def get_sources(self, video):
source_url = self.get_url(video)
hosters = []
if not source_url or source_url == FORCE_NO_MATCH: return hosters
page_url = scraper_utils.urljoin(self.base_url, source_url)
html = self._http_get(page_url, cache_limit=.5)
fragment = dom_parser2.parse_dom(html, 'div', {'class': 'film-container'})
if fragment:
iframe_url = dom_parser2.parse_dom(fragment[0].content, 'iframe', req='src')
if iframe_url:
iframe_url = scraper_utils.urljoin(self.base_url, iframe_url[0].attrs['src'])
headers = {'Referer': page_url}
html = self._http_get(iframe_url, headers=headers, cache_limit=.5)
sources = scraper_utils.parse_sources_list(self, html)
for source in sources:
quality = sources[source]['quality']
host = scraper_utils.get_direct_hostname(self, source)
stream_url = source + scraper_utils.append_headers({'User-Agent': scraper_utils.get_ua(), 'Referer': iframe_url})
hoster = {'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': True}
match = re.search('(\d+[a-z]bps)', source)
if match:
hoster['extra'] = match.group(1)
hosters.append(hoster)
hosters.sort(key=lambda x: x.get('extra', ''), reverse=True)
return hosters
def _get_episode_url(self, show_url, video):
show_url = scraper_utils.urljoin(self.base_url, show_url)
html = self._http_get(show_url, cache_limit=8)
pattern = '''href=['"]([^'"]+)[^>]+>\s*%s\.\s*Sezon<''' % (
video.season)
match = re.search(pattern, html)
if match:
episode_pattern = '''href=['"]([^'"]+-%s-sezon-%s-bolum[^'"]*)''' % (
video.season, video.episode)
season_url = scraper_utils.urljoin(self.base_url, match.group(1))
html = self._http_get(season_url, cache_limit=2)
ep_url = self._default_get_episode_url(html, video,
episode_pattern)
if ep_url: return ep_url
# front page fallback
html = self._http_get(self.base_url, cache_limit=2)
for slug in reversed(show_url.split('/')):
if slug: break
ep_url_frag = 'href="([^"]+/{slug}-{season}-sezon-{episode}-bolum[^"]*)'.format(
slug=slug, season=video.season, episode=video.episode)
match = re.search(ep_url_frag, html)
if match:
return scraper_utils.pathify_url(match.group(1))
def get_sources(self, video):
hosters = []
source_url = self.get_url(video)
if not source_url or source_url == FORCE_NO_MATCH: return hosters
url = scraper_utils.urljoin(self.base_url, source_url)
entry = ''
while True:
html = self._http_get(url, cache_limit=.5)
if not html:
url = scraper_utils.urljoin(BASE_URL2, source_url)
html = self._http_get(url, cache_limit=.5)
entry = dom_parser2.parse_dom(html, 'div', {'class': 'entry'})
if entry:
entry = entry[0].content
match = re.search('Watch it here\s*:.*?href="([^"]+)', entry, re.I)
if not match: break
url = match.group(1)
else:
entry = ''
break
for _attribs, tab in dom_parser2.parse_dom(entry, 'div', {'class': 'postTabs_divs'}):
match = dom_parser2.parse_dom(tab, 'iframe', req='src')
if not match: continue
link = match[0].attrs['src']
host = urlparse.urlparse(link).hostname
hoster = {'multi-part': False, 'host': host, 'class': self, 'quality': scraper_utils.get_quality(video, host, QUALITIES.HIGH), 'views': None, 'rating': None, 'url': link, 'direct': False}
hosters.append(hoster)
return hosters
def _get_episode_url(self, show_url, video):
show_url = scraper_utils.urljoin(self.base_url, show_url)
headers = {'Referer': self.base_url}
html = self._http_get(show_url, headers=headers, cache_limit=.25)
data = dom_parser2.parse_dom(html,
'div', {'id': 'dizidetay'},
req=['data-dizi', 'data-id'])
if not data: return
episode_pattern = '''href=['"]([^'"]*/%s-sezon-%s-[^'"]*bolum[^'"]*)''' % (
video.season, video.episode)
title_pattern = '''href=['"](?P<url>[^'"]+)[^>]*>(?P<title>[^<]+)'''
airdate_pattern = '''href=['"]([^"']+)[^>]*>[^<]*</a>\s*</td>\s*<td class="right aligned">{p_day}\.{p_month}\.{year}'''
season_url = scraper_utils.urljoin(self.base_url, SEASON_URL)
queries = {
'sekme': 'bolumler',
'id': data[0].attrs['data-id'],
'dizi': data[0].attrs['data-dizi']
}
headers = {'Referer': show_url, 'Content-Length': 0}
headers.update(XHR)
html = self._http_get(season_url,
params=queries,
headers=headers,
method='POST',
cache_limit=2)
result = self._default_get_episode_url(html, video, episode_pattern,
title_pattern, airdate_pattern)
if result and 'javascript:;' not in result:
return result
def search(self, video_type, title, year, season=''): # @UnusedVariable
results = []
search_url = scraper_utils.urljoin(self.base_url, '/search/')
search_url = scraper_utils.urljoin(search_url,
urllib.quote_plus(title))
html = self._http_get(search_url, require_debrid=True, cache_limit=8)
for _attrs, fragment in dom_parser2.parse_dom(html, 'div',
{'class': 'list'}):
if not dom_parser2.parse_dom(fragment, 'div',
{'class': 'lists_titles'}):
continue
for attrs, match_title_year in dom_parser2.parse_dom(
fragment, 'a', {'class': 'title'}, req='href'):
match_url = attrs['href']
match_title_year = re.sub('</?[^>]*>', '', match_title_year)
is_show = re.search('\(d{4|-\)', match_title_year)
if (is_show and video_type == VIDEO_TYPES.MOVIE) or (
not is_show and video_type == VIDEO_TYPES.TVSHOW):
continue
match_title, match_year = scraper_utils.extra_year(
match_title_year)
if not year or not match_year or year == match_year:
result = {
'url': scraper_utils.pathify_url(match_url),
'title': scraper_utils.cleanse_title(match_title),
'year': match_year
}
results.append(result)
return results
def get_sources(self, video):
source_url = self.get_url(video)
hosters = []
sources = {}
if not source_url or source_url == FORCE_NO_MATCH: return hosters
url = scraper_utils.urljoin(self.base_url, source_url)
html = self._http_get(url, require_debrid=True, cache_limit=.5)
if not html:
url = scraper_utils.urljoin(self.old_base_url, source_url)
html = self._http_get(url, require_debrid=True, cache_limit=.5)
sources.update(self.__get_post_links(html, video))
if kodi.get_setting('%s-include_comments' %
(self.get_name())) == 'true':
for _attrs, comment in dom_parser2.parse_dom(
html, 'div', {'id': re.compile('commentbody-\d+')}):
sources.update(self.__get_comment_links(comment, video))
for source in sources:
if scraper_utils.excluded_link(source): continue
host = urlparse.urlparse(source).hostname
hoster = {
'multi-part': False,
'host': host,
'class': self,
'views': None,
'url': source,
'rating': None,
'quality': sources[source],
'direct': False
}
hosters.append(hoster)
return hosters
def search(self, video_type, title, year, season=''): # @UnusedVariable
results = []
if video_type == VIDEO_TYPES.MOVIE:
url = scraper_utils.urljoin(self.base_url, '/movies/a-z/')
else:
url = scraper_utils.urljoin(self.base_url, '/tv/a-z/')
if title.upper().startswith('THE '):
search_title = title[4:5]
elif title.upper().startswith('A '):
search_title = title[2:3]
else:
search_title = title
if title[:1] in string.digits:
first_letter = '1'
else:
first_letter = search_title[:1]
url = url + first_letter.upper()
html = self._http_get(url, cache_limit=48)
norm_title = scraper_utils.normalize_title(title)
pattern = 'class=star.*?href=([^>]+)>(.*?)</a>'
for match in re.finditer(pattern, html, re.DOTALL):
match_url, match_title_year = match.groups()
match_title, match_year = scraper_utils.extra_year(match_title_year)
if norm_title in scraper_utils.normalize_title(match_title) and (not year or not match_year or year == match_year):
result = {'url': match_url, 'title': scraper_utils.cleanse_title(match_title), 'year': match_year}
results.append(result)
return results
def search(self, video_type, title, year, season=''):
results = []
search_url = scraper_utils.urljoin(self.base_url, '/movies/search')
html = self._http_get(search_url, params={'s': title}, cache_limit=8)
for _attrs, item in dom_parser2.parse_dom(html, 'div', {'class': 'item_movie'}):
match = dom_parser2.parse_dom(item, 'a', req=['href', 'title'])
if not match: continue
match_title_year = match[0].attrs['title']
match_url = match[0].attrs['href']
is_season = re.search('S(?:eason\s+)?(\d+)', match_title_year, re.I)
match_vt = video_type == (VIDEO_TYPES.MOVIE and not is_season) or (video_type == VIDEO_TYPES.SEASON and is_season)
match_year = ''
if video_type == VIDEO_TYPES.SEASON:
if not season and not match_vt: continue
if match_vt:
if season and int(is_season.group(1)) != int(season): continue
else:
if season and int(season) != 1: continue
site_title, site_year = scraper_utils.extra_year(match_title_year)
if scraper_utils.normalize_title(site_title) not in scraper_utils.normalize_title(title) or year != site_year: continue
