"
# 由于抓取到的IP可能是数字地址或域名不固定，统一采用域名
#ip = "vod.pplive.com.cust.footprint.net"
keyl = doc.xpath("//dt[@ft=%s]/key" % ft)
if not keyl:
continue
else:
key = keyl[0].text
sgml = doc.xpath("//dragdata[@ft=%s]/sgm[@no]" % ft)
l = []
for sgm in sgml:
dseg = sgm.attrib
real_url = self._real_url % (ip, dseg['no'], rid,
key)
dur = dseg.get('dur', '')
#dur = str(int(float(dur)))
dur = str(dur)
l.append({'url': real_url, 'duration': dur})
if not l:
continue
result['seg'][format] = l
format_list.append(format)
if not format_list:
result = {'error': 1, 'code': ErrorCode.NO_RESPONSE}
else:
result['start'] = ''
result['end'] = ''
result['type'] = ParseType.DIRECT
else:
result = {'error': 1, 'code': ErrorCode.NO_RESPONSE}
else:
result = {'error': 1, 'code': ErrorCode.PARAS_ERROR}
except Exception, e:
log.app_log.error(traceback.format_exc())
result = {'error': 1, 'code': ErrorCode.NO_RESPONSE}
finally:
class YoukuCracker(object):
def __init__(self):
self._ctx = PyV8.JSContext()
self._ctx.enter()
self._httpcli = HttpDownload()
#load js
self._js = ""
base_dir = os.path.abspath(".")
filename = base_dir + "/js/youku.js"
jsfile = open(filename)
#jsfile = open('/tmp/crack_server/cracker/youku.js')
try:
self._js = jsfile.read()
finally:
jsfile.close()
self._func = self._ctx.eval(self._js)
def crack(self, para):
#log.app_log.info('%s : %s' % (self.__class__.__name__, json.dumps(para)))
result = {}
try:
tvid = para['yvid']
turl = "http://v.youku.com/player/getPlayList/VideoIDS/" + tvid + "/Pf/4/ctype/12/ev/1"
resp = self._httpcli.get_data(turl)
if resp:
tjresp = json.loads(resp)
jresp = tjresp["data"][0]
sjresp = json.dumps(jresp)
#sjresp = json.dumps(tjresp["data"][0])
res = self._func(sjresp)
#print res
res_list = res.split(",")
type = ""
urls_num = 0
tnum = len(res_list) - 2
if tnum >= 1:
type = res_list[tnum]
urls_num = int(res_list[tnum + 1])
segs = []
if "segs" in jresp and type in jresp["segs"] and len(
jresp["segs"][type]) == int(urls_num):
i = 0
for i in range(urls_num):
seg = {}
seg["url"] = res_list[i]
seg["duration"] = str(
jresp["segs"][type][i]["seconds"])
segs.append(seg)
#result["seg"] = {type:segs}
#result["format"]=[type]
result["seg"] = {'high': segs}
result["format"] = ['high']
result["type"] = ParseType.DIRECT
result["start"] = ""
result["end"] = ""
#print json.dumps(resp)
except Exception, e:
log.app_log.error(traceback.format_exc())
result = {'error': 1, 'code': ErrorCode.NO_RESPONSE}
finally:
def __init__(self):
self._api_url = "http://web-play.pptv.com/webplay3-0-%s.xml?version=4&type=web.fpp"
self._real_url = "http://%s/%s/%s?fpp.ver=1.3.0.19&k=%s&type=web.fpp"
self._all_format = ['fluent', 'high', 'super', 'original']
#self._all_format = ['fluent', 'high', 'super', 'original', 'original_high']
self._httpcli = HttpDownload()
def __init__(self):
self._httpcli = HttpDownload()
self._format_map = {1: 'normal', 2: 'high', 3: 'super'}
def __init__(self):
self._httpcli = HttpDownload()
def __init__(self):
self._api_url = 'http://mobile.api.hunantv.com/v5/video/getSource?appVersion=4.6.7&osType=android&videoId=%s'
self._httpcli = HttpDownload()
class CAcfunCracker(object):
def __init__(self):
self._httpcli = HttpDownload()
