def get_sources(self, video):
source_url = self.get_url(video)
hosters = []
if source_url and source_url != FORCE_NO_MATCH:
params = urlparse.parse_qs(source_url)
if video.video_type == VIDEO_TYPES.MOVIE:
cmd = '{"jsonrpc": "2.0", "method": "VideoLibrary.GetMovieDetails", "params": {"movieid": %s, "properties" : ["file", "playcount", "streamdetails"]}, "id": "libMovies"}'
result_key = 'moviedetails'
else:
cmd = '{"jsonrpc": "2.0", "method": "VideoLibrary.GetEpisodeDetails", "params": {"episodeid": %s, "properties" : ["file", "playcount", "streamdetails"]}, "id": "libTvShows"}'
result_key = 'episodedetails'
run = cmd % (params['id'][0])
meta = xbmc.executeJSONRPC(run)
meta = scraper_utils.parse_json(meta)
log_utils.log('Source Meta: %s' % (meta), log_utils.LOGDEBUG)
if 'result' in meta and result_key in meta['result']:
details = meta['result'][result_key]
def_quality = [item[0] for item in sorted(SORT_KEYS['quality'].items(), key=lambda x:x[1])][self.def_quality]
host = {'multi-part': False, 'class': self, 'url': details['file'], 'host': 'XBMC Library', 'quality': def_quality, 'views': details['playcount'], 'rating': None, 'direct': True}
stream_details = details['streamdetails']
if len(stream_details['video']) > 0 and 'width' in stream_details['video'][0]:
host['quality'] = scraper_utils.width_get_quality(stream_details['video'][0]['width'])
hosters.append(host)
return hosters
def __get_links(self, url, video):
hosters = []
search_url = self.__translate_search(url)
html = self._http_get(search_url, cache_limit=.5)
js_result = scraper_utils.parse_json(html, search_url)
if 'data' in js_result:
for item in js_result['data']:
post_hash, size, post_title, ext, duration = item['0'], item['4'], item['10'], item['11'], item['14']
checks = [False] * 6
if not scraper_utils.title_check(video, post_title): checks[0] = True
if 'alangs' in item and item['alangs'] and 'eng' not in item['alangs']: checks[1] = True
if re.match('^\d+s', duration) or re.match('^[0-5]m', duration): checks[2] = True
if 'passwd' in item and item['passwd']: checks[3] = True
if 'virus' in item and item['virus']: checks[4] = True
if 'type' in item and item['type'].upper() != 'VIDEO': checks[5] = True
if any(checks):
log_utils.log('EasyNews Post excluded: %s - |%s|' % (checks, item), log_utils.LOGDEBUG)
continue
stream_url = urllib.quote('%s%s/%s%s' % (post_hash, ext, post_title, ext))
stream_url = 'http://members.easynews.com/dl/%s' % (stream_url)
stream_url = stream_url + '|Cookie=%s' % (self._get_stream_cookies())
host = self._get_direct_hostname(stream_url)
quality = scraper_utils.width_get_quality(item['width'])
hoster = {'multi-part': False, 'class': self, 'views': None, 'url': stream_url, 'rating': None, 'host': host, 'quality': quality, 'direct': True}
if size: hoster['size'] = size
if post_title: hoster['extra'] = post_title
hosters.append(hoster)
return hosters
def __get_links(self, url, video):
hosters = []
search_url = self.__translate_search(url)
html = self._http_get(search_url, cache_limit=.5)
js_result = scraper_utils.parse_json(html, search_url)
if 'data' in js_result:
for item in js_result['data']:
post_hash, size, post_title, ext, duration = item['0'], item['4'], item['10'], item['11'], item['14']
checks = [False] * 6
if not scraper_utils.title_check(video, post_title): checks[0] = True
if 'alangs' in item and item['alangs'] and 'eng' not in item['alangs']: checks[1] = True
if re.match('^\d+s', duration) or re.match('^[0-5]m', duration): checks[2] = True
if 'passwd' in item and item['passwd']: checks[3] = True
if 'virus' in item and item['virus']: checks[4] = True
if 'type' in item and item['type'].upper() != 'VIDEO': checks[5] = True
if any(checks):
log_utils.log('EasyNews Post excluded: %s - |%s|' % (checks, item), log_utils.LOGDEBUG)
continue
stream_url = urllib.quote('%s%s/%s%s' % (post_hash, ext, post_title, ext))
stream_url = 'http://members.easynews.com/dl/%s' % (stream_url)
stream_url = stream_url + '|Cookie=%s' % (self._get_stream_cookies())
host = self._get_direct_hostname(stream_url)
quality = scraper_utils.width_get_quality(item['width'])
