def get(self, options):
parse = urlparse(self.url)
try:
other = parse.fragment
except KeyError:
log.error("Something wrong with that url")
sys.exit(2)
match = re.search("^/(.*).html", other)
if not match:
log.error("Cant find video file")
sys.exit(2)
url = "http://www.hbo.com/data/content/%s.xml" % match.group(1)
data = get_http_data(url)
xml = ET.XML(data)
videoid = xml.find("content")[1].find("videoId").text
url = "http://render.cdn.hbo.com/data/content/global/videos/data/%s.xml" % videoid
data = get_http_data(url)
xml = ET.XML(data)
ss = xml.find("videos")
if is_py2_old:
sa = list(ss.getiterator("size"))
else:
sa = list(ss.iter("size"))
for i in sa:
videourl = i.find("tv14").find("path").text
match = re.search("/([a-z0-9]+:[a-z0-9]+)/", videourl)
options.other = "-y %s" % videourl[videourl.index(match.group(1)):]
yield RTMP(copy.copy(options),
videourl[:videourl.index(match.group(1))],
i.attrib["width"])
def get(self, options, url):
parse = urlparse(url)
data = get_http_data(url)
match = re.search("abTvArticlePlayer-player-(.*)-[0-9]+-[0-9]+-clickOverlay", data)
if not match:
log.error("Can't find video file")
sys.exit(2)
try:
start = parse_qs(parse[4])["start"][0]
except KeyError:
start = 0
url = "http://www.aftonbladet.se/resource/webbtv/article/%s/player" % match.group(1)
data = get_http_data(url)
xml = ET.XML(data)
url = xml.find("articleElement").find("mediaElement").find("baseUrl").text
path = xml.find("articleElement").find("mediaElement").find("media").attrib["url"]
live = xml.find("articleElement").find("mediaElement").find("isLive").text
options.other = "-y %s" % path
if start > 0:
options.other = "%s -A %s" % (options.other, str(start))
if live == "true":
options.live = True
if url == None:
log.error("Can't find any video on that page")
sys.exit(3)
if url[0:4] == "rtmp":
download_rtmp(options, url)
else:
filename = url + path
download_http(options, filename)
def get(self, options):
match = re.search(r'mrss\s+:\s+"([^"]+)"', self.get_urldata())
if not match:
log.error("Can't find id for the video")
sys.exit(2)
swfurl = re.search(r'embedSWF\( "([^"]+)"', self.get_urldata())
options.other = "-W %s" % swfurl.group(1)
data = get_http_data(match.group(1))
xml = ET.XML(data)
mediagen = xml.find("channel").find("item").find(
"{http://search.yahoo.com/mrss/}group")
title = xml.find("channel").find("item").find("title").text
if options.output_auto:
directory = os.path.dirname(options.output)
if len(directory):
options.output = "%s/%s" % (directory, title)
else:
options.output = title
contenturl = mediagen.find(
"{http://search.yahoo.com/mrss/}content").attrib["url"]
content = get_http_data(contenturl)
xml = ET.XML(content)
ss = xml.find("video").find("item")
if is_py2_old:
sa = list(ss.getiterator("rendition"))
else:
sa = list(ss.iter("rendition"))
for i in sa:
yield RTMP(options, i.find("src").text, i.attrib["bitrate"])
def download_hds(options, url, swf=None):
data = get_http_data(url)
streams = {}
bootstrap = {}
xml = ET.XML(data)
prefix = xml.find("{http://ns.adobe.com/f4m/1.0}id").text
if sys.version_info < (2, 7):
bootstrapIter = xml.getiterator("{http://ns.adobe.com/f4m/1.0}bootstrapInfo")
mediaIter = xml.getiterator("{http://ns.adobe.com/f4m/1.0}media")
else:
bootstrapIter = xml.iter("{http://ns.adobe.com/f4m/1.0}bootstrapInfo")
mediaIter = xml.iter("{http://ns.adobe.com/f4m/1.0}media")
for i in bootstrapIter:
bootstrap[i.attrib["id"]] = i.text
for i in mediaIter:
streams[int(i.attrib["bitrate"])] = {"url": i.attrib["url"], "bootstrapInfoId": i.attrib["bootstrapInfoId"], "metadata": i.find("{http://ns.adobe.com/f4m/1.0}metadata").text}
test = select_quality(options, streams)
bootstrap = base64.b64decode(bootstrap[test["bootstrapInfoId"]])
box = readboxtype(bootstrap, 0)
if box[2] == "abst":
antal = readbox(bootstrap, box[0])
baseurl = url[0:url.rfind("/")]
i = 1
if options.output != "-":
extension = re.search("(\.[a-z0-9]+)$", options.output)
if not extension:
options.output = "%s.flv" % options.output
log.info("Outfile: %s", options.output)
file_d = open(options.output, "wb")
else:
file_d = sys.stdout
metasize = struct.pack(">L", len(base64.b64decode(test["metadata"])))[1:]
file_d.write(binascii.a2b_hex(b"464c560105000000090000000012"))
file_d.write(metasize)
file_d.write(binascii.a2b_hex(b"00000000000000"))
file_d.write(base64.b64decode(test["metadata"]))
file_d.write(binascii.a2b_hex(b"00000000"))
total = antal[1]["total"]
eta = ETA(total)
while i <= total:
url = "%s/%sSeg1-Frag%s" % (baseurl, test["url"], i)
if options.output != "-":
eta.update(i)
progressbar(total, i, ''.join(["ETA: ", str(eta)]))
data = get_http_data(url)
number = decode_f4f(i, data)
file_d.write(data[number:])
i += 1
if options.output != "-":
file_d.close()
progress_stream.write('\n')
def get(self, options):
data = self.get_urldata()
match = re.search('data-aptomaId="([-0-9a-z]+)"', data)
if not match:
log.error("Can't find video info")
sys.exit(2)
videoId = match.group(1)
match = re.search(r'data-isLive="(\w+)"', data)
if not match:
log.error("Can't find live info")
sys.exit(2)
if match.group(1) == "true":
options.live = True
if not options.live:
dataurl = "http://aftonbladet-play-metadata.cdn.drvideo.aptoma.no/video/%s.json" % videoId
data = get_http_data(dataurl)
data = json.loads(data)
videoId = data["videoId"]
streamsurl = "http://aftonbladet-play-static-ext.cdn.drvideo.aptoma.no/actions/video/?id=%s&formats&callback=" % videoId
streams = json.loads(get_http_data(streamsurl))
hlsstreams = streams["formats"]["hls"]
if "level3" in hlsstreams.keys():
hls = hlsstreams["level3"]["csmil"][0]
else:
hls = hlsstreams["akamai"]["m3u8"][0]
address = hls["address"]
path = hls["path"]
for i in hls["files"]:
if "filename" in i.keys():
playlist = "http://%s/%s/%s/master.m3u8" % (address, path, i["filename"])
else:
playlist = "http://%s/%s/%s/master.m3u8" % (address, path, hls["filename"])
yield HLS(copy.copy(options), playlist, i["bitrate"])
def get(self, options, url):
data = get_http_data(url)
match = re.search("xmlUrl: '(http://www.expressen.*)'", data)
if not match:
log.error("Can't find video file")
sys.exit(2)
url = "http://tv.expressen.se/%s/?standAlone=true&output=xml" % quote_plus(match.group(1))
url = match.group(1)
data = get_http_data(url)
xml = ET.XML(data)
ss = xml.find("vurls")
if sys.version_info < (2, 7):
sa = list(ss.getiterator("vurl"))
else:
sa = list(ss.iter("vurl"))
streams = {}
for i in sa:
streams[int(i.attrib["bitrate"])] = i.text
test = select_quality(options, streams)
filename = test
match = re.search("rtmp://([0-9a-z\.]+/[0-9]+/)(.*)", filename)
filename = "rtmp://%s" % match.group(1)
options.other = "-y %s" % match.group(2)
download_rtmp(options, filename)
def get(self, options):
vid = None
data = self.get_urldata()
match = re.search(r'video url-([^"]+)', data)
if not match:
match = re.search(r'embed.jsp\?id=([^&]+)&', data)
if not match:
log.error("Cant find video id")
sys.exit(2)
vid = match.group(1)
if not vid:
path = unquote_plus(match.group(1))
data = get_http_data("http://www.svd.se%s" % path)
match = re.search(r'embed.jsp\?id=([^&]+)&', data)
if not match:
log.error("Cant find video id2")
sys.exit(2)
vid = match.group(1)
url = "http://amz.lwcdn.com/api/cache/VideoCache.jsp?id=%s" % vid
data = get_http_data(url)
xml = ET.XML(data)
videofile = xml.find("{http://www.lemonwhale.com/xml11}VideoFile")
mediafiles = videofile.find(
"{http://www.lemonwhale.com/xml11}MediaFiles")
high = mediafiles.find("{http://www.lemonwhale.com/xml11}VideoURLHigh")
if high.text:
yield HTTP(copy.copy(options), high.text, 720)
videourl = mediafiles.find(
"{http://www.lemonwhale.com/xml11}VideoURL").text
yield HTTP(copy.copy(options), videourl, 480)
def get(self, options):
vid = None
data = self.get_urldata()
match = re.search(r'video url-([^"]+)', data)
if not match:
match = re.search(r'embed.jsp\?id=([^&]+)&', data)
if not match:
log.error("Cant find video id")
sys.exit(2)
vid = match.group(1)
if not vid:
path = unquote_plus(match.group(1))
data = get_http_data("http://www.svd.se%s" % path)
match = re.search(r'embed.jsp\?id=([^&]+)&', data)
if not match:
log.error("Cant find video id2")
sys.exit(2)
vid = match.group(1)
url = "http://amz.lwcdn.com/api/cache/VideoCache.jsp?id=%s" % vid
data = get_http_data(url)
xml = ET.XML(data)
videofile = xml.find("{http://www.lemonwhale.com/xml11}VideoFile")