self._format_map = {
'3gphd': 'normal',
'flv': 'normal',
'flvhd': 'high',
'mp4hd': 'high',
'mp4hd2': 'super',
'mp4hd3': 'original'
}
self.init()
def init(self):
# get vid, cover, title by content url, args need aid
self._content_url = "http://api.aixifan.com/contents/%s"
# get sourceId as video_id by plays url, args need vid
self._plays_url = "http://api.aixifan.com/plays/%s"
# get sign by custom url, args need video_id and refer
self._custom_url = "https://api.youku.com/players/custom.json?type=h5&client_id=908a519d032263f8&video_id=%s&embsig=%s&%s"
# youku get json url, args need sign
self._youku_json_url = "http://play.youku.com/partner/get.json?vid=%s&ct=86&cid=908a519d032263f8&sign=%s"
# refer,need by custom url, args need vid, cover, title
self._refer = 'http://m.acfun.tv/ykplayer?date=undefined#vid=%s;cover=%s;title=%s&callback=ykv.callbacks.cb_AEFkYaN'
self._headers = {}
self._headers['deviceType'] = '2'
# crack youku
self._mk = {'a3': '1z4i', 'a4': '86rv'}
self._user_cache = {'a1': 'v', 'a2': 'b'}
# _rc4_decrypt_key get from _decrypt_seed
self._rc4_decrypt_key = "10ehfkbv"
# _rc4_encrypt_key get from _encrypt_seed
self._rc4_encrypt_key = "msjv7h2b"
type_3gphd = {
'hd': 1,
'key': '3gphd',
'loghd': 4,
'play': True,
'quality': 'mp4',
'suffix': 'mp4'
}
type_flv = {
'hd': 0,
'key': 'flv',
'loghd': 0,
'play': False,
'quality': 'flv',
'suffix': 'flv'
}
type_flvhd = {
'hd': 0,
'key': 'flvhd',
'loghd': 0,
'play': False,
'quality': 'flv',
'suffix': 'flv'
}
type_mp4hd = {
'hd': 1,
'key': 'mp4hd',
'loghd': 1,
'play': True,
'quality': 'mp4',
'suffix': 'mp4'
}
type_mp4hd2 = {
'hd': 2,
'key': 'mp4hd2',
'loghd': 2,
'play': False,
'quality': 'hd2',
'suffix': 'flv'
}
type_mp4hd3 = {
'hd': 3,
'key': 'mp4hd3',
'loghd': 3,
'play': False,
'quality': 'hd3',
'suffix': 'flv'
}
self._stream_types = {
'3gphd': type_3gphd,
'flv': type_flv,
'flvhd': type_flvhd,
'mp4hd': type_mp4hd,
'mp4hd2': type_mp4hd2,
'mp4hd3': type_mp4hd3
}
self._decrypt_seed = "1z4iogbv"
self._encrypt_seed = "86rvailb"
self._e = [
19, 1, 4, 7, 30, 14, 28, 8, 24, 17, 6, 35, 34, 16, 9, 10, 13, 22,
32, 29, 31, 21, 18, 3, 2, 23, 25, 27, 11, 20, 5, 15, 12, 0, 33, 26
]
#not useful, we know rc4_key is always same
def get_rc4_key(self, t):
n = []
i = 0
length = len(t)
while i < length:
r = 0
if t[i] >= 'a' and t[i] <= 'z':
r = ord(t[i]) - ord('a')
else:
r = ord(t[i]) - ord('0') + 26
o = 0
while 36 > o:
if self._e[o] == r:
r = o
break
o += 1
if r > 25:
n.append(str(r - 26))
else:
n.append(chr(r + 97))
i += 1
return "".join(n)
def get_sid_token(self, base64_str):
msg = self.rc4_decrypt(base64_str)
if msg:
ret = msg.split('_')
if len(ret) == 2:
self._sid = ret[0]
self._token = ret[1]
def rc4_decrypt(self, base64_str):
encrypt_str = base64.b64decode(base64_str)
cipher = ARC4.new(self._rc4_decrypt_key)
msg = cipher.decrypt(encrypt_str)
return msg
def rc4_encrypt(self, src):
cipher = ARC4.new(self._rc4_encrypt_key)
msg = cipher.encrypt(src)
encrypt_str = base64.b64encode(msg)
return encrypt_str
def get_field_id(self, field_id, seg_num):
i = field_id[0:8]
r = self.get_hex_string(seg_num)
o = field_id[10:]
n = i + r + o
return n
def get_hex_string(self, seg_num):
r = hex(seg_num)[2:]
