def solve(url, cj, user_agent=None, name=None):
if user_agent is None: user_agent = USER_AGENT
headers = {'User-Agent': user_agent, 'Referer': url}
request = urllib2.Request(url)
for key in headers: request.add_header(key, headers[key])
try:
response = urllib2.urlopen(request)
html = response.read()
except urllib2.HTTPError as e:
html = e.read()
match = re.search('data-sitekey="([^"]+)', html)
match1 = re.search('data-ray="([^"]+)', html)
if match and match1:
token = recaptcha_v2.UnCaptchaReCaptcha().processCaptcha(match.group(1), lang='en', name=name, referer=url)
if token:
data = {'g-recaptcha-response': token, 'id': match1.group(1)}
scheme = urlparse.urlparse(url).scheme
domain = urlparse.urlparse(url).hostname
url = '%s://%s/cdn-cgi/l/chk_captcha?%s' % (scheme, domain, urllib.urlencode(data))
if cj is not None:
try: cj.load(ignore_discard=True)
except: pass
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))
urllib2.install_opener(opener)
try:
request = urllib2.Request(url)
for key in headers: request.add_header(key, headers[key])
opener = urllib2.build_opener(NoRedirection)
urllib2.install_opener(opener)
response = urllib2.urlopen(request)
while response.getcode() in [301, 302, 303, 307]:
if cj is not None:
cj.extract_cookies(response, request)
redir_url = response.info().getheader('location')
if not redir_url.startswith('http'):
redir_url = urlparse.urljoin(url, redir_url)
request = urllib2.Request(redir_url)
for key in headers: request.add_header(key, headers[key])
if cj is not None:
cj.add_cookie_header(request)
response = urllib2.urlopen(request)
final = response.read()
if cj is not None:
cj.extract_cookies(response, request)
cj.save(ignore_discard=True)
return final
except urllib2.HTTPError as e:
logger.log('CF Captcha Error: %s on url: %s' % (e.code, url), log_utils.LOGWARNING)
return False
else:
logger.log('CF Captcha without sitekey/data-ray: %s' % (url), log_utils.LOGWARNING)
def resolve_link(self, link):
try:
headers = dict(
[item.split('=') for item in (link.split('|')[1]).split('&')])
for key in headers:
headers[key] = urllib.unquote(headers[key])
link = link.split('|')[0]
except:
headers = {}
if not link.startswith('http'):
link = urlparse.urljoin(self.base_url, link)
html = self._http_get(link, headers=headers, cache_limit=0)
fragment = dom_parser.parse_dom(html, 'div', {'class': 'player'})
if fragment:
iframe_url = dom_parser.parse_dom(fragment[0], 'iframe', ret='src')
if iframe_url:
iframe_url = iframe_url[0]
headers = {'Referer': link}
html = self._http_get(iframe_url,
headers=headers,
cache_limit=0)
sitekey = dom_parser.parse_dom(html,
'div', {'class': 'g-recaptcha'},
ret='data-sitekey')
if sitekey:
token = recaptcha_v2.UnCaptchaReCaptcha().processCaptcha(
sitekey[0], lang='en')
if token:
data = {'g-recaptcha-response': token}
html = self._http_get(iframe_url,
data=data,
cache_limit=0)
match = re.search(
"\.replace\(\s*'([^']+)'\s*,\s*'([^']*)'\s*\)", html, re.I)
if match:
html = html.replace(match.group(1), match.group(2))
match = re.search("window\.atob[\([]+'([^']+)", html)
if match:
func_count = len(re.findall('window\.atob', html))
html = match.group(1)
for _i in xrange(func_count):
html = base64.decodestring(html)
streams = []
for match in re.finditer(
'''<source[^>]+src=["']([^;'"]+)[^>]+label=['"]([^'"]+)''',
html):
streams.append(match.groups())
if len(streams) > 1:
if not self.auto_pick:
result = xbmcgui.Dialog().select(
i18n('choose_stream'), [e[1] for e in streams])
if result > -1:
return streams[result][0] + '|User-Agent=%s' % (
scraper_utils.get_ua())
else:
best_stream = ''
best_q = 0
for stream in streams:
stream_url, label = stream
if Q_ORDER[scraper_utils.height_get_quality(
label)] > best_q:
best_q = Q_ORDER[
scraper_utils.height_get_quality(label)]
best_stream = stream_url
if best_stream:
return best_stream + '|User-Agent=%s' % (
scraper_utils.get_ua())
elif streams:
return streams[0][0] + '|User-Agent=%s' % (
scraper_utils.get_ua())
iframe_url = dom_parser.parse_dom(html, 'iframe', ret='src')
if iframe_url:
return iframe_url[0]
log_utils.log('No WatchHD Link Found: %s' % (html),
log_utils.LOGWARNING)