def test(self):
url = 'https://y.qq.com/portal/mv/v/s0017amxyfd.html' # don't care music
url = 'https://v.qq.com/x/cover/tu0kfx77pkwk3t6.html?vid=k00205g5xhk' # don't add proxy='auto'
url = 'http://v.qq.com/iframe/player.html?vid=i00167ai266&tiny=0&auto=0'
hutf = self.get_hutf(url)
#title, vid, mp = self.getvinfo(url)
echo(hutf)
def query_info(self, url):
#url = "http://www.dailymotion.com/embed/video/k7alsxAgBgcMGaachYS"
#url = "http://www.dailymotion.com/embed/video/k4BjypcByJGUTDl6Bvx"
hutf = self.get_hutf(url)
#echo(hutf)
# "720":[{"type":"application\/x-mpegURL","url":"http:\/\/www.dailymotion.com\/cdn\/manifest\/video\/x2hpv0i.m3u8?auth=1482432896-2562-0fq84z9d-24047244e9a36f0f3fab8388642b74c1&include=720"},{"type":"video\/mp4","url":"http:\/\/www.dailymotion.com\/cdn\/H264-1280x720\/video\/x2hpv0i.mp4?auth=1482432896-2562-pvg451ll-4c251ca9aa8a1bf6f56c88d318eccd65"}]}
m = re.search("var config = ([^\n]+);", hutf)
j = json.loads(m.group(1))
mr, mq, mu, ex = -2, '', '', ''
qua = ['auto', '144', '240', '380', '480', '720']
for k, vs in j['metadata']['qualities'].items():
if k not in qua:
echo("New qua", k)
continue
r = qua.index(k)
if r > mr:
for v in vs:
t = v.get('type', '')
if t.startswith('video/'):
mr, mq = r, k
mu = v['url']
ex = t[-3:]
echo("ext=%s, mq=%s, url=%s" % (ex, mq, mu))
title = j['metadata']['title'].strip('.')
return title, ex, [mu], None
def test1(self, args):
# http://m.bookdown.com.cn/read/31314.html
url = 'http://m.bookdown.com.cn/read/31314.html'
#hutf = self.get_hutf(url)
#print hutf
#m = re.findall("http://m.bookdown.com.cn/read/31314_\d+.html", hutf)
#print m
#hutf = self.get_html("http://m.bookdown.com.cn/read/31314_2.html")
#print(hutf)
#url = "http://m.bookdown.com.cn/read/31314_1.html"
#url = "http://m.bookdown.com.cn/read/31314_1_2.html"
while True:
print >> sys.stderr, url
hutf = self.get_hutf(url)
# class="articlecon
for div in SelStr('div.articlecon', hutf):
#echo(div)
#echo(" ".join(div.text.split(" ")))
echo(
re.sub(u"分节阅读.+，请点击下一页继续阅读。", "",
re.sub(" ", " ", div.text)))
#echo(hutf)
m = re.findall(
u'''<a class="btn" href="(http://m\.bookdown\.com\.cn/read/31314_.+\.html)">下一章</a>''',
hutf)
#m = re.findall(u'''\<a class="btn" href=".+"\>下一章\</a\>''', hutf) #, re.U)
#echo(m)
if not m:
break
url = m[0]
def get_playlist(self, url):
#url = "https://www.shuquge.com/txt/12236/index.html"
base = os.path.dirname(url)
hutf = self.get_hutf(url)
#hutf = open("s.html").read().decode('utf8')
#echo(hutf)
tt = SelStr("div.book div.info h2", hutf)
if not tt:
return []
#echo(tt[0].text)
title = tt[0].text
echo(title)
ul = SelStr("div.listmain dl", hutf)
if not ul:
return []
#for u in ul.descendants:
sel = True
lst = []
for u in ul[0].children:
#echo(u)
if u.tag == 'dt':
sel = u"最新章节" not in u.text
continue
if sel and u.tag == 'dd':
l = os.path.join(base, u.select("a")[0]['href'])
echo(l, u.text)
lst.append((u.text, l))
return lst
def detail_key(self, url):
ci = get_ci(debug())
qnrr = Queue()
def nrr(ci, msg):
url = msg['params']['response']['url']
if '/api/video/detail' in url:
qnrr.put(msg['params']['requestId'])
ci.reg("Network.responseReceived", nrr)
try:
ci.Page.navigate(url=url)
req_id = qnrr.get(timeout=ci.get_to())
ret = ci.Network.getResponseBody(requestId=req_id)
body = json.loads(ret['result']['body'])
bdi0 = body['data']['info'][0]
title, channel = bdi0['title'], bdi0['channel']
keys = [g['key'] for g in bdi0['guestSeriesList']]
debug("keys = ", keys)
return channel, title, keys
except Exception as e:
echo("detail_key out:", repr(e))
finally:
ci.close()
return None, None, []
def get_one(self, url, t=UTITLE, n=False):
if t == UTITLE:
hutf = self.get_hutf(url)
t = match1(hutf, '\<meta name="title" content="([^"]+)"\>')
#echo(url, t)
echo("download", t)
echo("")
#return
dn = os.path.dirname(os.path.abspath(__file__))
fn = os.path.abspath(os.path.join(dn, "../you-get/you-get"))
p = Popen([fn, "-o", self.out_dir, "--no-caption", url])
p.wait()
if not self.parsed_args.post_uri:
return
for i in range(1, len(t)):
n = t[:i] + "*"