mediafiles = videofile.find("{http://www.lemonwhale.com/xml11}MediaFiles")
high = mediafiles.find("{http://www.lemonwhale.com/xml11}VideoURLHigh")
if high.text:
yield HTTP(copy.copy(options), high.text, 720)
file = mediafiles.find("{http://www.lemonwhale.com/xml11}VideoURL").text
yield HTTP(copy.copy(options), file, 480)
def get(self, options, url):
parse = urlparse(url)
try:
other = parse[5]
except KeyError:
log.error("Something wrong with that url")
sys.exit(2)
match = re.search("^/(.*).html", other)
if not match:
log.error("Cant find video file")
sys.exit(2)
url = "http://www.hbo.com/data/content/%s.xml" % match.group(1)
data = get_http_data(url)
xml = ET.XML(data)
videoid = xml.find("content")[1].find("videoId").text
url = "http://render.cdn.hbo.com/data/content/global/videos/data/%s.xml" % videoid
data = get_http_data(url)
xml = ET.XML(data)
ss = xml.find("videos")
if sys.version_info < (2, 7):
sa = list(ss.getiterator("size"))
else:
sa = list(ss.iter("size"))
streams = {}
for i in sa:
stream = {}
stream["path"] = i.find("tv14").find("path").text
streams[int(i.attrib["width"])] = stream
test = select_quality(options, streams)
download_rtmp(options, test["path"])
def get(self, options):
parse = urlparse(self.url)
try:
other = parse.fragment
except KeyError:
log.error("Something wrong with that url")
sys.exit(2)
match = re.search("^/(.*).html", other)
if not match:
log.error("Cant find video file")
sys.exit(2)
url = "http://www.hbo.com/data/content/%s.xml" % match.group(1)
data = get_http_data(url)
xml = ET.XML(data)
videoid = xml.find("content")[1].find("videoId").text
url = "http://render.cdn.hbo.com/data/content/global/videos/data/%s.xml" % videoid
data = get_http_data(url)
xml = ET.XML(data)
ss = xml.find("videos")
if is_py2_old:
sa = list(ss.getiterator("size"))
else:
sa = list(ss.iter("size"))
for i in sa:
videourl = i.find("tv14").find("path").text
match = re.search("/([a-z0-9]+:[a-z0-9]+)/", videourl)
options.other = "-y %s" % videourl[videourl.index(match.group(1)):]
yield RTMP(copy.copy(options), videourl[:videourl.index(match.group(1))], i.attrib["width"])
def get(self, options):
match = re.search(r'mrss\s+:\s+"([^"]+)"', self.get_urldata())
if not match:
log.error("Can't find id for the video")
sys.exit(2)
swfurl = re.search(r'embedSWF\( "([^"]+)"', self.get_urldata())
options.other = "-W %s" % swfurl.group(1)
data = get_http_data(match.group(1))
xml = ET.XML(data)
mediagen = xml.find("channel").find("item").find("{http://search.yahoo.com/mrss/}group")
title = xml.find("channel").find("item").find("title").text
if options.output_auto:
directory = os.path.dirname(options.output)
if len(directory):
options.output = "%s/%s" % (directory, title)
else:
options.output = title
contenturl = mediagen.find("{http://search.yahoo.com/mrss/}content").attrib["url"]
content = get_http_data(contenturl)
xml = ET.XML(content)
ss = xml.find("video").find("item")
if is_py2_old:
sa = list(ss.getiterator("rendition"))
else:
sa = list(ss.iter("rendition"))
for i in sa:
yield RTMP(options, i.find("src").text, i.attrib["bitrate"])
def get(self, options):
if re.findall(r"sydsvenskan.se", self.url):
data = self.get_urldata()
match = re.search(r"data-qbrick-mcid=\"([0-9A-F]+)\"", data)
if not match:
log.error("Can't find video file")
sys.exit(2)
mcid = match.group(1)
host = "http://vms.api.qbrick.com/rest/v3/getsingleplayer/%s" % mcid
elif re.findall(r"di.se", self.url):
data = self.get_urldata()
match = re.search("src=\"(http://qstream.*)\"></iframe", data)
if not match:
log.error("Can't find video info")
sys.exit(2)
data = get_http_data(match.group(1))
match = re.search(r"data-qbrick-ccid=\"([0-9A-Z]+)\"", data)
if not match:
log.error("Can't find video file")
sys.exit(2)
host = "http://vms.api.qbrick.com/rest/v3/getplayer/%s" % match.group(1)
elif re.findall(r"svd.se", self.url):
match = re.search(r'video url-([^"]*)\"', self.get_urldata())
if not match:
log.error("Can't find video file")
sys.exit(2)
path = unquote_plus(match.group(1))
data = get_http_data("http://www.svd.se%s" % path)
match = re.search(r"mcid=([A-F0-9]+)\&width=", data)
if not match:
log.error("Can't find video file")
sys.exit(2)
host = "http://vms.api.qbrick.com/rest/v3/getsingleplayer/%s" % match.group(1)
else:
log.error("Can't find site")
sys.exit(2)
data = get_http_data(host)
xml = ET.XML(data)
try:
url = xml.find("media").find("item").find("playlist").find("stream").find("format").find("substream").text
except AttributeError:
log.error("Can't find video file")
sys.exit(2)
live = xml.find("media").find("item").find("playlist").find("stream").attrib["isLive"]
if live == "true":
options.live = True
data = get_http_data(url)
xml = ET.XML(data)
server = xml.find("head").find("meta").attrib["base"]
streams = xml.find("body").find("switch")
if is_py2_old:
sa = list(streams.getiterator("video"))
else:
sa = list(streams.iter("video"))
for i in sa:
options.other = "-y '%s'" % i.attrib["src"]
yield RTMP(copy.copy(options), server, i.attrib["system-bitrate"])
def get(self, options, url):
if re.findall("dn.se", url):
data = get_http_data(url)
match = re.search("data-qbrick-mcid=\"([0-9A-F]+)\"", data)
if not match:
match = re.search("mediaId = \'([0-9A-F]+)\';", data)
if not match:
log.error("Can't find video file")
sys.exit(2)
mcid = "%sDE1BA107" % match.group(1)
else:
mcid = match.group(1)
host = "http://vms.api.qbrick.com/rest/v3/getsingleplayer/%s" % mcid
elif re.findall("di.se", url):
data = get_http_data(url)
match = re.search("ccid: \"(.*)\"\,", data)
if not match:
log.error("Can't find video file")
sys.exit(2)
host = "http://vms.api.qbrick.com/rest/v3/getplayer/%s" % match.group(1)
elif re.findall("svd.se", url):
match = re.search("_([0-9]+)\.svd", url)
if not match:
log.error("Can't find video file")
sys.exit(2)
data = get_http_data("http://www.svd.se/?service=ajax&type=webTvClip&articleId=%s" % match.group(1))
match = re.search("mcid=([A-F0-9]+)\&width=", data)
if not match:
log.error("Can't find video file")
sys.exit(2)
host = "http://vms.api.qbrick.com/rest/v3/getsingleplayer/%s" % match.group(1)
else:
log.error("Can't find site")
sys.exit(2)
data = get_http_data(host)
xml = ET.XML(data)
try:
url = xml.find("media").find("item").find("playlist").find("stream").find("format").find("substream").text
except AttributeError:
log.error("Can't find video file")
sys.exit(2)
data = get_http_data(url)
xml = ET.XML(data)
server = xml.find("head").find("meta").attrib["base"]
streams = xml.find("body").find("switch")
if sys.version_info < (2, 7):
sa = list(streams.getiterator("video"))
else:
sa = list(streams.iter("video"))
streams = {}
for i in sa:
streams[int(i.attrib["system-bitrate"])] = i.attrib["src"]
path = select_quality(options, streams)
options.other = "-y %s" % path
download_rtmp(options, server)
def get(self, options):
match = re.search(r".*video/([0-9]+)", self.url)
if not match:
log.error("Can't find video file")
sys.exit(2)
video_id = match.group(1)
if options.username and options.password:
#bogus
cc = Cookie(None, 'asdf', None, '80', '80', 'www.kanal5play.se', None, None, '/', None, False, False, 'TestCookie', None, None, None)
self.cj.set_cookie(cc)
#get session cookie
data = get_http_data("http://www.kanal5play.se/", cookiejar=self.cj)
authurl = "https://kanal5swe.appspot.com/api/user/login?callback=jQuery171029989&email=%s&password=%s&_=136250" % (options.username, options.password)
data = get_http_data(authurl)
match = re.search(r"({.*})\);", data)
jsondata = json.loads(match.group(1))
if jsondata["success"] == False:
log.error(jsondata["message"])
sys.exit(2)
authToken = jsondata["userData"]["auth"]
cc = Cookie(version=0, name='authToken',
value=authToken,
port=None, port_specified=False,
domain='www.kanal5play.se',
domain_specified=True,
domain_initial_dot=True, path='/',
path_specified=True, secure=False,
expires=None, discard=True, comment=None,
comment_url=None, rest={'HttpOnly': None})
self.cj.set_cookie(cc)
url = "http://www.kanal5play.se/api/getVideo?format=FLASH&videoId=%s" % video_id
data = json.loads(get_http_data(url, cookiejar=self.cj))
if not options.live:
options.live = data["isLive"]
if data["hasSubtitle"]:
yield subtitle_json("http://www.kanal5play.se/api/subtitles/%s" % video_id)
for i in data["streams"]:
if i["drmProtected"]:
log.error("We cant download drm files for this site.")
