def fetch_mozecname(vid):
# vid: seems non-interrelated with result
global mozecname
if len(mozecname) == 4:
return
digits = list(
'0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ')
def i2b(d):
if base == 10:
return str(d)
b = []
while d:
d, m = divmod(d, base)
b.append(digits[m])
return ''.join(b[::-1]) or '0'
def b2i(text):
try:
i = int(text, base)
except ValueError:
i = p = 0
for d in text[::-1]:
i += digits.index(d) * base**p
p += 1
return i
def encrypt(text):
'''fake, only for existed texts'''
return i2b(keys_dict[text])
def decrypt(text):
return keys_list[b2i(text)] or text
html = get_content('https://m.fun.tv/vplay/?vid=' + vid)
for path in matchall(html[:html.find('</head>')],
'src="(/static/js/v12/pkg/m\w{4}_v12_\w{9}.js)"'):
js = get_content('https://m.fun.tv' + path).strip()
crypt, base, _, keys, sep = re.search(
r"}\('(.+?)[^\\]',(\d+),(\d+),'(.+?)'\.split\('(.)'", js).groups()
base = int(base)
keys_list = keys.split(sep)
keys_dict = {k: i for i, k in enumerate(keys_list)}
pattern = '\\.'.join(
encrypt(text)
for text in ['document', 'mozEcName', 'push']) + '\("(\w+)'
mozecname += [decrypt(text) for text in matchall(crypt, pattern)]
site.logger.debug('mozEcName: %s', mozecname)
mozecname = {int(m[-1]): int(m[:-1], 16) for m in mozecname}
def get_vid_title(self):
av_id = match1(self.url, '(?:/av|aid=)(\d+)')
page_index = '1'
if "#page=" in self.url or "?p=" in self.url or 'index_' in self.url:
page_index = match1(self.url, '(?:#page|\?p)=(\d+)',
'index_(\d+)\.')
if page_index == '1':
self.url = 'https://www.bilibili.com/av{}/'.format(av_id)
else:
self.url = 'https://www.bilibili.com/av{}/?p={}'.format(
av_id, page_index)
if not self.vid:
html = get_content(self.url)
#vid = match1(html, 'cid=(\d+)', 'cid="(\d+)', '"cid":(\d+)')
title = match1(html, '"title":"([^"]+)', '<h1 title="([^"]+)',
'<title>([^<]+)').strip()
video_list = matchall(
html,
['"cid":(\d+),"page":(\d+),"from":"[^"]+","part":"([^"]*)",'])
for cid, page, part in video_list:
if page == page_index:
vid = cid
if len(video_list) > 1:
title = u'{} - {} - {}'.format(title, page, part)
elif part:
title = u'{} - {}'.format(title, part)
break
return vid, title
def prepare_list(self):
av_id = match1(self.url, '(?:/av|aid=)(\d+)')
self.url = 'https://www.bilibili.com/av{}/'.format(av_id)
html = get_content(self.url)
video_list = matchall(html, ['"page":(\d+),'])
if video_list:
return ['https://www.bilibili.com/av{}/?p={}'.format(av_id, p) for p in video_list]
def get_realurl(url):
location = get_location(url)
if location != url:
return location
else:
html = get_content(url)
return matchall(html, ['CDATA\[([^\]]+)'])[1]
def prepare(self):
info = VideoInfo(self.name)
if not self.vid:
self.vid = match1(self.url, '#([a-zA-Z0-9\-]+)',
'/([a-zA-Z0-9\-]+).shtml')
if not self.vid:
html = get_content(self.url)
self.vid = match1(html, '"vid": "([^"]+)', 'vid: "([^"]+)')
xml = get_content(
'http://vxml.ifengimg.com/video_info_new/{}/{}/{}.xml'.format(
self.vid[-2], self.vid[-2:], self.vid))
info.title = match1(xml, 'SE_Title="([^"]+)')
urls = matchall(xml, 'playurl="([^"]+)')
urls = ['http://ips.ifeng.com/' + u[7:] for u in urls]
info.stream_types.append('current')
info.streams['current'] = {
'container': 'mp4',
'video_profile': 'current',
'src': urls,
'size': 0
}
return info
def prepare(self):
info = VideoInfo(self.name)
if self.url and not self.vid:
vid = matchall(self.url, ['curid=([^_]+)_([\w]+)'])
if vid:
self.vid = vid[0]
info_u = 'http://mixer.video.iqiyi.com/jp/mixin/videos/' + self.vid[
0]
mixin = get_content(info_u)
mixin_json = json.loads(mixin[len('var tvInfoJs='):])
real_u = mixin_json['url']
real_html = get_content(real_u)
info.title = match1(real_html, '<title>([^<]+)').split('-')[0]
if self.url and not self.vid:
html = get_content(self.url)
video_info = match1(html, ":video-info='(.+?)'")