debug("ls " + n)
ls = glob(n)
if len(ls) == 0:
break
if len(ls) == 1:
post_file(ls[0], self.parsed_args.post_uri)
return
raise Exception("can not find " + t)
def query_info(self, url):
uid = match1(url, '''openload.co/embed/([^/]+)''')
hutf = self.chrome_hutf(url)
vid = match1(hutf, r'>(%s[^<]+)<' % uid)
url = "https://openload.co/stream/%s?mime=true" % vid
echo(url)
return self.title, None, [url], None
def test(self):
url = 'https://y.qq.com/portal/mv/v/s0017amxyfd.html' # don't care music
url = 'https://v.qq.com/x/cover/tu0kfx77pkwk3t6.html?vid=k00205g5xhk' # don't add proxy='auto'
url = 'http://v.qq.com/iframe/player.html?vid=i00167ai266&tiny=0&auto=0'
hutf = self.get_hutf(url)
#title, vid, mp = self.getvinfo(url)
echo(hutf)
def query_info(self, url):
#url = "http://www.dailymotion.com/embed/video/k7alsxAgBgcMGaachYS"
#url = "http://www.dailymotion.com/embed/video/k4BjypcByJGUTDl6Bvx"
hutf = self.get_hutf(url)
#echo(hutf)
# "720":[{"type":"application\/x-mpegURL","url":"http:\/\/www.dailymotion.com\/cdn\/manifest\/video\/x2hpv0i.m3u8?auth=1482432896-2562-0fq84z9d-24047244e9a36f0f3fab8388642b74c1&include=720"},{"type":"video\/mp4","url":"http:\/\/www.dailymotion.com\/cdn\/H264-1280x720\/video\/x2hpv0i.mp4?auth=1482432896-2562-pvg451ll-4c251ca9aa8a1bf6f56c88d318eccd65"}]}
m = re.search("var config = ([^\n]+);", hutf)
j = json.loads(m.group(1))
mr, mq, mu, ex = -2, '', '', ''
qua = ['auto', '144', '240', '380', '480', '720']
for k, vs in j['metadata']['qualities'].items():
if k not in qua:
echo("New qua", k)
continue
r = qua.index(k)
if r > mr:
for v in vs:
t = v.get('type', '')
if t.startswith('video/'):
mr, mq = r, k
mu = v['url']
ex = t[-3:]
echo("ext=%s, mq=%s, url=%s" % (ex, mq, mu))
title = j['metadata']['title'].strip('.')
return title, ex, [mu], None
def test1(self, args):
# http://m.bookdown.com.cn/read/31314.html
url = 'http://m.bookdown.com.cn/read/31314.html'
#hutf = self.get_hutf(url)
#print hutf
#m = re.findall("http://m.bookdown.com.cn/read/31314_\d+.html", hutf)
#print m
#hutf = self.get_html("http://m.bookdown.com.cn/read/31314_2.html")
#print(hutf)
#url = "http://m.bookdown.com.cn/read/31314_1.html"
#url = "http://m.bookdown.com.cn/read/31314_1_2.html"
while True:
print >> sys.stderr, url
hutf = self.get_hutf(url)
# class="articlecon
for div in SelStr('div.articlecon', hutf):
#echo(div)
#echo(" ".join(div.text.split(" ")))
echo(re.sub(u"分节阅读.+，请点击下一页继续阅读。", "",
re.sub(" ", " ", div.text)))
#echo(hutf)
m = re.findall(u'''<a class="btn" href="(http://m\.bookdown\.com\.cn/read/31314_.+\.html)">下一章</a>''', hutf)
#m = re.findall(u'''\<a class="btn" href=".+"\>下一章\</a\>''', hutf) #, re.U)
#echo(m)
if not m:
break
url = m[0]
def query_info(self, url):
# http://m.bookdown.com.cn/read/31314_97_2.html
hutf = self.get_hutf(url)
echo(hutf)
us = self._get_m3u8_urls(url, hutf)
#return "", "mp4", us, None
return "", "book", us, None
def query_info(self, url):
# http://m.bookdown.com.cn/read/31314_97_2.html
hutf = self.get_hutf(url)
echo(hutf)
us = self._get_m3u8_urls(url, hutf)
#return "", "mp4", us, None
return "", None, us, None
def query_info(self, url):
# title, ext, urls, totalsize
#url = "http://www.iqiyi.com/v_19rr26qr38.html"
#url = "https://www.iqiyi.com/v_19rr04z9is.html?list=19rrm106om"
#url = "https://www.iqiyi.com/v_19rr04z9is.html"
hutf = self.get_hutf(url)
for s in ('meta[name=irTitle]', 'meta[property=og:title]'):
try:
title = SelStr(s, hutf)[0]["content"]
break
except IndexError:
title = self.title
#echo(hutf)
tvid = match1(hutf, """param\['tvid'\] = "(\d+)";""")
vid = match1(hutf, """param\['vid'\] = "([^"]+)";""")
echo("tvid=", tvid, ", vid=", vid)
dat = I2().getVMS(tvid, vid)
#echo(dat)
vd, url = self.get_vd_url(dat)
#title = "%s_vd%02d" % (title, vd)
echo(title)
#return
hutf = self.get_hutf(url)
us = self._get_m3u8_urls(url, hutf)
if '.ts?' in us[0]:
return title, "ts", us, None
# title, ext, urls, totalsize
return title, None, us, None
def query_info(self, url):
url = 'http://tv.sohu.com/20110220/n279432193.shtml'
url = 'http://tv.sohu.com/20150705/n416207533.shtml'