if len(r) == 1:
r = '0' + r
return r
def get_ep(self, field_id):
src = self._sid + '_' + field_id + '_' + self._token
#src = '846191191252886064b76_030020010056CF207CA72D2D9B7D2F958141AE-2EDF-6B01-E970-E557BC2CB3FB_7096'
ep = self.rc4_encrypt(src)
data = {'ep': ep}
ep = urllib.urlencode(data)
return ep
def parse_path(self, s):
n = ''
for k, v in s.items():
a = k + '/' + v + '/'
n = a + n
return n
def build_params(self, u):
e = []
for k, v in u.items():
n = k + '=' + str(v)
e.append(n)
return '&'.join(e)
def get_mp4_src(self, s, u):
i = self.parse_path(s)
url = "http://k.youku.com/player/getFlvPath/" + i + self.build_params(
u)
return url
def get_all_urls(self, streams):
result = {}
for stream in streams:
stream_type = self._stream_types[stream['stream_type']]
result[stream['stream_type']] = []
st = stream_type['suffix']
stream_field_id = stream['stream_fileid']
segs = stream['segs']
num = 0
for seg in segs:
key = seg['key']
seconds = int(seg['total_milliseconds_video']) / 1000
current_field_id = self.get_field_id(stream_field_id, num)
sid = self._sid + '_' + self.get_hex_string(num)
ep = self.get_ep(current_field_id)
ep = ep[3:]
s = {'sid': sid, 'fileid': current_field_id, 'st': st}
u = {
'K': key,
'hd': stream_type['hd'],
'myp': 0,
'ts': seconds,
'ypp': 0,
'ep': ep,
'ctype': '86',
'ev': 1,
'token': self._token,
'oip': self._oip
}
url = self.get_mp4_src(s, u)
result[stream['stream_type']].append({
"url": url,
"duration": seconds
})
num += 1
return result
def crack(self, para):
result = {}
try:
aid = para['aid']
content_url = self._content_url % (aid)
resp = self._httpcli.get_data(content_url,
headers=self._headers,
timeout=5)
if resp:
resp_json = json.loads(resp)
# bug to do:里面有多个个video的，只取第一个
vid = resp_json['data']['videos'][0]['videoId']
cover = resp_json['data']['cover']
title = resp_json['data']['title']
plays_url = self._plays_url % (vid)
resp = self._httpcli.get_data(plays_url,
headers=self._headers,
timeout=5)
if resp:
resp_json = json.loads(resp)
video_id = resp_json['data']['sourceId']
embsig = resp_json['data']['embsig']
refer = self._refer % (vid, cover, title)
data = {'refer': refer.encode('UTF-8')}
urlencode_refer = urllib.urlencode(data)
custom_url = self._custom_url % (video_id, embsig,
urlencode_refer)
resp = self._httpcli.get_data(custom_url, timeout=5)
if resp:
resp_json = json.loads(resp)
sign = resp_json['playsign']
youku_json_url = self._youku_json_url % (video_id,
sign)
resp = self._httpcli.get_data(youku_json_url,
timeout=5)
if resp:
resp_json = json.loads(resp)
encrypt_str = resp_json['data']['security'][
'encrypt_string']
self._oip = resp_json['data']['security']['ip']
self.get_sid_token(encrypt_str)
streams = resp_json['data']['stream']
urls = self.get_all_urls(streams)
formats = []
segs = {}
for k, v in urls.items():
format = self._format_map[k]
if not format in formats:
formats.append(format)
segs[format] = v
if segs:
result["format"] = formats
result["seg"] = segs
result["type"] = ParseType.DIRECT
result["start"] = ""
result["end"] = ""
except Exception, e:
print e
log.app_log.error(traceback.format_exc())
result = {'error': 1, 'code': ErrorCode.NO_RESPONSE}
finally:
def __init__(self):