if video_info:
video_info = json.loads(video_info)
self.vid = str(video_info['tvId']), str(video_info['vid'])
info.title = video_info['name']
else:
tvid = match1(html, 'data-player-tvid="([^"]+)"',
'tvid="(.+?)"', 'tvId:([^,]+)',
r'''param\['tvid'\]\s*=\s*"(.+?)"''',
r'"tvid":\s*"(\d+)"')
videoid = match1(html, 'data-player-videoid="([^"]+)"',
'vid="(.+?)"', 'vid:"([^"]+)',
r'''param\['vid'\]\s*=\s*"(.+?)"''',
r'"vid":\s*"(\w+)"')
self.vid = (tvid, videoid)
info.title = match1(html, '<title>([^<]+)').split('-')[0]
tvid, vid = self.vid
vps_data = getvps(tvid, vid)
assert vps_data['code'] == 'A00000', 'can\'t play this video!!'
url_prefix = vps_data['data']['vp']['du']
stream = vps_data['data']['vp']['tkl'][0]
vs_array = stream['vs']
for vs in vs_array:
bid = vs['bid']
fs_array = vs['fs']
real_urls = []
for seg_info in fs_array:
url = url_prefix + seg_info['l']
json_data = json.loads(get_content(url))
down_url = json_data['l']
real_urls.append(down_url)
stream = self.vd_2_id[bid]
info.stream_types.append(stream)
stream_profile = self.id_2_profile[stream]
info.streams[stream] = {
'video_profile': stream_profile,
'container': 'flv',
'src': real_urls,
'size': 0
}
info.stream_types = sorted(info.stream_types, key=self.ids.index)
return info
def prepare(self):
info = VideoInfo(self.name)
id1 = match1(self.url, 'a/([^\.]+)\.')
api1 = 'http://www.kankanews.com/vxml/{}.xml'.format(id1)
video_data1 = get_content(api1)
self.vid = match1(video_data1, '<omsid>([^<]+)<')
if self.vid == '0' or not self.vid:
html = get_content(self.url)
id1 = match1(html, 'xmlid=([^\"]+)') or match1(
html, 'embed/([^\"]+)').replace('_', '/')
api1 = 'http://www.kankanews.com/vxml/{}.xml'.format(id1)
video_data1 = get_content(api1)
self.vid = match1(video_data1, '<omsid>([^<]+)<')
assert self.vid != '0' and self.vid, self.url + ': Not a video news link!'
api2 = 'http://vapi.kankanews.com/index.php?app=api&mod=public&act=getvideo&id={}'.format(
self.vid)
video_data2 = get_content(api2)
urls = matchall(video_data2, ['<videourl><!\[CDATA\[([^\]]+)'])
info.title = match1(video_data2, '<otitle><!\[CDATA\[([^\]]+)')
info.stream_types.append('current')
info.streams['current'] = {
'container': 'mp4',
'video_profile': 'current',
'src': urls,
'size': 0
}
return info
def prepare_list(self):
av_id = match1(self.url, '(?:/av|aid=)(\d+)')
self.url = 'https://www.bilibili.com/av{}/'.format(av_id)
html = get_content(self.url)
video_list = matchall(html, ['"page":(\d+),'])
if video_list:
return ['https://www.bilibili.com/av{}/?p={}'.format(av_id, p) for p in video_list]
def get_realurl(url):
location = get_location(url)
if location != url:
return location
else:
html = get_content(url)
return matchall(html, ['CDATA\[([^\]]+)'])[1]
def prepare(self):
if self.url and not self.vid:
#maybe error!!