html = self.get_html(url)
vid = mg1(r'\Wvid\s*[\:=]\s*[\'"]?(\d+)[\'"]?', html)
echo('vid =', vid)
hutf = self.get_data_by_vid(vid)
debug(hutf)
data = json.loads(hutf)
for qtyp in ["oriVid", "superVid", "highVid", "norVid", "relativeId"]:
hqvid = data['data'][qtyp]
if hqvid != 0 and hqvid != vid:
break
debug(qtyp)
data = json.loads(self.get_data_by_vid(hqvid))
debug(data)
host = data['allot']
prot = data['prot']
tvid = data['tvid']
urls = []
data = data['data']
title = data['tvName']
size = sum(data['clipsBytes'])
ret = []
for new, cu, ck in zip(data['su'], data['clipsURL'], data['ck']):
urls.append(("%s%02d.mp4" % (title, len(ret) + 1),
self.real_url(host, vid, tvid, new, cu, ck)))
debug("title=%s, size=%d" % (title, size))
debug(urls)
def query_info(self, url):
# https://vip.pp63.org/20180615/20jqyayZ/hls/index.m3u8
hutf = self.get_hutf(url)
echo(hutf)
us = self._get_m3u8_urls(url, hutf)
#return "", "mp4", us, None
return "", None, us, None
def query_info(self, url):
url = 'http://tv.sohu.com/20110220/n279432193.shtml'
url = 'http://tv.sohu.com/20150705/n416207533.shtml'
html = self.get_html(url)
vid = mg1(r'\Wvid\s*[\:=]\s*[\'"]?(\d+)[\'"]?', html)
echo('vid =', vid)
hutf = self.get_data_by_vid(vid)
debug(hutf)
data = json.loads(hutf)
for qtyp in ["oriVid", "superVid", "highVid", "norVid", "relativeId"]:
hqvid = data['data'][qtyp]
if hqvid != 0 and hqvid != vid:
break
debug(qtyp)
data = json.loads(self.get_data_by_vid(hqvid))
debug(data)
host = data['allot']
prot = data['prot']
tvid = data['tvid']
urls = []
data = data['data']
title = data['tvName']
size = sum(data['clipsBytes'])
ret = []
for new, cu, ck in zip(data['su'], data['clipsURL'], data['ck']):
urls.append(("%s%02d.mp4" % (title, len(ret) + 1),
self.real_url(host, vid, tvid, new, cu, ck)))
debug("title=%s, size=%d" % (title, size))
debug(urls)
def test(self, args):
import time
from urllib2 import urlopen
from urllib import urlencode
#url = "http://qdrama.org/k2/"
hutf = self.get_hutf(args.url)
#echo(hutf)
title = SelStr("div.title.sizing h1", hutf)[0].text
#echo("title =", title)
nodes = SelStr("div#playsource a", hutf)
cnt = 0
for node in nodes:
cnt += 1
t = "%s_%02d" % (title.encode('utf8'), cnt)
u = node['href']
if 'daily' not in u:
continue
echo(t, u)
if cnt < 0:
continue
data = urlencode({"aviurl": u,
"avitil": t,
"destdn": "../dwm/xman/",
"sub": "Start"})
urlopen("http://127.0.0.1:8080/", data).read()
time.sleep(2)
def query_info(self, m3u8url):
hutf = self.get_hutf(m3u8url)
#echo(hutf)
#url = "https://www.y3600.com/hanju/2017/1017.html"
m = re.findall('''var redirecturl = "(.+)";''', hutf)
if m:
echo(m)
b = m[0]
m = re.findall('''var main = "(.+index.m3u8.+)";''', hutf)
echo(m)
m3u8url = b + m[0]
us = self.try_m3u8(m3u8url)
#echo(us)
#if len(us) == 1:
# t, s = get_kind_size(us[0])
# if t == 'm3u8':
# us = self.try_m3u8(us[0])
#us = self._read_m3u8(m3u8url)
#print(us)
#us = self._read_m3u8(us[0])
#print(us)
return "", None, us, None
def get_stream(self, data):
for dat in self.stream_types:
for ss in data['stream']:
if dat[0] == ss['stream_type']:
echo(dat)
return dat[0], dat[1], ss
echo(data)
def query_info(self, url):
# title, ext, urls, totalsize
#url = "http://www.iqiyi.com/v_19rr26qr38.html"
#url = "https://www.iqiyi.com/v_19rr04z9is.html?list=19rrm106om"
#url = "https://www.iqiyi.com/v_19rr04z9is.html"
hutf = self.get_hutf(url)
for s in ('meta[name=irTitle]',
'meta[property=og:title]'):
try:
title = SelStr(s, hutf)[0]["content"]
break
except IndexError:
title = self.title
#echo(hutf)
tvid = match1(hutf, """param\['tvid'\] = "(\d+)";""")
vid = match1(hutf, """param\['vid'\] = "([^"]+)";""")
echo("tvid=", tvid, ", vid=", vid)
dat = I2().getVMS(tvid, vid)
#echo(dat)
vd, url = self.get_vd_url(dat)
#title = "%s_vd%02d" % (title, vd)
echo(title)
#return
hutf = self.get_hutf(url)
us = self._get_m3u8_urls(url, hutf)
if '.ts?' in us[0]:
return title, "ts", us, None
# title, ext, urls, totalsize
return title, None, us, None
def query_info(self, url):
