def sources(self, url, hostDict, hostprDict):
sources = []
try:
if url is None:
return sources
if debrid.status() is False:
return sources
data = parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '')
for i in data])
title = data['tvshowtitle'] if 'tvshowtitle' in data else data[
'title']
title = title.replace('&', 'and').replace('Special Victims Unit',
'SVU')
hdlr = 'S%02dE%02d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else data['year']
query = '%s %s' % (title, hdlr)
query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query)
url = self.search_link % quote(query)
url = urljoin(self.base_link, url)
# log_utils.log('url = %s' % url, log_utils.LOGDEBUG)
html = client.request(url)
html = html.replace(' ', ' ')
try:
results = client.parseDOM(html,
'table',
attrs={'id': 'searchResult'})
except:
return sources
url2 = url.replace('/0/', '/1/')
html2 = client.request(url2)
html2 = html2.replace(' ', ' ')
try:
results += client.parseDOM(html2,
'table',
attrs={'id': 'searchResult'})
except:
return sources
results = ''.join(results)
rows = re.findall('<tr(.+?)</tr>', results, re.DOTALL)
if rows is None:
return sources
for entry in rows:
if 'magnet' not in entry:
continue
try:
url = 'magnet:%s' % (re.findall('a href="magnet:(.+?)"',
entry, re.DOTALL)[0])
url = unquote_plus(url).replace('&',
'&').replace(' ', '.')
url = url.split('&tr')[0]
hash = re.compile('btih:(.*?)&').findall(url)[0]
name = re.findall('class="detLink" title=".+?">(.+?)</a>',
entry, re.DOTALL)[0]
name = unquote_plus(name)
name = re.sub('[^A-Za-z0-9]+', '.', name).lstrip('.')
if source_utils.remove_lang(name):
continue
match = source_utils.check_title(title, name, hdlr,
data['year'])
if not match:
continue
try:
seeders = int(
re.findall(
'<td align="right">([0-9]+|[0-9]+,[0-9]+)</td>',
entry, re.DOTALL)[0].replace(',', ''))
if self.min_seeders > seeders:
continue
except:
seeders = 0
pass
quality, info = source_utils.get_release_quality(name, url)
try:
size = re.findall(
'((?:\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|MB|MiB))',
entry)[-1]
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
dsize = 0
pass
info = ' | '.join(info)
sources.append({
'source': 'torrent',
'seeders': seeders,
'hash': hash,
'name': name,
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True,
'size': dsize
})
except:
source_utils.scraper_error('PIRATEBAY')
continue
return sources
except:
source_utils.scraper_error('PIRATEBAY')
return sources
def sources(self, url, hostDict, hostprDict):
try:
sources = []
if url is None:
return sources
if debrid.status() is False:
return sources
hostDict = hostprDict + hostDict
data = urlparse.parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '')
for i in data])
title = data['tvshowtitle'] if 'tvshowtitle' in data else data[
'title']
title = title.replace('&', 'and').replace('Special Victims Unit',
'SVU')
hdlr = 'S%02dE%02d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else data['year']
query = '%s %s' % (title, hdlr)
query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query)
url = self.search_link % urllib.quote_plus(query)
url = urlparse.urljoin(self.base_link, url).replace('-', '+')
# log_utils.log('url = %s' % url, log_utils.LOGDEBUG)
r = client.request(url)
posts = client.parseDOM(r, "table", attrs={"class": "download"})
if posts == []:
return sources
for post in posts:
items = zip(client.parseDOM(post, 'a', ret='title'),
client.parseDOM(post, 'a', ret='href'))
for item in items:
try:
name = item[0].replace(' ', '.')
t = name.split(hdlr)[0].replace(
data['year'],
'').replace('(',
'').replace(')',
'').replace('&', 'and')
if cleantitle.get(t) != cleantitle.get(title):
continue
if hdlr not in name:
continue
if source_utils.remove_lang(name):
continue
i = str(item[1])
i = self.base_link + i
r = client.request(i)
u = client.parseDOM(r,
"div",
attrs={"class": "dl-links"})
for t in u:
r = zip(
re.compile(
"a href=.+? dl\W+'(.+?)'\W+").findall(t),
re.findall('>.\((.+?Mb)\)', t))
for link in r:
url = link[0]
if any(x in url for x in
['.rar', '.zip', '.iso', '.sample.']):
continue
if url in str(sources):
continue
quality, info = source_utils.get_release_quality(
name, url)
try:
dsize, isize = source_utils._size(link[1])
info.insert(0, isize)
except:
dsize = 0
pass
info = ' | '.join(info)
valid, host = source_utils.is_host_valid(
url, hostDict)
if not valid:
continue
host = client.replaceHTMLCodes(host)
host = host.encode('utf-8')
sources.append({
'source': host,
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True,
'size': dsize
})
except:
source_utils.scraper_error('DDLSPOT')
pass
return sources
except:
source_utils.scraper_error('DDLSPOT')
return
def sources(self, url, hostDict, hostprDict):
try:
sources = []
if url == None:
return sources
if debrid.status() is False:
return sources
data = urlparse.parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '')
for i in data])
title = data['title'].replace(':', '').lower()
year = data['year']
query = '%s %s' % (data['title'], data['year'])
query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query)
url = urlparse.urljoin(self.base_link, self.post_link)
# log_utils.log('url = %s' % url, log_utils.LOGDEBUG)
post = 'do=search&subaction=search&search_start=0&full_search=0&result_from=1&story=%s' % urllib.quote_plus(
query)
r = client.request(url, post=post)
r = client.parseDOM(r, 'div', attrs={'class': 'box-out margin'})
r = [(dom_parser.parse_dom(i, 'div', attrs={'class':
'news-title'}))
for i in r if data['imdb'] in i]
r = [(dom_parser.parse_dom(i[0], 'a', req='href')) for i in r if i]
r = [(i[0].attrs['href'], i[0].content) for i in r if i]
hostDict = hostprDict + hostDict
for item in r:
try:
name = item[0].replace(' ', '.')
s = re.findall(
'((?:\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))',
name)
s = s[0] if s else '0'
data = client.request(item[0])
data = dom_parser.parse_dom(data,
'div',
attrs={'id': 'r-content'})
data = re.findall('\s*<b><a href="(.+?)".+?</a></b>',
data[0].content, re.DOTALL)
for url in data:
url = client.replaceHTMLCodes(url)
url = url.encode('utf-8')
if 'turbobit' not in url:
continue
valid, host = source_utils.is_host_valid(url, hostDict)
if not valid:
continue
try:
qual = client.request(url)
quals = re.findall(
'span class="file-title" id="file-title">(.+?)</span',
qual)
for quals in quals:
quality = source_utils.check_sd_url(quals)
info = []
if '3D' in name or '.3D.' in quals:
info.append('3D')
quality = '1080p'
if any(i in ['hevc', 'h265', 'x265']
for i in quals):
info.append('HEVC')
info = ' | '.join(info)
sources.append({
'source': host,
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': True,
'debridonly': False
})
except:
source_utils.scraper_error('ULTRAHDINDIR')
pass
except:
source_utils.scraper_error('ULTRAHDINDIR')
pass
return sources
except Exception:
source_utils.scraper_error('ULTRAHDINDIR')
return sources
def sources(self, url, hostDict, hostprDict):
try:
sources = []
if url is None:
return sources
if debrid.status() is False:
return sources
data = urlparse.parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '')
for i in data])
title = data['tvshowtitle'] if 'tvshowtitle' in data else data[
'title']
title = title.replace('&', 'and').replace('Special Victims Unit',
'SVU')
hdlr = 'S%02dE%02d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else data['year']
query = '%s %s' % (title, hdlr)
query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query)
url = urlparse.urljoin(
self.base_link,
self.search_link.format(query[0].lower(),
cleantitle.geturl(query)))
# log_utils.log('url = %s' % url, log_utils.LOGDEBUG)
r = client.request(url)
if '<tbody' not in r:
return sources
r = client.parseDOM(r, 'tbody')[0]
results = client.parseDOM(r, 'tr')
posts = [i for i in results if 'magnet:' in i]
try:
next_page = [i for i in results if 'Next Page' in i]
if next_page == []:
raise Exception()
page = client.parseDOM(next_page,
'a',
ret='href',
attrs={'title':
'Downloads | Page 2'})[0]
r2 = client.request(self.base_link + page)
results2 = client.parseDOM(r2, 'tr')
posts += [i for i in results2 if 'magnet:' in i]
except:
pass
for post in posts:
post = post.replace(' ', ' ')
links = client.parseDOM(post, 'a', ret='href')
magnet = [
i.replace('&', '&') for i in links if 'magnet:' in i
][0]
url = magnet.split('&tr')[0]
if any(x in url.lower() for x in [
'french', 'italian', 'spanish', 'truefrench',
'dublado', 'dubbed'
]):
continue
name = client.parseDOM(post, 'a', ret='title')[1]
name = urllib.unquote_plus(name).replace(' ', '.')
if source_utils.remove_lang(name):
continue
t = name.split(hdlr)[0].replace(data['year'], '').replace(
'(', '').replace(')', '').replace('&', 'and').replace(
'.US.', '.').replace('.us.', '.')