hoster = {'multi-part': False, 'class': self, 'views': None, 'url': stream_url, 'rating': None, 'host': host, 'quality': quality, 'direct': True}
if size: hoster['size'] = size
if post_title: hoster['extra'] = post_title
hosters.append(hoster)
return hosters
def get_sources(self, video):
source_url = self.get_url(video)
hosters = []
if source_url and source_url != FORCE_NO_MATCH:
params = urlparse.parse_qs(source_url)
if video.video_type == VIDEO_TYPES.MOVIE:
cmd = '{"jsonrpc": "2.0", "method": "VideoLibrary.GetMovieDetails", "params": {"movieid": %s, "properties" : ["file", "playcount", "streamdetails"]}, "id": "libMovies"}'
result_key = 'moviedetails'
else:
cmd = '{"jsonrpc": "2.0", "method": "VideoLibrary.GetEpisodeDetails", "params": {"episodeid": %s, "properties" : ["file", "playcount", "streamdetails"]}, "id": "libTvShows"}'
result_key = 'episodedetails'
run = cmd % (params['id'][0])
meta = xbmc.executeJSONRPC(run)
meta = scraper_utils.parse_json(meta)
log_utils.log('Source Meta: %s' % (meta), log_utils.LOGDEBUG)
if 'result' in meta and result_key in meta['result']:
details = meta['result'][result_key]
def_quality = [item[0] for item in sorted(SORT_KEYS['quality'].items(), key=lambda x:x[1])][self.def_quality]
host = {'multi-part': False, 'class': self, 'url': details['file'], 'host': 'XBMC Library', 'quality': def_quality, 'views': details['playcount'], 'rating': None, 'direct': True}
stream_details = details['streamdetails']
if len(stream_details['video']) > 0 and 'width' in stream_details['video'][0]:
host['quality'] = scraper_utils.width_get_quality(stream_details['video'][0]['width'])
hosters.append(host)
return hosters
def __get_cloud_links(self, html, page_url, sub):
hosters = []
html = html.replace('\\"', '"').replace('\\/', '/')
match = re.search("dizi_kapak_getir\('([^']+)", html)
if match:
ep_id = match.group(1)
for script_url in dom_parser.parse_dom(html, 'script', {'data-cfasync': 'false'}, ret='src'):
html = self._http_get(script_url, cache_limit=24)
match1 = re.search("var\s+kapak_url\s*=\s*'([^']+)", html)
match2 = re.search("var\s+aCtkp\s*=\s*'([^']+)", html)
if match1 and match2:
link_url = '%s?fileid=%s&access_token=%s' % (match1.group(1), ep_id, match2.group(1))
headers = {'Referer': page_url}
html = self._http_get(link_url, headers=headers, cache_limit=.5)
js_data = scraper_utils.parse_json(html, link_url)
for variant in js_data.get('variants', {}):
stream_host = random.choice(variant.get('hosts', []))
if stream_host:
stream_url = STREAM_URL % (stream_host, variant['path'], scraper_utils.get_ua(), urllib.quote(page_url))
if not stream_url.startswith('http'):
stream_url = 'http://' + stream_url
host = self._get_direct_hostname(stream_url)
if 'width' in variant:
quality = scraper_utils.width_get_quality(variant['width'])
elif 'height' in variant:
quality = scraper_utils.height_get_quality(variant['height'])
else:
quality = QUALITIES.HIGH
hoster = {'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': True}
hoster['subs'] = sub
hosters.append(hoster)
return hosters
def __get_links(self, url, video):
hosters = []
search_url = urlparse.urljoin(self.base_url, SEARCH_URL)
query = self.__translate_search(url)
result = self._http_get(search_url, data=query, allow_redirect=False, cache_limit=.5)
if 'files' in result:
for item in result['files']:
checks = [False] * 6
if 'type' not in item or item['type'].upper() != 'VIDEO': checks[0] = True
if 'is_ready' in item and item['is_ready'] != '1': checks[1] = True
if 'av_result' in item and item['av_result'] in ['warning', 'infected']: checks[2] = True
if 'video_info' not in item: checks[3] = True
if 'video_info' in item and item['video_info'] and not re.search('#0:(?:0|1)(?:\(eng\)|\(und\))?:\s*Audio:', item['video_info']): checks[4] = True
if video.video_type == VIDEO_TYPES.EPISODE:
sxe = '[. ][Ss]%02d[Ee]%02d[. ]' % (int(video.season), int(video.episode))
if not re.search(sxe, item['name']):
if video.ep_airdate:
airdate_pattern = '[. ]%s[. ]%02d[. ]%02d[. ]' % (video.ep_airdate.year, video.ep_airdate.month, video.ep_airdate.day)
if not re.search(airdate_pattern, item['name']): checks[5] = True
