def loadM3U8(url):
txt = xurl.load(url)
txt = txt.replace('\/', '/')
txt = txt.replace('\\n', '\n')
m = re.search(r'"m3u8":"([^"]*)"', txt)
if m:
m3u8 = m.group(1)
local = xurl.genLocal(url, prefix='vod_list_', suffix='.m3u8')
xurl.saveLocal(local, m3u8)
return local
results = []
for l in re.finditer(r'"l":"([^"]*)"', txt):
part = l.group(1)
if re.search(r'f4v\?', part):
if part.startswith('http'):
results.append(part)
else:
data_url = 'https://data.video.iqiyi.com/videos' + part
for v in re.finditer(r'"l":"([^"]*)"', xurl.load(data_url)):
results.append(v.group(1))
if len(results):
local = xurl.genLocal(url, prefix='vod_list_', suffix='.m3u8')
xurl.saveM3U8(local, results)
return local
return None
def parseJson(path):
print('\n[ytdl][parseJson]\n')
results = []
cookies = None
fd = open(path, "r")
lines = fd.readlines()
fd.close()
for line in lines:
try:
data = json.loads(line)
urls = data['url']
except:
print('\texception')
continue
try:
cookies = data['http_headers']['Cookie'].encode('utf8')
except:
cookies = None
if not isinstance(urls, basestring):
results.append(urls)
else:
encoded = re.search(
r'data:application/vnd.apple.mpegurl;base64,([a-zA-Z0-9+/=]*)',
urls)
if encoded:
local = xurl.genLocal(path, prefix='vod_list_', suffix='.m3u')
decoded = base64.b64decode(encoded.group(1))
xurl.saveLocal(local, decoded)
results.append(local)
else:
results.append(urls)
if cookies:
print('\thdr : %s' % (cookies))
if len(results) == 0:
print('\tNo results')
return None, None
elif len(results) == 1:
print('\tret : %s' % (results[0]))
return results[0], cookies
else:
m3u = xurl.genLocal(path, prefix='vod_list_', suffix='.m3u8')
xurl.saveM3U8(m3u, results)
print('\tret : %s' % (m3u))
return m3u, cookies
def extractSUB(url, subtitle=None):
print('\n[ytdl][extracSUB]\n')
sub = xurl.genLocal(url, prefix='vod_sub_')
sub_dir = os.path.dirname(sub)
for f in os.listdir(sub_dir):
if f.startswith(sub):
print('\tsub: ' + sub_dir + f)
return f
try:
opt = ''
if subtitle == 'auto-generated':
opt += '--write-auto-sub '
cmd = '%s %s %s -o %s \'%s\'' % (ytdlcmd(), defvals.ytdlsub, opt, sub,
url)
start_time = timeit.default_timer()
output = subprocess.check_output(cmd, shell=True)
elapsed = timeit.default_timer() - start_time
print('\tsec: ' + str(elapsed))
except:
print('\texception')
return None
m = re.search(r'Writing video subtitles to: (.*)', output)
if m:
local = m.group(1)
print('\tsub: ' + local)
return local
return None
def extract(url):
objs = []
basename = url.split('/')[-1]
if len(basename) == 15:
url_tv = 'https://www.pianku.tv/ajax/downurl/%s_tv/' % (basename[0:10])
local_cookie = xurl.genLocal(url, suffix='.cookie')
opts = []
opts.append('-c %s' % (local_cookie))
xurl.load(url, opts=opts)
opts = []
opts.append('-b %s' % (local_cookie))
opts.append('-H \'x-requested-with: XMLHttpRequest\'')
opts.append('-H \'referer: %s\'' % (url))
txt = xurl.load(url_tv, opts=opts)
for m in re.finditer(r'<li><a href="([^"]*)">(.*?)</a></li>', txt):
link, title = urljoin(url, m.group(1)), m.group(2)
objs.append(entryObj(link, title))
else:
for m in re.finditer(
r'<a href="(.*?)" title="(.*?)" target="_blank"><img src=".*?"\s+data-funlazy="(.*?)"',
load(url)):
link, title, img = urljoin(url, m.group(1)), m.group(2), urljoin(
url, m.group(3))
objs.append(pageObj(link, title, img))
return objs
def get_tracks(no, bno, args):
url = 'https://histock.tw/stock/brokertrace.aspx?bno={b}&no={n}'.format(
b=bno, n=no)