self.vid = (vu, uu) = matchall(self.url,
["vu=([^&]+)", "uu=([^&]+)"])
return self.letvcloud_download_by_vu()
def download_playlist(self, url, param):
self.url = url
self.param = param
html = get_content(self.url)
vids = matchall(html, ['vid="(\d+)"'])
for v in vids:
self.download(v, param)
def download_playlist(self, url, param):
self.url = url
self.param = param
html = get_content(self.url)
vids = matchall(html, ['vid="(\d+)"'])
for v in vids:
self.download(v,param)
def prepare_list(self):
av_id = match1(self.url, '(?:/av|aid=)(\d+)')
if "aid=" in self.url:
self.url = 'https://www.bilibili.com/video/av' + av_id
html = get_content(self.url)
video_list = matchall(html, ['"page":(\d+),'])
if video_list:
return ['https://www.bilibili.com/av{}/index_{}.html'.format(av_id, p) for p in video_list]
def prepare_list(self):
html = get_content(self.url)
video_list = matchall(html, [',"ep_id":(\d+),'])
if video_list:
del video_list[0]
return [
'https://www.bilibili.com/bangumi/play/ep{}'.format(eid)
for eid in video_list
]
def get_url(self):
if self.url_patterns:
v_url = []
for url in matchall(self.html, self.url_patterns):
if url[:2] == '//':
url = 'http:' + url
if url not in v_url:
v_url.append(url)
self.v_url = v_url
def prepare_list(self):
# backup https://api.bilibili.com/x/player/pagelist?bvid=
vid = match1(self.url, '/(av\d+|(?:BV|bv)[0-9A-Za-z]{10})')
if vid[:2] == 'av':
vid = av2bv(vid)
html = get_content(self.url)
video_list = matchall(html, ['"page":(\d+),'])
if video_list:
return ['https://www.bilibili.com/video/{}?p={}'.format(vid, p) for p in video_list]
def prepare_list(self):
html = get_content(self.url)
eplist = match1(html, '"epList":(\[.+?\])')
if eplist:
eplist = matchall(eplist, [',"id":(\d+),'])
return [
'https://www.bilibili.com/bangumi/play/ep{}'.format(eid)
for eid in eplist
]
def get_url(self):
if self.url_patterns:
v_url = []
for url in matchall(self.html, *self.url_patterns):
if url[:2] == '//':
url = 'http:' + url
if url not in v_url:
v_url.append(url)
self.v_url = v_url
def prepare_list(self):
html = get_content(self.url)
video_list = matchall(html, ['<option value=\'([^\']*)\''])
if video_list:
return ['http://www.bilibili.com'+v for v in video_list]
sid = match1(html, 'var season_id = "(\d+)";')
j_ = get_content("http://bangumi.bilibili.com/jsonp/seasoninfo/{}.ver".format(sid))
s_data = json.loads(j_)
urls = [e['webplay_url'] for e in sorted(s_data['result']['episodes'], key=lambda e: e['index'])]
return urls
def prepare_list(self):
html = get_content(self.url)
eplist = matchall(html, ['"epList":(\[.*?\])'])
if eplist:
eplist = sum(
map(matchall, eplist, [[',"id":(\d+),']] * len(eplist)), [])
return [
'https://www.bilibili.com/bangumi/play/ep{}'.format(eid)
for eid in eplist
]
def prepare(self):
info = VideoInfo(self.name)
if self.url:
html = get_content(self.url)
self.vid = match1(html, 'playVideo\(\"(\d+)')
self.logger.debug("VID: {}".format(self.vid))
xml = video_info_xml(self.vid)
info.title = match1(xml, '<vname><!\[CDATA\[([^\]]+)')
urls = matchall(xml, ['<url><!\[CDATA\[([^\]]+)'])
sizes = matchall(xml, ['<filesize>([^<]+)'])
size = 0
for s in sizes:
size += int(s)
info.stream_types.append('current')
info.streams['current'] = {'container': 'hlv', 'video_profile': 'current', 'src': urls, 'size' : size}
return info
def prepare(self):
self.live = True
if not self.vid:
html = get_content(self.url)
self.vid = match1(html, 'cid=([^&]+)')
t = match1(html, '<title>([^<]+)').split('-')
self.title = t[0]
self.artist = t[1]
info = get_content('http://live.bilibili.com/api/playurl?cid={}'.format(self.vid))
urls = [matchall(info, ['CDATA\[([^\]]+)'])[1]]
size = float('inf')
ext = 'flv'
self.stream_types.append('current')
self.streams['current'] = {'container': ext, 'video_profile': 'current', 'src' : urls, 'size': size}
def prepare(self):
info = VideoInfo(self.name, True)
if not self.vid:
html = get_content(self.url)
self.vid = match1(html, 'var ROOMID = (\d+);')
t = match1(html, '<title>([^<]+)').split('-')
info.title = t[0]
info.artist = t[1]
data = get_content('http://live.bilibili.com/api/playurl?cid={}'.format(self.vid))
urls = [matchall(data, ['CDATA\[([^\]]+)'])[1]]
size = float('inf')
ext = 'flv'
info.stream_types.append('current')
info.streams['current'] = {'container': ext, 'video_profile': 'current', 'src' : urls, 'size': size}
return info
def prepare(self):
info = VideoInfo(self.name)
if not self.vid:
self.vid = match1(self.url, 'resourceId=([0-9]+)')
if not self.url:
self.url = "http://www.joy.cn/video?resourceId={}".format(self.vid)
html= get_content(self.url)
info.title = match1(html, '<meta content=\"([^\"]+)')
url = matchall(html, ['<source src=\"([^\"]+)'])[3]
_, ext, size = url_info(url)
info.stream_types.append('current')
info.streams['current'] = {'container': ext, 'src': [url], 'size': size }
return info
def prepare(self):
info = VideoInfo(self.name)
if self.url and not self.vid:
vid = matchall(self.url, ['curid=([^_]+)_([\w]+)'])
if vid:
self.vid = vid[0]
info.title = self.name + '_' + str(self.vid)
if self.url and not self.vid:
html = get_content(self.url)
tvid = match1(html, 'data-player-tvid="([^"]+)"', 'tvid=([^&]+)',
'tvId:([^,]+)')
videoid = match1(html, 'data-player-videoid="([^"]+)"',
'vid=([^&]+)', 'vid:"([^"]+)')
self.vid = (tvid, videoid)
info.title = match1(html, '<title>([^<]+)').split('-')[0]
tvid, vid = self.vid
vps_data = getvps(tvid, vid)
assert vps_data['code'] == 'A00000', 'can\'t play this video!!'