if any(checks):
log_utils.log('Furk.net result excluded: %s - |%s|' % (checks, item['name']), log_utils.LOGDEBUG)
continue
match = re.search('(\d{3,})\s?x\s?(\d{3,})', item['video_info'])
if match:
width, _ = match.groups()
quality = scraper_utils.width_get_quality(width)
else:
if video.video_type == VIDEO_TYPES.MOVIE:
_, _, height, _ = scraper_utils.parse_movie_link(item['name'])
quality = scraper_utils.height_get_quality(height)
elif video.video_type == VIDEO_TYPES.EPISODE:
_, _, _, height, _ = scraper_utils.parse_episode_link(item['name'])
if int(height) > -1:
quality = scraper_utils.height_get_quality(height)
else:
quality = QUALITIES.HIGH
else:
quality = QUALITIES.HIGH
if 'url_pls' in item:
size_gb = scraper_utils.format_size(int(item['size']), 'B')
if self.max_bytes and int(item['size']) > self.max_bytes:
log_utils.log('Result skipped, Too big: |%s| - %s (%s) > %s (%sGB)' % (item['name'], item['size'], size_gb, self.max_bytes, self.max_gb))
continue
stream_url = item['url_pls']
host = self._get_direct_hostname(stream_url)
hoster = {'multi-part': False, 'class': self, 'views': None, 'url': stream_url, 'rating': None, 'host': host, 'quality': quality, 'direct': True}
hoster['size'] = size_gb
hoster['extra'] = item['name']
hosters.append(hoster)
else:
log_utils.log('Furk.net result skipped - no playlist: |%s|' % (json.dumps(item)), log_utils.LOGDEBUG)
return hosters
def get_sources(self, video):
source_url = self.get_url(video)
hosters = []
if source_url and source_url != FORCE_NO_MATCH:
url = urlparse.urljoin(self.base_url, source_url)
html = self._http_get(url, cache_limit=.5)
match = re.search('((?:pic|emb|vb)=[^<]+)', html)
if match:
embeds = match.group(1)
for stream_url in embeds.split('&'):
if stream_url.startswith('vb='):
stream_url = 'http://www.vidbux.com/%s' % (
stream_url[3:])
host = 'vidbux.com'
direct = False
quality = scraper_utils.get_quality(
video, host, QUALITIES.HD1080)
elif stream_url.startswith('pic='):
data = {'url': stream_url[4:]}
html = self._http_get(PHP_URL,
data=data,
auth=False,
cache_limit=1)
js_data = scraper_utils.parse_json(html, PHP_URL)
host = self._get_direct_hostname(stream_url)
direct = True
for item in js_data:
if 'medium' in item and item['medium'] == 'video':
stream_url = item['url']
quality = scraper_utils.width_get_quality(
item['width'])
break
else:
continue
elif stream_url.startswith('emb='):
stream_url = stream_url.replace('emb=', '')
host = urlparse.urlparse(stream_url).hostname
direct = False
quality = scraper_utils.get_quality(
video, host, QUALITIES.HD720)
else:
continue
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_quality(self, item, video):
if 'width' in item:
return scraper_utils.width_get_quality(item['width'])
elif 'height' in item:
return scraper_utils.height_get_quality(item['height'])
else:
if video.video_type == VIDEO_TYPES.MOVIE:
_title, _year, height, _extra = scraper_utils.parse_movie_link(item['name'])
else:
_title, _season, _episode, height, _extra = scraper_utils.parse_episode_link(item['name'])
return scraper_utils.height_get_quality(height)
def __get_cloud_links(self, html, page_url, sub):
hosters = []
html = html.replace('\\"', '"').replace('\\/', '/')
match = re.search("dizi_kapak_getir\('([^']+)", html)
if match:
ep_id = match.group(1)
for attrs, _content in dom_parser2.parse_dom(
html, 'script', {'data-cfasync': 'false'}, req='src'):
script_url = attrs['src']
html = self._http_get(script_url, cache_limit=24)
match1 = re.search("var\s+kapak_url\s*=\s*'([^']+)", html)
match2 = re.search("var\s+aCtkp\s*=\s*'([^']+)", html)
if match1 and match2:
link_url = '%s?fileid=%s&access_token=%s' % (
match1.group(1), ep_id, match2.group(1))
headers = {'Referer': page_url}
html = self._http_get(link_url,
headers=headers,
cache_limit=.5)
js_data = scraper_utils.parse_json(html, link_url)
for variant in js_data.get('variants', {}):
stream_host = random.choice(variant.get('hosts', []))
if stream_host:
stream_url = stream_host + variant[
'path'] + scraper_utils.append_headers(
{
'User-Agent': scraper_utils.get_ua(),
'Referer': page_url
})
if not stream_url.startswith('http'):