sys.exit(2)
steambaseurl = data["streamBaseUrl"]
bitrate = i["bitrate"]
if bitrate > 1000:
bitrate = bitrate / 1000
options2 = copy.copy(options)
options2.other = "-W %s -y %s " % ("http://www.kanal5play.se/flash/K5StandardPlayer.swf", i["source"])
options2.live = True
yield RTMP(options2, steambaseurl, bitrate)
url = "http://www.kanal5play.se/api/getVideo?format=IPAD&videoId=%s" % video_id
data = json.loads(get_http_data(url, cookiejar=self.cj))
for i in data["streams"]:
streams = hlsparse(i["source"])
for n in list(streams.keys()):
yield HLS(copy.copy(options), streams[n], n)
def get(self, options, url):
data = get_http_data(url)
match = re.search(r'(http://load.cache.is/vodruv.*)"', data)
js_url = match.group(1)
js = get_http_data(js_url)
tengipunktur = js.split('"')[1]
match = re.search(r"http.*tengipunktur [+] '([:]1935.*)'", data)
m3u8_url = "http://" + tengipunktur + match.group(1)
base_url = m3u8_url.rsplit("/", 1)[0]
download_hls(options, m3u8_url, base_url)
def download(self):
if self.options.live and not self.options.force:
raise LiveHLSException(self.url)
error, m3u8 = get_http_data(self.url)
if error:
log.error("Cant get m3u8 file.")
return
globaldata, files = parsem3u(m3u8)
encrypted = False
key = None
if "KEY" in globaldata:
keydata = globaldata["KEY"]
encrypted = True
if encrypted:
try:
from Crypto.Cipher import AES
except ImportError:
log.error("You need to install pycrypto to download encrypted HLS streams")
sys.exit(2)
match = re.search(r'URI="(https?://.*?)"', keydata)
error, key = get_http_data(match.group(1))
if error:
log.error("Can't get crypto key to decode files.")
return
rand = os.urandom(16)
decryptor = AES.new(key, AES.MODE_CBC, rand)
file_d = output(self.options, "ts")
if hasattr(file_d, "read") is False:
return
n = 1
eta = ETA(len(files))
for i in files:
item = _get_full_url(i[0], self.url)
if self.options.output != "-":
eta.increment()
progressbar(len(files), n, "".join(["ETA: ", str(eta)]))
n += 1
error, data = get_http_data(item)
if error:
log.error("Missing segment in playlist")
return
if encrypted:
data = decryptor.decrypt(data)
file_d.write(data)
if self.options.output != "-":
file_d.close()
progress_stream.write("\n")
def get(self, options):
if re.findall("svt.se", self.url):
match = re.search(r"data-json-href=\"(.*)\"", self.get_urldata())
if match:
filename = match.group(1).replace("&", "&").replace("&format=json", "")
url = "http://www.svt.se%s" % filename
else:
log.error("Can't find video file")
sys.exit(2)
else:
url = self.url
pos = url.find("?")
if pos < 0:
dataurl = "%s?&output=json&format=json" % url
else:
dataurl = "%s&output=json&format=json" % url
data = json.loads(get_http_data(dataurl))
if "live" in data["video"]:
options.live = data["video"]["live"]
else:
options.live = False
if data["video"]["subtitleReferences"]:
try:
subtitle = data["video"]["subtitleReferences"][0]["url"]
except KeyError:
pass
if len(subtitle) > 0:
yield subtitle_wsrt(subtitle)
for i in data["video"]["videoReferences"]:
parse = urlparse(i["url"])
if parse.path.find("m3u8") > 0:
streams = hlsparse(i["url"])
for n in list(streams.keys()):
yield HLS(copy.copy(options), streams[n], n)
elif parse.path.find("f4m") > 0:
match = re.search(r"\/se\/secure\/", i["url"])
if not match:
parse = urlparse(i["url"])
manifest = "%s://%s%s?%s&hdcore=3.3.0" % (parse.scheme, parse.netloc, parse.path, parse.query)
streams = hdsparse(copy.copy(options), manifest)
for n in list(streams.keys()):
yield streams[n]
elif parse.scheme == "rtmp":
embedurl = "%s?type=embed" % url
data = get_http_data(embedurl)
match = re.search(r"value=\"(/(public)?(statiskt)?/swf(/video)?/svtplayer-[0-9\.a-f]+swf)\"", data)
swf = "http://www.svtplay.se%s" % match.group(1)
options.other = "-W %s" % swf
yield RTMP(copy.copy(options), i["url"], i["bitrate"])
else:
yield HTTP(copy.copy(options), i["url"], "0")
def download(self):
if self.options.live and not self.options.force:
raise LiveHLSException(self.url)
m3u8 = get_http_data(self.url)
globaldata, files = parsem3u(m3u8)
encrypted = False
key = None
try:
keydata = globaldata["KEY"]
encrypted = True
except KeyError:
pass
if encrypted:
try:
from Crypto.Cipher import AES
except ImportError:
log.error("You need to install pycrypto to download encrypted HLS streams")
sys.exit(2)
match = re.search(r'URI="(https?://.*?)"', keydata)
key = get_http_data(match.group(1))
rand = os.urandom(16)
decryptor = AES.new(key, AES.MODE_CBC, rand)
if self.options.output != "-":
extension = re.search(r"(\.[a-z0-9]+)$", self.options.output)
if not extension:
self.options.output = "%s.ts" % self.options.output
log.info("Outfile: %s", self.options.output)
if os.path.isfile(self.options.output) and not self.options.force:
log.info("File already exists. use --force to overwrite")
return
file_d = open(self.options.output, "wb")
else:
file_d = sys.stdout
n = 0
eta = ETA(len(files))
for i in files:
item = _get_full_url(i[0], self.url)
if self.options.output != "-":
eta.increment()
progressbar(len(files), n, ''.join(['ETA: ', str(eta)]))
n += 1
data = get_http_data(item)
if encrypted:
data = decryptor.decrypt(data)
file_d.write(data)
if self.options.output != "-":
file_d.close()
progress_stream.write('\n')
def get(self, options):
error, data = self.get_urldata()
if error:
log.error("Can't download page.")