self._httpcli = HttpDownload()
self._format = 'high'
class CTucaoCracker(object):
def __init__(self):
self._httpcli = HttpDownload()
self._format = 'high'
def build_url(self, type, tvid):
timestamp = int(time.time())
#暂时发现服务器端没检查key
key = "tucao4c35fe3d.cc"
url = 'http://api.tucao.tv/api/playurl?type=%s&vid=%s&key=%s&r=%s' % (
type, tvid, key, str(timestamp))
return url
def build_result(self, seg):
result = {}
segs = {}
formats = []
segs[self._format] = seg
formats.append(self._format)
result["format"] = formats
result["seg"] = segs
result["type"] = ParseType.DIRECT
result["start"] = ""
result["end"] = ""
return result
def crack(self, para):
result = {}
try:
extra = para['extra']
ret = urlparse.parse_qs(extra, True)
if ret.get('file'):
#有播放地址，直接返回
seg = []
seg.append({"url": ret['file'][0], "duration": ''})
result = self.build_result(seg)
return result
type = ret['type'][0]
tvid = ret['vid'][0]
url = self.build_url(type, tvid)
resp = self._httpcli.get_data(url, timeout=5)
if resp:
buffer = StringIO(resp)
doc = etree.parse(buffer)
seg = []
for node in doc.xpath("//video/durl"):
duration = ''
play_url = ''
length_sel = node.xpath('./length/text()')
if length_sel:
duration = length_sel[0]
url_sel = node.xpath('./url/text()')
if url_sel:
play_url = url_sel[0]
if play_url:
seg.append({
"url": play_url,
"duration": str(int(duration) / 1000)
})
if seg:
result = self.build_result(seg)
except Exception, e:
log.app_log.error(traceback.format_exc())
result = {'error': 1, 'code': ErrorCode.NO_RESPONSE}
finally:
class CIfengCracker(object):
def __init__(self):
self._httpcli = HttpDownload()
self._format_map = {'VideoPlayUrl': 'normal', 'VideoPlayUrlH': 'high'}
self._format_map1 = {'350k': 'normal', '500k': 'high'}
def build_url(self, guid):
url = 'http://vxml.ifengimg.com/video_info_new/' + guid[
34] + '/' + guid[34:] + '/' + guid + '.xml'
return url
def crack(self, para):
result = {}
try:
guid = para['guid']
url = self.build_url(guid)
resp = self._httpcli.get_data(url, timeout=5)
if resp:
buffer = StringIO(resp)
doc = etree.parse(buffer)
segs = {}
formats = []
duration = ''
duration_sel = doc.xpath('//PlayList/item/@Duration')
if duration_sel:
duration = duration_sel[0]
nodes = doc.xpath('//PlayList/videos/video[@mediaType="mp4"]')
if nodes:
for node in nodes:
seg = []
format_sel = node.xpath('./@bitrate')
url_sel = node.xpath('./@VideoPlayUrl')
if format_sel and url_sel:
format = self._format_map1[format_sel[0]]
seg.append({
"url": url_sel[0],
"duration": duration
})
segs[format] = seg
formats.append(format)
else:
for af, ff in self._format_map.items():
url_sel = doc.xpath('//PlayList/item/@%s' % (af))
seg = []
if url_sel:
seg.append({
"url": url_sel[0],
"duration": duration
})
segs[ff] = seg
formats.append(ff)
if segs:
result["format"] = formats
result["seg"] = segs
result["type"] = ParseType.DIRECT
result["start"] = ""
result["end"] = ""
except Exception, e:
print e
log.app_log.error(traceback.format_exc())
result = {'error': 1, 'code': ErrorCode.NO_RESPONSE}
finally:
def __init__(self):
self._httpcli = HttpDownload()
self._format_map = {'VideoPlayUrl': 'normal', 'VideoPlayUrlH': 'high'}
self._format_map1 = {'350k': 'normal', '500k': 'high'}