stream_url = 'http://' + stream_url
host = scraper_utils.get_direct_hostname(
self, stream_url)
if 'width' in variant:
quality = scraper_utils.width_get_quality(
variant['width'])
elif 'height' in variant:
quality = scraper_utils.height_get_quality(
variant['height'])
else:
quality = QUALITIES.HIGH
hoster = {
'multi-part': False,
'host': host,
'class': self,
'quality': quality,
'views': None,
'rating': None,
'url': stream_url,
'direct': True
}
hoster['subs'] = sub
hosters.append(hoster)
return hosters
def __get_links(self, url, video):
hosters = []
search_url = self.__translate_search(url)
html = self._http_get(search_url, cache_limit=.5)
js_result = scraper_utils.parse_json(html, search_url)
down_url = js_result.get('downURL')
dl_farm = js_result.get('dlFarm')
dl_port = js_result.get('dlPort')
for item in js_result.get('data', []):
post_hash, size, post_title, ext, duration = item['0'], item['4'], item['10'], item['11'], item['14']
checks = [False] * 6
if not scraper_utils.release_check(video, post_title): checks[0] = True
if 'alangs' in item and item['alangs'] and 'eng' not in item['alangs']: checks[1] = True
if re.match('^\d+s', duration) or re.match('^[0-5]m', duration): checks[2] = True
if 'passwd' in item and item['passwd']: checks[3] = True
if 'virus' in item and item['virus']: checks[4] = True
if 'type' in item and item['type'].upper() != 'VIDEO': checks[5] = True
if any(checks):
log_utils.log('EasyNews Post excluded: %s - |%s|' % (checks, item), log_utils.LOGDEBUG)
continue
stream_url = down_url + urllib.quote('/%s/%s/%s%s/%s%s' % (dl_farm, dl_port, post_hash, ext, post_title, ext))
stream_url = stream_url + '|Authorization=%s' % (urllib.quote(self.auth))
host = self._get_direct_hostname(stream_url)
quality = None
if 'width' in item:
try: width = int(item['width'])
except: width = 0
if width:
quality = scraper_utils.width_get_quality(width)
if quality is None:
if video.video_type == VIDEO_TYPES.MOVIE:
meta = scraper_utils.parse_movie_link(post_title)
else:
meta = scraper_utils.parse_episode_link(post_title)
quality = scraper_utils.height_get_quality(meta['height'])
if self.max_bytes:
match = re.search('([\d.]+)\s+(.*)', size)
if match:
size_bytes = scraper_utils.to_bytes(*match.groups())
if size_bytes > self.max_bytes:
log_utils.log('Result skipped, Too big: |%s| - %s (%s) > %s (%s GB)' % (post_title, size_bytes, size, self.max_bytes, self.max_gb))
continue
hoster = {'multi-part': False, 'class': self, 'views': None, 'url': stream_url, 'rating': None, 'host': host, 'quality': quality, 'direct': True}
if any(i for i in ['X265', 'HEVC'] if i in post_title.upper()): hoster['format'] = 'x265'
if size: hoster['size'] = size
if post_title: hoster['extra'] = post_title
hosters.append(hoster)
return hosters
def __get_quality(self, item, video):
if 'width' in item:
return scraper_utils.width_get_quality(item['width'])
elif 'height' in item:
return scraper_utils.height_get_quality(item['height'])
else:
if video.video_type == VIDEO_TYPES.MOVIE:
_title, _year, height, _extra = scraper_utils.parse_movie_link(
item['name'])
else:
_title, _season, _episode, height, _extra = scraper_utils.parse_episode_link(
item['name'])
return scraper_utils.height_get_quality(height)
def __get_quality(self, item, video):
if item.get('width'):
return scraper_utils.width_get_quality(item['width'])
elif item.get('height'):
return scraper_utils.height_get_quality(item['height'])
elif 'name' in item:
if video.video_type == VIDEO_TYPES.MOVIE:
meta = scraper_utils.parse_movie_link(item['name'])
else:
meta = scraper_utils.parse_episode_link(item['name'])
return scraper_utils.height_get_quality(meta['height'])
else:
return QUALITIES.HIGH
def __get_quality(self, item, video):
if 'width' in item and item['width']:
return scraper_utils.width_get_quality(item['width'])
elif 'height' in item and item['height']:
return scraper_utils.height_get_quality(item['height'])
elif 'name' in item:
if video.video_type == VIDEO_TYPES.MOVIE:
meta = scraper_utils.parse_movie_link(item['name'])
else:
meta = scraper_utils.parse_episode_link(item['name'])
return scraper_utils.height_get_quality(meta['height'])