match_title = match_title_year
else:
if not match_vt: continue
match_title, match_year = scraper_utils.extra_year(match_title_year)
match_url = scraper_utils.urljoin(match_url, 'watching.html')
if not year or not match_year or year == match_year:
result = {'url': scraper_utils.pathify_url(match_url), 'title': scraper_utils.cleanse_title(match_title), 'year': match_year}
results.append(result)
return results
def __login(self):
url = scraper_utils.urljoin(self.base_url, '/apis/v2/user/login.json')
data = {'email': self.username, 'password': self.password, 'rememberMe': True}
referer = scraper_utils.urljoin(self.base_url, '/login')
headers = {'Content-Type': 'application/json', 'Referer': referer}
headers.update(XHR)
html = super(self.__class__, self)._http_get(url, data=json.dumps(data), headers=headers, cache_limit=0)
js_data = scraper_utils.parse_json(html, url)
return js_data.get('status') == 'success'
def get_sources(self, video):
hosters = []
source_url = self.get_url(video)
if not source_url or source_url == FORCE_NO_MATCH: return hosters
url = scraper_utils.urljoin(self.base_url, source_url)
html = self._http_get(url, cache_limit=.5)
views = None
fragment = dom_parser2.parse_dom(
html, 'img', {'src': re.compile('[^"]*view_icon.png')})
if fragment:
match = re.search('(\d+)', fragment[0].content)
if match:
views = match.group(1)
match = re.search('href="([^"]+-full-movie-[^"]+)', html)
if match:
url = match.group(1)
html = self._http_get(url, cache_limit=.5)
sources = self.__get_embedded(html)
for link in dom_parser2.parse_dom(html,
'span', {'class': 'btn-eps'},
req='link'):
link = link.attrs['link']
ajax_url = scraper_utils.urljoin(self.base_url, AJAX_URL)
headers = {'Referer': url}
headers.update(XHR)
html = self._http_get(ajax_url,
params={'v': link},
headers=headers,
cache_limit=.5)
sources.update(self.__get_sources(html))
for source in sources:
if sources[source]['direct']:
host = scraper_utils.get_direct_hostname(self, source)
else:
host = urlparse.urlparse(source).hostname
stream_url = source + scraper_utils.append_headers(
{'User-Agent': scraper_utils.get_ua()})
direct = sources[source]['direct']
quality = sources[source]['quality']
hoster = {
'multi-part': False,
'host': host,
'class': self,
'quality': quality,
'views': views,
'rating': None,
'url': stream_url,
'direct': direct
}
hosters.append(hoster)
return hosters
def get_sources(self, video):
source_url = self.get_url(video)
hosters = []
sources = {}
headers = {'Accept-Language': 'en-US,en;q=0.5'}
if not source_url or source_url == FORCE_NO_MATCH: return hosters
page_url = scraper_utils.urljoin(self.base_url, source_url)
html = self._http_get(page_url, headers=headers, cache_limit=2)
if video.video_type == VIDEO_TYPES.MOVIE:
sources.update(self.__scrape_sources(html, page_url))
pages = set([
r.attrs['href'] for r in dom_parser2.parse_dom(
html, 'a', {'class': 'btn-eps'}, req='href')
])
active = set([
r.attrs['href'] for r in dom_parser2.parse_dom(
html, 'a', {'class': 'active'}, req='href')
])
for page in list(pages - active):
page_url = scraper_utils.urljoin(self.base_url, page)
html = self._http_get(page_url, headers=headers, cache_limit=2)
sources.update(self.__scrape_sources(html, page_url))
else:
for page in self.__match_episode(video, html):
page_url = scraper_utils.urljoin(self.base_url, page)
html = self._http_get(page_url, headers=headers, cache_limit=2)
sources.update(self.__scrape_sources(html, page_url))
for source, values in sources.iteritems():
if not source.lower().startswith('http'): continue
if values['direct']:
host = scraper_utils.get_direct_hostname(self, source)
if host != 'gvideo':
stream_url = source + scraper_utils.append_headers(
{
'User-Agent': scraper_utils.get_ua(),
'Referer': page_url
})
else:
stream_url = source
else:
host = urlparse.urlparse(source).hostname
stream_url = source
hoster = {
'multi-part': False,
'host': host,
'class': self,
'quality': values['quality'],
'views': None,
'rating': None,
'url': stream_url,
'direct': values['direct']
}
hosters.append(hoster)
return hosters
def search(self, video_type, title, year, season=''):
results = []
search_url = scraper_utils.urljoin(self.base_url, '/search/')
headers = {'Accept-Language': 'en-US,en;q=0.5'}