url_prefix = vps_data['data']['vp']['du']
stream = vps_data['data']['vp']['tkl'][0]
vs_array = stream['vs']
for vs in vs_array:
bid = vs['bid']
fs_array = vs['fs']
real_urls = []
for seg_info in fs_array:
url = url_prefix + seg_info['l']
json_data = json.loads(get_content(url))
down_url = json_data['l']
real_urls.append(down_url)
stream = self.vd_2_id[bid]
info.stream_types.append(stream)
stream_profile = self.id_2_profile[stream]
info.streams[stream] = {
'video_profile': stream_profile,
'container': 'flv',
'src': real_urls,
'size': 0
}
info.stream_types = sorted(info.stream_types, key=self.ids.index)
return info
def prepare(self):
info = VideoInfo(self.name)
id1 = match1(self.url, 'a/([^\.]+)\.')
api1 = 'http://www.kankanews.com/vxml/{}.xml'.format(id1)
video_data1 = get_content(api1)
self.vid = match1(video_data1, '<omsid>([^<]+)<')
if self.vid == '0' or not self.vid:
html = get_content(self.url)
id1 = match1(html, 'xmlid=([^\"]+)') or match1(html, 'embed/([^\"]+)').replace('_', '/')
api1 = 'http://www.kankanews.com/vxml/{}.xml'.format(id1)
video_data1 = get_content(api1)
self.vid = match1(video_data1, '<omsid>([^<]+)<')
assert self.vid != '0' and self.vid, self.url + ': Not a video news link!'
api2 = 'http://vapi.kankanews.com/index.php?app=api&mod=public&act=getvideo&id={}'.format(self.vid)
video_data2 = get_content(api2)
urls = matchall(video_data2, ['<videourl><!\[CDATA\[([^\]]+)'])
info.title = match1(video_data2, '<otitle><!\[CDATA\[([^\]]+)')
info.stream_types.append('current')
info.streams['current'] = {'container': 'mp4', 'video_profile': 'current', 'src' : urls, 'size': 0}
return info
def prepare(self):
info = VideoInfo(self.name)
html = get_content(self.url)
self.vid = match1(html, 'webcfg\s*=\s*{"id":\s*(\d+)')
xml = get_content(
'http://web-play.pptv.com/webplay3-0-{}.xml?type=web.fpp'.format(
self.vid))
host = match1(xml, '<sh>([^<>]+)</sh>')
k = match1(xml, '<key expire=[^<>]+>([^<>]+)</key>')
rid = match1(xml, 'rid="([^"]+)"')
info.title = match1(xml, 'nm="([^"]+)"')
st = match1(xml, '<st>([^<>]+)</st>')[:-4]
st = time.mktime(
time.strptime(st)) * 1000 - 60 * 1000 - time.time() * 1000
st += time.time() * 1000
st = st / 1000
key = constructKey(st)
pieces = matchall(xml, ['<sgm no="(\d+)"[^<>]+fs="(\d+)"'])
numbers, fs = zip(*pieces)
urls = [
"http://{}/{}/{}?key={}&fpp.ver=1.3.0.4&k={}&type=web.fpp".format(
host, i, rid, key, k)
for i in range(max(map(int, numbers)) + 1)
]
total_size = sum(map(int, fs))
info.stream_types.append('current')
info.streams['current'] = {
'container': 'mp4',
'video_profile': 'current',
'src': urls,
'size': total_size
}
return info
def prepare(self):
self.live = True
if not self.vid:
html = get_content(self.url)
self.vid = match1(html, 'cid=([^&]+)')
t = match1(html, '<title>([^<]+)').split('-')
self.title = t[0]
self.artist = t[1]
info = get_content(
'http://live.bilibili.com/api/playurl?cid={}'.format(self.vid))
urls = [matchall(info, ['CDATA\[([^\]]+)'])[1]]
size = float('inf')
ext = 'flv'
self.stream_types.append('current')
self.streams['current'] = {
'container': ext,
'video_profile': 'current',
'src': urls,
'size': size
}
def prepare(self):
info = VideoInfo(self.name)
if not self.vid:
self.vid = match1(self.url, 'resourceId=([0-9]+)')
if not self.url:
self.url = "http://www.joy.cn/video?resourceId={}".format(self.vid)
html = get_content(self.url)
info.title = match1(html, '<meta content=\"([^\"]+)')
url = matchall(html, '<source src=\"([^\"]+)')[3]
_, ext, size = url_info(url)
info.stream_types.append('current')
info.streams['current'] = {
'container': ext,
'src': [url],
'size': size
}
return info
def prepare(self):
info = VideoInfo(self.name, True)
if not self.vid:
html = get_content(self.url)
self.vid = match1(html, 'var ROOMID = (\d+);')
t = match1(html, '<title>([^<]+)').split('-')
info.title = t[0]