else:
return QUALITIES.HIGH
def get_sources(self, video):
source_url = self.get_url(video)
hosters = []
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('((?:pic|emb|vb|dir|emb2)=[^<]+)', html)
if match:
embeds = match.group(1)
for stream_url in embeds.split('&'):
if stream_url.startswith('dir='):
headers = {'Referer': url}
html = self._http_get(DIR_URL, params={'v': stream_url[3:]}, headers=headers, auth=False, allow_redirect=False, cache_limit=.5)
if html.startswith('http'):
stream_url = html + scraper_utils.append_headers({'User-Agent': scraper_utils.get_ua(), 'Referer': url})
host = scraper_utils.get_direct_hostname(self, stream_url)
direct = True
quality = QUALITIES.HD720
else:
continue
elif stream_url.startswith('vb='):
stream_url = 'http://www.vidbux.com/%s' % (stream_url[3:])
host = 'vidbux.com'
direct = False
quality = scraper_utils.get_quality(video, host, QUALITIES.HD1080)
elif stream_url.startswith('pic='):
data = {'url': stream_url[4:]}
html = self._http_get(PHP_URL, data=data, auth=False, cache_limit=1)
js_data = scraper_utils.parse_json(html, PHP_URL)
host = scraper_utils.get_direct_hostname(self, stream_url)
direct = True
for item in js_data:
if item.get('medium') == 'video':
stream_url = item['url']
quality = scraper_utils.width_get_quality(item['width'])
break
else:
continue
elif stream_url.startswith(('emb=', 'emb2=')):
stream_url = re.sub('emb\d*=', '', stream_url)
host = urlparse.urlparse(stream_url).hostname
direct = False
quality = scraper_utils.get_quality(video, host, QUALITIES.HD720)
else:
continue
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_pk_links(self, html):
hosters = []
match = re.search('var\s+parametros\s*=\s*"([^"]+)', html)
if match:
params = scraper_utils.parse_query(match.group(1))
if 'pic' in params:
data = {'sou': 'pic', 'fv': '25', 'url': params['pic']}
html = self._http_get(PK_URL,
headers=XHR,
data=data,
cache_limit=0)
js_data = scraper_utils.parse_json(html, PK_URL)
for item in js_data:
if 'url' in item and item['url']:
if 'width' in item and item['width']:
quality = scraper_utils.width_get_quality(
item['width'])
elif 'height' in item and item['height']:
quality = scraper_utils.height_get_quality(
item['height'])
else:
quality = QUALITIES.HD720
stream_url = item['url'] + scraper_utils.append_headers(
{'User-Agent': scraper_utils.get_ua()})
hoster = {
'multi-part':
False,
'url':
stream_url,
'class':
self,
'quality':
quality,
'host':
scraper_utils.get_direct_hostname(
self, item['url']),
'rating':
None,
'views':
None,
'direct':
True
}
hosters.append(hoster)
return hosters
def __get_links(self, url, video):
hosters = []
search_url = scraper_utils.urljoin(self.base_url, SEARCH_URL)
query = self.__translate_search(url)
result = self._http_get(search_url, data=query, allow_redirect=False, cache_limit=.5)
for item in result.get('files', []):
checks = [False] * 6
if item.get('type', '').upper() != 'VIDEO': checks[0] = True
if item.get('is_ready') != '1': checks[1] = True
if item.get('av_result') in ['warning', 'infected']: checks[2] = True
if 'video_info' not in item: checks[3] = True
if item.get('video_info') and not re.search('#0:(0|1)(\((eng|und)\))?:\s*Audio:', item['video_info'], re.I): checks[4] = True
if not scraper_utils.release_check(video, item['name']): checks[5] = True
if any(checks):
logger.log('Furk.net result excluded: %s - |%s|' % (checks, item['name']), log_utils.LOGDEBUG)
continue
match = re.search('(\d{3,})\s*x\s*(\d{3,})', item['video_info'])
if match:
width, _height = match.groups()
quality = scraper_utils.width_get_quality(width)
else:
if video.video_type == VIDEO_TYPES.MOVIE:
meta = scraper_utils.parse_movie_link(item['name'])
else:
meta = scraper_utils.parse_episode_link(item['name'])
quality = scraper_utils.height_get_quality(meta['height'])
if 'url_pls' in item:
size_gb = scraper_utils.format_size(int(item['size']), 'B')
if self.max_bytes and int(item['size']) > self.max_bytes:
logger.log('Result skipped, Too big: |%s| - %s (%s) > %s (%sGB)' % (item['name'], item['size'], size_gb, self.max_bytes, self.max_gb))
continue
stream_url = item['url_pls']