html = self._http_get(search_url,
params={'q': title},
headers=headers,
cache_limit=8)
norm_title = scraper_utils.normalize_title(title)
for _attrs, item in dom_parser2.parse_dom(html, 'div',
{'class': 'ml-item'}):
match_title = dom_parser2.parse_dom(item, 'span',
{'class': 'mli-info'})
match_url = dom_parser2.parse_dom(item, 'a', req='href')
year_frag = dom_parser2.parse_dom(item, 'img', req='alt')
is_episodes = dom_parser2.parse_dom(item, 'span',
{'class': 'mli-eps'})
if (video_type == VIDEO_TYPES.MOVIE
and not is_episodes) or (video_type == VIDEO_TYPES.SEASON
and is_episodes):
if match_title and match_url:
match_url = match_url[0].attrs['href']
match_title = match_title[0].content
match_title = re.sub('</?h2>', '', match_title)
match_title = re.sub('\s+\d{4}$', '', match_title)
if video_type == VIDEO_TYPES.SEASON:
if season and not re.search(
'Season\s+0*%s$' % (season), match_title):
continue
if not match_url.endswith('/'): match_url += '/'
match_url = scraper_utils.urljoin(match_url, 'watch/')
match_year = ''
if video_type == VIDEO_TYPES.MOVIE and year_frag:
match = re.search('\s*-\s*(\d{4})$',
year_frag[0].attrs['alt'])
if match:
match_year = match.group(1)
match_norm_title = scraper_utils.normalize_title(
match_title)
title_match = (norm_title
in match_norm_title) or (match_norm_title
in norm_title)
if title_match and (not year or not match_year
or year == match_year):
result = {
'title': scraper_utils.cleanse_title(match_title),
'year': match_year,
'url': scraper_utils.pathify_url(match_url)
}
results.append(result)
return results
def get_sources(self, video):
hosters = []
sources = {}
source_url = self.get_url(video)
if not source_url or source_url == FORCE_NO_MATCH: return hosters
page_url = scraper_utils.urljoin(self.base_url, source_url)
html = self._http_get(page_url, cache_limit=.5)
match = re.search("load_player\('([^']+)", html)
if not match: return hosters
headers = {'Referer': page_url, 'Server': 'cloudflare-nginx', 'Accept': 'text/html, */*; q=0.01',
'Accept-Language': 'en-US,en;q=0.5', 'Accept-Formating': 'application/json, text/javascript', 'Accept-Encoding': 'gzip, deflate'}
headers.update(XHR)
params = {'id': match.group(1)}
player_url = scraper_utils.urljoin(self.base_url, PLAYER_URL)
html = self._http_get(player_url, params=params, headers=headers, cache_limit=1)
js_data = scraper_utils.parse_json(html, player_url)
pl_url = js_data.get('value') or js_data.get('download')
if not pl_url: return hosters
headers = {'Referer': page_url}
if pl_url.startswith('//'): pl_url = 'https:' + pl_url
html = self._http_get(pl_url, headers=headers, allow_redirect=False, cache_limit=0)
if html.startswith('http'):
streams = [(html, '')]
else:
js_data = scraper_utils.parse_json(html, pl_url)
try: streams = [(source['file'], source.get('label', '')) for source in js_data['playlist'][0]['sources']]
except: streams = []
for stream in streams:
stream_url, label = stream
if scraper_utils.get_direct_hostname(self, stream_url) == 'gvideo':
sources[stream_url] = {'quality': scraper_utils.gv_get_quality(stream_url), 'direct': True}
else:
if label:
quality = scraper_utils.height_get_quality(label)
else:
quality = QUALITIES.HIGH
sources[stream_url] = {'quality': quality, 'direct': False}
for source, value in sources.iteritems():
direct = value['direct']
quality = value['quality']
if direct:
host = scraper_utils.get_direct_hostname(self, source)
else:
host = urlparse.urlparse(source).hostname
stream_url = source + scraper_utils.append_headers({'User-Agent': scraper_utils.get_ua()})
hoster = {'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': direct}
hosters.append(hoster)
return hosters
def get_sources(self, video):
hosters = []
source_url = self.get_url(video)
if not source_url or source_url == FORCE_NO_MATCH: return hosters
page_url = scraper_utils.urljoin(self.base_url, source_url)
html = self._http_get(page_url, require_debrid=True, cache_limit=.5)
if video.video_type == VIDEO_TYPES.MOVIE:
page_url = self.__get_release(html, video)
if page_url is None: return hosters
page_url = scraper_utils.urljoin(self.base_url, page_url)
html = self._http_get(page_url,
require_debrid=True,
cache_limit=.5)
hevc = False