uid = match1(url, '''openload.co/embed/([^/]+)''')
hutf = self.chrome_hutf(url)
vid = match1(hutf, r'>(%s[^<]+)<' % uid)
url = "https://openload.co/stream/%s?mime=true" % vid
echo(url)
return self.title, None, [url], None
def query_info(self, url):
hutf = self.get_hutf(url)
debug(hutf)
title = SelStr('title', hutf)[0].text
k = None
if title.endswith('.mp4'):
title, k = title[:-4], 'mp4'
#url = "https://www.rapidvideo.com/embed/FUZ35WDLM7"
# https://www3731.playercdn.net/187/0/G4i-UJ6bQxIZI6FWc_F5dg/1536365722/180905/692FUZ37O792IXDCUZDFX.mp4
v = SelStr("video#videojs source", hutf)
if v:
u = v[0]["src"]
return title, k, [u], None
#url = 'https://www.rapidvideo.com/embed/ZsNSciBj'
# https://admkis.playercdn.net/85/1/sQ52oTwwZ6vCo3Vk7-RS2g/1482741547/161202/063k10VmKldzoX8.mp4
hutf = self.get_hutf(url, postdata='block=1')
data = match1(hutf, 'jwplayer\("home_video"\)\.setup\(([^\(\)]+)\);')
debug(data)
data = match1(data, '"sources":\s*(\[[^\[\]]+\])')
ml, u = 0, ''
for src in json.loads(data):
l = src['label']
if l not in self.labels:
echo("new label", l)
i = self.labels.index(l)
if i > ml:
ml, u = i, src['file']
debug(title, u)
return title, k, [u], None
def handle_sp_list(self, url):
# serial play list
urls = []
# http://www.bilibili.com/sp/维京传奇
# base.special.js line 25, loadBgmPage
# http://www.bilibili.com/sppage/bangumi-21542-913-1.html
# first find 21542
hutf = self.get_hutf(url)
#echo(hutf)
spid = search_first(hutf, 'var spid = "(\d+)";').group(1)
echo("spid=", spid)
for li in SelStr('ul#season_selector li', hutf):
data = self.get_hutf("http://www.bilibili.com/sppage/bangumi-%s-%s-1.html" % (
spid, li['season_id']))
for n in SelStr('div.season_list li a.t', data):
urls.append((n['title'].strip(),
'http://www.bilibili.com' + n['href']))
args = copy(self.parsed_args)
sk = args.playlist_skip
args.playlist_skip = -1315
tp = args.playlist_top
args.playlist_top = 0
cnt = 0
for t, u in urls:
cnt = cnt + 1
if cnt > tp > 0:
break
if cnt < sk:
continue
echo(t, u)
b = BILIBILI()
b.title = t
args.url = u
run(b, args)
sys.exit(1)
def query_info(self, url):
hutf = self.get_hutf(url)
debug(hutf)
title = SelStr('title', hutf)[0].text
k = None
if title.endswith('.mp4'):
title, k = title[:-4], 'mp4'
#url = "https://www.rapidvideo.com/embed/FUZ35WDLM7"
# https://www3731.playercdn.net/187/0/G4i-UJ6bQxIZI6FWc_F5dg/1536365722/180905/692FUZ37O792IXDCUZDFX.mp4
v = SelStr("video#videojs source", hutf)
if v:
u = v[0]["src"]
return title, k, [u], None
#url = 'https://www.rapidvideo.com/embed/ZsNSciBj'
# https://admkis.playercdn.net/85/1/sQ52oTwwZ6vCo3Vk7-RS2g/1482741547/161202/063k10VmKldzoX8.mp4
hutf = self.get_hutf(url, postdata='block=1')
data = match1(hutf, 'jwplayer\("home_video"\)\.setup\(([^\(\)]+)\);')
debug(data)
data = match1(data, '"sources":\s*(\[[^\[\]]+\])')
ml, u = 0, ''
for src in json.loads(data):
l = src['label']
if l not in self.labels:
echo("new label", l)
i = self.labels.index(l)
if i > ml:
ml, u = i, src['file']
debug(title, u)
return title, k, [u], None
def query_info(self, url):
# https://vip.pp63.org/20180615/20jqyayZ/hls/index.m3u8
hutf = self.get_hutf(url)
echo(hutf)
#us = self._get_m3u8_urls(url, hutf)
us = self.try_m3u8(url)
return "", None, us, None
def test(self, args):
url = "https://www.shuquge.com/txt/12236/46252712.html"
hutf = open("s1.html").read().decode('utf8')
#hutf = self.get_hutf(url)
#echo(hutf)
#ct = SelStr("div.content", hutf)[0]
echo(ct.text)
def query_info(self, url):
#'http://www.le.com/ptv/vplay/1877906.html?ch=sougou_mfdy&fromvsogou=1'
html = self.get_html(url)
hutf = html.decode('utf8')
if re.match(r'http://www.le.com/ptv/vplay/(\d+).html', url):
vid = match1(url, r'http://www.le.com/ptv/vplay/(\d+).html')
elif re.match(r'http://www.letv.com/ptv/vplay/(\d+).html', url):
vid = match1(url, r'http://www.letv.com/ptv/vplay/(\d+).html')
else:
vid = match1(hutf, r'vid="(\d+)"')
title = match1(hutf, r'name="irTitle" content="(.*?)"')
echo("vid =", vid)
echo("title =", title)
tkey = calcTimeKey(int(time.time()))
u = 'http://api.letv.com/mms/out/video/playJson?'