if cleantitle.get(t) != cleantitle.get(title):
continue
if hdlr not in name:
continue
quality, info = source_utils.get_release_quality(name, url)
try:
size = re.findall(
'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GiB|MiB|GB|MB))',
post)[0]
div = 1 if size.endswith(('GB', 'GiB')) else 1024
size = float(
re.sub('[^0-9|/.|/,]', '', size.replace(',',
'.'))) / div
size = '%.2f GB' % size
info.insert(0, size)
except:
pass
info = ' | '.join(info)
sources.append({
'source': 'torrent',
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True
})
return sources
except:
source_utils.scraper_error('MAGNETDL')
return sources
def sources(self, url, hostDict, hostprDict):
sources = []
try:
if url is None:
return sources
if debrid.status() is False:
return sources
data = parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data])
title = data['tvshowtitle'] if 'tvshowtitle' in data else data['title']
title = title.replace('&', 'and').replace('Special Victims Unit', 'SVU')
hdlr = 'S%02dE%02d' % (int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else data['year']
hdlr2 = 'S%d - %d' % (int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else data['year']
query = '%s %s' % (title, hdlr)
query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query)
query2 = '%s %s' % (title, hdlr2)
query2 = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query2)
urls = []
url = self.search_link % quote_plus(query)
url = urljoin(self.base_link, url)
urls.append(url)
url2 = self.search_link % quote_plus(query2)
url2 = urljoin(self.base_link, url2)
urls.append(url2)
# log_utils.log('urls = %s' % urls, log_utils.LOGDEBUG)
for url in urls:
try:
r = client.request(url)
if 'magnet' not in r:
return sources
r = re.sub(r'\n', '', r)
r = re.sub(r'\t', '', r)
tbody = client.parseDOM(r, 'tbody')
rows = client.parseDOM(tbody, 'tr')
for row in rows:
links = zip(re.findall('href="(magnet:.+?)"', row, re.DOTALL), re.findall('((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))', row, re.DOTALL), [re.findall('<td class="text-center">([0-9]+)</td>', row, re.DOTALL)])
for link in links:
url = unquote_plus(link[0]).replace('&', '&').replace(' ', '.')
url = url.split('&tr')[0]
try:
url = url.encode('ascii', errors='ignore').decode('ascii', errors='ignore')
except:
pass
hash = re.compile('btih:(.*?)&').findall(url)[0]
name = url.split('&dn=')[1]
name = re.sub('[^A-Za-z0-9]+', '.', name).lstrip('.')
# if name.startswith('www'):
# try:
# name = re.sub(r'www(.*?)\W{2,10}', '', name)
# except:
# name = name.split('-.', 1)[1].lstrip()
if hdlr not in name and hdlr2 not in name:
continue
if source_utils.remove_lang(name):
continue
if hdlr in name:
t = name.split(hdlr)[0].replace(data['year'], '').replace('(', '').replace(')', '').replace('&', 'and').replace('.US.', '.').replace('.us.', '.')
if hdlr2 in name:
t = name.split(hdlr2)[0].replace(data['year'], '').replace('(', '').replace(')', '').replace('&', 'and').replace('.US.', '.').replace('.us.', '.')
# if cleantitle.get(t) != cleantitle.get(title):
# continue
seeders = int(link[2][0])
if self.min_seeders > seeders:
continue
quality, info = source_utils.get_release_quality(name, url)
try:
size = link[1]
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
dsize = 0
pass
info = ' | '.join(info)
sources.append({'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'quality': quality,
'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize})
except:
source_utils.scraper_error('NYAA')
return sources
return sources
except:
source_utils.scraper_error('NYYAA')
return sources
def sources(self, url, hostDict, hostprDict):
sources = []
try:
if url is None:
return sources
if debrid.status() is False:
return sources
data = parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '')
for i in data])
title = data['tvshowtitle'] if 'tvshowtitle' in data else data[
'title']
title = title.replace('&', 'and').replace('Special Victims Unit',
'SVU')
aliases = data['aliases']
episode_title = data['title'] if 'tvshowtitle' in data else None
hdlr = 'S%02dE%02d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else data['year']
query = '%s %s' % (title, hdlr)
query = re.sub('[^A-Za-z0-9\s\.-]+', '', query)
url = self.search_link % quote_plus(query)
url = urljoin(self.base_link, url)
# log_utils.log('url = %s' % url, log_utils.LOGDEBUG)
r = client.request(url)
if '<tbody' not in r:
return sources
posts = client.parseDOM(r, 'tbody')[0]
posts = client.parseDOM(posts, 'tr')
except:
source_utils.scraper_error('SKYTORRENTS')
return sources
for post in posts:
try:
post = re.sub(r'\n', '', post)
post = re.sub(r'\t', '', post)
link = re.findall(
'href="(magnet:.+?)".+<td style="text-align: center;color:green;">([0-9]+|[0-9]+,[0-9]+)</td>',
post, re.DOTALL)
for url, seeders, in link:
url = unquote_plus(url).split('&tr')[0].replace(
'&', '&').replace(' ', '.')
url = source_utils.strip_non_ascii_and_unprintable(url)
if url in str(self.sources):
return
hash = re.compile('btih:(.*?)&').findall(url)[0]
name = url.split('&dn=')[1]
name = source_utils.clean_name(title, name)
if source_utils.remove_lang(name, episode_title):
continue
if not source_utils.check_title(title, aliases, name, hdlr,
data['year']):
continue
# filter for episode multi packs (ex. S01E01-E17 is also returned in query)
if episode_title:
if not source_utils.filter_single_episodes(hdlr, name):
continue
try:
seeders = int(seeders)
if self.min_seeders > seeders:
continue
except:
seeders = 0
pass
quality, info = source_utils.get_release_quality(name, url)
try:
size = re.findall(
'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GiB|MiB|GB|MB))',
post)[0]
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
dsize = 0
pass
info = ' | '.join(info)
sources.append({
'source': 'torrent',
'seeders': seeders,
'hash': hash,
'name': name,
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True,
'size': dsize
})
except:
source_utils.scraper_error('SKYTORRENTS')
return sources
return sources
def sources(self, url, hostDict, hostprDict):
try:
sources = []
if url is None:
return sources
if debrid.status() is False:
return sources
data = parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '')
for i in data])
title = data['tvshowtitle'] if 'tvshowtitle' in data else data[
'title']
title = title.replace('&', 'and').replace('Special Victims Unit',
'SVU')
aliases = data['aliases']
episode_title = data['title'] if 'tvshowtitle' in data else None
hdlr = 'S%02dE%02d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else ('(' +
data['year'] +
')')
# query = '%s %s' % (title, hdlr) #site now fails with year in query
query = title
query = re.sub('[^A-Za-z0-9\s\.-]+', '', query)
if 'tvshowtitle' in data:
url = self.show_link % query.replace(' ', '-')
else:
url = self.search_link % quote_plus(query)
url = urljoin(self.base_link, url)
# log_utils.log('url = %s' % url, __name__, log_utils.LOGDEBUG)
r = client.request(url)
if not r:
return sources
if 'No results were found' in r:
return sources
r = client.parseDOM(r, 'div', attrs={'class': 'card'})
for i in r:
url = re.compile('href="(magnet.+?)\s*?"').findall(i)[0]
try:
url = unquote_plus(url).decode('utf8').replace(
'&', '&').replace(' ', '.')
except:
url = unquote_plus(url).replace('&',
'&').replace(' ', '.')
url = url.split('&tr=')[0].replace(' ', '.')