url_opts = []
if args.cookies:
url_opts.append('-H \'cookie: ' + args.cookies + '\'')
local = xurl.genLocal(url, prefix='twstock_load_broker_')
txt = xurl.load(url,
local=local,
opts=url_opts,
cache=args.cache,
cacheOnly=args.cacheOnly,
verbose=args.verbose)
vec = []
for m in re.finditer(
r'<td>(.*?)</td><td>([\d|,]+)</td><td>(\d+[.]\d*)</td><td>([\d|,]+)</td><td>(\d+[.]\d*)</td><td>(\d+[.]\d*)</td>',
txt):
vec.insert(
0,
track(m.group(1), m.group(2), m.group(3), m.group(4), m.group(5),
m.group(6)))
if len(vec) == 0 and re.search('alert', txt):
os.remove(local)
return vec
def executeJSCode(code):
local = xurl.genLocal(str(os.getuid), prefix='vod_code_')
xurl.saveLocal(local, code)
try:
output = subprocess.check_output('nodejs ' + local,
shell=True).rstrip('\n')
except:
return None
output = output.replace("\/", "/")
showAll(code, output)
return output
def getSource(url, fmt, ref):
txt = xurl.load(url)
video = []
audio = []
video_ids = ['64', '32', '16']
audio_ids = ['30280', '30216']
video_id = None
audio_id = None
for m in re.finditer(r'"id":(\d+),"baseUrl":"([^"]*)"', txt):
_id, _url = m.group(1), m.group(2)
if _id in video_ids:
if not video_id:
video_id = _id
if _id == video_id:
video.append(_url)
if _id in audio_ids:
if not audio_id:
audio_id = _id
if _id == audio_id:
audio.append(_url)
local_a = xurl.genLocal(url, prefix='vod_list_', suffix='.audio.m3u8')
local_v = xurl.genLocal(url, prefix='vod_list_', suffix='.video.m3u8')
local = xurl.genLocal(url, prefix='vod_list_', suffix='.m3u8')
xurl.saveM3U8(local_a, audio)
xurl.saveM3U8(local_v, video)
s = []
s.append('#EXTM3U')
s.append(
'#EXT-X-MEDIA:TYPE=AUDIO,GROUP-ID="audio",LANGUAGE="eng",URI="%s"' %
(local_a))
s.append('#EXT-X-STREAM-INF:AUDIO="audio"')
s.append(local_v)
xurl.saveLocal(local, '\n'.join(s))
return local
def extractURL(url, fmt, key=None, ref=None, dontParseJson=False):
print('\n[ytdl][extractURL]\n')
url = redirectURL(url)
arg = '-i -j --no-playlist --no-warnings'
fmt = getFormat(url, fmt)
local = xurl.genLocal(url + fmt, prefix='vod_list_', suffix='.json')
if key:
arg = ' '.join([arg, '--video-password='******' '.join([arg, '--referer=\'%s\'' % (ref)])
print('\targ : %s' % (arg or ''))
print('\tfmt : %s' % (fmt or ''))
if os.path.exists(local) and not xurl.checkExpire(local):
print('\tret : %s' % (local))
if dontParseJson:
return local
return parseJson(local)
cmd = '%s -f \'%s\' --user-agent \'%s\' %s \'%s\' > %s' % (
ytdlcmd(), fmt, defvals.ua, arg, url, local)
try:
start_time = timeit.default_timer()
output = subprocess.check_output(cmd, shell=True)
elapsed = timeit.default_timer() - start_time
except:
elapsed = timeit.default_timer() - start_time
print('\texception')
return None
print('\tsec : %s' % (str(elapsed)))
print('\tret : %s' % (local))
if dontParseJson:
return local
return parseJson(local)
def findYouTubeNextPage(url, q):
objs = []
local = xurl.genLocal(url, suffix='.old')
txt = xurl.load(url,
local,
opts=['--cookie \"PREF=f1=50000000;f6=1408;f5=30;hl=en\"'])
pages = re.search(r'search-pager(.*?)</div>', txt,
re.DOTALL | re.MULTILINE)
if pages:
for m in re.finditer(r'<(a|button) .*?</(a|button)>', pages.group(1)):
label = re.search(r'<span.*?">(.*?)</span>', m.group())
label = label.group(1) if label else None
link = None
if m.group(1) == 'a':
href = re.search(r'href="([^"]*)"', m.group())
link = urljoin(url, href.group(1)) if href else None
objs.append(navObj(label, link))
return objs