return
if self.exclude(options):
return
match = re.search(r'resource:[ ]*"([^"]*)",', data)
if match:
resource_url = match.group(1)
error, resource_data = get_http_data(resource_url)
if error:
log.error("Can't get resource data")
return
resource = json.loads(resource_data)
streams = find_stream(options, resource)
for i in streams:
yield i
else:
match = re.search(r'resource="([^"]*)"', data)
if not match:
log.error("Cant find resource info for this video")
return
resource_url = "%s" % match.group(1)
error, resource_data = get_http_data(resource_url)
if error:
log.error("Can't get resource data")
return
resource = json.loads(resource_data)
if "SubtitlesList" in resource:
suburl = resource["SubtitlesList"][0]["Uri"]
yield subtitle(copy.copy(options), "wrst", suburl)
if "Data" in resource:
streams = find_stream(options, resource)
for i in streams:
yield i
else:
for stream in resource['Links']:
if stream["Target"] == "HDS":
streams = hdsparse(copy.copy(options), stream["Uri"])
if streams:
for n in list(streams.keys()):
yield streams[n]
if stream["Target"] == "HLS":
streams = hlsparse(stream["Uri"])
for n in list(streams.keys()):
yield HLS(copy.copy(options), streams[n], n)
if stream["Target"] == "Streaming":
options.other = "-v -y '%s'" % stream['Uri'].replace("rtmp://vod.dr.dk/cms/", "")
rtmp = "rtmp://vod.dr.dk/cms/"
yield RTMP(copy.copy(options), rtmp, stream['Bitrate'])
def get(self, options):
vid = self._get_video_id()
if vid is None:
log.error("Cant find video file")
sys.exit(2)
url = "http://playapi.mtgx.tv/v3/videos/%s" % vid
options.other = ""
data = get_http_data(url)
dataj = json.loads(data)
if "msg" in dataj:
log.error("%s" % dataj["msg"])
return
if dataj["type"] == "live":
options.live = True
if dataj["sami_path"]:
yield subtitle_sami(dataj["sami_path"])
streams = get_http_data("http://playapi.mtgx.tv/v3/videos/stream/%s" %
vid)
streamj = json.loads(streams)
if "msg" in streamj:
log.error(
"Can't play this because the video is either not found or geoblocked."
)
return
if streamj["streams"]["medium"]:
filename = streamj["streams"]["medium"]
if filename[len(filename) - 3:] == "f4m":
manifest = "%s?hdcore=2.8.0&g=hejsan" % filename
streams = hdsparse(copy.copy(options), manifest)
if streams:
for n in list(streams.keys()):
yield streams[n]
else:
parse = urlparse(filename)
match = re.search("^(/[^/]+)/(.*)", parse.path)
if not match:
log.error("Somthing wrong with rtmpparse")
sys.exit(2)
filename = "%s://%s:%s%s" % (parse.scheme, parse.hostname,
parse.port, match.group(1))
path = "-y %s" % match.group(2)
options.other = "-W http://flvplayer.viastream.viasat.tv/flvplayer/play/swf/player.swf %s" % path
yield RTMP(copy.copy(options), filename, 800)
if streamj["streams"]["hls"]:
streams = hlsparse(streamj["streams"]["hls"])
for n in list(streams.keys()):
yield HLS(copy.copy(options), streams[n], n)
def get(self, options):
vid = self._get_video_id()
if vid is None:
log.error("Cant find video file")
sys.exit(2)
url = "http://playapi.mtgx.tv/v3/videos/%s" % vid
options.other = ""
data = get_http_data(url)
dataj = json.loads(data)
if "msg" in dataj:
log.error("%s" % dataj["msg"])
return
if dataj["type"] == "live":
options.live = True
if dataj["sami_path"]:
yield subtitle_sami(dataj["sami_path"])
streams = get_http_data("http://playapi.mtgx.tv/v3/videos/stream/%s" % vid)
streamj = json.loads(streams)
if "msg" in streamj:
log.error("Can't play this because the video is either not found or geoblocked.")
return
if streamj["streams"]["medium"]:
filename = streamj["streams"]["medium"]
if filename[len(filename)-3:] == "f4m":
manifest = "%s?hdcore=2.8.0&g=hejsan" % filename
streams = hdsparse(copy.copy(options), manifest)
if streams:
for n in list(streams.keys()):
yield streams[n]
else:
parse = urlparse(filename)
match = re.search("^(/[^/]+)/(.*)", parse.path)
if not match:
log.error("Somthing wrong with rtmpparse")
sys.exit(2)
filename = "%s://%s:%s%s" % (parse.scheme, parse.hostname, parse.port, match.group(1))
path = "-y %s" % match.group(2)
options.other = "-W http://flvplayer.viastream.viasat.tv/flvplayer/play/swf/player.swf %s" % path
yield RTMP(copy.copy(options), filename, 800)
if streamj["streams"]["hls"]:
streams = hlsparse(streamj["streams"]["hls"])
for n in list(streams.keys()):
yield HLS(copy.copy(options), streams[n], n)
def get(self, options):
data = self.get_urldata()
match = re.search(r'resource:[ ]*"([^"]*)",', data)
if match:
resource_url = match.group(1)
resource_data = get_http_data(resource_url)
resource = json.loads(resource_data)
tempresource = resource['Data'][0]['Assets']
# To find the VideoResource, they have Images as well
for resources in tempresource:
if resources['Kind'] == 'VideoResource':
links = resources['Links']
break
for i in links:
if i["Target"] == "Ios":
streams = hlsparse(i["Uri"])
for n in list(streams.keys()):
yield HLS(copy.copy(options), streams[n], n)
else:
if i["Target"] == "Streaming":
options.other = "-y '%s'" % i["Uri"].replace("rtmp://vod.dr.dk/cms/", "")
rtmp = "rtmp://vod.dr.dk/cms/"
yield RTMP(copy.copy(options), rtmp, i["Bitrate"])
else:
match = re.search(r'resource="([^"]*)"', data)
if not match:
log.error("Cant find resource info for this video")
sys.exit(2)
resource_url = "%s" % match.group(1)
resource_data = get_http_data(resource_url)
resource = json.loads(resource_data)
for stream in resource['Links']:
if stream["Target"] == "HDS":
manifest = "%s?hdcore=2.8.0&g=hejsan" % stream["Uri"]
streams = hdsparse(copy.copy(options), manifest)
for n in list(streams.keys()):
yield streams[n]
if stream["Target"] == "HLS":
streams = hlsparse(stream["Uri"])
for n in list(streams.keys()):
yield HLS(copy.copy(options), streams[n], n)
if stream["Target"] == "Streaming":
options.other = "-v -y '%s'" % stream['Uri'].replace("rtmp://vod.dr.dk/cms/", "")
rtmp = "rtmp://vod.dr.dk/cms/"
yield RTMP(copy.copy(options), rtmp, stream['Bitrate'])
def download(self):
if self.options.live and not self.options.force:
raise LiveHLSException(self.url)
m3u8 = get_http_data(self.url)
globaldata, files = parsem3u(m3u8)
encrypted = False
key = None
try:
keydata = globaldata["KEY"]
encrypted = True
except KeyError:
pass
if encrypted:
try:
from Crypto.Cipher import AES
except ImportError:
log.error("You need to install pycrypto to download encrypted HLS streams")
sys.exit(2)
match = re.search(r'URI="(https?://.*?)"', keydata)
key = get_http_data(match.group(1))
rand = os.urandom(16)
decryptor = AES.new(key, AES.MODE_CBC, rand)
file_d = output(self.options, self.options.output, "ts")
if hasattr(file_d, "read") is False:
return
n = 1
eta = ETA(len(files))
for i in files:
item = _get_full_url(i[0], self.url)
if self.options.output != "-":
eta.increment()
progressbar(len(files), n, ''.join(['ETA: ', str(eta)]))
n += 1
data = get_http_data(item)
if encrypted:
data = decryptor.decrypt(data)
file_d.write(data)
if self.options.output != "-":
file_d.close()
progress_stream.write('\n')
def download(self, options):
self.subtitle = get_http_data(self.url)
i = 1
data = ""
tree = ET.ElementTree(ET.fromstring(self.subtitle))
xml = tree.find("{http://www.w3.org/2006/10/ttaf1}body").find(
"{http://www.w3.org/2006/10/ttaf1}div")
plist = list(xml.findall("{http://www.w3.org/2006/10/ttaf1}p"))
for node in plist:
tag = norm(node.tag)
if tag == "p" or tag == "span":
begin = node.attrib["begin"]
if not ("dur" in node.attrib):
duration = node.attrib["duration"]
else:
duration = node.attrib["dur"]
if not ("end" in node.attrib):
begin2 = begin.split(":")
duration2 = duration.split(":")
sec = float(begin2[2]) + float(duration2[2])
end = "%02d:%02d:%06.3f" % (int(begin[0]), int(
begin[1]), sec)
else:
end = node.attrib["end"]
data += '%s\n%s --> %s\n' % (i, begin.replace(
".", ","), end.replace(".", ","))
data = tt_text(node, data)
data += "\n"
i += 1
if is_py2:
data = data.encode('utf8')
save(options, data)
def download(self, options):
self.subtitle = get_http_data(self.url)
recomp = re.compile(
r"(\d+)\r\n([\d:\.]+ --> [\d:\.]+)?([^\r\n]+)?\r\n([^\r\n]+)\r\n(([^\r\n]*)\r\n)?"