hash = re.compile('btih:(.*?)&').findall(url)[0]
name = url.split('&dn=')[1]
name = source_utils.clean_name(title, name)
if source_utils.remove_lang(name, episode_title):
continue
if not source_utils.check_title(
title, aliases, name,
hdlr.replace('(', '').replace(')', ''), data['year']):
continue
seeders = 0 # seeders not available on topnow
quality, info = source_utils.get_release_quality(name, url)
try:
size = re.findall(
'((?:\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|MB|MiB))', i
)[-1] # file size is no longer available on topnow's new site
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
dsize = 0
pass
info = ' | '.join(info)
sources.append({
'source': 'torrent',
'seeders': seeders,
'hash': hash,
'name': name,
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True,
'size': dsize
})
return sources
except:
source_utils.scraper_error('TOPNOW')
return sources
def sources(self, url, hostDict, hostprDict):
sources = []
try:
if not url:
return sources
if debrid.status() is False:
return sources
data = parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data])
title = data['tvshowtitle'] if 'tvshowtitle' in data else data['title']
title = title.replace('&', 'and').replace('Special Victims Unit', 'SVU')
aliases = data['aliases']
hdlr = 'S%02dE%02d' % (int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else data['year']
episode_title = data['title'] if 'tvshowtitle' in data else None
query = '%s %s' % (title, hdlr)
query = re.sub('[^A-Za-z0-9\s\.-]+', '', query)
url = self.search_link % quote(query)
url = urljoin(self.base_link, url)
# log_utils.log('url = %s' % url, log_utils.LOGDEBUG)
rjson = client.request(url, error=True)
if not rjson or 'No results returned' in str(rjson) or 'Connection Time-out' in str(rjson):
return sources
files = json.loads(rjson)
for file in files:
try:
hash = file['info_hash']
name = file['name']
name = source_utils.clean_name(title, name)
if source_utils.remove_lang(name, episode_title):
continue
url = 'magnet:?xt=urn:btih:%s&dn=%s' % (hash, name)
if not source_utils.check_title(title, aliases, name, hdlr, data['year']):
continue
# filter for episode multi packs (ex. S01E01-E17 is also returned in query)
if episode_title:
if not source_utils.filter_single_episodes(hdlr, name):
continue
try:
seeders= file['seeders']
if self.min_seeders > seeders:
continue
except:
seeders = 0
pass
quality, info = source_utils.get_release_quality(name, url)
try:
dsize, isize = source_utils.convert_size(float(file["size"]), to='GB')
info.insert(0, isize)
except:
dsize = 0
pass
info = ' | '.join(info)
sources.append({'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'quality': quality,
'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize})
except:
source_utils.scraper_error('PIRATEBAY')
continue
return sources
except:
source_utils.scraper_error('PIRATEBAY')
return sources
def sources(self, url, hostDict, hostprDict):
try:
sources = []
if url == None: return sources
if debrid.status() == False: raise Exception()
data = urlparse.parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '')
for i in data])
title = data['tvshowtitle'] if 'tvshowtitle' in data else data[
'title']
hdlr = 'S%02dE%02d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else data['year']
query = '%s S%02dE%02d' % (
data['tvshowtitle'], int(data['season']),
int(data['episode'])) if 'tvshowtitle' in data else '%s %s' % (
data['title'], data['year'])
query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query)
url = self.search_link % urllib.quote_plus(query)
url = urlparse.urljoin(self.base_link, url)
r = self.scraper.get(url).content
posts = client.parseDOM(r, 'item')
hostDict = hostprDict + hostDict
items = []
for post in posts:
try:
t = client.parseDOM(post, 'title')[0]
c = client.parseDOM(post, 'content.+?')[0]
u = client.parseDOM(c, 'p')
u = [client.parseDOM(i, 'a', ret='href') for i in u]
u = [i[0] for i in u if len(i) == 1]
if not u: raise Exception()
if 'tvshowtitle' in data:
u = [(re.sub('(720p|1080p)', '', t) + ' ' +
[x for x in i.strip('//').split('/')][-1], i)
for i in u]
else:
u = [(t, i) for i in u]
items += u
except:
pass
for item in items:
try:
name = item[0]
name = client.replaceHTMLCodes(name)
t = re.sub(
'(\.|\(|\[|\s)(\d{4}|S\d*E\d*|S\d*|3D)(\.|\)|\]|\s|)(.+|)',
'', name)
if not cleantitle.get(t) == cleantitle.get(title):
raise Exception()
y = re.findall(
'[\.|\(|\[|\s](\d{4}|S\d*E\d*|S\d*)[\.|\)|\]|\s]',
name)[-1].upper()
if not y == hdlr: raise Exception()
fmt = re.sub(
'(.+)(\.|\(|\[|\s)(\d{4}|S\d*E\d*|S\d*)(\.|\)|\]|\s)',
'', name.upper())
fmt = re.split('\.|\(|\)|\[|\]|\s|\-', fmt)
fmt = [i.lower() for i in fmt]
if any(
i.endswith(('subs', 'sub', 'dubbed', 'dub'))
for i in fmt):
raise Exception()
if any(i in ['extras'] for i in fmt): raise Exception()
if '1080p' in fmt: quality = '1080p'
elif '720p' in fmt: quality = 'HD'
else: quality = 'SD'
if any(i in ['dvdscr', 'r5', 'r6'] for i in fmt):
quality = 'SCR'
elif any(i in [
'camrip', 'tsrip', 'hdcam', 'hdts', 'dvdcam',
'dvdts', 'cam', 'telesync', 'ts'
] for i in fmt):
quality = 'CAM'
info = []
if '3d' in fmt: info.append('3D')
try:
size = re.findall(
'((?:\d+\.\d+|\d+\,\d+|\d+) (?:GB|GiB|MB|MiB))',
item[2])[-1]
div = 1 if size.endswith(('GB', 'GiB')) else 1024
size = float(re.sub('[^0-9|/.|/,]', '', size)) / div
size = '%.2f GB' % size
info.append(size)
except:
pass
if any(i in ['hevc', 'h265', 'x265'] for i in fmt):
info.append('HEVC')
info = ' | '.join(info)
url = item[1]
if any(x in url for x in ['.rar', '.zip', '.iso']):
raise Exception()
url = client.replaceHTMLCodes(url)
url = url.encode('utf-8')
host = re.findall(
'([\w]+[.][\w]+)$',
urlparse.urlparse(url.strip().lower()).netloc)[0]
if not host in hostDict: raise Exception()
host = client.replaceHTMLCodes(host)
host = host.encode('utf-8')
sources.append({
'source': host,
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True
})
except:
pass
check = [i for i in sources if not i['quality'] == 'CAM']
if check: sources = check
return sources
except:
return sources
def sources(self, url, hostDict, hostprDict):
sources = []
try:
if url is None:
return sources
if debrid.status() is False:
return sources
data = urlparse.parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '')
for i in data])
title = data['tvshowtitle'] if 'tvshowtitle' in data else data[
'title']
title = title.replace('&', 'and').replace('Special Victims Unit',
'SVU')
hdlr = 'S%02dE%02d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else data['year']
query = '%s %s' % (title, hdlr)
query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query)
url = self.search_link % urllib.quote_plus(query)
url = urlparse.urljoin(self.base_link, url)
# log_utils.log('url = %s' % url, log_utils.LOGDEBUG)
try:
r = client.request(url)
links = zip(
client.parseDOM(
r,
'a',
attrs={
'class':
'btn btn-default magnet-button stats-action banner-button'
},
ret='href'),
client.parseDOM(r, 'td', attrs={'class': 'size'}))
for link in links:
url = link[0].replace('&', '&')
url = re.sub(r'(&tr=.+)&dn=', '&dn=',
url) # some links on bitlord &tr= before &dn=
url = url.split('&tr=')[0]
if 'magnet' not in url:
continue
size = int(link[1])
name = url.split('&dn=')[1]
name = urllib.unquote_plus(name).replace(' ', '.')
if source_utils.remove_lang(name):
continue
t = name.split(hdlr)[0].replace(data['year'], '').replace(
'(', '').replace(')', '').replace('&', 'and').replace(
'.US.', '.').replace('.us.', '.')
if cleantitle.get(t) != cleantitle.get(title):
continue
if hdlr not in name:
continue
quality, info = source_utils.get_release_quality(name, url)
try:
if size < 5.12: raise Exception()
size = float(size) / 1024
size = '%.2f GB' % size
info.insert(0, size)
except:
pass
info = ' | '.join(info)
sources.append({
'source': 'torrent',
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True
})
return sources
except:
source_utils.scraper_error('BITLORD')
return sources
except:
source_utils.scraper_error('BITLORD')
return sources
def sources(self, url, hostDict, hostprDict):
scraper = cfscrape.create_scraper()
sources = []
try:
if url is None:
return sources
if debrid.status() is False:
return sources
hostDict = hostprDict + hostDict
data = urlparse.parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '')
for i in data])
title = data['tvshowtitle'] if 'tvshowtitle' in data else data[
'title']
title = title.replace('&', 'and').replace('Special Victims Unit',
'SVU')
hdlr = 'S%02dE%02d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else data['year']
query = '%s %s' % (title, hdlr)
query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query)
query = query.replace("&", "and")
query = re.sub('\s', '-', query)
# log_utils.log('query = %s' % query, log_utils.LOGDEBUG)
url = self.search_link % urllib.quote_plus(query)
url = urlparse.urljoin(self.base_link, url)
url = "http://rlsbb.ru/" + query
if 'tvshowtitle' not in data:
url = url + "-1080p"
r = scraper.get(url).content
if r is None and 'tvshowtitle' in data:
season = re.search('S(.*?)E', hdlr)
season = season.group(1)
query = title
query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query)