host = scraper_utils.get_direct_hostname(self, stream_url)
hoster = {'multi-part': False, 'class': self, 'views': None, 'url': stream_url, 'rating': None, 'host': host, 'quality': quality, 'direct': True}
hoster['size'] = size_gb
hoster['extra'] = item['name']
hosters.append(hoster)
else:
logger.log('Furk.net result skipped - no playlist: |%s|' % (json.dumps(item)), log_utils.LOGDEBUG)
return hosters
def __get_pk_links(self, html):
hosters = []
match = re.search('var\s+parametros\s*=\s*"([^"]+)', html)
if match:
params = scraper_utils.parse_query(match.group(1))
if 'pic' in params:
data = {'sou': 'pic', 'fv': '25', 'url': params['pic']}
html = self._http_get(PK_URL, headers=XHR, data=data, cache_limit=0)
js_data = scraper_utils.parse_json(html, PK_URL)
for item in js_data:
if 'url' in item and item['url']:
if 'width' in item and item['width']:
quality = scraper_utils.width_get_quality(item['width'])
elif 'height' in item and item['height']:
quality = scraper_utils.height_get_quality(item['height'])
else:
quality = QUALITIES.HD720
stream_url = item['url'] + scraper_utils.append_headers({'User-Agent': scraper_utils.get_ua()})
hoster = {'multi-part': False, 'url': stream_url, 'class': self, 'quality': quality, 'host': scraper_utils.get_direct_hostname(self, item['url']), 'rating': None, 'views': None, 'direct': True}
hosters.append(hoster)
return hosters
def get_sources(self, video):
source_url = self.get_url(video)
hosters = []
if source_url and source_url != FORCE_NO_MATCH:
url = urlparse.urljoin(self.base_url, source_url)
html = self._http_get(url, cache_limit=.5)
match = re.search('((?:pic|emb|vb)=[^<]+)', html)
if match:
embeds = match.group(1)
for stream_url in embeds.split('&'):
if stream_url.startswith('vb='):
stream_url = 'http://www.vidbux.com/%s' % (stream_url[3:])
host = 'vidbux.com'
direct = False
quality = scraper_utils.get_quality(video, host, QUALITIES.HD1080)
elif stream_url.startswith('pic='):
data = {'url': stream_url[4:]}
html = self._http_get(PHP_URL, data=data, auth=False, cache_limit=1)
js_data = scraper_utils.parse_json(html, PHP_URL)
host = self._get_direct_hostname(stream_url)
direct = True
for item in js_data:
if 'medium' in item and item['medium'] == 'video':
stream_url = item['url']
quality = scraper_utils.width_get_quality(item['width'])
break
else:
continue
elif stream_url.startswith('emb='):
stream_url = stream_url.replace('emb=', '')
host = urlparse.urlparse(stream_url).hostname
direct = False
quality = scraper_utils.get_quality(video, host, QUALITIES.HD720)
else:
continue
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):
source_url = self.get_url(video)
hosters = []
if source_url and source_url != FORCE_NO_MATCH:
url = urlparse.urljoin(self.base_url, source_url)
html = self._http_get(url, cache_limit=.5)
fragment = ''
if video.video_type == VIDEO_TYPES.EPISODE:
pattern = 'Season\s+%s\s+Serie\s+%s</h3>(.*?)</table>' % (
video.season, video.episode)
match = re.search(pattern, html, re.DOTALL)
if match:
fragment = match.group(1)
else:
fragment = html
if fragment:
for match in re.finditer('data-width="([^"]+)"[^>]+>([^<]+)',
fragment, re.DOTALL):
width, url = match.groups()
host = urlparse.urlsplit(url).hostname.replace(
'embed.', '')
url = url.replace('&', '&')
hoster = {
'multi-part': False,
'host': host,
'class': self,
'quality': scraper_utils.width_get_quality(width),
'views': None,
'rating': None,
'url': url,
'direct': False
}
hoster['quality'] = scraper_utils.get_quality(
video, host, hoster['quality'])
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
url = scraper_utils.urljoin(self.base_url, source_url)
html = self._http_get(url, cache_limit=.5)
fragment = ''
if video.video_type == VIDEO_TYPES.EPISODE:
pattern = 'Season\s+%s\s+Serie\s+%s<(.*?)</table>' % (video.season, video.episode)
match = re.search(pattern, html, re.DOTALL)
if match:
fragment = match.group(1)
else:
fragment = html
if not fragment: return hosters
for attrs, stream_url in dom_parser2.parse_dom(fragment, 'td', {'class': 'linkHiddenUrl'}, req='data-width'):
host = urlparse.urlsplit(stream_url).hostname.replace('embed.', '')
url = url.replace('&', '&')
