def get_file_url(self):
"""
Returns the absolute downloadable filepath
"""
if not self.data:
self.download_html()
return html_unescape(re.search(r'hashlink=(http.*?)"', self.data).group(1))
def handle_free(self, pyfile):
fileid = re.search(self.FILEID_PATTERN, self.data).group(1)
self.log_debug("FileID: " + fileid)
token = re.search(self.TOKEN_PATTERN, self.data).group(1)
self.log_debug("Token: " + token)
self.data = self.load("http://lolabits.es/action/License/Download",
post={'fileId' : fileid,
'__RequestVerificationToken' : token},
decode="unicode-escape")
self.link = html_unescape(re.search(self.LINK_PATTERN, self.data).group(1))
def handle_web_links(self):
self.log_debug("Search for Web links ")
package_links = []
pattern = r'<form action="http://linkcrypt.ws/out.html"[^>]*?>.*?<input[^>]*?value="(.+?)"[^>]*?name="file"'
ids = re.findall(pattern, self.data, re.I | re.S)
self.log_debug("Decrypting %d Web links" % len(ids))
for idx, weblink_id in enumerate(ids):
try:
res = self.load("http://linkcrypt.ws/out.html", post = {'file':weblink_id})
indexs = res.find("window.location =") + 19
indexe = res.find('"', indexs)
link2 = res[indexs:indexe]
link2 = html_unescape(link2)
package_links.append(link2)
except Exception, detail:
self.log_debug("Error decrypting Web link %s, %s" % (weblink_id, detail))
def get_file_name(self):
file_name_pattern = r'<h1 class=\'globalHd\'>(.*)</h1>'
return html_unescape(re.search(file_name_pattern, self.data).group(1).replace("/", "") + '.flv')
def process(self, pyfile):
pyfile.url = replace_patterns(pyfile.url, self.URL_REPLACEMENTS)
html = self.load(pyfile.url)
if re.search(r'<div id="player-unavailable" class="\s*player-width player-height\s*">', html):
self.offline()
if "We have been receiving a large volume of requests from your network." in html:
self.temp_offline()
#: Get config
use3d = self.get_config('3d')
if use3d:
quality = {'sd': 82, 'hd': 84, 'fullhd': 85, '240p': 83, '360p': 82,
'480p': 82, '720p': 84, '1080p': 85, '3072p': 85}
else:
quality = {'sd': 18, 'hd': 22, 'fullhd': 37, '240p': 5, '360p': 18,
'480p': 35, '720p': 22, '1080p': 37, '3072p': 38}
desired_fmt = self.get_config('fmt')
if not desired_fmt:
desired_fmt = quality.get(self.get_config('quality'), 18)
elif desired_fmt not in self.formats:
self.log_warning(_("FMT %d unknown, using default") % desired_fmt)
desired_fmt = 0
#: Parse available streams
streams = re.search(r'"url_encoded_fmt_stream_map":"(.+?)",', html).group(1)
streams = [x.split('\u0026') for x in streams.split(',')]
streams = [dict((y.split('=', 1)) for y in x) for x in streams]
streams = [(int(x['itag']), urllib.unquote(x['url'])) for x in streams]
# self.log_debug("Found links: %s" % streams)
self.log_debug("AVAILABLE STREAMS: %s" % [x[0] for x in streams])
#: Build dictionary of supported itags (3D/2D)
allowed = lambda x: self.get_config(self.formats[x][0])
streams = [x for x in streams if x[0] in self.formats and allowed(x[0])]
if not streams:
self.fail(_("No available stream meets your preferences"))
fmt_dict = dict([x for x in streams if self.formats[x[0]][4] is use3d] or streams)
self.log_debug("DESIRED STREAM: ITAG:%d (%s) %sfound, %sallowed" %
(desired_fmt, "%s %dx%d Q:%d 3D:%s" % self.formats[desired_fmt],
"" if desired_fmt in fmt_dict else "NOT ", "" if allowed(desired_fmt) else "NOT "))
#: Return fmt nearest to quality index
if desired_fmt in fmt_dict and allowed(desired_fmt):
fmt = desired_fmt
else:
sel = lambda x: self.formats[x][3] #: Select quality index
comp = lambda x, y: abs(sel(x) - sel(y))
self.log_debug("Choosing nearest fmt: %s" % [(x, allowed(x), comp(x, desired_fmt)) for x in fmt_dict.keys()])
fmt = reduce(lambda x, y: x if comp(x, desired_fmt) <= comp(y, desired_fmt) and
sel(x) > sel(y) else y, fmt_dict.keys())
self.log_debug("Chosen fmt: %s" % fmt)
url = fmt_dict[fmt]
self.log_debug("URL: %s" % url)
#: Set file name
file_suffix = self.formats[fmt][0] if fmt in self.formats else ".flv"
file_name_pattern = '<meta name="title" content="(.+?)">'
name = re.search(file_name_pattern, html).group(1).replace("/", "")
#: Cleaning invalid characters from the file name
name = name.encode('ascii', 'replace')
for c in self.invalid_chars:
name = name.replace(c, '_')
pyfile.name = html_unescape(name)
time = re.search(r"t=((\d+)m)?(\d+)s", pyfile.url)
ffmpeg = which("ffmpeg")
if ffmpeg and time:
m, s = time.groups()[1:]
if m is None:
m = "0"
pyfile.name += " (starting at %s:%s)" % (m, s)
pyfile.name += file_suffix
filename = self.download(url)
if ffmpeg and time:
inputfile = filename + "_"
os.rename(filename, inputfile)
subprocess.call([
ffmpeg,
"-ss", "00:%s:%s" % (m, s),
"-i", inputfile,
"-vcodec", "copy",
"-acodec", "copy",
filename])
os.remove(inputfile)
def handle_captcha(self, inputs):
m = re.search(self.CAPTCHA_PATTERN, self.data)
if m is not None:
captcha_url = m.group(1)
inputs['code'] = self.captcha.decrypt(captcha_url)
return
m = re.search(self.CAPTCHA_BLOCK_PATTERN, self.data, re.S)
if m is not None:
captcha_div = m.group(1)
numerals = re.findall(r'<span.*?padding-left\s*:\s*(\d+).*?>(\d)</span>', html_unescape(captcha_div))
self.log_debug(captcha_div)
inputs['code'] = "".join(a[1] for a in sorted(numerals, key=lambda num: int(num[0])))
self.log_debug("Captcha code: %s" % inputs['code'], numerals)
return
recaptcha = ReCaptcha(self)
try:
captcha_key = re.search(self.RECAPTCHA_PATTERN, self.data).group(1)
except Exception:
captcha_key = recaptcha.detect_key()
else:
self.log_debug("ReCaptcha key: %s" % captcha_key)
if captcha_key:
inputs['recaptcha_response_field'], inputs['recaptcha_challenge_field'] = recaptcha.challenge(captcha_key)
return
solvemedia = SolveMedia(self)
try:
captcha_key = re.search(self.SOLVEMEDIA_PATTERN, self.data).group(1)
except Exception:
captcha_key = solvemedia.detect_key()
else:
self.log_debug("SolveMedia key: %s" % captcha_key)
if captcha_key:
inputs['adcopy_response'], inputs['adcopy_challenge'] = solvemedia.challenge(captcha_key)