u = u + ("id=%s&platid=1&splatid=101&format=1" % vid)
u = u + ("&tkey=%d&domain=www.letv.com" % tkey)
#u = u + ("&tkey=%d&domain=www.le.com" % tkey)
data = self.get_html(u)
info = json.loads(data.decode("utf-8"))
stream_id = None
kwargs = {}
support_stream_id = info["playurl"]["dispatch"].keys()
si = kwargs.get("stream_id", "")
if self.is_playlist:
si = kwargs.get("stream_id", "720p")
else:
si = kwargs.get("stream_id", "1080p")
if si and si.lower() in support_stream_id:
stream_id = si
else:
echo("Current Video Supports:")
for i in support_stream_id:
echo("\t--format", i, "<URL>")
if "1080p" in support_stream_id:
stream_id = '1080p'
elif "720p" in support_stream_id:
stream_id = '720p'
else:
sids = sorted(support_stream_id, key=lambda i: int(i[1:]))
stream_id = sids[-1]
echo("stream_id =", stream_id)
u2 = info["playurl"]["domain"][0]
u2 = u2 + info["playurl"]["dispatch"][stream_id][0]
ext = info["playurl"]["dispatch"][stream_id][1].split('.')[-1]
u2 = u2 + "&ctv=pc&m3v=1&termid=1&format=1&hwtype=un&ostype=Linux"
u2 = u2 + ("&tag=letv&sign=letv&expect=3&tn=%d" % random.random())
u2 = u2 + ("&pay=0&iscpn=f9051&rateid=%s" % stream_id)
r2 = self.get_html(u2)
info2 = json.loads(r2.decode("utf-8"))
m3u8 = self.get_html(info2["location"])
m3u8_list = decode_m3u8(bytearray(m3u8))
us = re.findall(r'^[^#][^\r]*', m3u8_list, re.MULTILINE)
#return title, ext, us, None
return title, None, us, None
def query_info(self, url):
# http://www.tudou.com/albumplay/zgdaPAjRz1s/8cUPFUj8sl4.html
hutf = self.get_hutf(url)
vcode = match1(hutf, U("vcode:\s*'([^']+)',\s*lan\:\s*'粤语'"))
echo("vcode", vcode)
yu = "http://youku.com/v_show/id_" + vcode
#return title, None, [url], None
return YOUKU().query_info(yu)
def test1(self, argv):
url = 'http://vmus.online/the-outpost-s01.html'
#hutf = self.chrome_hutf(url)
hutf = self.get_hutf(url)
#echo(hutf)
ret = SelStr("a.fasc-button", hutf)
#ret = [str(a) for a in ret]
ret = [(0, a['href']) for a in ret]
echo(ret)
def test1(self, argv):
mu = self.get_m3u8(argv.url)
echo(mu)
sect, tvid, ptid = self.get_stp(argv.url)
u = 'https://www.kantv6.com/index.php/video/part'
u = '%s?tvid=%s' % (u, tvid)
dat = self.get_hutf(u)
dat = json.loads(dat)
debug(json.dumps(dat, indent=2))
def test(self, argv):
url = 'https://www.dnvod.tv/Movie/detail.aspx?id=TEee8%2fITNg4%3d'
url = 'https://www.dnvod.tv/Movie/Readyplay.aspx?id=OIfaQTVHEiA%3d'
ru = 'http://server3.dnvod.tv/hvod/lxj-tscgwlb-50-022061041.mp4?sourceIp=154.20.114.142&signature=856ddbf8ecd34fb9b3aae7ad4c8beddf.56b9f1609633f7eacbc18ecd0dd5e4be&start=1536543792.79147&custom=0&ua=62e66f1213d2881d9f80510593ffe2ec'
#ru = 'http://server3.dnvod.tv/hvod/lxj-tscgwlb-50-022061041.mp4'
url = "https://www.dnvod.tv/play?id=TW29RCmFL4o%3D"
#hutf = self.get_hutf(url)
hutf = self.chrome_hutf(url)
echo(hutf)
def test(self, argv):
url = 'https://www.dnvod.tv/Movie/detail.aspx?id=TEee8%2fITNg4%3d'
url = 'https://www.dnvod.tv/Movie/Readyplay.aspx?id=OIfaQTVHEiA%3d'
ru = 'http://server3.dnvod.tv/hvod/lxj-tscgwlb-50-022061041.mp4?sourceIp=154.20.114.142&signature=856ddbf8ecd34fb9b3aae7ad4c8beddf.56b9f1609633f7eacbc18ecd0dd5e4be&start=1536543792.79147&custom=0&ua=62e66f1213d2881d9f80510593ffe2ec'
#ru = 'http://server3.dnvod.tv/hvod/lxj-tscgwlb-50-022061041.mp4'
url = "https://www.dnvod.tv/play?id=TW29RCmFL4o%3D"
#hutf = self.get_hutf(url)
hutf = self.chrome_hutf(url)
echo(hutf)
def test(self, args):
#url = 'https://www.youtube.com/watch?v=dF2X2Bl9fps'
#'https://www.youtube.com/watch?v=dF2X2Bl9fps&pbj=1'
hutf = self.get_hutf(args.url)
#dat = parse_qs(unquote(hutf))
#echo(json.dumps(dat, indent=2))
#echo(hutf)
# <meta name="title" content="心經唱誦36次 -齊豫居士">
ret = match1(hutf, '\<meta name="title" content="([^"]+)"\>')
echo(repr(ret))
def test(self, args):
'''
curl 'https://s8-e1.dnvodcdn.me/cdn/_definst_/mp4:s8/jvod/xj-csywm-480p-011A7CB68.mp4/chunklist.m3u8?dnvodendtime=1630365931&dnvodhash=UdJqjguhoxl8IjH7zE3VmVYSt1lmRk7jfX4VhHl-sME=&dnvodCustomParameter=0_64.180.112.212.CA_1&lb=4e0618fc4b0ea2e45d57e6ea11efb267&us=1&vv=d1a310cefe1e3333a2b6021eb7e5e9fd&pub=CJOpC34vCp4oEIusD3KnCryXeAzDZGkCJWmBZ4nCYuoCJ9VP3CpCpKmCZanC3CpD3OuD64oC3SnOZOnP34rCpKpEJXVEJ5XPZHcPcDcPMGuOs8sOpHbC39cOZOnOpGvD68pEM5' -H 'authority: s8-e1.dnvodcdn.me' -H 'pragma: no-cache' -H 'cache-control: no-cache' -H 'sec-ch-ua: "Chromium";v="92", " Not A;Brand";v="99", "Google Chrome";v="92"' -H 'sec-ch-ua-mobile: ?0' -H 'user-agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.131 Safari/537.36'