for _attrs, content in dom_parser2.parse_dom(
html, 'span', {'class': 'releaselabel'}):
if re.search('(hevc|x265)', content, re.I):
hevc = 'x265'
match = re.search('(\d+)x(\d+)', content)
if match:
_width, height = match.groups()
quality = scraper_utils.height_get_quality(height)
break
else:
quality = QUALITIES.HIGH
streams = [
attrs['href'] for attrs, _content in dom_parser2.parse_dom(
html, 'a', {'class': 'links'}, req='href')
]
streams += [
content for _attrs, content in dom_parser2.parse_dom(
html, 'pre', {'class': 'links'})
]
for stream_url in streams:
if scraper_utils.excluded_link(stream_url): continue
host = urlparse.urlparse(stream_url).hostname
hoster = {
'multi-part': False,
'host': host,
'class': self,
'views': None,
'url': stream_url,
'rating': None,
'quality': quality,
'direct': False
}
if hevc: hoster['format'] = hevc
hosters.append(hoster)
return hosters
def _get_episode_url(self, show_url, video):
episode_pattern = 'href="([^"]+/season/%s/episode/%s/?)"' % (
video.season, video.episode)
title_pattern = 'href="(?P<url>[^"]+)"[^>]+title="(?:S\d+\s*E\d+:\s*)?(?P<title>[^"]+)'
headers = {'Referer': scraper_utils.urljoin(self.base_url, show_url)}
season_url = scraper_utils.urljoin(show_url,
'/season/%s' % (video.season))
season_url = scraper_utils.urljoin(self.base_url, season_url)
html = self._http_get(season_url, headers=headers, cache_limit=2)
fragment = dom_parser2.parse_dom(html, 'div', {'id': 'episodes'})
return self._default_get_episode_url(fragment, video, episode_pattern,
title_pattern)
def get_sources(self, video):
hosters = []
source_url = self.get_url(video)
if not source_url or source_url == FORCE_NO_MATCH: return hosters
page_url = scraper_utils.urljoin(self.base_url, source_url)
html = self._http_get(page_url, cache_limit=8)
fragment = dom_parser2.parse_dom(html, 'div', {'class': 'playex'})
if fragment: html = fragment[0].content
iframe_url = dom_parser2.parse_dom(html, 'iframe', req='src')
if not iframe_url: return hosters
iframe_url = iframe_url[0].attrs['src']
if iframe_url.startswith('/'):
iframe_url = scraper_utils.urljoin(self.base_url, iframe_url)
html = self._http_get(iframe_url,
headers={'Referer': page_url},
cache_limit=.5)
obj = dom_parser2.parse_dom(html, 'object', req='data')
if obj:
streams = dict((stream_url, {
'quality': scraper_utils.gv_get_quality(stream_url),
'direct': True
}) for stream_url in scraper_utils.parse_google(
self, obj[0].attrs['data']))
else:
streams = scraper_utils.parse_sources_list(self, html)
for stream_url, values in streams.iteritems():
host = scraper_utils.get_direct_hostname(self, stream_url)
if host == 'gvideo':
quality = scraper_utils.gv_get_quality(stream_url)
else:
quality = values['quality']
stream_url += scraper_utils.append_headers({
'User-Agent':
scraper_utils.get_ua(),
'Referer':
page_url
})
source = {
'multi-part': False,
'url': stream_url,
'host': host,
'class': self,
'quality': quality,
'views': None,
'rating': None,
'direct': True
}
hosters.append(source)
return hosters
def get_sources(self, video):
sources = []
source_url = self.get_url(video)
if not source_url or source_url == FORCE_NO_MATCH: return sources
try:
url = scraper_utils.urljoin(self.base_url, source_url)
html = self._http_get(url, cache_limit=2)
pattern = '<iframe id="videoframe" src="([^"]+)'
match = re.search(pattern, html)
url = scraper_utils.urljoin(self.base_url, match.group(1))
html = self._http_get(url, cache_limit=0)
match = re.search('lastChild\.value="([^"]+)"(?:\s*\+\s*"([^"]+))?', html)
secret = ''.join(match.groups(''))
match = re.search('"&t=([^"]+)', html)
t = match.group(1)
match = re.search('(?:\s+|,)s\s*=(\d+)', html)
s_start = int(match.group(1))
match = re.search('(?:\s+|,)m\s*=(\d+)', html)
m_start = int(match.group(1))
for _attrs, fragment in dom_parser2.parse_dom(html, 'div', {'class': 'ripdiv'}):
match = re.match('<b>(.*?)</b>', fragment)
if match:
q_str = match.group(1).replace(' ', '').upper()
quality = QUALITY_MAP.get(q_str, QUALITIES.HIGH)
else:
quality = QUALITIES.HIGH
for attrs, label in dom_parser2.parse_dom(fragment, 'a', {'rel': re.compile('\d+')}, req='onclick'):
link_id = re.sub('[^\d]', '', attrs['onclick'])
match = re.match('([^:]+:)\s*(.*)', label)
if not match: continue