info.artist = t[1]
data = get_content(
'http://live.bilibili.com/api/playurl?cid={}'.format(self.vid))
urls = [matchall(data, ['CDATA\[([^\]]+)'])[1]]
size = float('inf')
ext = 'flv'
info.stream_types.append('current')
info.streams['current'] = {
'container': ext,
'video_profile': 'current',
'src': urls,
'size': size
}
return info
def get_vid_title(self):
av_id = match1(self.url, '(?:/av|aid=)(\d+)')
page_index = '1'
if "#page=" in self.url or "?p=" in self.url or 'index_' in self.url:
page_index = match1(self.url, '(?:#page|\?p)=(\d+)', 'index_(\d+)\.')
if page_index == '1':
self.url = 'https://www.bilibili.com/av{}/'.format(av_id)
else:
self.url = 'https://www.bilibili.com/av{}/?p={}'.format(av_id, page_index)
if not self.vid:
html = get_content(self.url)
#vid = match1(html, 'cid=(\d+)', 'cid="(\d+)', '"cid":(\d+)')
title = match1(html, '"title":"([^"]+)', '<h1 title="([^"]+)', '<title>([^<]+)').strip()
video_list = matchall(html, ['"cid":(\d+),"page":(\d+),"from":"[^"]+","part":"([^"]*)",'])
for cid, page, part in video_list:
if page == page_index:
vid = cid
if len(video_list) > 1:
title = u'{} - {} - {}'.format(title, page, part)
elif part:
title = u'{} - {}'.format(title, part)
break
return vid, title
def prepare(self):
info = VideoInfo(self.name)
if self.url and not self.vid:
vid = matchall(self.url, ['curid=([^_]+)_([\w]+)'])
if vid:
self.vid = vid[0]
info.title = self.name + '_' + str(self.vid)
if self.url and not self.vid:
html = get_content(self.url)
tvid = match1(html, 'data-player-tvid="([^"]+)"', 'tvid=([^&]+)' , 'tvId:([^,]+)')
videoid = match1(html, 'data-player-videoid="([^"]+)"', 'vid=([^&]+)', 'vid:"([^"]+)')
self.vid = (tvid, videoid)
info.title = match1(html, '<title>([^<]+)').split('-')[0]
tvid, vid = self.vid
vps_data = getvps(tvid, vid)
assert vps_data['code'] == 'A00000', 'can\'t play this video!!'
url_prefix = vps_data['data']['vp']['du']
stream = vps_data['data']['vp']['tkl'][0]
vs_array = stream['vs']
for vs in vs_array:
bid = vs['bid']
fs_array = vs['fs']
real_urls = []
for seg_info in fs_array:
url = url_prefix + seg_info['l']
json_data=json.loads(get_content(url))
down_url = json_data['l']
real_urls.append(down_url)
stream = self.vd_2_id[bid]
info.stream_types.append(stream)
stream_profile = self.id_2_profile[stream]
info.streams[stream] = {'video_profile': stream_profile, 'container': 'flv', 'src': real_urls, 'size' : 0}
info.stream_types = sorted(info.stream_types, key = self.ids.index)
return info
def prepare_list(self):
html = get_content(self.url, headers={})
return matchall(html, ['"a-pic-play" href="([^"]+)"'])
def prepare_list(self):
html = get_content(self.url)
return matchall(html, ['id=\"([^\"]+)\S title'])
def prepare_list(self):
html = get_content(self.url)
return matchall(html, ['video_id: ([^,]+)'])
def prepare_list(self):
html = get_content(self.url, headers={})
return matchall(html, ['"a-pic-play" href="([^"]+)"'])
def prepare_list(self):
html = get_content(self.url)
vids = matchall(html, ['vid="(\d+)"'])
# fake urls
return ['http://live.le.com/izt/vid={}'.format(vid) for vid in vids]
def prepare_list(self):
html = get_content(self.url)
return matchall(html, ['data-tvid=\"([^\"]+)\" data-vid=\"([^\"]+)\"'])
def prepare_list(self):
html = get_content(self.url)
return matchall(html, ['vid="(\d+)"'])
def prepare_list(self):
html = get_content(self.url)
return matchall(html, douyu_match_pattern)
def prepare(self):
info = VideoInfo(self.name)
if self.url and not self.vid:
vid = matchall(self.url, ['curid=([^_]+)_([\w]+)'])
if vid:
self.vid = vid[0]
info_u = 'http://pcw-api.iqiyi.com/video/video/playervideoinfo?tvid=' + self.vid[0]
try:
info_json = json.loads(get_content(info_u))
info.title = info_json['data']['vn']
except:
self.vid = None
def get_vid():
html = get_content(self.url)
video_info = match1(html, ":video-info='(.+?)'")