)
srt = ""
subtract = False
for i in recomp.finditer(self.subtitle):
number = int(i.group(1))
match = re.search(
r'(\d+):(\d+):([\d\.]+) --> (\d+):(\d+):([\d\.]+)', i.group(2))
hour1 = int(match.group(1))
hour2 = int(match.group(4))
if number == 1:
if hour1 > 9:
subtract = True
if subtract:
hour1 -= 10
hour2 -= 10
time = "%s:%s:%s --> %s:%s:%s" % (
hour1, match.group(2), match.group(3).replace(".", ","), hour2,
match.group(5), match.group(6).replace(".", ","))
sub = "%s\n%s\n%s\n" % (i.group(1), time, i.group(4))
if len(i.group(6)) > 0:
sub += "%s\n" % i.group(6)
sub += "\n"
sub = re.sub('<[^>]*>', '', sub)
srt += sub
save(options, srt)
def get(self, options, url):
data = get_http_data(url)
match = re.search("liveStationsRedundancy = ({.*});</script>", data)
parse = urlparse(url)
station = parse.path[1:]
streams = None
if match:
data = json.loads(match.group(1))
for i in data["stations"]:
if station == i["name"].lower().replace(" ", ""):
streams = i["streams"]
break
else:
log.error("Can't find any streams.")
sys.exit(2)
if streams:
if options.hls:
try:
m3u8_url = streams["hls"]
base_url = m3u8_url.rsplit("/", 1)[0]
download_hls(options, m3u8_url, base_url)
except KeyError:
log.error("Can't find any streams.")
sys.exit(2)
else:
try:
rtmp = streams["rtmp"]
download_rtmp(options, rtmp)
except KeyError:
mp3 = streams["mp3"]
download_http(options, mp3)
else:
log.error("Can't find any streams.")
sys.exit(2)
def find_all_episodes(self, options):
parse = urlparse(self.url)
show = parse.path[parse.path.find("/", 1)+1:]
if not re.search("%", show):
show = quote_plus(show)
error, data = get_http_data("http://webapi.tv4play.se/play/video_assets?type=episode&is_live=false&platform=web&node_nids=%s&per_page=99999" % show)
if error:
log.error("Can't get api page")
return
jsondata = json.loads(data)
episodes = []
n = 1
for i in jsondata["results"]:
try:
days = int(i["availability"]["availability_group_free"])
except (ValueError, TypeError):
days = 999
if days > 0:
video_id = i["id"]
url = "http://www.tv4play.se/program/%s?video_id=%s" % (
show, video_id)
episodes.append(url)
if n == options.all_last:
break
n += 1
return episodes
def get(self, options, url):
data = get_http_data(url, referer="")
match = data.split(' = {config:')[1].split(',assets:')[0]
if match:
jsondata = json.loads(match)
sig = jsondata['request']['signature']
vidid = jsondata["video"]["id"]
timestamp = jsondata['request']['timestamp']
referer = jsondata["request"]["referrer"]
avail_quality = jsondata["video"]["files"]["h264"]
selected_quality = None
for i in avail_quality:
if options.quality == i:
selected_quality = i
if options.quality and selected_quality is None:
log.error("Can't find that quality. (Try one of: %s)",
", ".join(map(str, avail_quality)))
sys.exit(4)
elif options.quality is None and selected_quality is None:
selected_quality = avail_quality[0]
url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=H264,VP8,VP6&type=moogaloop_local&embed_location=%s" % (vidid, sig, timestamp, selected_quality, referer)
download_http(options, url)
else:
log.error("Can't find any streams.")
sys.exit(2)
def get(self, options):
data = self.get_urldata()
match = re.search('data-subtitlesurl = "(/.*)"', data)
if match:
parse = urlparse(self.url)
subtitle = "%s://%s%s" % (parse.scheme, parse.netloc, match.group(1))
yield subtitle_tt(subtitle)
match = re.search(r'data-media="(.*manifest.f4m)"', data)
if match:
manifest_url = match.group(1)
else:
match = re.search(r'data-video-id="(\d+)"', data)
if match is None:
log.error("Can't find video id.")
sys.exit(2)
vid = match.group(1)
match = re.search(r"PS_VIDEO_API_URL : '([^']*)',", data)
if match is None:
log.error("Can't find server address with media info")
sys.exit(2)
dataurl = "%smediaelement/%s" % (match.group(1), vid)
data = json.loads(get_http_data(dataurl))
manifest_url = data["mediaUrl"]
options.live = data["isLive"]
hlsurl = manifest_url.replace("/z/", "/i/").replace("manifest.f4m", "master.m3u8")
streams = hlsparse(hlsurl)
for n in list(streams.keys()):
yield HLS(copy.copy(options), streams[n], n)
manifest_url = "%s?hdcore=2.8.0&g=hejsan" % manifest_url
streams = hdsparse(copy.copy(options), manifest_url)
for n in list(streams.keys()):
yield streams[n]
def get(self, options):
match = re.search("xmlUrl=([^ ]+)\" ", self.get_urldata())
if match:
xmlurl = unquote_plus(match.group(1))
else:
match = re.search("moviesList: \[\{\"VideoId\":\"(\d+)\"", self.get_urldata())
if not match:
log.error("Can't find video id")
sys.exit(2)
vid = match.group(1)
xmlurl = "http://www.expressen.se/Handlers/WebTvHandler.ashx?id=%s" % vid
data = get_http_data(xmlurl)
xml = ET.XML(data)
live = xml.find("live").text
if live != "0":
options.live = True
ss = xml.find("vurls")
if is_py2_old:
sa = list(ss.getiterator("vurl"))
else:
sa = list(ss.iter("vurl"))
for i in sa:
options2 = copy.copy(options)
match = re.search(r"rtmp://([-0-9a-z\.]+/[-a-z0-9]+/)(.*)", i.text)
filename = "rtmp://%s" % match.group(1)
options2.other = "-y %s" % match.group(2)
yield RTMP(options2, filename, int(i.attrib["bitrate"]))
ipadurl = xml.find("mobileurls").find("ipadurl").text
streams = hlsparse(ipadurl)
for n in list(streams.keys()):
yield HLS(copy.copy(options), streams[n], n)
def find_all_episodes(self, options):
page = 1
match = re.search(r'"http://www.oppetarkiv.se/etikett/titel/([^"/]+)',
self.get_urldata())
if match is None:
match = re.search(
r'"http://www.oppetarkiv.se/etikett/titel/([^"/]+)', self.url)
if match is None:
log.error("Couldn't find title")
sys.exit(2)
program = match.group(1)
more = True
episodes = []
while more:
url = "http://www.oppetarkiv.se/etikett/titel/%s/?sida=%s&sort=tid_stigande&embed=true" % (
program, page)
data = get_http_data(url)
visa = re.search(r'svtXColorDarkLightGrey', data)
if not visa:
more = False
regex = re.compile(r'(http://www.oppetarkiv.se/video/[^"]+)')