query = query + "-S" + season
query = query.replace("&", "and")
query = query.replace(" ", " ")
query = query.replace(" ", "-")
url = "http://rlsbb.ru/" + query
r = scraper.get(url).content
posts = client.parseDOM(r, "div", attrs={"class": "content"})
items = []
for post in posts:
try:
# size = re.findall('>\nSize: (.+?)<', post, re.DOTALL)
# log_utils.log('size = %s' % size, log_utils.LOGDEBUG)
u = client.parseDOM(post, 'a', ret='href')
for i in u:
try:
name = i.encode('ascii', errors='ignore').decode(
'ascii',
errors='ignore').replace(' ', ' ')
tit = name.rsplit('/', 1)[1]
t = tit.split(hdlr)[0].replace(
data['year'], '').replace('(', '').replace(
')', '').replace('&', 'and')
if cleantitle.get(t) != cleantitle.get(title):
continue
if hdlr in name.upper():
items.append(name)
except:
source_utils.scraper_error('RLSBB')
pass
except:
source_utils.scraper_error('RLSBB')
pass
seen_urls = set()
for item in items:
try:
info = []
url = str(item)
url = client.replaceHTMLCodes(url)
url = url.encode('utf-8')
if url in seen_urls:
continue
seen_urls.add(url)
host = url.replace("\\", "")
host2 = host.strip('"')
if url in str(sources):
continue
host = re.findall(
'([\w]+[.][\w]+)$',
urlparse.urlparse(host2.strip().lower()).netloc)[0]
if not host in hostDict:
continue
if any(x in host2 for x in ['.rar', '.zip', '.iso']):
continue
quality, info = source_utils.get_release_quality(host2)
# this site is an absolute nightmare to parse size. Some comment section 16gb but size reflects all links in comment
try:
size = re.findall(
'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))',
name)[0]
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
dsize = 0
pass
info = ' | '.join(info)
host = client.replaceHTMLCodes(host)
host = host.encode('utf-8')
sources.append({
'source': host,
'quality': quality,
'language': 'en',
'url': host2,
'info': info,
'direct': False,
'debridonly': True,
'size': dsize
})
except:
source_utils.scraper_error('RLSBB')
pass
return sources
except:
source_utils.scraper_error('RLSBB')
return sources
def sources(self, url, hostDict, hostprDict):
try:
sources = []
if url == None:
return sources
if debrid.status() is False:
raise Exception()
data = urlparse.parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data])
title = data['tvshowtitle'] if 'tvshowtitle' in data else data['title']
hdlr = 'S%02dE%02d' % (int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else data['year']
query = '%s S%02dE%02d' % (data['tvshowtitle'], int(data['season']), int(data['episode'])) \
if 'tvshowtitle' in data else '%s %s' % (data['title'], data['year'])
query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query)
url = self.search_link % urllib.quote_plus(query)
url = urlparse.urljoin(self.base_link, url)
html = client.request(url)
posts = client.parseDOM(html, 'item')
hostDict = hostprDict + hostDict
items = []
for post in posts:
try:
t = client.parseDOM(post, 'title')[0]
u = client.parseDOM(post, 'a', ret='href')
s = re.search('((?:\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|MB|MiB))', post)
s = s.groups()[0] if s else '0'
items += [(t, i, s) for i in u]
except:
pass
for item in items:
try:
url = item[1]
if any(x in url for x in ['.rar', '.zip', '.iso']):
raise Exception()
url = client.replaceHTMLCodes(url)
url = url.encode('utf-8')
if url in str(sources):
continue
valid, host = source_utils.is_host_valid(url, hostDict)
if not valid:
raise Exception()
host = client.replaceHTMLCodes(host)
host = host.encode('utf-8')
name = item[0]
name = client.replaceHTMLCodes(name)
t = re.sub('(\.|\(|\[|\s)(\d{4}|S\d*E\d*|S\d*|3D)(\.|\)|\]|\s|)(.+|)', '', name, flags=re.I)
if not cleantitle.get(t) == cleantitle.get(title):
raise Exception()
y = re.findall('[\.|\(|\[|\s](\d{4}|S\d*E\d*|S\d*)[\.|\)|\]|\s]', name)[-1].upper()
if not y == hdlr:
raise Exception()
quality, info = source_utils.get_release_quality(name, url)
try:
size = re.findall('((?:\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|MB|MiB))', item[2])[-1]
div = 1 if size.endswith(('GB', 'GiB')) else 1024
size = float(re.sub('[^0-9|/.|/,]', '', size)) / div
size = '%.2f GB' % size
info.append(size)
except:
pass
info = ' | '.join(info)
sources.append({'source': host, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True})
except:
pass
check = [i for i in sources if not i['quality'] == 'CAM']
if check:
sources = check
return sources
except:
return
def sources(self, url, hostDict, hostprDict):
sources = []
try:
self.scraper = cfscrape.create_scraper()
if url is None:
return sources
if debrid.status() is False:
return sources
hostDict = hostprDict + hostDict
data = urlparse.parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '')
for i in data])
title = data['tvshowtitle'] if 'tvshowtitle' in data else data[
'title']
title = title.replace('&', 'and').replace('Special Victims Unit',
'SVU')
hdlr = 'S%02dE%02d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else data['year']
query = '%s %s' % (title, hdlr)
query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query)
url = self.search_link % urllib.quote_plus(query)
url = urlparse.urljoin(self.base_link, url).replace('%3A+', '+')
# log_utils.log('url = %s' % url, log_utils.LOGDEBUG)
r = self.scraper.get(url).content
if r is None and 'tvshowtitle' in data:
season = re.search('S(.*?)E', hdlr)
season = season.group(1)
url = title
r = self.scraper.get(url).content
for loopCount in range(0, 2):
if loopCount == 1 or (r is None and 'tvshowtitle' in data):
r = self.scraper.get(url).content
posts = client.parseDOM(r, "h2", attrs={"class": "postTitle"})
items = []
for post in posts:
try:
u = client.parseDOM(post, 'a', ret='href')
for i in u:
link = str(i)
name = link.rsplit('/', 1)[0]
name = name.rsplit('/', 1)[1].upper()
if source_utils.remove_lang(name):
return
t = name.split(hdlr)[0].replace(
data['year'], '').replace('(', '').replace(
')', '').replace('&', 'and')
if cleantitle.get(t) != cleantitle.get(title):
break
if hdlr not in name:
break
# check year for reboot/remake show issues if year is available-crap shoot
# if 'tvshowtitle' in data:
# if re.search(r'([1-3][0-9]{3})', name):
# if not any(value in name for value in [data['year'], str(int(data['year'])+1), str(int(data['year'])-1)]):
# break
items.append(link)
except:
source_utils.scraper_error('MAXRLS')
pass
if len(items) > 0:
break
for item in items:
try:
i = str(item)
r = self.scraper.get(url).content
u = client.parseDOM(r,
"div",
attrs={"class": "postContent"})
for t in u:
links = zip(
re.findall('Download: (.*?)</strong>', t,
re.DOTALL),
re.findall(
'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GiB|MiB|GB|MB|gb|mb))',
t, re.DOTALL))
for link in links:
urls = link[0]
results = re.compile('href="(.+?)"',
re.DOTALL).findall(urls)
for url in results:
if url in str(self.sources):
return
quality, info = source_utils.get_release_quality(
url)
try:
dsize, isize = source_utils._size(link[1])
info.insert(0, isize)
except:
dsize = 0
pass
info = ' | '.join(info)
valid, host = source_utils.is_host_valid(
url, hostDict)
if not valid:
continue
sources.append({
'source': host,
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True,
'size': dsize
})
except:
source_utils.scraper_error('MAXRLS')
pass
return sources
except:
source_utils.scraper_error('MAXRLS')
return sources
def sources(self, url, hostDict, hostprDict):
try:
sources = []
if url is None: return sources
if debrid.status() is False: raise Exception()
data = urlparse.parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data])
title = data['tvshowtitle'] if 'tvshowtitle' in data else data['title']
hdlr = 'S%02dE%02d' % (int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else data['year']
query = '%s S%02dE%02d' % (
data['tvshowtitle'], int(data['season']),
int(data['episode'])) if 'tvshowtitle' in data else '%s %s' % (
data['title'], data['year'])
query = re.sub('(\\\|/| -|:|;|\*|\?|"|<|>|\|)', ' ', query)
url = self.search_link % urllib.quote_plus(query)
url = urlparse.urljoin(self.base_link, url)
html = client.request(url)
html = html.replace(' ', ' ')
try:
results = client.parseDOM(html, 'table', attrs={'id': 'searchResult'})[0]
except Exception:
return sources
rows = re.findall('<tr(.+?)</tr>', results, re.DOTALL)
if rows is None:
return sources
for entry in rows:
try:
try:
name = re.findall('class="detLink" title=".+?">(.+?)</a>', entry, re.DOTALL)[0]
name = client.replaceHTMLCodes(name)
# t = re.sub('(\.|\(|\[|\s)(\d{4}|S\d*E\d*|S\d*|3D)(\.|\)|\]|\s|)(.+|)', '', name, flags=re.I)
if not cleantitle.get(title) in cleantitle.get(name):
continue
except Exception:
continue
y = re.findall('[\.|\(|\[|\s](\d{4}|S\d*E\d*|S\d*)[\.|\)|\]|\s]', name)[-1].upper()
if not y == hdlr:
continue
try:
seeders = int(re.findall('<td align="right">(.+?)</td>', entry, re.DOTALL)[0])
except Exception:
continue
if self.min_seeders > seeders:
continue
try:
link = 'magnet:%s' % (re.findall('a href="magnet:(.+?)"', entry, re.DOTALL)[0])
link = str(client.replaceHTMLCodes(link).split('&tr')[0])
except Exception:
continue
quality, info = source_utils.get_release_quality(name, name)
try:
size = re.findall('((?:\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|MB|MiB))', entry)[-1]