if video_info:
video_info = json.loads(video_info)
self.vid = str(video_info['tvId']), str(video_info['vid'])
info.title = video_info['name']
else:
tvid = match1(html,
'tvId:\s*"([^"]+)',
'data-video-tvId="([^"]+)',
'''\['tvid'\]\s*=\s*"([^"]+)''',
'"tvId":\s*([^,]+)')
videoid = match1(html,
'data-video-vid="([^"]+)',
'vid:\s*"([^"]+)',
'''\['vid'\]\s*=\s*"([^"]+)''',
'"vid":\s*([^,]+)')
if not (tvid and videoid):
url = match1(html, '(www\.iqiyi\.com/v_\w+\.html)')
if url:
self.url = 'https://' + url
return get_vid()
self.vid = (tvid, videoid)
info.title = match1(html, '<title>([^<]+)').split('-')[0]
if self.url and not self.vid:
get_vid()
tvid, vid = self.vid
assert tvid and vid, 'can\'t play this video!!'
def push_stream_vd(vs):
vd = vs['vd']
stream = self.vd_2_id[vd]
if not stream in info.streams:
info.stream_types.append(stream)
elif int(vd) < 10:
return
m3u8 = vs['m3utx']
stream_profile = self.id_2_profile[stream]
info.streams[stream] = {
'video_profile': stream_profile,
'container': 'm3u8',
'src': [m3u8],
'size': 0
}
def push_stream_bid(bid, container, fs_array, size):
stream = self.vd_2_id[bid]
if stream in info.streams:
return
real_urls = []
for seg_info in fs_array:
url = url_prefix + seg_info['l']
json_data = json.loads(get_content(url))
down_url = json_data['l']
real_urls.append(down_url)
info.stream_types.append(stream)
stream_profile = self.id_2_profile[stream]
info.streams[stream] = {
'video_profile': stream_profile,
'container': container,
'src': real_urls,
'size': size
}
try:
# try use tmts first
# less http requests, get results quickly
tmts_data = gettmts(tvid, vid)
self.logger.debug('tmts_data:\n' + str(tmts_data))
assert tmts_data['code'] == 'A00000', 'can\'t play this video!!'
vs_array = tmts_data['data']['vidl']
for vs in vs_array:
push_stream_vd(vs)
vip_conf = tmts_data['data'].get('ctl', {}).get('configs')
if vip_conf:
for vds in (('10', '19'), ('18', '5')):
for vd in vds:
if vd in vip_conf:
tmts_data = gettmts(tvid, vip_conf[vd]['vid'])
if tmts_data['code'] == 'A00000':
push_stream_vd(tmts_data['data'])
break
except:
try:
# use vps as preferred fallback
vps_data = getvps(tvid, vid)
self.logger.debug('vps_data:\n' + str(vps_data))
assert vps_data['code'] == 'A00000', 'can\'t play this video!!'
url_prefix = vps_data['data']['vp']['du']
vs_array = vps_data['data']['vp']['tkl'][0]['vs']
for vs in vs_array:
bid = vs['bid']
fs_array = vs['fs']
size = vs['vsize']
push_stream_bid(bid, 'flv', fs_array, size)
except:
# use dash as fallback
for bid in (500, 300, 200, 100):
dash_data = getdash(tvid, vid, bid)
self.logger.debug('dash_data:\n' + str(dash_data))
assert dash_data['code'] == 'A00000', 'can\'t play this video!!'