'''
'''
https://www.ifsp.tv/play?id=h0zrX16TdlV
'''
url = 'https://www.ifsp.tv/play?id=m0IXOmqu894'
url = 'https://s8-e1.dnvodcdn.me/cdn/_definst_/mp4:s8/jvod/xj-csywm-480p-011A7CB68.mp4/chunklist.m3u8?dnvodendtime=1630365931&dnvodhash=UdJqjguhoxl8IjH7zE3VmVYSt1lmRk7jfX4VhHl-sME=&dnvodCustomParameter=0_64.180.112.212.CA_1&lb=4e0618fc4b0ea2e45d57e6ea11efb267&us=1&vv=d1a310cefe1e3333a2b6021eb7e5e9fd&pub=CJOpC34vCp4oEIusD3KnCryXeAzDZGkCJWmBZ4nCYuoCJ9VP3CpCpKmCZanC3CpD3OuD64oC3SnOZOnP34rCpKpEJXVEJ5XPZHcPcDcPMGuOs8sOpHbC39cOZOnOpGvD68pEM5'
url = 'https://s8-e1.dnvodcdn.me/cdn/_definst_/mp4:s8/jvod/xj-csywm-480p-011A7CB68.mp4/chunklist.m3u8?dnvodendtime=1630365740&dnvodhash=otFp1V-_aeahcOjnMSbBLDfxVITK4IK95JzEJvtIaeg=&dnvodCustomParameter=0_64.180.112.212.CA_1&lb=4e0618fc4b0ea2e45d57e6ea11efb267&us=1&vv=93e0e71677f8618bd245507435fe10d8&pub=CJOpC34vCZapE2utDJ4uD5yXeAzDZGkCJWmBZ4nCYuoCJ9VC6KoD6OpDc8mE6KnD65bE3bYOc9cOJHbEJ9XCZTZDMHVDZWpD3GmDZPbOJatPZDZCJOrPM4vPcCtE65ZDZCoDJ7'
echo(self.get_hutf(url))
def test(self, args):
url = "http://www.tudou.com/albumplay/zgdaPAjRz1s/8cUPFUj8sl4.html"
#youku = "http://youku.com/v_show/id_XNzYxNzM0MDk2"
#,vcode: 'XNzYxNzM0MDk2'
hutf = self.get_hutf(url)
#vcode = match1(hutf, "vcode:\s*'([^']+)'")
vcode = match1(hutf, U("vcode:\s*'([^']+)',\s*lan\:\s*'粤语'"))
#vcode = match1(hutf, "id:\s*3\s*,\s*vcode:\s*'([^']+)',\s*lan:")
echo("vcode", vcode)
yu = "http://youku.com/v_show/id_" + vcode
echo(YOUKU().query_info(yu))
def query_info(self, url):
# http://8drama.com/122804/
#http://8drama.net/ipobar_.php?sign=251438...
echo('phantomjs wait ...')
p = Popen(["./phantomjs", "dwm.js", "300", url], stdout=PIPE)
html = p.stdout.read()
hutf = html.decode('utf8')
p.wait()
url = SelStr('video source', hutf)[0]['src']
title = SelStr('h1.entry-title', hutf)[0].text
return title, None, [url], None
def query_info(self, url):
# http://8drama.com/122804/
#http://8drama.net/ipobar_.php?sign=251438...
echo('phantomjs wait ...')
p = Popen(["./phantomjs", "dwm.js", "300", url], stdout=PIPE)
html = p.stdout.read()
hutf = html.decode('utf8')
p.wait()
url = SelStr('video source', hutf)[0]['src']
title = SelStr('h1.entry-title', hutf)[0].text
return title, None, [url], None
def post_one(fn, conn, dst):
echo(fn)
#conn = HTTPConnection(ip, port)
bun = "-----------------12123135---61b3e9bf8df4ee45---------------"
fo = UpFile(fn, 'attachment', bun)
headers = {"Content-Type": "multipart/form-data; boundary=%s" % bun,
"Content-Length": str(fo.size()),
}
conn.request("POST", dst, fo, headers)
resp = conn.getresponse()
#print
echo(resp.status, resp.reason)
def test(self, args):
'''
wget -U 'Mozilla/5.0 (X11; Linux i686) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.109 Safari/537.36' -O 10_4.mp4 --header="Referer: http://video66.org/embed.php?w=798&h=449&vid=vids4/w_2016_-_10_clip4.mp4" "http://gateway.play44.net:3010/old/w_2016_-_10_clip4.mp4?st=MTJmZmQ1Yzc0ODM4ZDg5ZWQ4MmMyOTc4NDEyZDRlYzU&e=1497829689"
'''
url = "http://video66.org/embed.php?w=798&h=449&vid=vids4/w_2016_-_10_clip4.mp4"
hutf = self.get_hutf(url)
m = re.search("player\.load\(\{\s+file: \"([^\"]+)\",\s+image\:", hutf)
if m:
u = m.group(1)
echo(u)
self.extra_headers['Referer'] = url
html = self.get_html(u)
def login_hutf(self, url):
# then we try to login
#url = 'http://vmus.co/%E9%99%90%E5%88%B6%E7%B4%9A%E6%AF%92%E6%A2%9F-narcos-%E7%AC%AC%E4%B8%80%E5%AD%A3-%E7%AC%AC%E4%BA%94%E9%9B%86-s01e05-%E7%B7%9A%E4%B8%8A%E7%9C%8B-%E7%B0%A1%E4%B8%AD%E8%8B%B1%E5%AD%97%E5%B9%95/'
#post_data = 'log=vm16&pwd=vm16&wp-submit=%E5%85%8D%E8%A8%BB%E5%86%8A%E7%99%BB%E5%85%A5%28%E6%96%B9%E6%B3%95%E8%AB%8B%E8%A6%8B%E4%B8%8A%E6%96%B9%E8%AA%AA%E6%98%8E%29+%C2%BB&redirect_to=%2F%25E9%2599%2590%25E5%2588%25B6%25E7%25B4%259A%25E6%25AF%2592%25E6%25A2%259F-narcos-%25E7%25AC%25AC%25E4%25B8%2580%25E5%25AD%25A3-%25E7%25AC%25AC%25E4%25BA%2594%25E9%259B%2586-s01e05-%25E7%25B7%259A%25E4%25B8%258A%25E7%259C%258B-%25E7%25B0%25A1%25E4%25B8%25AD%25E8%258B%25B1%25E5%25AD%2597%25E5%25B9%2595%2F'