version, host_fragment = match.groups()
source = {'multi-part': False, 'quality': quality, 'class': self, 'version': version, 'rating': None, 'views': None, 'direct': False}
source['host'] = re.sub('(</?[^>]*>)', '', host_fragment)
s = s_start + random.randint(3, 100)
m = m_start + random.randint(21, 100)
url = AJAX_URL.format(link_id=link_id, s=s, m=m, secret=secret, t=t)
source['url'] = url
sources.append(source)
except Exception as e:
logger.log('Failure (%s) during icefilms get sources: |%s|' % (str(e), video), log_utils.LOGWARNING)
return sources
def search(self, video_type, title, year, season=''): # @UnusedVariable
results = []
search_url = scraper_utils.urljoin(self.base_url, '/results')
params = {'q': title}
referer = search_url + '?' + urllib.urlencode(params)
headers = {'Referer': referer}
headers.update(XHR)
_html = self._http_get(scraper_utils.urljoin(self.base_url, 'av'),
headers=headers,
method='POST',
cache_limit=0)
cookies = {'begin_referer': referer, 'prounder': 1}
html = self._http_get(search_url,
params=params,
cookies=cookies,
cache_limit=8)
if any('jquery.js' in match.attrs['src']
for match in dom_parser2.parse_dom(html, 'script', req='src')):
html = self._http_get(search_url,
params=params,
cookies=cookies,
cache_limit=0)
for _attrs, result in dom_parser2.parse_dom(html, 'div',
{'class': 'cell'}):
title_frag = dom_parser2.parse_dom(result, 'div',
{'class': 'video_title'})
year_frag = dom_parser2.parse_dom(result, 'div',
{'class': 'video_quality'})
if not title_frag: continue
match = dom_parser2.parse_dom(title_frag[0].content,
'a',
req='href')
if not match: continue
match_url = match[0].attrs['href']
match_title = match[0].content
try:
match = re.search('\s+(\d{4})\s+', year_frag[0].content)
match_year = match.group(1)
except:
match_year = ''
if not year or not match_year or year == match_year:
result = {
'url': scraper_utils.pathify_url(match_url),
'title': scraper_utils.cleanse_title(match_title),
'year': match_year
}
results.append(result)
return results
def __add_torrent(self, hash_id):
list_url = scraper_utils.urljoin(self.base_url, LIST_URL)
js_data = self._json_get(list_url, cache_limit=0)
for transfer in js_data.get('transfers', []):
if transfer['hash'].lower() == hash_id:
return True
add_url = scraper_utils.urljoin(self.base_url, ADD_URL)
data = {'src': MAGNET_LINK % hash_id}
js_data = self._json_get(add_url, data=data, cache_limit=0)
if js_data.get('status') == 'success':
return True
else:
return False
def _get_episode_url(self, show_url, video):
url = scraper_utils.urljoin(self.base_url, show_url)
html = self._http_get(url, cache_limit=24)
fragment = dom_parser2.parse_dom(html, 'div', {'class': 'poster'})
if not fragment: return
show_url = dom_parser2.parse_dom(fragment[0].content, 'a', req='href')
if not show_url: return
show_url = scraper_utils.urljoin(self.base_url,
show_url[0].attrs['href'])
html = self._http_get(show_url, cache_limit=2)
fragment = dom_parser2.parse_dom(html, 'div', {'id': 'servers'})
episode_pattern = 'href="([^"]+)[^>]+>[Ee][Pp]\s*(?:[Ss]0*%s-)?E?p?0*%s(?!\d)' % (
video.season, video.episode)
return self._default_get_episode_url(fragment or html, video,
episode_pattern)
def search(self, video_type, title, year, season=''): # @UnusedVariable
results = []
search_url = scraper_utils.urljoin(self.base_url, '/advanced-search/')
headers = {'Referer': self.base_url}
params = {'search_query': title, 'orderby': '', 'order': '', 'wpas': 1}
html = self._http_get(search_url,
params=params,
headers=headers,
cache_limit=8)
norm_title = scraper_utils.normalize_title(title)
for _attrs, item in dom_parser2.parse_dom(html, 'div',
{'class': 'datos'}):
match = dom_parser2.parse_dom(item, 'a', req='href')
if not match: continue
match_url = match[0].attrs['href']
is_tvshow = '/tvshows/' in match_url
if is_tvshow and video_type == VIDEO_TYPES.MOVIE or not is_tvshow and video_type == VIDEO_TYPES.TVSHOW:
continue
match_title = match[0].content
match_title, match_year = scraper_utils.extra_year(match_title)
if scraper_utils.normalize_title(match_title) in norm_title and (
not year or not match_year or year == match_year):
result = {
'title': scraper_utils.cleanse_title(match_title),
'year': match_year,