url_prefix = dash_data['data']['dd']
streams = dash_data['data']['program']['video']
for stream in streams:
if 'fs' in stream:
_bid = stream['bid']
container = stream['ff']
fs_array = stream['fs']
size = stream['vsize']
break
push_stream_bid(_bid, container, fs_array, size)
info.stream_types = sorted(info.stream_types, key=self.ids.index)
return info
def prepare_list(self):
html = get_content(self.url)
return matchall(html, ['data-tvid=\"([^\"]+)\" data-vid=\"([^\"]+)\"'])
def prepare(self):
info = VideoInfo(self.name)
if self.url and not self.vid:
vid = matchall(self.url, ['curid=([^_]+)_([\w]+)'])
if vid:
self.vid = vid[0]
if self.url and not self.vid:
html = get_content(self.url)
tvid = match1(html, 'data-player-tvid="([^"]+)"', 'tvid=([^&]+)' , 'tvId:([^,]+)')
videoid = match1(html, 'data-player-videoid="([^"]+)"', 'vid=([^&]+)', 'vid:"([^"]+)')
self.vid = (tvid, videoid)
info.title = match1(html, '<title>([^<]+)').split('-')[0]
tvid, vid = self.vid
data = getVMS(tvid, vid)
if not data['code'] == 'A00000':
for bid in self.id_h5:
h5_data = geth5VMS(tvid, vid, bid)
if h5_data["code"] == "A00000":
stream = self.vd_2_id[bid]
profile = self.id_2_profile[stream]
info.title = h5_data['data']['playInfo']['vn']
info.stream_types.append(stream)
info.streams[stream] = {'container': 'mp4', 'video_profile': profile, 'src' : [h5_data['data']['m3u']], 'size' : 0}
return info
for stream in data['data']['vidl']:
try:
stream_id = self.vd_2_id[stream['vd']]
if stream_id in info.stream_types or stream_id in self.id_ignore:
continue
stream_profile = self.id_2_profile[stream_id]
info.stream_types.append(stream_id)
info.streams[stream_id] = {'video_profile': stream_profile, 'container': 'm3u8', 'src': [stream['m3u']], 'size' : 0}
except:
log.i("vd: {} is not handled".format(stream['vd']))
log.i("info is {}".format(stream))
# why I need do below???
try:
vip_vds = data['data']['ctl']['vip']['bids']
vip_conf = data['data']['ctl']['configs']
except:
info.stream_types = sorted(info.stream_types, key = self.ids.index)
return info
if not 'BD' in info.stream_types:
p1080_vids = []
if 5 in vip_vds:
p1080_vids.append(vip_conf['5']['vid'])
for v in p1080_vids:
p1080_info = getVMS(tvid, v)
if p1080_info['code'] == 'A00000':
p1080_url = p1080_info['data']['m3u']
info.stream_types.append('BD')
info.streams['BD'] = {'video_profile': '1080p', 'container': 'm3u8', 'src': [p1080_url], 'size' : 0}
break
if not '4k' in info.stream_types:
k4_vids = []
if 10 in vip_vds:
k4_vids.append(vip_conf['10']['vid'])
for v in k4_vids:
k4_info = getVMS(tvid, v)
if k4_info['code'] == 'A00000':
k4_url = k4_info['data']['m3u']
info.stream_types.append('4k')
info.streams['4k'] = {'video_profile': '4k', 'container': 'm3u8', 'src': [k4_url], 'size' : 0}
break
info.stream_types = sorted(info.stream_types, key = self.ids.index)
return info
def prepare_list(self):
html = get_content(self.url)
return matchall(html, ['id=\"([^\"]+)\S title'])
def prepare_list(self):
html = get_content(self.url)
video_list = match1(html, 'video_list=\[([^\]]+)')
return matchall(video_list, ['\"([^\",]+)'])
def prepare(self):
if self.url and not self.vid:
#maybe error!!
self.vid = (vu, uu) = matchall(self.url, ["vu=([^&]+)","uu=([^&]+)"])
return self.letvcloud_download_by_vu()
def prepare_list(self):
html = get_content(self.url)
return matchall(html, douyu_match_pattern)
def prepare(self):
info = VideoInfo(self.name)
if self.url and not self.vid:
vid = matchall(self.url, ['curid=([^_]+)_([\w]+)'])
if vid:
self.vid = vid[0]
info_u = 'http://pcw-api.iqiyi.com/video/video/playervideoinfo?tvid=' + self.vid[
0]
try:
info_json = json.loads(get_content(info_u))
info.title = info_json['data']['vn']
except:
self.vid = None
def get_vid():
html = get_content(self.url)
video_info = match1(html, ":video-info='(.+?)'")