div = 1 if size.endswith(('GB', 'GiB')) else 1024
size = float(re.sub('[^0-9|/.|/,]', '', size)) / div
size = '%.2f GB' % size
info.append(size)
except Exception:
pass
info = ' | '.join(info)
sources.append(
{'source': 'Torrent', 'quality': quality, 'language': 'en', 'url': link, 'info': info,
'direct': False, 'debridonly': True})
except Exception:
continue
check = [i for i in sources if not i['quality'] == 'CAM']
if check:
sources = check
return sources
except Exception:
return sources
def sources(self, url, hostDict, hostprDict):
try:
sources = []
if url is None:
return sources
if debrid.status() is False:
return sources
data = urlparse.parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '')
for i in data])
title = data['tvshowtitle'] if 'tvshowtitle' in data else data[
'title']
title = title.replace('&', 'and').replace('Special Victims Unit',
'SVU')
hdlr = 'S%02dE%02d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else data['year']
category = '+category%3ATV' if 'tvshowtitle' in data else '+category%3AMovies'
query = '%s %s' % (title, hdlr)
query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query)
url = self.search_link % urllib.quote_plus(query)
url = urlparse.urljoin(self.base_link, url) + str(category)
# log_utils.log('url = %s' % url, log_utils.LOGDEBUG)
html = client.request(url)
html = html.replace(' ', ' ')
try:
results = client.parseDOM(
html,
'table',
attrs={
'class': 'table table-condensed table-torrents vmiddle'
})[0]
except:
return sources
rows = re.findall('<tr(.+?)</tr>', results, re.DOTALL)
if rows is None:
return sources
for entry in rows:
try:
try:
url = 'magnet:%s' % (re.findall(
'href="magnet:(.+?)"', entry, re.DOTALL)[0])
url = str(client.replaceHTMLCodes(url).split('&tr')[0])
if url in str(sources):
continue
except:
continue
if any(x in url.lower() for x in [
'french', 'italian', 'spanish', 'truefrench',
'dublado', 'dubbed'
]):
continue
try:
name = re.findall('<a class=".+?>(.+?)</a>', entry,
re.DOTALL)[0]
name = client.replaceHTMLCodes(name).replace(
'<hl>', '').replace('</hl>', '')
except:
continue
# allot of movies have foreign title translation in front so remove it
if ' / ' in name:
name = name.split(' / ')[1]
t = name.split(hdlr)[0].replace(data['year'], '').replace(
'(', '').replace(')', '').replace('&', 'and')
if cleantitle.get(t) != cleantitle.get(title):
continue
if hdlr not in name:
continue
try:
seeders = int(
re.findall(
'class="progress prog trans90" title="Seeders: (.+?) \|',
entry, re.DOTALL)[0])
except:
continue
if self.min_seeders > seeders:
continue
quality, info = source_utils.get_release_quality(name, url)
try:
size = re.findall(
'((?:\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|MB|MiB))',
entry)[-1]
div = 1 if size.endswith(('GB', 'GiB')) else 1024
size = float(re.sub('[^0-9|/.|/,]', '', size)) / div
size = '%.2f GB' % size
info.append(size)
except:
pass
info = ' | '.join(info)
sources.append({
'source': 'torrent',
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True
})
except:
continue
return sources
except:
source_utils.scraper_error('ZOOGLE')
return sources
def sources(self, url, hostDict, hostprDict):
sources = []
try:
if url is None:
return sources
if debrid.status() is False:
return sources
data = parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '')
for i in data])
title = data['tvshowtitle'].replace('&', 'and').replace(
'Special Victims Unit', 'SVU')
hdlr = 'S%02dE%02d' % (int(data['season']), int(data['episode']))
query = '%s %s' % (title, hdlr)
query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query)
url = self.search_link % (quote_plus(query).replace('+', '-'))
url = urljoin(self.base_link, url)
# log_utils.log('url = %s' % url, log_utils.LOGDEBUG)
html = client.request(url)
try:
results = client.parseDOM(
html, 'table', attrs={'class': 'forum_header_border'})
for result in results:
if 'magnet:' in result:
results = result
break
except:
return sources
rows = re.findall(
'<tr name="hover" class="forum_header_border">(.+?)</tr>',
results, re.DOTALL)
if rows is None:
return sources
for entry in rows:
try:
try:
columns = re.findall('<td\s.+?>(.+?)</td>', entry,
re.DOTALL)
derka = re.findall(
'href="magnet:(.+?)" class="magnet" title="(.+?)"',
columns[2], re.DOTALL)[0]
except:
continue
url = 'magnet:%s' % (str(
client.replaceHTMLCodes(derka[0]).split('&tr')[0]))
try:
url = unquote(url).decode('utf8')
except:
pass
hash = re.compile('btih:(.*?)&').findall(url)[0]
magnet_title = derka[1]
name = unquote_plus(magnet_title)
name = re.sub('[^A-Za-z0-9]+', '.', name).lstrip('.')
if source_utils.remove_lang(name):
continue
match = source_utils.check_title(title, name, hdlr,
data['year'])
if not match:
continue
try:
seeders = int(
re.findall(
'<font color=".+?">([0-9]+|[0-9]+,[0-9]+)</font>',
columns[5], re.DOTALL)[0].replace(',', ''))
if self.min_seeders > seeders:
continue
except:
seeders = 0
pass
quality, info = source_utils.get_release_quality(name, url)
try:
size = re.findall(
'((?:\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|MB|MiB))',
magnet_title)[-1]
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
dsize = 0
pass
info = ' | '.join(info)
sources.append({
'source': 'torrent',
'seeders': seeders,
'hash': hash,
'name': name,
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True,
'size': dsize
})
except:
source_utils.scraper_error('EZTV')
continue
return sources
except:
source_utils.scraper_error('EZTV')
return sources
def sources(self, url, hostDict, hostprDict):
try:
sources = []
if url is None:
return sources
if debrid.status() is False:
raise Exception()
hostDict = hostprDict + hostDict
data = urlparse.parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '')
for i in data])
title = data['tvshowtitle'] if 'tvshowtitle' in data else data[
'title']
title = title.replace('&', 'and').replace('Special Victims Unit',
'SVU')
hdlr = 'S%02dE%02d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else data['year']
query = '%s %s' % (title, hdlr)
query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query)
url = self.search_link % urllib.quote_plus(query)
url = urlparse.urljoin(self.base_link, url).replace('-', '+')
# log_utils.log('url = %s' % url, log_utils.LOGDEBUG)
r = client.request(url)
if r is None and 'tvshowtitle' in data:
season = re.search('S(.*?)E', hdlr)
season = season.group(1)
url = title
r = client.request(url)
for loopCount in range(0, 2):
if loopCount == 1 or (r is None and 'tvshowtitle' in data):
r = client.request(url)
posts = client.parseDOM(r,
"table",
attrs={"class": "download"})
items = []
for post in posts:
try:
u = client.parseDOM(post, 'a', ret='href')
for i in u:
try:
name = str(i)
items.append(name)
except:
pass
except:
source_utils.scraper_error('DDLSPOT')
pass
if len(items) > 0:
break
for item in items:
try:
info = []
i = str(item)
i = self.base_link + i
r = client.request(i)
u = client.parseDOM(r, "div", attrs={"class": "dl-links"})
for t in u:
r = re.compile(
'a href=".+?" rel=".+?">(.+?)<').findall(t)
for url in r:
if any(x in url for x in ['.rar', '.zip', '.iso']):
continue
quality, info = source_utils.get_release_quality(
url)
valid, host = source_utils.is_host_valid(
url, hostDict)
sources.append({
'source': host,
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True
})
except:
source_utils.scraper_error('DDLSPOT')
pass
return sources
except:
source_utils.scraper_error('DDLSPOT')
return
def sources(self, url, hostDict, hostprDict):
try:
sources = []
if url is None: return sources
if debrid.status() is False: raise Exception()
data = urlparse.parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data])
title = data['tvshowtitle'] if 'tvshowtitle' in data else data['title']
hdlr = 'S%02dE%02d' % (int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else data['year']
query = '%s S%02dE%02d' % (
data['tvshowtitle'], int(data['season']),
int(data['episode'])) if 'tvshowtitle' in data else '%s %s' % (
data['title'], data['year'])
query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query)
url = self.search_link % urllib.quote_plus(query)
url = urlparse.urljoin(self.base_link, url)
r = client.request(url)
posts = client.parseDOM(r, 'item')
hostDict = hostprDict + hostDict
items = []
for post in posts:
try:
t = client.parseDOM(post, 'title')[0]
u = client.parseDOM(post, 'link')[0]
s = re.findall('((?:\d+\.\d+|\d+\,\d+|\d+)\s*(?:GiB|MiB|GB|MB))', t)
s = s[0] if s else '0'
items += [(t, u, s)]
except:
pass
urls = []
for item in items:
try:
name = item[0]
name = client.replaceHTMLCodes(name)
t = re.sub('(\.|\(|\[|\s)(\d{4}|S\d*E\d*|S\d*|3D)(\.|\)|\]|\s|)(.+|)', '', name)
if not cleantitle.get(t) == cleantitle.get(title): raise Exception()
y = re.findall('[\.|\(|\[|\s](\d{4}|S\d*E\d*|S\d*)[\.|\)|\]|\s]', name)[-1].upper()
if not y == hdlr: raise Exception()
quality, info = source_utils.get_release_quality(name, item[1])
if any(x in quality for x in ['CAM', 'SD']): continue
try:
size = re.sub('i', '', item[2])
div = 1 if size.endswith('GB') else 1024
size = float(re.sub('[^0-9|/.|/,]', '', size)) / div
size = '%.2f GB' % size
info.append(size)
except:
pass
info = ' | '.join(info)
url = item[1]
links = self.links(url)
urls += [(i, quality, info) for i in links]
except:
pass
for item in urls:
if 'earn-money' in item[0]: continue
if any(x in item[0] for x in ['.rar', '.zip', '.iso']): continue
url = client.replaceHTMLCodes(item[0])
url = url.encode('utf-8')
valid, host = source_utils.is_host_valid(url, hostDict)
if not valid: continue
host = client.replaceHTMLCodes(host)
host = host.encode('utf-8')
sources.append(
{'source': host, 'quality': item[1], 'language': 'en', 'url': url, 'info': item[2], 'direct': False,
'debridonly': True})
return sources
except:
return sources
def sources(self, url, hostDict, hostprDict):
try:
sources = []
if url == None:
return sources
if debrid.status() is False:
raise Exception()
hostDict = hostprDict + hostDict
data = urlparse.parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '')
for i in data])
title = data['tvshowtitle'] if 'tvshowtitle' in data else data[
'title']
hdlr = 's%02de%02d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else data['year']
query = '%s s%02de%02d' % (
data['tvshowtitle'], int(data['season']),
int(data['episode'])) if 'tvshowtitle' in data else '%s %s' % (
data['title'], data['year'])
query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query)
try:
url = self.search_link % urllib.quote_plus(query)
url = urlparse.urljoin(self.base_link, url)
r = requests.get(url).content
posts = client.parseDOM(r, 'h2', attrs={'class': 'title'})
items = []
dupes = []
for post in posts:
try:
u = client.parseDOM(post, 'a', ret='href')
for r in u:
r = requests.get(r).content
u = client.parseDOM(r,
"div",
attrs={"id": "content"})
u = client.parseDOM(u, 'a', ret='href')
u = [(i.strip('/').split('/')[-1], i) for i in u]
items += u
except:
pass
except:
pass
for item in items:
try:
name = item[0]
name = client.replaceHTMLCodes(name)
t = re.sub(
'(\.|\(|\[|\s)(\d{4}|S\d*E\d*|S\d*|3D)(\.|\)|\]|\s|)(.+|)',
'', name)
if not cleantitle.get(t) == cleantitle.get(title):
continue
quality, info = source_utils.get_release_quality(
name, item[1])
url = item[1]
if any(x in url for x in ['.rar', '.zip', '.iso']):
raise Exception()
url = client.replaceHTMLCodes(url)
url = url.encode('utf-8')
if url in str(sources):
continue
host = re.findall(
'([\w]+[.][\w]+)$',
urlparse.urlparse(url.strip().lower()).netloc)[0]
if not host in hostDict:
raise Exception()
host = client.replaceHTMLCodes(host)
host = host.encode('utf-8')
sources.append({
'source': host,
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True
})
except:
pass
return sources
except:
return sources
def sources(self, url, hostDict, hostprDict):
sources = []
try:
if url is None: return sources
if debrid.status() is False: raise Exception()
data = urlparse.parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '')
for i in data])
title = data['tvshowtitle'] if 'tvshowtitle' in data else data[
'title']
hdlr = 'S%02dE%02d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else data['year']
query = '%s s%02de%02d' % (
data['tvshowtitle'], int(data['season']),
int(data['episode'])) if 'tvshowtitle' in data else '%s %s' % (
data['title'], data['year'])
query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query)
url = self.search_link % urllib.quote_plus(query)
url = urlparse.urljoin(self.base_link, url)
r = client.request(url)
try:
posts = client.parseDOM(r,
'h2',
attrs={'class': 'entry-title'})
for post in posts:
data = client.parseDOM(post, 'a', ret='href')
for u in data:
r = client.request(u)
r = client.parseDOM(
r,
'div',
attrs={'class': 'clearfix entry-content'})
for t in r:
link = re.findall(
'a class="buttn magnet" href="(.+?)"', t)[0]
quality, info = source_utils.get_release_quality(u)
try:
size = re.findall(
'((?:\d+\.\d+|\d+\,\d+|\d+)\s*(?:gb|gib|mb|mib))',
str(data))[-1]
div = 1 if size.endswith(('gb')) else 1024
size = float(re.sub('[^0-9|/.|/,]', '',
size)) / div
size = '%.2f gb' % size
info.append(size)
except:
pass
info = ' | '.join(info)
sources.append({
'source': 'Torrent',
'quality': quality,
'language': 'en',
'url': link,
'info': info,
'direct': False,
'debridonly': True
})
except:
return
return sources
except:
return sources
def sources(self, url, hostDict, hostprDict):
try:
sources = []
if url is None:
return sources
if debrid.status() is False:
return sources
data = urlparse.parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '')
for i in data])
title = data['tvshowtitle'] if 'tvshowtitle' in data else data[
'title']
title = title.replace('&', 'and').replace('Special Victims Unit',
'SVU')
hdlr = 'S%02dE%02d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else data['year']
query = '%s %s' % (title, hdlr)
query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query)
url = self.search_link % urllib.quote_plus(query)
url = urlparse.urljoin(self.base_link, url)
# log_utils.log('url = %s' % url, log_utils.LOGDEBUG)
try:
r = self.scraper.get(url).content
posts = client.parseDOM(r, 'li')
for post in posts:
link = re.findall(
'a title="Download using magnet" href="(magnet:.+?)"',
post, re.DOTALL)
for url in link:
url = url.split('&tr')[0]
name = url.split('&dn=')[1]
name = urllib.unquote_plus(name).replace(' ', '.')
if source_utils.remove_lang(name):
continue
if name.startswith('www.'):
try:
name = name.split(' - ')[1].lstrip()
except:
name = re.sub(r'\www..+? ', '', name)
t = name.split(hdlr)[0].replace(
data['year'],
'').replace('(', '').replace(')', '').replace(
'&', 'and').replace('.US.',
'.').replace('.us.', '.')
if cleantitle.get(t) != cleantitle.get(title):
continue
if hdlr not in name:
continue
quality, info = source_utils.get_release_quality(url)
try:
size = re.findall(
'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GiB|MiB|GB|MB))',
post)[0]
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
pass
info = ' | '.join(info)
sources.append({
'source': 'torrent',
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True,
'size': dsize
})
except:
source_utils.scraper_error('BTDB')
return
return sources
except:
source_utils.scraper_error('BTDB')
return sources
def sources(self, url, hostDict, hostprDict):
try:
hostDict = hostDict + hostprDict
sources = []
query_bases = []
options = []
if url is None:
return sources
if not debrid.status():
return sources
data = urlparse.parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data])
title = (data['tvshowtitle'] if 'tvshowtitle' in data else data['title'])
hdlr = 'S%02dE%02d' % (int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else data['year']
# tvshowtitle
if 'tvshowtitle' in data:
query_bases.append('%s ' % (data['tvshowtitle'].replace("-", "")))
if 'year' in data:
query_bases.append('%s %s ' % (data['tvshowtitle'], data['year']))
options.append('S%02dE%02d' % (int(data['season']), int(data['episode'])))
options.append('S%02d' % (int(data['season'])))
else:
query_bases.append('%s %s ' % (data['title'], data['year']))
query_bases.append('%s ' % (data['title']))
query_bases.append('2160p')
query_bases.append('')
for option in options:
for query_base in query_bases:
q = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query_base + option)
q = q.replace(" ", " ").replace(" ", "+")
url = self.base_link + self.search_link % q
html = self.scraper.get(url)
if html.status_code == 200:
posts = client.parseDOM(html.content, "h3", attrs={"class": "elegantwp-fp09-post-title"})
for post in posts:
url = client.parseDOM(post, "a", ret='href')
if len(url) > 0:
html = self.scraper.get(url[0])
if html.status_code == 200:
quotes = client.parseDOM(html.content, "div", attrs={"class": "entry-content "
"clearfix"})
log_utils.log('best-moviez.ws - href: \n' + str(quotes))
for quote in quotes:
hrefs = client.parseDOM(quote, "a", ret='href')
if not hrefs:
continue
for href in hrefs:
if any(x in href for x in ['.rar', '.zip', '.iso']):
continue
quality = source_utils.check_sd_url(href)
href = href.encode('utf-8')
valid, host = source_utils.is_host_valid(href, hostDict)
if not valid:
continue
if hdlr in href.upper() and cleantitle.get(title) in cleantitle.get(href):
sources.append(
{'source': host, 'quality': quality, 'language': 'en', 'url': href,
'direct': False, 'debridonly': False})
if len(sources) > 0:
return sources
return sources
except:
return sources
def sources(self, url, hostDict, hostprDict):
sources = []
try:
if url is None:
return sources
if debrid.status() is False:
return sources
hostDict = hostprDict + hostDict
data = urlparse.parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data])
ref_url = url = data['url']
# log_utils.log('url = %s' % url, log_utils.LOGDEBUG)
title = data['tvshowtitle'] if 'tvshowtitle' in data else data['title']
hdlr = 'S%02dE%02d' % (int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else data['year']
_headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:61.0) Gecko/20100101 Firefox/72.0'}
r = client.request(url, headers=_headers)
posts = client.parseDOM(r, 'h2', attrs={'class': 'title'})
posts = zip(client.parseDOM(posts, 'a', ret='title'), client.parseDOM(posts, 'a', ret='href'))
if posts == []:
return sources
for item in posts:
try:
name = item[0].replace(' ', '.')