up = "vm%02d" % random.randint(1, 30)
echo(up)
post_data = "log=%s&pwd=%s&wp-submit=" % (up, up)
post_data = post_data + "%E5%85%8D%E8%A8%BB%E5%86%8A%E7%99%BB%E5%85%A5%28%E6%96%B9%E6%B3%95%E8%AB%8B%E8%A6%8B%E4%B8%8A%E6%96%B9%E8%AA%AA%E6%98%8E%29+%C2%BB&redirect_to="
post_data = post_data + urllib.quote(url)
html = self.get_html(self.login_url, postdata=post_data)
hutf = html.decode('utf8')
return hutf
def query_info(self, url):
hutf = self.get_hutf(url)
#echo(hutf)
title = SelStr("div.title.sizing h1", hutf)[0].text
#echo("title =", title)
nodes = SelStr("div#playsource a", hutf)
urls = []
dm = DM()
for node in nodes:
t, e, us, s = dm.query_info(node['href'])
echo(us)
urls += us
return title, None, urls, None
def qi2(self, hutf):
# http://www.dianyingbar.com/11184.html
ret = re.findall("videoarr.push\('YKYun\.php\?id\=([^\(\)]+)'\)", hutf)
echo(ret)
ns = SelStr('article.article-content > p > strong', hutf)
title = ns[0].text
urls = []
tsize = 0
for vid in ret:
url = 'https://vipwobuka.dianyingbar.com:998/api/yUrl.php?id=%s&type=mp4' % vid
#self.extra_headers['Referer'] = 'https://vipwobuka.dianyingbar.com:998/ckplayer/YKYun.php?id=' + vid
urls.append(url)
break
#echo("title=", title, 'mp4')
return title, 'mp4', urls, None
def qi2(self, hutf):
# http://www.dianyingbar.com/11184.html
ret = re.findall("videoarr.push\('YKYun\.php\?id\=([^\(\)]+)'\)", hutf)
echo(ret)
ns = SelStr('article.article-content > p > strong', hutf)
title = ns[0].text
urls = []
tsize = 0
for vid in ret:
url = 'https://vipwobuka.dianyingbar.com:998/api/yUrl.php?id=%s&type=mp4' % vid
#self.extra_headers['Referer'] = 'https://vipwobuka.dianyingbar.com:998/ckplayer/YKYun.php?id=' + vid
urls.append(url)
break
#echo("title=", title, 'mp4')
return title, 'mp4', urls, None
def get_vd_url(self, dat):
for vd in (4, # TD: '720p'
17, # TD_H265': 720p H265
2, # HD: '540p'
5, # BD: 1080p
):
for stream in dat['data']['vidl']:
if vd == stream["vd"]:
echo("4, 17, 2, 5, vd =", vd)
url = stream['m3u']
return vd, url
else:
vd = dat['data']['vidl'][0]['vd']
#echo("vd =", dat['data']['vidl'][0]['vd'])
url = dat['data']['vidl'][0]['m3u']
return vd, url
def get_playlist(self, url):
#url = 'https://www.dnvod.eu/Movie/detail.aspx?id=NU%2bOQHwQObI%3d'
#url = 'https://www.dnvod.eu/Movie/Readyplay.aspx?id=deYM01Pf0bo%3d'
#hutf = self.get_hutf(url)
#debug(hutf)
#for a in SelStr('ul[data-identity=guest] > li > div.bfan-n > a', hutf):
# debug(a.text, a['href'])
# urls.append((a.text, 'https://www.dnvod.eu' + a['href']))
hutf = self.chrome_hutf(url)
urls = []
for a in SelStr('ul[data-identity=guest] > li > div.bfan-n > div.bfan-n > a', hutf):
#debug(a.text, a['href'])
#urls.append((a.text, 'https://www.dnvod.eu/Movie/' + a['href']))
urls.append((self.title, 'https://www.dnvod.tv/Movie/' + a['href']))
echo(urls)
return urls
def read(self, bufsize):
#FIXME, if bufsize < len(self.pre) or bufsize < len(self.end)
if self.s == 0:
self.s = 1
#print '#',
return self.pre
if self.s == 1:
buf = self.f.read(bufsize)
if buf:
#print '#',
self.cnt += len(buf)
sys.stdout.write("\r%0.1f" % (self.cnt * 100.0 / self.tal))
return buf
self.s = 2
echo("")
return self.end
return ""
def query_info(self, url):
hutf = self.chrome_hutf(url)
#echo(hutf)
title = SelStr("html head title", hutf)[0].text
echo("title =", title)
ret = SelStr("video#video_player", hutf)
echo(ret)
if ret:
u = ret[0]["src"]
return title, None, [u], None
#return
ci = get_ci(DEBUG)
try:
return self.query_info_chrome(ci, url)
finally:
print("ci.stop()")
ci.stop()
def getvinfo(self, url, fmt='shd'):
hutf = self.get_hutf(url)
#echo(hutf)
ss = SelStr('script[r-notemplate=true]', hutf)
for s in ss:
if 'VIDEO_INFO' in s.text:
data = s.text
break
match = re.search('var\s+COVER_INFO\s?=\s?({[^;]+);', data)
cover_info = to_dict(match.group(1))
match = re.search('var\s+VIDEO_INFO\s?=\s?({[^;]+);', data)
video_info = to_dict(match.group(1))
title = video_info['title']
vid = video_info['vid']
echo('title =', title, 'vid =', vid)
mp = self.get_vinfo_do(url, vid, fmt)
return title, vid, mp