for match in regex.finditer(data):
episodes.append(match.group(1))
page += 1
return episodes
def find_all_episodes(self, options):
match = re.search(r'<link rel="alternate" type="application/rss\+xml" [^>]*href="([^"]+)"',
self.get_urldata()[1])
if match is None:
match = re.findall(r'a class="play[^"]+"\s+href="(/video[^"]+)"', self.get_urldata()[1])
if not match:
log.error("Couldn't retrieve episode list")
return
episodes = [urljoin("http://www.svtplay.se", x) for x in match]
else:
error, data = get_http_data(match.group(1))
if error:
log.error("Cant get rss page")
return
xml = ET.XML(data)
episodes = [x.text for x in xml.findall(".//item/link")]
episodes_new = []
n = 1
for i in episodes:
episodes_new.append(i)
if n == options.all_last:
break
n += 1
return sorted(episodes_new)
def get(self, options):
match = re.search("xmlUrl=([^ ]+)\" ", self.get_urldata())
if match:
xmlurl = unquote_plus(match.group(1))
else:
match = re.search(r"moviesList: \[\{\"VideoId\":\"(\d+)\"",
self.get_urldata())
if not match:
log.error("Can't find video id")
sys.exit(2)
vid = match.group(1)
xmlurl = "http://www.expressen.se/Handlers/WebTvHandler.ashx?id=%s" % vid
data = get_http_data(xmlurl)
xml = ET.XML(data)
live = xml.find("live").text
if live != "0":
options.live = True
ss = xml.find("vurls")
if is_py2_old:
sa = list(ss.getiterator("vurl"))
else:
sa = list(ss.iter("vurl"))
for i in sa:
options2 = copy.copy(options)
match = re.search(r"rtmp://([-0-9a-z\.]+/[-a-z0-9]+/)(.*)", i.text)
filename = "rtmp://%s" % match.group(1)
options2.other = "-y %s" % match.group(2)
yield RTMP(options2, filename, int(i.attrib["bitrate"]))
ipadurl = xml.find("mobileurls").find("ipadurl").text
streams = hlsparse(ipadurl)
for n in list(streams.keys()):
yield HLS(copy.copy(options), streams[n], n)
def get(self, options):
match = re.search(r'data-videoid="([^"]+)"', self.get_urldata())
if not match:
parse = urlparse(self.url)
match = re.search(r'video/(\d+)/', parse.fragment)
if not match:
log.error("Can't find video id")
sys.exit(2)
videoid = match.group(1)
data = get_http_data("http://svp.vg.no/svp/api/v1/vgtv/assets/%s?appName=vgtv-website" % videoid)
jsondata = json.loads(data)
if options.output_auto:
directory = os.path.dirname(options.output)
title = "%s" % jsondata["title"]
title = filenamify(title)
if len(directory):
options.output = "%s/%s" % (directory, title)
else:
options.output = title
if "hds" in jsondata["streamUrls"]:
parse = urlparse(jsondata["streamUrls"]["hds"])
manifest = "%s://%s%s?%s&hdcore=3.3.0" % (parse.scheme, parse.netloc, parse.path, parse.query)
streams = hdsparse(copy.copy(options), manifest)
if streams:
for n in list(streams.keys()):
yield streams[n]
if "hls" in jsondata["streamUrls"]:
streams = hlsparse(jsondata["streamUrls"]["hls"])
for n in list(streams.keys()):
yield HLS(copy.copy(options), streams[n], n)
if "mp4" in jsondata["streamUrls"]:
yield HTTP(copy.copy(options), jsondata["streamUrls"]["mp4"])
def get(self, options):
error, data = self.get_urldata()
if error:
log.error("Cant get page")
return
match = re.search(r"mgid=\"(mgid.*[0-9]+)\" data-wi", data)
if not match:
log.error("Can't find video file")
return
url = "http://media.mtvnservices.com/player/html5/mediagen/?uri=%s" % match.group(1)
error, data = get_http_data(url)
if error:
log.error("Cant get stream info")
return
start = data.index("<?xml version=")
data = data[start:]
xml = ET.XML(data)
ss = xml.find("video").find("item")
if is_py2_old:
sa = list(ss.getiterator("rendition"))
else:
sa = list(ss.iter("rendition"))
if self.exclude(options):
return
for i in sa:
temp = i.find("src").text.index("gsp.comedystor")
url = "http://mtvnmobile.vo.llnwd.net/kip0/_pxn=0+_pxK=18639+_pxE=mp4/44620/mtvnorigin/%s" % i.find("src").text[temp:]
yield HTTP(copy.copy(options), url, i.attrib["height"])
def get_media(url, options):
stream = service_handler(url)
if not stream:
url, stream = Generic().get(url)
url = url.replace("&", "&")
if not stream:
log.error("That site is not supported. Make a ticket or send a message")
sys.exit(2)
if not options.output or os.path.isdir(options.output):
data = get_http_data(url)
match = re.search("(?i)<title.*>\s*(.*?)\s*</title>", data)
if match:
if sys.version_info > (3, 0):
title = re.sub('[^\w\s-]', '', match.group(1)).strip().lower()
if options.output:
options.output = options.output + re.sub('[-\s]+', '-', title)
else:
options.output = re.sub('[-\s]+', '-', title)
else:
title = unicode(re.sub('[^\w\s-]', '', match.group(1)).strip().lower())
if options.output:
options.output = unicode(options.output + re.sub('[-\s]+', '-', title))
else:
options.output = unicode(re.sub('[-\s]+', '-', title))
stream.get(options, url)
def get(self, options):
error, data = self.get_urldata()
if error:
log.error("Can't get the page")
return
if self.exclude(options):
return
match = re.search(r'href="(/sida/[\.\/=a-z0-9&;\?]+\d+)" aria-label', data)
if not match:
log.error("Can't find audio info")
return
path = quote_plus(match.group(1))
dataurl = "http://sverigesradio.se/sida/ajax/getplayerinfo?url=%s&isios=false&playertype=html5" % path
error, data = get_http_data(dataurl)
if error:
log.error("Cant get stream info")
return
playerinfo = json.loads(data)["playerInfo"]
for i in playerinfo["AudioSources"]:
url = i["Url"]
if not url.startswith('http'):
url = 'http:%s' % url
yield HTTP(copy.copy(options), url, i["Quality"]/1000)
def hdsparse(options, manifest):
data = get_http_data(manifest)
streams = {}
bootstrap = {}
xml = ET.XML(data)
if is_py2_old:
bootstrapIter = xml.getiterator("{http://ns.adobe.com/f4m/1.0}bootstrapInfo")
mediaIter = xml.getiterator("{http://ns.adobe.com/f4m/1.0}media")
else:
bootstrapIter = xml.iter("{http://ns.adobe.com/f4m/1.0}bootstrapInfo")
mediaIter = xml.iter("{http://ns.adobe.com/f4m/1.0}media")
if xml.find("{http://ns.adobe.com/f4m/1.0}drmAdditionalHeader") is not None:
log.error("HDS DRM protected content.")