quality = scraper_utils.width_get_quality(attrs['data-width'])
hoster = {'multi-part': False, 'host': host, 'class': self, 'quality': quality, 'views': None, 'rating': None, 'url': stream_url, 'direct': False}
hoster['quality'] = scraper_utils.get_quality(video, host, hoster['quality'])
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
url = scraper_utils.urljoin(self.base_url, source_url)
html = self._http_get(url, cache_limit=.5)
fragment = ''
if video.video_type == VIDEO_TYPES.EPISODE:
pattern = 'Season\s+%s\s+Serie\s+%s<(.*?)</table>' % (
video.season, video.episode)
match = re.search(pattern, html, re.DOTALL)
if match:
fragment = match.group(1)
else:
fragment = html
if not fragment: return hosters
for attrs, stream_url in dom_parser2.parse_dom(
fragment, 'td', {'class': 'linkHiddenUrl'}, req='data-width'):
host = urlparse.urlsplit(stream_url).hostname.replace('embed.', '')
url = url.replace('&', '&')
quality = scraper_utils.width_get_quality(attrs['data-width'])
hoster = {
'multi-part': False,
'host': host,
'class': self,
'quality': quality,
'views': None,
'rating': None,
'url': stream_url,
'direct': False
}
hoster['quality'] = scraper_utils.get_quality(
video, host, hoster['quality'])
hosters.append(hoster)
return hosters
def __get_links(self, url, video):
hosters = []
search_url, params = self.__translate_search(url)
html = self._http_get(search_url, params=params, cache_limit=.5)
js_result = scraper_utils.parse_json(html, search_url)
down_url = js_result.get('downURL')
dl_farm = js_result.get('dlFarm')
dl_port = js_result.get('dlPort')
for item in js_result.get('data', []):
post_hash, size, post_title, ext, duration = item['0'], item[
'4'], item['10'], item['11'], item['14']
checks = [False] * 6
if not scraper_utils.release_check(video, post_title):
checks[0] = True
if 'alangs' in item and item['alangs'] and 'eng' not in item[
'alangs']:
checks[1] = True
if re.match('^\d+s', duration) or re.match('^[0-5]m', duration):
checks[2] = True
if 'passwd' in item and item['passwd']: checks[3] = True
if 'virus' in item and item['virus']: checks[4] = True
if 'type' in item and item['type'].upper() != 'VIDEO':
checks[5] = True
if any(checks):
logger.log(
'EasyNews Post excluded: %s - |%s|' % (checks, item),
log_utils.LOGDEBUG)
continue
stream_url = down_url + urllib.quote(
'/%s/%s/%s%s/%s%s' %
(dl_farm, dl_port, post_hash, ext, post_title, ext))
stream_url = stream_url + '|Authorization=%s' % (urllib.quote(
self.auth))
host = scraper_utils.get_direct_hostname(self, stream_url)
quality = None
if 'width' in item:
try:
width = int(item['width'])
except:
width = 0
if width:
quality = scraper_utils.width_get_quality(width)
if quality is None:
if video.video_type == VIDEO_TYPES.MOVIE:
meta = scraper_utils.parse_movie_link(post_title)
else:
meta = scraper_utils.parse_episode_link(post_title)
quality = scraper_utils.height_get_quality(meta['height'])
if self.max_bytes:
match = re.search('([\d.]+)\s+(.*)', size)
if match:
size_bytes = scraper_utils.to_bytes(*match.groups())
if size_bytes > self.max_bytes:
logger.log(
'Result skipped, Too big: |%s| - %s (%s) > %s (%s GB)'
% (post_title, size_bytes, size, self.max_bytes,
self.max_gb))
continue
hoster = {
'multi-part': False,
'class': self,
'views': None,
'url': stream_url,
'rating': None,
'host': host,
'quality': quality,
'direct': True
}
if any(i for i in ['X265', 'HEVC'] if i in post_title.upper()):
hoster['format'] = 'x265'
if size: hoster['size'] = size
if post_title: hoster['extra'] = post_title
hosters.append(hoster)
return hosters
def get_sources(self, video):
source_url = self.get_url(video)
hosters = []
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('((?:pic|emb|vb|dir|emb2)=[^<]+)', html)
if match:
embeds = match.group(1)
for stream_url in embeds.split('&'):
if stream_url.startswith('dir='):
headers = {'Referer': url}
html = self._http_get(DIR_URL,
params={'v': stream_url[3:]},
headers=headers,
auth=False,
allow_redirect=False,
cache_limit=.5)
if html.startswith('http'):
stream_url = html + scraper_utils.append_headers(
{
'User-Agent': scraper_utils.get_ua(),
'Referer': url