def test(self, args):
url = "http://www.bookdown.com.cn/bookinfo/30258.html"
#url = "http://www.bookdown.com.cn/read/30258_1.html"
ret = match1(url, "/bookinfo/(\d+)\.html", "/read/(\d+).*\.html")
bid = int(ret[0])
echo("bid =", bid)
url = "http://www.bookdown.com.cn/read/%d_1.html" % bid
while True:
#print >> sys.stderr, url
hutf = self.get_hutf(url)
#echo(hutf)
for div in SelStr('div#view_content_txt', hutf):
echo(re.sub(u"分节阅读.+，请点击下一页继续阅读。", "",
re.sub(" ", " ", div.text)))
al = SelStr("a#nextPage", hutf)
if not al:
break
url = al[0]['href']
def query_info(self, url):
# return title, ext, urls, size
vid = self.get_vid_from_url(url)
echo("vid =", vid)
api_url = 'http://play.youku.com/play/get.json?vid=%s&ct=12' % vid
hutf = self.get_hutf(api_url)
meta = json.loads(hutf)
data12 = meta['data']
data = data12
debug(data)
title = data['video']['title']
sec_ep = data12['security']['encrypt_string']
sec_ip = data12['security']['ip']
echo(title, sec_ep, sec_ip)
stype, ext, stm = self.get_stream(data)
# get url list
e_code = self.trans_e(self.f_code_1,
base64.b64decode(sec_ep.encode('ascii')))
#base64.b64decode(bytes(sec_ep, 'ascii')) )
sid, token = e_code.split('_')
echo(sid, token)
urls = []
streamfileid = stm['stream_fileid']
for no, seg in enumerate(stm['segs'], 0):
k = seg['key']
if k == -1:
raise # we hit the paywall; stop here
fileid = "%s%02X%s" % (streamfileid[0:8], no, streamfileid[10:])
ep = self.generate_ep(fileid, sid, token)
q = parse.urlencode(dict(
ctype = self.ctype,
ev = 1,
K = k,
ep = parse.unquote(ep),
oip = str(sec_ip),
token = token,
yxon = 1
))
u = 'http://k.youku.com/player/getFlvPath/sid/{sid}_00' \
'/st/{container}/fileid/{fileid}?{q}'.format(
sid = sid,
container = ext,
fileid = fileid,
q = q
)
html = self.get_html(u, True)
for i in json.loads(html.decode("utf8")):
echo(i['server'])
urls.append(i['server'])
k, size = self.get_total_size(urls)
return title, ext, urls, size
def get_playlist(self, page_url):
#http://www.iqiyi.com/playlist521743802.html
if '/playlist' in page_url:
hutf = self.get_hutf(page_url)
els = SelStr("div.site-piclist_pic > a.site-piclist_pic_link",
hutf)
return [(e['title'], e['href']) for e in els]
# http://www.iqiyi.com/a_19rrhb9eet.html 太阳的后裔
echo("get_list phantomjs wait 200 ...")
p = Popen(["./phantomjs", "dwm.js", "200", page_url], stdout=PIPE)
html = p.stdout.read()
p.wait()
hutf = html.decode("utf8")
#c = hutf.split("<!--视频列表区域 -->")[1]
urls = [(a.text, a['href'])
for a in SelStr('div.smalList > ul > li > a', hutf)]
self.align_num = len(str(len(urls)))
return urls
def query_info(self, url):
#url = 'http://www.ttwanda.com/films/us/1693.html?xf'
hutf = self.get_hutf(url)
if '?' not in url:
a = SelStr('section.p5 div a', hutf)[0]['href']
url = url + a
hutf = self.get_hutf(url)
title = SelStr("div.video-content article p strong", hutf)[0].text
r = "《(.+)》"
if not py3:
r = r.decode('utf8')
t = match1(title, r)
if t and '/films/' in url:
title = t
src = SelStr('iframe.player', hutf)[0]['src']
if '/player/v.php?url=' in src:
# http://www.ttwanda.com/tv/ustv/945.html
# ../../player/v.php?url=www.le.com/ptv/vplay/20723618.html
src = 'http://' + src.split('?url=', 1)[1]
from letv import LETV
return LETV().query_info(src)
if not src.startswith("http://") and not src.startswith("https://"):
src = 'http://www.ttwanda.com/' + src
echo(src)
self.extra_headers['Referer'] = url # this is important
hutf = self.get_hutf(src)
dst = match1(hutf, 'var play_url \= "([^"]+)"')
echo(dst)
if not dst:
echo("Can not find var play_url")
sys.exit(1)
if ('youku.com/' in dst and '/m3u8' in dst) \
or 'lecloud.com/' in dst \
or '/letv-uts/' in dst:
return title, None, self.try_m3u8(dst), None
if 'ttwanda.com/ftn_handler/' in dst:
cs = ["%s=%s" % (c.name, c.value)
for c in self.cookie.cookiejar
if c.name != 'PHPSESSID']
echo(cs)
self.wget_cookie = "; ".join(cs)
k, s = get_kind_size(dst, self.wget_cookie)
return title, k, [dst], s
#if 'mgtv.com/' in dst or '189.cn/v5/downloadFile' in dst:
# # http://www.ttwanda.com/films/us/907.html?style=cq
# return title, None, [dst], None
#echo('TTWanda has new source')
#echo(dst)
#sys.exit(1)
return title, None, [dst], None