return
for i in bootstrapIter:
if "id" in i.attrib:
bootstrap[i.attrib["id"]] = i.text
else:
bootstrap["0"] = i.text
parse = urlparse(manifest)
querystring = parse.query
for i in mediaIter:
if len(bootstrap) == 1:
bootstrapid = bootstrap["0"]
else:
bootstrapid = bootstrap[i.attrib["bootstrapInfoId"]]
streams[int(i.attrib["bitrate"])] = HDS(options, i.attrib["url"], i.attrib["bitrate"], manifest=manifest, bootstrap=bootstrapid,
metadata=i.find("{http://ns.adobe.com/f4m/1.0}metadata").text, querystring=querystring)
return streams
def _get_static_video(self, vid, options, vidtype):
url = "http://api.justin.tv/api/broadcast/by_%s/%s.xml?onsite=true" % (
vidtype, vid)
data = get_http_data(url)
xml = ET.XML(data)
url = xml.find("archive").find("video_file_url").text
yield HTTP(copy.copy(options), url)
def get(self, options):
parse = urlparse(self.url)
if parse.hostname == "video.disney.se":
match = re.search(r"Grill.burger=({.*}):", self.get_urldata())
if not match:
log.error("Can't find video info")
return
jsondata = json.loads(match.group(1))
for n in jsondata["stack"]:
if len(n["data"]) > 0:
for x in n["data"]:
if "flavors" in x:
for i in x["flavors"]:
if i["format"] == "mp4":
yield HTTP(copy.copy(options), i["url"],
i["bitrate"])
else:
match = re.search(r"uniqueId : '([^']+)'", self.get_urldata())
if not match:
log.error("Can't find video info")
return
uniq = match.group(1)
match = re.search("entryId : '([^']+)'", self.get_urldata())
entryid = match.group(1)
match = re.search("partnerId : '([^']+)'", self.get_urldata())
partnerid = match.group(1)
match = re.search("uiConfId : '([^']+)'", self.get_urldata())
uiconfid = match.group(1)
url = "http://cdnapi.kaltura.com/html5/html5lib/v1.9.7.6/mwEmbedFrame.php?&wid=%s&uiconf_id=%s&entry_id=%s&playerId=%s&forceMobileHTML5=true&urid=1.9.7.6&callback=mwi" % \
(partnerid, uiconfid, entryid, uniq)
data = get_http_data(url)
match = re.search(r"mwi\(({.*})\);", data)
jsondata = json.loads(match.group(1))
data = jsondata["content"]
match = re.search(r"window.kalturaIframePackageData = ({.*});",
data)
jsondata = json.loads(match.group(1))
ks = jsondata["enviornmentConfig"]["ks"]
if options.output_auto:
name = jsondata["entryResult"]["meta"]["name"]
directory = os.path.dirname(options.output)
options.service = "disney"
title = "%s-%s" % (name, options.service)
title = filenamify(title)
if len(directory):
options.output = "%s/%s" % (directory, title)
else:
options.output = title
url = "http://cdnapi.kaltura.com/p/%s/sp/%s00/playManifest/entryId/%s/format/applehttp/protocol/http/a.m3u8?ks=%s&referrer=aHR0cDovL3d3dy5kaXNuZXkuc2U=&" % (
partnerid[1:], partnerid[1:], entryid, ks)
redirect = check_redirect(url)
streams = hlsparse(redirect)
for n in list(streams.keys()):
yield HLS(copy.copy(options), streams[n], n)
def hlsparse(url):
data = get_http_data(url)
files = (parsem3u(data))[1]
streams = {}
for i in files:
bitrate = float(i[1]["BANDWIDTH"])/1000
streams[int(bitrate)] = _get_full_url(i[0], url)
return streams
def get(self, options):
data = self.get_urldata()
match = re.search('data-aptomaId="([-0-9a-z]+)"', data)
if not match:
log.error("Can't find video info")
sys.exit(2)
videoId = match.group(1)
match = re.search(r'data-isLive="(\w+)"', data)
if not match:
log.error("Can't find live info")
sys.exit(2)
if match.group(1) == "true":
options.live = True
if not options.live:
dataurl = "http://aftonbladet-play-metadata.cdn.drvideo.aptoma.no/video/%s.json" % videoId
data = get_http_data(dataurl)
data = json.loads(data)
videoId = data["videoId"]
streamsurl = "http://aftonbladet-play-static-ext.cdn.drvideo.aptoma.no/actions/video/?id=%s&formats&callback=" % videoId
streams = json.loads(get_http_data(streamsurl))
hlsstreams = streams["formats"]["hls"]
if "level3" in hlsstreams.keys():
hls = hlsstreams["level3"]
else:
hls = hlsstreams["akamai"]
if "csmil" in hls.keys():
hls = hls["csmil"][0]
else:
hls = hls["m3u8"][0]
address = hls["address"]
path = hls["path"]
for i in hls["files"]:
if "filename" in i.keys():
plist = "http://%s/%s/%s/master.m3u8" % (address, path,
i["filename"])
else:
plist = "http://%s/%s/%s" % (address, path, hls["filename"])
streams = hlsparse(plist)
for n in list(streams.keys()):
yield HLS(copy.copy(options), streams[n], n)
def find_all_episodes(self, options):
match = re.search(
r'<link rel="alternate" type="application/rss\+xml" [^>]*href="([^"]+)"',
self.get_urldata())
if match is None:
log.error("Couldn't retrieve episode list")
sys.exit(2)
url = "http://urplay.se%s" % match.group(1).replace("&", "&")
xml = ET.XML(get_http_data(url))
return sorted(x.text for x in xml.findall(".//item/link"))
def get(self, options):
data = self.get_urldata()
match = re.search(r'resource:[ ]*"([^"]*)",', data)
if match:
resource_url = match.group(1)
resource_data = get_http_data(resource_url)
resource = json.loads(resource_data)
streams = find_stream(options, resource)
for i in streams:
yield i
else:
match = re.search(r'resource="([^"]*)"', data)
if not match:
log.error("Cant find resource info for this video")
sys.exit(2)
resource_url = "%s" % match.group(1)
resource_data = get_http_data(resource_url)
resource = json.loads(resource_data)
if "Data" in resource:
streams = find_stream(options, resource)
for i in streams:
yield i
else:
for stream in resource['Links']:
if stream["Target"] == "HDS":
manifest = "%s?hdcore=2.8.0&g=hejsan" % stream["Uri"]
streams = hdsparse(copy.copy(options), manifest)
if streams:
for n in list(streams.keys()):
yield streams[n]
if stream["Target"] == "HLS":
streams = hlsparse(stream["Uri"])
for n in list(streams.keys()):
yield HLS(copy.copy(options), streams[n], n)
if stream["Target"] == "Streaming":
options.other = "-v -y '%s'" % stream['Uri'].replace(
"rtmp://vod.dr.dk/cms/", "")
rtmp = "rtmp://vod.dr.dk/cms/"
yield RTMP(copy.copy(options), rtmp, stream['Bitrate'])
def find_all_episodes(self, options):
format_id = re.search(r'data-format-id="(\d+)"', self.get_urldata())
if not format_id:
log.error("Can't find video info")
sys.exit(2)
data = get_http_data(
"http://playapi.mtgx.tv/v1/sections?sections=videos.one,seasons.videolist&format=%s"
% format_id.group(1))
jsondata = json.loads(data)
videos = jsondata["_embedded"]["sections"][1]["_embedded"]["seasons"][
0]["_embedded"]["episodelist"]["_embedded"]["videos"]
return sorted(x["sharing"]["url"] for x in videos)
def get(self, url):
data = get_http_data(url)
match = re.search(r"src=\"(http://www.svt.se/wd.*)\" height", data)
stream = None
if match:
url = match.group(1)
for i in sites:
if i.handles(url):
url = url.replace("&", "&")
return url, i(url)
match = re.search(r"src=\"(http://player.vimeo.com/video/[0-9]+)\" ", data)
if match:
for i in sites:
if i.handles(match.group(1)):
return match.group(1), i(url)
match = re.search(r"tv4play.se/iframe/video/(\d+)?", data)
if match:
url = "http://www.tv4play.se/?video_id=%s" % match.group(1)
for i in sites:
if i.handles(url):
return url, i(url)
match = re.search(r"embed.bambuser.com/broadcast/(\d+)", data)
if match:
url = "http://bambuser.com/v/%s" % match.group(1)
for i in sites:
if i.handles(url):
return url, i(url)
match = re.search(r'iframe src="(http://tv.aftonbladet[^"]*)"', data)
if match:
url = match.group(1)
for i in sites:
if i.handles(url):
return url, i(url)
match = re.search(r'a href="(http://tv.aftonbladet[^"]*)" class="abVi', data)
if match:
url = match.group(1)
for i in sites:
if i.handles(url):
return url, i(url)
match = re.search(r"iframe src='(http://www.svtplay[^']*)'", data)
if match:
url = match.group(1)
for i in sites:
if i.handles(url):
return url, i(url)
return url, stream
def get(self, options):
match = re.search(r'href="(/sida/[\.\/=a-z0-9&;\?]+\d+)" aria-label',
self.get_urldata())
if not match:
log.error("Can't find audio info")
sys.exit(2)
path = quote_plus(match.group(1))
dataurl = "http://sverigesradio.se/sida/ajax/getplayerinfo?url=%s&isios=false&playertype=html5" % path
data = get_http_data(dataurl)
playerinfo = json.loads(data)["playerInfo"]
for i in playerinfo["AudioSources"]:
url = i["Url"]
if not url.startswith('http'):
url = 'http:%s' % url
yield HTTP(copy.copy(options), url, i["Quality"])
def download(self, options):
self.subtitle = get_http_data(self.url, cookiejar=options.cookiejar)
data = json.loads(self.subtitle)
number = 1
subs = ""
for i in data:
subs += "%s\n%s --> %s\n" % (number, timestr(int(
i["startMillis"])), timestr(int(i["endMillis"])))
if is_py2:
subs += "%s\n\n" % i["text"].encode("utf-8")
else:
subs += "%s\n\n" % i["text"]
number += 1
save(options, subs)
def _ajax_get(self, method):
url = "%s/%s" % (self.api_base_url, method)
# Logic found in Twitch's global.js. Prepend /kraken/ to url
# path unless the API method already is absolute.
if method[0] != '/':
method = '/kraken/%s' % method
# There are references to a api_token in global.js; it's used
# with the "Twitch-Api-Token" HTTP header. But it doesn't seem
# to be necessary.
payload = get_http_data(url, header={
'Accept': 'application/vnd.twitchtv.v2+json'
})
return json.loads(payload)
def get(self, options):
match = re.search(r'id="(bcPl[^"]+)"', self.get_urldata())
if not match:
log.error("Can't find flash id.")