if video_info:
video_info = json.loads(video_info)
self.vid = str(video_info['tvId']), str(video_info['vid'])
info.title = video_info['name']
else:
tvid = match1(html, 'tvId:\s*"([^"]+)',
'data-video-tvId="([^"]+)',
'''\['tvid'\]\s*=\s*"([^"]+)''',
'"tvId":\s*([^,]+)')
videoid = match1(html, 'data-video-vid="([^"]+)',
'vid"?\'?\]?\s*(?:=|:)\s*"?\'?([^"\',]+)')
if not (tvid and videoid):
url = match1(html, '(www\.iqiyi\.com/v_\w+\.html)')
if url:
self.url = 'https://' + url
return get_vid()
self.vid = (tvid, videoid)
info.title = match1(html, '<title>([^<]+)').split('-')[0]
if self.url and not self.vid:
get_vid()
tvid, vid = self.vid
assert tvid and vid, 'can\'t play this video!!'
def push_stream_vd(vs):
vd = vs['vd']
stream = self.vd_2_id[vd]
if stream in info.streams:
# prefer H264 than H265
if vs.get('fileFormat') == 'H265':
return
else:
info.stream_types.append(stream)
m3u8 = vs['m3utx']
stream_profile = self.id_2_profile[stream]
info.streams[stream] = {
'video_profile': stream_profile,
'container': 'm3u8',
'src': [m3u8],
'size': 0
}
def push_stream_bid(bid, container, fs_array, size):
stream = self.vd_2_id[bid]
if stream in info.streams:
return
real_urls = []
for seg_info in fs_array:
url = url_prefix + seg_info['l']
json_data = json.loads(get_content(url))
down_url = json_data['l']
real_urls.append(down_url)
info.stream_types.append(stream)
stream_profile = self.id_2_profile[stream]
info.streams[stream] = {
'video_profile': stream_profile,
'container': container,
'src': real_urls,
'size': size
}
try:
# try use tmts first
# less http requests, get results quickly
tmts_data = gettmts(tvid, vid)
self.logger.debug('tmts_data:\n' + str(tmts_data))
assert tmts_data['code'] == 'A00000', 'can\'t play this video!!'
vs_array = tmts_data['data']['vidl']
for vs in vs_array:
push_stream_vd(vs)
vip_conf = tmts_data['data'].get('ctl', {}).get('configs')
if vip_conf:
# prefer H264 than H265
for vds in (('5', '18'), ('10', '19')):
for vd in vds:
if vd in vip_conf:
tmts_data = gettmts(tvid, vip_conf[vd]['vid'])
if tmts_data['code'] == 'A00000':
push_stream_vd(tmts_data['data'])
break
except:
try:
# use vps as preferred fallback
vps_data = getvps(tvid, vid)
self.logger.debug('vps_data:\n' + str(vps_data))
assert vps_data['code'] == 'A00000', 'can\'t play this video!!'
url_prefix = vps_data['data']['vp']['du']
vs_array = vps_data['data']['vp']['tkl'][0]['vs']
for vs in vs_array:
bid = vs['bid']
fs_array = vs['fs']
size = vs['vsize']
push_stream_bid(bid, 'flv', fs_array, size)
except:
# use dash as fallback
for bid in (500, 300, 200, 100):
dash_data = getdash(tvid, vid, bid)
self.logger.debug('dash_data:\n' + str(dash_data))
assert dash_data[
'code'] == 'A00000', 'can\'t play this video!!'
url_prefix = dash_data['data']['dd']
streams = dash_data['data']['program']['video']
for stream in streams:
if 'fs' in stream:
_bid = stream['bid']
container = stream['ff']
fs_array = stream['fs']
size = stream['vsize']
push_stream_bid(_bid, container, fs_array, size)
break
assert info.streams, 'can\'t play this video!!'
info.stream_types = sorted(info.stream_types, key=self.ids.index)
return info
def download_playlist(self, url, param):
html = get_content(url)
vids = matchall(html, ['id=\"([^\"]+)\S title'])
for vid in vids:
self.download(vid, param)
def get_path_list(self):
html = get_content(self.url)
videos = matchall(html,
['href=[\'"](/v/[a-zA-Z0-9_]+)[\'"] title=[\'"]'])
return videos
def prepare_list(self):
html = get_content(self.url)
return matchall(html, ['vid="(\d+)"'])
def prepare_list(self):
html = get_content(self.url)
video_list = matchall(html, ['<option value=\'([^\']*)\''])
return ['http://www.bilibili.com'+v for v in video_list]
def prepare_list(self):
html = get_content(self.url)
video_list = match1(html, 'video_list=\[([^\]]+)')
return matchall(video_list, ['\"([^\",]+)'])
def prepare_list(self):
html = get_content(self.url)
return matchall(html, ['video_id: ([^,]+)'])
def prepare_list(self):
html = get_content(self.url)
eplist = match1(html, '"epList":(\[.+?\])')
if eplist:
eplist = matchall(eplist, [',"id":(\d+),'])
return ['https://www.bilibili.com/bangumi/play/ep{}'.format(eid) for eid in eplist]