'url': scraper_utils.pathify_url(match_url)
}
results.append(result)
return results
def get_sources(self, video):
hosters = []
source_url = self.get_url(video)
if not source_url or source_url == FORCE_NO_MATCH: return hosters
page_url = scraper_utils.urljoin(self.base_url, source_url)
html = self._http_get(page_url, cache_limit=.5)
best_quality = QUALITIES.HIGH
fragment = dom_parser2.parse_dom(html, 'div', {'class': 'entry'})
if fragment:
for match in re.finditer('href="[^"]*/movies-quality/[^"]*[^>]*>([^<]+)', fragment[0].content, re.I):
quality = Q_MAP.get(match.group(1).upper(), QUALITIES.HIGH)
if Q_ORDER[quality] > Q_ORDER[best_quality]:
best_quality = quality
sources = []
for attrs, _content in dom_parser2.parse_dom(html, 'a', req='data-vid'):
try:
vid_url = dom_parser2.parse_dom(scraper_utils.cleanse_title(attrs['data-vid']), 'iframe', req='src')
sources.append(vid_url[0])
except:
pass
fragment = dom_parser2.parse_dom(html, 'table', {'class': 'additional-links'})
if fragment:
sources += dom_parser2.parse_dom(fragment[0].content, 'a', req='href')
for stream_url in sources:
stream_url = stream_url.attrs.get('href') or stream_url.attrs.get('src')
host = urlparse.urlparse(stream_url).hostname
quality = scraper_utils.get_quality(video, host, best_quality)
hoster = {'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': False}
hosters.append(hoster)
return hosters
def search(self, video_type, title, year, season=''): # @UnusedVariable
results = []
search_url = scraper_utils.urljoin(self.base_url, '/search')
html = self._http_get(search_url, params={'q': title}, cache_limit=8)
for _attrs, item in dom_parser2.parse_dom(html, 'div',
{'class': 'movie-item'}):
match = dom_parser2.parse_dom(item,
'a', {'itemprop': 'url'},
req='href')
if not match: continue
match_url, match_title_year = match[0].attrs['href'], match[
0].content
match_title, match_year = scraper_utils.extra_year(
match_title_year)
if not match_year:
try:
match_year = dom_parser2.parse_dom(
item, 'div', {'class': 'overlay-year'})[0].content
except:
match_year = ''
if not year or not match_year or year == match_year:
result = {
'title': scraper_utils.cleanse_title(match_title),
'year': match_year,
'url': scraper_utils.pathify_url(match_url)
}
results.append(result)
return results
def _get_episode_url(self, show_url, video):
episode_pattern = 'href=([^>]+)>0*%sx0*%s\s+' % (video.season, video.episode)
title_pattern = 'href=(?P<url>[^>]+)>(?:\d+x\d+\s+)+(?P<title>[^<]+)'
show_url = scraper_utils.urljoin(self.base_url, show_url)
html = self._http_get(show_url, cache_limit=2)
fragment = dom_parser2.parse_dom(html, 'span', {'class': 'list'})
return self._default_get_episode_url(fragment, video, episode_pattern, title_pattern)
def _get_episode_url(self, show_url, video):
force_title = scraper_utils.force_title(video)
title_fallback = kodi.get_setting('title-fallback') == 'true'
norm_title = scraper_utils.normalize_title(video.ep_title)
page_url = [show_url]
too_old = False
while page_url and not too_old:
url = scraper_utils.urljoin(self.base_url, page_url[0])
html = self._http_get(url, require_debrid=True, cache_limit=1)
for _attrs, post in dom_parser2.parse_dom(
html, 'div', {'id': re.compile('post-\d+')}):
if self.__too_old(post):
too_old = True
break
if show_url not in post: continue
match = dom_parser2.parse_dom(post, 'a', req='href')
if match:
url, title = match[0].attrs['href'], match[0].content
if not force_title:
if scraper_utils.release_check(video,
title,
require_title=False):
return scraper_utils.pathify_url(url)
else:
if title_fallback and norm_title:
match = re.search('</strong>(.*?)</p>', post)
if match and norm_title == scraper_utils.normalize_title(
match.group(1)):
return scraper_utils.pathify_url(url)
page_url = dom_parser2.parse_dom(html,
'a', {'class': 'nextpostslink'},
req='href')
if page_url: page_url = [page_url[0].attrs['href']]
def search(self, video_type, title, year, season=''): # @UnusedVariable
results = []
seen_urls = set()
for page in ['/latest-added/', '/popular-today/', '/most-popular/']:
url = scraper_utils.urljoin(self.base_url, page)
html = self._http_get(url, cache_limit=24)
fragment = dom_parser2.parse_dom(html, 'div', {'class': 'home'})
if fragment:
norm_title = scraper_utils.normalize_title(title)
for attrs, match_title_year in dom_parser2.parse_dom(
fragment[0].content, 'a', req='href'):
match_url = attrs['href']
match_title, match_year = scraper_utils.extra_year(
match_title_year)
if norm_title in scraper_utils.normalize_title(
match_title) and (not year or not match_year
or year == match_year):
match_url = scraper_utils.pathify_url(match_url)
if match_url in seen_urls: continue
seen_urls.add(match_url)
result = {
'url': match_url,
'title': scraper_utils.cleanse_title(match_title),
'year': match_year
}
results.append(result)
return results
def get_sources(self, video):
source_url = self.get_url(video)
hosters = []
if not source_url or source_url == FORCE_NO_MATCH: return hosters
page_url = scraper_utils.urljoin(self.base_url, source_url)
html = self._http_get(page_url, cache_limit=.25)
for _attrs, button in dom_parser2.parse_dom(
html, 'li', {'class': 'playing_button'}):
try:
link = dom_parser2.parse_dom(button, 'a', req='href')
match = re.search('php\?.*?=?([^"]+)', link[0].attrs['href'])
stream_url = base64.b64decode(match.group(1))
match = re.search('(https?://.*)', stream_url)
stream_url = match.group(1)
host = urlparse.urlparse(stream_url).hostname
quality = scraper_utils.get_quality(video, host,
QUALITIES.HIGH)
hoster = {
'multi-part': False,
'host': host,
'class': self,
'quality': quality,
'views': None,
'rating': None,
'url': stream_url,
'direct': False
}
hosters.append(hoster)
except Exception as e:
logger.log(
'Exception during tvonline source: %s - |%s|' %
(e, button), log_utils.LOGDEBUG)
return hosters
def search(self, video_type, title, year, season=''): # @UnusedVariable
results = []
search_in = 'm' if video_type == VIDEO_TYPES.MOVIE else 't'
search_url = scraper_utils.urljoin(self.base_url, '/search')
html = self._http_get(search_url,
data={
'searchquery': title,
'searchin': search_in
},
cache_limit=8)
fragment = dom_parser2.parse_dom(html, 'div', {'class': 'search-page'})
if not fragment: return results
fragment = dom_parser2.parse_dom(fragment[0].content, 'table')
if not fragment: return results
for attrs, match_title_year in dom_parser2.parse_dom(
fragment[0].content, 'a', req='href'):
match_url = attrs['href']
match_title, match_year = scraper_utils.extra_year(
match_title_year)
if not year or not match_year or year == match_year:
result = {
'url': scraper_utils.pathify_url(match_url),
'title': scraper_utils.cleanse_title(match_title),
'year': match_year
}
results.append(result)
return results
def get_sources(self, video):
hosters = []
source_url = self.get_url(video)
if not source_url or source_url == FORCE_NO_MATCH: return hosters
url = scraper_utils.urljoin(self.base_url, source_url)
html = self._http_get(url, cache_limit=.5)
match = re.search('This movie is of poor quality', html, re.I)
if match:
quality = QUALITIES.LOW
else:
quality = QUALITIES.HIGH
for match in re.finditer('href="([^"]+/embed\d*/[^"]+)', html):
url = match.group(1)
embed_html = self._http_get(url, cache_limit=.5)
hosters += self.__get_links(embed_html)
pattern = 'href="([^"]+)[^>]*>\s*<[^>]+play_video.gif'
for match in re.finditer(pattern, html, re.I):
stream_url = match.group(1)
host = urlparse.urlparse(stream_url).hostname
quality = scraper_utils.get_quality(video, host, quality)
hoster = {
'multi-part': False,
'url': stream_url,
'host': host,
'class': self,
'quality': quality,
'rating': None,
'views': None,
'direct': False
}
hosters.append(hoster)
return hosters
def __get_ajax_sources(self, html, page_url):
hosters = []
match = re.search('''url\s*:\s*"([^"]+)"\s*,\s*data:'id=''', html)
if match:
ajax_url = match.group(1)
for data_id in re.findall("kaynakdegis\('([^']+)", html):
url = scraper_utils.urljoin(self.base_url, ajax_url)
data = {'id': data_id}
headers = {'Referer': page_url}
headers.update(XHR)
result = self._http_get(url,
data=data,
headers=headers,
cache_limit=.5)
js_data = scraper_utils.parse_json(result, url)
if 'iframe' in js_data:
if self.base_url in js_data['iframe']:
hosters += self.__get_iframe_sources(
js_data['iframe'], page_url)
else:
hosters.append(
self.__create_source(js_data['iframe'],
720,
page_url,
direct=False))
else:
hosters += self.__get_js_sources(js_data, page_url)
pass
return hosters