sys.exit(2)
flashid = match.group(1)
match = re.search(r'playerID" value="([^"]+)"', self.get_urldata())
if not match:
log.error("Can't find playerID")
sys.exit(2)
playerid = match.group(1)
match = re.search(r'playerKey" value="([^"]+)"', self.get_urldata())
if not match:
log.error("Can't find playerKey")
sys.exit(2)
playerkey = match.group(1)
match = re.search(r'videoPlayer" value="([^"]+)"', self.get_urldata())
if not match:
log.error("Can't find videoPlayer info")
sys.exit(2)
videoplayer = match.group(1)
dataurl = "http://c.brightcove.com/services/viewer/htmlFederated?flashID=%s&playerID=%s&playerKey=%s&isVid=true&isUI=true&dynamicStreaming=true&@videoPlayer=%s" % (
flashid, playerid, playerkey, videoplayer)
data = get_http_data(dataurl)
match = re.search(r'experienceJSON = ({.*});', data)
if not match:
log.error("Can't find json data")
sys.exit(2)
jsondata = json.loads(match.group(1))
renditions = jsondata["data"]["programmedContent"]["videoPlayer"][
"mediaDTO"]["renditions"]
for i in renditions:
if i["defaultURL"].endswith("f4m"):
manifest = "%s?hdcore=3.3.0" % i["defaultURL"]
streams = hdsparse(copy.copy(options), manifest)
if streams:
for n in list(streams.keys()):
yield streams[n]
if i["defaultURL"].endswith("m3u8"):
streams = hlsparse(i["defaultURL"])
for n in list(streams.keys()):
yield HLS(copy.copy(options), streams[n], n)
def find_all_episodes(self, options):
match = re.search(
r'<link rel="alternate" type="application/rss\+xml" [^>]*href="([^"]+)"',
self.get_urldata())
if match is None:
log.error("Couldn't retrieve episode list")
sys.exit(2)
xml = ET.XML(get_http_data(match.group(1)))
if options.episode_list_exclude_filter:
episode_list = sorted(
x.text for x in xml.findall(".//item/link")
if options.episode_list_exclude_filter not in x.text)
else:
episode_list = sorted(x.text for x in xml.findall(".//item/link"))
return episode_list
def get(self, options):
match = re.search(r"v/(\d+)", self.url)
if not match:
log.error("Can't find video id in url")
sys.exit(2)
json_url = "http://player-c.api.bambuser.com/getVideo.json?api_key=005f64509e19a868399060af746a00aa&vid=%s" % match.group(1)
data = get_http_data(json_url)
info = json.loads(data)["result"]
video = info["url"]
if video[:4] == "rtmp":
playpath = info["id"][len(info["id"])-36:]
options.other = "-y %s" % playpath
if info["type"] == "live":
options.live = True
yield RTMP(copy.copy(options), video, "0")
else:
yield HTTP(copy.copy(options), video, "0")
def get(self, options):
match = re.search("data-config-url=\"(.*)\" data-fallback-url",
self.get_urldata())
if not match:
log.error("Can't find data")
sys.exit(4)
player_url = match.group(1).replace("&", "&")
player_data = get_http_data(player_url)
if player_data:
jsondata = json.loads(player_data)
avail_quality = jsondata["request"]["files"]["h264"]
for i in avail_quality.keys():
yield HTTP(copy.copy(options), avail_quality[i]["url"],
avail_quality[i]["bitrate"])
else:
log.error("Can't find any streams.")
sys.exit(2)
def download(self):
if self.options.live and not self.options.force:
raise LiveHDSException(self.url)
querystring = self.kwargs["querystring"]
bootstrap = base64.b64decode(self.kwargs["bootstrap"])
box = readboxtype(bootstrap, 0)
antal = None
if box[2] == b"abst":
antal = readbox(bootstrap, box[0])
baseurl = self.kwargs["manifest"][0:self.kwargs["manifest"].rfind("/")]
file_d = output(self.options, self.options.output, "flv")
if hasattr(file_d, "read") is False:
return
metasize = struct.pack(">L",
len(base64.b64decode(
self.kwargs["metadata"])))[1:]
file_d.write(binascii.a2b_hex(b"464c560105000000090000000012"))
file_d.write(metasize)
file_d.write(binascii.a2b_hex(b"00000000000000"))
file_d.write(base64.b64decode(self.kwargs["metadata"]))
file_d.write(binascii.a2b_hex(b"00000000"))
i = 1
start = antal[1]["first"]
total = antal[1]["total"]
eta = ETA(total)
while i <= total:
url = "%s/%sSeg1-Frag%s?%s" % (baseurl, self.url, start,
querystring)
if self.options.output != "-":
eta.update(i)
progressbar(total, i, ''.join(["ETA: ", str(eta)]))
data = get_http_data(url)
number = decode_f4f(i, data)
file_d.write(data[number:])
i += 1
start += 1
if self.options.output != "-":
file_d.close()
progress_stream.write('\n')
def find_all_episodes(self, options):
parse = urlparse(self.url)
show = parse.path[parse.path.find("/", 1)+1:]
if not re.search("%", show):
show = quote_plus(show)
data = get_http_data("http://webapi.tv4play.se/play/video_assets?type=episode&is_live=false&platform=web&node_nids=%s&per_page=99999" % show)
jsondata = json.loads(data)
episodes = []
for i in jsondata["results"]:
try:
days = int(i["availability"]["availability_group_free"])
except ValueError:
days = 999
if days > 0:
video_id = i["id"]
url = "http://www.tv4play.se/program/%s?video_id=%s" % (
show, video_id)
episodes.append(url)
return sorted(episodes)
def get(self, options):
data = self.get_urldata()
match = re.search("data-subtitlesurl = \"(/.*)\"", data)
if match:
parse = urlparse(self.url)
subtitle = "%s://%s%s" % (parse.scheme, parse.netloc,
match.group(1))
yield subtitle_tt(subtitle)
if options.force_subtitle:
return
match = re.search(r'data-media="(.*manifest.f4m)"', data)
if match:
manifest_url = match.group(1)
else:
match = re.search(r'data-video-id="(\d+)"', data)
if match is None:
log.error("Can't find video id.")
sys.exit(2)
vid = match.group(1)
match = re.search(r"PS_VIDEO_API_URL : '([^']*)',", data)
if match is None:
log.error("Can't find server address with media info")
sys.exit(2)
dataurl = "%smediaelement/%s" % (match.group(1), vid)
data = json.loads(get_http_data(dataurl))
manifest_url = data["mediaUrl"]
options.live = data["isLive"]
hlsurl = manifest_url.replace("/z/",
"/i/").replace("manifest.f4m",
"master.m3u8")
streams = hlsparse(hlsurl)
for n in list(streams.keys()):
yield HLS(copy.copy(options), streams[n], n)
manifest_url = "%s?hdcore=2.8.0&g=hejsan" % manifest_url
streams = hdsparse(copy.copy(options), manifest_url)
if streams:
for n in list(streams.keys()):
yield streams[n]
def get(self, options):
data = self.get_urldata()
ajax_auth = re.search(r"picsearch_ajax_auth = '(\w+)'", data)
if not ajax_auth:
log.error("Cant find token for video")
sys.exit(2)
mediaid = re.search(r"mediaId = '([^']+)';", data)
if not mediaid:
mediaid = re.search(r'media-id="([^"]+)"', data)
if not mediaid:
log.error("Cant find media id")
sys.exit(2)
jsondata = get_http_data("http://csp.picsearch.com/rest?jsonp=&eventParam=1&auth=%s&method=embed&mediaid=%s" % (ajax_auth.group(1), mediaid.group(1)))
jsondata = json.loads(jsondata)
files = jsondata["media"]["playerconfig"]["playlist"][1]["bitrates"]
server = jsondata["media"]["playerconfig"]["plugins"]["bwcheck"]["netConnectionUrl"]
for i in files:
options.other = "-y '%s'" % i["url"]
yield RTMP(copy.copy(options), server, i["height"])
def get(self, options):
match = re.search(r'"([^"]+geo.php)"', self.get_urldata())
if match:
data = get_http_data(match.group(1))
match = re.search(r'punktur=\(([^ ]+)\)', data)
if match:
janson = json.loads(match.group(1))
options.live = checklive(janson["result"][1])
streams = hlsparse(janson["result"][1])
for n in list(streams.keys()):
yield HLS(copy.copy(options), streams[n], n)
else:
match = re.search(r'<source [^ ]*[ ]*src="([^"]+)" ',
self.get_urldata())
if not match:
log.error("Can't find video info")
sys.exit(2)
m3u8_url = match.group(1)
options.live = checklive(m3u8_url)
yield HLS(copy.copy(options), m3u8_url, 800)