})
host = scraper_utils.get_direct_hostname(
self, stream_url)
direct = True
quality = QUALITIES.HD720
else:
continue
elif stream_url.startswith('vb='):
stream_url = 'http://www.vidbux.com/%s' % (stream_url[3:])
host = 'vidbux.com'
direct = False
quality = scraper_utils.get_quality(
video, host, QUALITIES.HD1080)
elif stream_url.startswith('pic='):
data = {'url': stream_url[4:]}
html = self._http_get(PHP_URL,
data=data,
auth=False,
cache_limit=1)
js_data = scraper_utils.parse_json(html, PHP_URL)
host = scraper_utils.get_direct_hostname(self, stream_url)
direct = True
for item in js_data:
if item.get('medium') == 'video':
stream_url = item['url']
quality = scraper_utils.width_get_quality(
item['width'])
break
else:
continue
elif stream_url.startswith(('emb=', 'emb2=')):
stream_url = re.sub('emb\d*=', '', stream_url)
host = urlparse.urlparse(stream_url).hostname
direct = False
quality = scraper_utils.get_quality(
video, host, QUALITIES.HD720)
else:
continue
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_links(self, url, video):
hosters = []
search_url = urlparse.urljoin(self.base_url, SEARCH_URL)
query = self.__translate_search(url)
result = self._http_get(search_url,
data=query,
allow_redirect=False,
cache_limit=.5)
if 'files' in result:
for item in result['files']:
checks = [False] * 6
if 'type' not in item or item['type'].upper() != 'VIDEO':
checks[0] = True
if 'is_ready' in item and item['is_ready'] != '1':
checks[1] = True
if 'av_result' in item and item['av_result'] in [
'warning', 'infected'
]:
checks[2] = True
if 'video_info' not in item: checks[3] = True
if 'video_info' in item and item[
'video_info'] and not re.search(
'#0:(?:0|1)(?:\(eng\)|\(und\))?:\s*Audio:',
item['video_info']):
checks[4] = True
if video.video_type == VIDEO_TYPES.EPISODE:
sxe = '[. ][Ss]%02d[Ee]%02d[. ]' % (int(
video.season), int(video.episode))
if not re.search(sxe, item['name']):
if video.ep_airdate:
airdate_pattern = '[. ]%s[. ]%02d[. ]%02d[. ]' % (
video.ep_airdate.year, video.ep_airdate.month,
video.ep_airdate.day)
if not re.search(airdate_pattern, item['name']):
checks[5] = True
if any(checks):
log_utils.log(
'Furk.net result excluded: %s - |%s|' %
(checks, item['name']), log_utils.LOGDEBUG)
continue
match = re.search('(\d{3,})\s?x\s?(\d{3,})',
item['video_info'])
if match:
width, _ = match.groups()
quality = scraper_utils.width_get_quality(width)
else:
if video.video_type == VIDEO_TYPES.MOVIE:
_, _, height, _ = scraper_utils.parse_movie_link(
item['name'])
quality = scraper_utils.height_get_quality(height)
elif video.video_type == VIDEO_TYPES.EPISODE:
_, _, _, height, _ = scraper_utils.parse_episode_link(
item['name'])
if int(height) > -1:
quality = scraper_utils.height_get_quality(height)
else:
quality = QUALITIES.HIGH
else:
quality = QUALITIES.HIGH
stream_url = item['url_pls']
host = self._get_direct_hostname(stream_url)
hoster = {
'multi-part': False,
'class': self,
'views': None,
'url': stream_url,
'rating': None,
'host': host,
'quality': quality,
'direct': True
}
hoster['size'] = scraper_utils.format_size(
int(item['size']), 'B')
hoster['extra'] = item['name']
hosters.append(hoster)
return hosters
def get_sources(self, video):
source_url = self.get_url(video)
hosters = []
if source_url and source_url != FORCE_NO_MATCH:
url = urlparse.urljoin(self.base_url, source_url)
html = self._http_get(url, cache_limit=.5)
fragment = ''
if video.video_type == VIDEO_TYPES.EPISODE:
pattern = 'Season\s+%s\s+Serie\s+%s</h3>(.*?)</table>' % (video.season, video.episode)
match = re.search(pattern, html, re.DOTALL)
if match:
fragment = match.group(1)
else:
fragment = html
if fragment:
for match in re.finditer('data-width="([^"]+)"[^>]+>([^<]+)', fragment, re.DOTALL):
width, url = match.groups()
host = urlparse.urlsplit(url).hostname.replace('embed.', '')
url = url.replace('&', '&')
hoster = {'multi-part': False, 'host': host, 'class': self, 'quality': scraper_utils.width_get_quality(width), 'views': None, 'rating': None, 'url': url, 'direct': False}
hoster['quality'] = scraper_utils.get_quality(video, host, hoster['quality'])
hosters.append(hoster)
return hosters