url = item[1]
r = client.request(url, headers=_headers)
list = client.parseDOM(r, 'div', attrs={'id': 'content'})
if 'tvshowtitle' in data:
regex = '(<strong>(.*?)</strong><br />\s?[A-Z,0-9]*?\s\|\s([A-Z,0-9,\s]*)\|\s((\d+\.\d+|\d*)\s?(?:GB|GiB|Gb|MB|MiB|Mb))?</p>(?:\s<p><a href=\".*?\" .*?_blank\">.*?</a></p>)+)'
else:
regex = '(<strong>Release Name:</strong>\s*(.*?)<br />\s?<strong>Size:</strong>\s?((\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+)\s(?:GB|GiB|Gb|MB|MiB|Mb))?<br />(.*\s)*)'
for match in re.finditer(regex, list[0].encode('ascii', errors='ignore').decode('ascii', errors='ignore').replace(' ', ' ')):
name = str(match.group(2))
t = name.split(hdlr)[0].replace(data['year'], '').replace('(', '').replace(')', '').replace('&', 'and')
if cleantitle.get(t) != cleantitle.get(title):
continue
if hdlr not in name:
continue
if source_utils.remove_lang(name):
continue
# audio = str(match.group(3))
if 'tvshowtitle' in data:
size = str(match.group(4))
else:
size = str(match.group(3))
links = client.parseDOM(match.group(1), 'a', attrs={'class': 'autohyperlink'}, ret='href')
for url in links:
try:
if any(x in url for x in ['.rar', '.zip', '.iso', '.sample.']):
continue
if url in str(sources):
continue
valid, host = source_utils.is_host_valid(url, hostDict)
if not valid:
continue
host = client.replaceHTMLCodes(host)
host = host.encode('utf-8')
quality, info = source_utils.get_release_quality(name, url)
try:
div = 1 if size.endswith(('GB', 'GiB', 'Gb')) else 1024
size = float(re.sub('[^0-9|/.|/,]', '', size.replace(',', '.'))) / div
size = '%.2f GB' % size
info.insert(0, size)
except:
pass
info = ' | '.join(info)
sources.append({'source': host, 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True})
except:
source_utils.scraper_error('TVDOWNLOADS')
pass
except:
source_utils.scraper_error('TVDOWNLOADS')
pass
return sources
except:
source_utils.scraper_error('TVDOWNLOADS')
return sources
def sources(self, url, hostDict, hostprDict):
try:
sources = []
scraper = cfscrape.create_scraper()
if url == None: return sources
if debrid.status() == False: raise Exception()
data = urlparse.parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '')
for i in data])
title = data['tvshowtitle'] if 'tvshowtitle' in data else data[
'title']
hdlr = 'S%02dE%02d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else data['year']
premDate = ''
query = '%s S%02dE%02d' % (
data['tvshowtitle'], int(data['season']),
int(data['episode'])) if 'tvshowtitle' in data else '%s %s' % (
data['title'], data['year'])
query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query)
query = query.replace("&", "and")
query = query.replace(" ", " ")
query = query.replace(" ", "-")
url = self.search_link % urllib.quote_plus(query)
url = urlparse.urljoin(self.base_link, url)
url = "http://rlsbb.ru/" + query
if 'tvshowtitle' not in data: url = url + "-1080p"
r = scraper.get(url).content
if r == None and 'tvshowtitle' in data:
season = re.search('S(.*?)E', hdlr)
season = season.group(1)
query = title
query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query)
query = query + "-S" + season
query = query.replace("&", "and")
query = query.replace(" ", " ")
query = query.replace(" ", "-")
url = "http://rlsbb.ru/" + query
r = scraper.get(url).content
for loopCount in range(0, 2):
if loopCount == 1 or (r == None and 'tvshowtitle' in data):
premDate = re.sub('[ \.]', '-', data['premiered'])
query = re.sub('[\\\\:;*?"<>|/\-\']', '',
data['tvshowtitle'])
query = query.replace("&", " and ").replace(" ",
" ").replace(
" ", "-")
query = query + "-" + premDate
url = "http://rlsbb.ru/" + query
url = url.replace('The-Late-Show-with-Stephen-Colbert',
'Stephen-Colbert')
r = scraper.get(url).content
posts = client.parseDOM(r, "div", attrs={"class": "content"})
hostDict = hostprDict + hostDict
items = []
for post in posts:
try:
u = client.parseDOM(post, 'a', ret='href')
for i in u:
try:
name = str(i)
if hdlr in name.upper():
items.append(name)
elif len(premDate
) > 0 and premDate in name.replace(
".", "-"):
items.append(name)
except:
pass
except:
pass
if len(items) > 0: break
seen_urls = set()
for item in items:
try:
info = []
url = str(item)
url = client.replaceHTMLCodes(url)
url = url.encode('utf-8')
if url in seen_urls: continue
seen_urls.add(url)
host = url.replace("\\", "")
host2 = host.strip('"')
host = re.findall(
'([\w]+[.][\w]+)$',
urlparse.urlparse(host2.strip().lower()).netloc)[0]
if not host in hostDict: raise Exception()
if any(x in host2 for x in ['.rar', '.zip', '.iso']):
continue
if '720p' in host2:
quality = 'HD'
elif '1080p' in host2:
quality = '1080p'
elif '2160p' in host2:
quality = '4K'
else:
quality = 'SD'
info = ' | '.join(info)
host = client.replaceHTMLCodes(host)
host = host.encode('utf-8')
sources.append({
'source': host,
'quality': quality,
'language': 'en',
'url': host2,
'info': info,
'direct': False,
'debridonly': False
})
except:
pass
check = [i for i in sources if not i['quality'] == 'CAM']
if check: sources = check
return sources
except:
return sources
def sources(self, url, hostDict, hostprDict):
scraper = cfscrape.create_scraper()
sources = []
try:
if url is None:
return sources
if debrid.status() is False:
return sources
hostDict = hostprDict + hostDict
data = urlparse.parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '')
for i in data])
title = data['tvshowtitle'] if 'tvshowtitle' in data else data[
'title']
title = title.replace('&', 'and').replace('Special Victims Unit',
'SVU')
hdlr = 'S%02dE%02d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else data['year']
query = '%s %s' % (title, hdlr)
query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query)
try:
url = self.search_link % urllib.quote_plus(query)
url = urlparse.urljoin(self.base_link, url)
# log_utils.log('url = %s' % url, log_utils.LOGDEBUG)
r = scraper.get(url).content
posts = client.parseDOM(r, 'div', attrs={'class': 'post'})
items = []
dupes = []
for post in posts:
try:
content = client.parseDOM(
post, "div", attrs={"class": "postContent"})
size = re.findall(
'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GiB|MiB|GB|MB))',
content[0])[0]
u = client.parseDOM(content, "h2")
u = client.parseDOM(u, 'a', ret='href')
u = [(i.strip('/').split('/')[-1], i, size) for i in u]
items += u
except:
source_utils.scraper_error('SCENERLS')
pass
except:
source_utils.scraper_error('SCENERLS')
pass
for item in items:
try:
name = item[0]
name = client.replaceHTMLCodes(name)
if source_utils.remove_lang(name):
return
t = name.split(hdlr)[0].replace(data['year'], '').replace(
'(', '').replace(')', '').replace('&', 'and')
if cleantitle.get(t) != cleantitle.get(title):
continue
if hdlr not in name:
continue
# check year for reboot/remake show issues if year is available-crap shoot
# if 'tvshowtitle' in data:
# if re.search(r'([1-3][0-9]{3})', name):
# if not any(value in name for value in [data['year'], str(int(data['year'])+1), str(int(data['year'])-1)]):
# continue
quality, info = source_utils.get_release_quality(
name, item[1])
try:
dsize, isize = source_utils._size(item[2])
info.insert(0, isize)
except:
dsize = 0
pass
info = ' | '.join(info)
url = item[1]
if any(x in url
for x in ['.rar', '.zip', '.iso', '.sample.']):
continue
url = client.replaceHTMLCodes(url)
url = url.encode('utf-8')
if url in str(sources):
continue
host = re.findall(
'([\w]+[.][\w]+)$',
urlparse.urlparse(url.strip().lower()).netloc)[0]
if not host in hostDict:
continue
host = client.replaceHTMLCodes(host)
host = host.encode('utf-8')
sources.append({
'source': host,
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True,
'size': dsize
})
except:
source_utils.scraper_error('SCENERLS')
pass
return sources
except:
source_utils.scraper_error('SCENERLS')
return sources
def sources(self, url, hostDict, hostprDict):
sources = []
try:
if url is None:
return sources
if debrid.status() is False:
return sources
data = urlparse.parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data])
title = data['tvshowtitle'] if 'tvshowtitle' in data else data['title']
title = title.replace('&', 'and').replace('Special Victims Unit', 'SVU')
hdlr = 'S%02dE%02d' % (int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else data['year']
query = '%s %s' % (title, hdlr)
query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query)
url = self.search_link % urllib.quote_plus(query)
url = urlparse.urljoin(self.base_link, url)
# log_utils.log('url = %s' % url, log_utils.LOGDEBUG)
try:
r = client.request(url)
posts = client.parseDOM(r, 'div', attrs={'class': 'results'})[0]
posts = client.parseDOM(posts, 'dl')
for post in posts:
links = re.findall('<dt><a href=/(.+)</a>', post, re.DOTALL)
for link in links:
magnet = link.split('</a>')[0]
hash = 'magnet:?xt=urn:btih:' + magnet.split('>')[0]
dn = '&dn=' + magnet.split('>')[1]
url = hash + dn
if any(x in url.lower() for x in ['french', 'italian', 'spanish', 'truefrench', 'dublado', 'dubbed']):
continue
name = url.split('&dn=')[1]
t = name.split(hdlr)[0].replace(data['year'], '').replace('(', '').replace(')', '').replace('&', 'and')
if cleantitle.get(t) != cleantitle.get(title):
continue
if hdlr not in name:
continue
quality, info = source_utils.get_release_quality(name, url)
try:
size = re.findall('((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GiB|MiB|GB|MB))', post)[0]
div = 1 if size.endswith('GB') else 1024
size = float(re.sub('[^0-9|/.|/,]', '', size.replace(',', '.'))) / div
size = '%.2f GB' % size
info.append(size)
except:
pass
info = ' | '.join(info)
sources.append({'source': 'torrent', 'quality': quality, 'language': 'en', 'url': url,
'info': info, 'direct': False, 'debridonly': True})
return sources
except:
source_utils.scraper_error('TORRENTZ')
return
except:
source_utils.scraper_error('TORRENTZ')
return sources
def sources(self, url, hostDict, hostprDict):
try:
sources = []
if url == None: return sources
if debrid.status() == False: raise Exception()
data = urlparse.parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '')
for i in data])
title = data['tvshowtitle'] if 'tvshowtitle' in data else data[
'title']
hdlr = 'S%02dE%02d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else data['year']
query = '%s S%02dE%02d' % (
data['tvshowtitle'], int(data['season']),
int(data['episode'])) if 'tvshowtitle' in data else '%s %s' % (
data['title'], data['year'])
query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query)
s = client.request(self.base_link)
s = re.findall('\'(http.+?)\'', s) + re.findall('\"(http.+?)\"', s)
s = [
i for i in s if urlparse.urlparse(self.base_link).netloc in i
and len(i.strip('/').split('/')) > 3
]
s = s[0] if s else urlparse.urljoin(self.base_link, 'posts')
s = s.strip('/')
url = s + self.search_link % urllib.quote_plus(query)
r = client.request(url)
r = client.parseDOM(r, 'h2', attrs={'class': 'post-title .+?'})
l = zip(client.parseDOM(r, 'a', ret='href'),
client.parseDOM(r, 'a', ret='title'))
r = [(i[0], i[1],
re.sub('(\.|\(|\[|\s)(\d{4}|3D)(\.|\)|\]|\s|)(.+|)', '',
i[1]),
re.findall('[\.|\(|\[|\s](\d{4}|)([\.|\)|\]|\s|].+)', i[1]))
for i in l]
r = [(i[0], i[1], i[2], i[3][0][0], i[3][0][1]) for i in r if i[3]]
r = [(i[0], i[1], i[2], i[3], re.split('\.|\(|\)|\[|\]|\s|\-',
i[4])) for i in r]
r = [
i for i in r if cleantitle.get(title) == cleantitle.get(i[2])
and data['year'] == i[3]
]
r = [
i for i in r if not any(x in i[4] for x in [
'HDCAM', 'CAM', 'DVDR', 'DVDRip', 'DVDSCR', 'HDTS', 'TS',
'3D'
])
]
r = [i for i in r if '1080p' in i[4]
][:1] + [i for i in r if '720p' in i[4]][:1]
if 'tvshowtitle' in data:
posts = [(i[1], i[0]) for i in l]
else:
posts = [(i[1], i[0]) for i in l]
hostDict = hostprDict + hostDict
items = []
for post in posts:
try:
t = post[0]
u = client.request(post[1])
u = re.findall('"(http.+?)"', u) + re.findall(
'"(http.+?)"', u)
u = [i for i in u if not '/embed/' in i]
u = [i for i in u if not 'youtube' in i]
items += [(t, i) for i in u]
except:
pass
for item in items:
try:
name = item[0]
name = client.replaceHTMLCodes(name)
t = re.sub(
'(\.|\(|\[|\s)(\d{4}|S\d*E\d*|S\d*|3D)(\.|\)|\]|\s|)(.+|)',
'', name)
if not cleantitle.get(t) == cleantitle.get(title):
raise Exception()
y = re.findall(
'[\.|\(|\[|\s](\d{4}|S\d*E\d*|S\d*)[\.|\)|\]|\s]',
name)[-1].upper()
if not y == hdlr: raise Exception()
fmt = re.sub(
'(.+)(\.|\(|\[|\s)(\d{4}|S\d*E\d*|S\d*)(\.|\)|\]|\s)',
'', name.upper())
fmt = re.split('\.|\(|\)|\[|\]|\s|\-', fmt)
fmt = [i.lower() for i in fmt]
print fmt
if any(
i.endswith(('subs', 'sub', 'dubbed', 'dub'))
for i in fmt):
raise Exception()
if any(i in ['extras'] for i in fmt): raise Exception()
if '1080p' in fmt:
quality = '1080p'
elif '720p' in fmt:
quality = '720p'
else:
quality = '720p'
if any(i in ['dvdscr', 'r5', 'r6'] for i in fmt):
quality = 'SCR'
elif any(i in [
'camrip', 'tsrip', 'hdcam', 'hdts', 'dvdcam',
'dvdts', 'cam', 'telesync', 'ts'
] for i in fmt):
quality = 'CAM'
info = []
if '3d' in fmt: info.append('3D')
try:
size = re.findall(
'((?:\d+\.\d+|\d+\,\d+|\d+) (?:GB|GiB|MB|MiB))',
item[2])[-1]
div = 1 if size.endswith(('GB', 'GiB')) else 1024
size = float(re.sub('[^0-9|/.|/,]', '', size)) / div
size = '%.2f GB' % size
info.append(size)
except:
pass
if any(i in ['hevc', 'h265', 'x265'] for i in fmt):
info.append('HEVC')
info = ' | '.join(info)
url = item[1]
if any(x in url for x in ['.rar', '.zip', '.iso']):
raise Exception()
url = client.replaceHTMLCodes(url)
url = url.encode('utf-8')
host = re.findall(
'([\w]+[.][\w]+)$',
urlparse.urlparse(url.strip().lower()).netloc)[0]
if not host in hostDict: raise Exception()
host = client.replaceHTMLCodes(host)
host = host.encode('utf-8')
sources.append({
'source': host,
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True
})
except:
pass
check = [i for i in sources if not i['quality'] == 'CAM']
if check: sources = check
return sources
except:
return
def sources(self, url, hostDict, hostprDict):
sources = []
try:
if url is None:
return sources
if debrid.status() is False:
raise Exception()
data = urlparse.parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '')
for i in data])
title = data['tvshowtitle'] if 'tvshowtitle' in data else data[
'title']
hdlr = 'S%02dE%02d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else data['year']
query = '%s s%02de%02d' % (
data['tvshowtitle'], int(data['season']),
int(data['episode'])) if 'tvshowtitle' in data else '%s %s' % (
data['title'], data['year'])
query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query)
url = self.search_link % urllib.quote_plus(query)
url = urlparse.urljoin(self.base_link, url)
try:
r = client.request(url)
posts = client.parseDOM(r, 'tr')
for post in posts:
links = re.findall('<a href="(/torrent/.+?)">(.+?)<', post,
re.DOTALL)
for link, data in links:
link = urlparse.urljoin(self.base_link, link)
link = client.request(link)
link = re.findall(
'a class=".+?" rel=".+?" href="(magnet:.+?)"',
link, re.DOTALL)
try:
size = re.findall(
'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GiB|MiB|GB|MB))',
post)[0]
div = 1 if size.endswith('GB') else 1024
size = float(
re.sub('[^0-9|/.|/,]', '',
size.replace(',', '.'))) / div
size = '%.2f GB' % size
except BaseException:
size = '0'
for url in link:
if hdlr not in url:
continue
url = url.split('&tr')[0]
quality, info = source_utils.get_release_quality(
data)
if any(x in url for x in [
'Tamil', 'FRENCH', 'Ita', 'italian',
'TRUEFRENCH', '-lat-', 'Dublado'
]):
continue
info.append(size)
info = ' | '.join(info)
sources.append({
'source': 'Torrent',
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True
})
except:
return
return sources
except:
return sources
def sources(self, url, hostDict, hostprDict):
try:
sources = []
if url is None: return sources
if debrid.status() is False: raise Exception()
data = urlparse.parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '')
for i in data])
title = data['tvshowtitle']
hdlr = 'S%02dE%02d' % (int(data['season']), int(data['episode']))
query = '%s S%02dE%02d' % (
data['tvshowtitle'], int(data['season']),
int(data['episode'])) if 'tvshowtitle' in data else '%s %s' % (
data['title'], data['year'])
query = re.sub('(\\\|/| -|:|;|\*|\?|"|<|>|\|)', ' ', query)
url = self.search_link % (urllib.quote_plus(query).replace(
'+', '-'))
url = urlparse.urljoin(self.base_link, url)
html = client.request(url)
try:
results = client.parseDOM(
html, 'table', attrs={'class': 'forum_header_border'})
for result in results:
if 'magnet:' in result:
results = result
break
except Exception:
return sources
rows = re.findall(
'<tr name="hover" class="forum_header_border">(.+?)</tr>',
results, re.DOTALL)
if rows is None:
return sources
for entry in rows:
try:
try:
columns = re.findall('<td\s.+?>(.+?)</td>', entry,
re.DOTALL)
derka = re.findall(
'href="magnet:(.+?)" class="magnet" title="(.+?)"',
columns[2], re.DOTALL)[0]
name = derka[1]
link = 'magnet:%s' % (str(
client.replaceHTMLCodes(derka[0]).split('&tr')[0]))
t = name.split(hdlr)[0]
if not cleantitle.get(re.sub(
'(|)', '', t)) == cleantitle.get(title):
continue
except Exception:
continue
y = re.findall(
'[\.|\(|\[|\s](\d{4}|S\d*E\d*|S\d*)[\.|\)|\]|\s]',
name)[-1].upper()
if not y == hdlr:
continue
try:
seeders = int(
re.findall('<font color=".+?">(.+?)</font>',
columns[5], re.DOTALL)[0])
except Exception:
continue
if self.min_seeders > seeders:
continue
quality, info = source_utils.get_release_quality(
name, name)
try:
size = re.findall(
'((?:\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|MB|MiB))',
name)[-1]
div = 1 if size.endswith(('GB', 'GiB')) else 1024
size = float(re.sub('[^0-9|/.|/,]', '', size)) / div
size = '%.2f GB' % size
info.append(size)
except Exception:
pass
info = ' | '.join(info)
sources.append({
'source': 'Torrent',
'quality': quality,
'language': 'en',
'url': link,
'info': info,
'direct': False,
'debridonly': True
})
except Exception:
continue
check = [i for i in sources if not i['quality'] == 'CAM']
if check:
sources = check
return sources
except Exception:
return sources
def sources(self, url, hostDict, hostprDict):
try:
sources = []
if url is None:
return sources
if debrid.status() is False:
return sources
hostDict = hostprDict + hostDict
data = urlparse.parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '')
for i in data])
title = data['tvshowtitle'] if 'tvshowtitle' in data else data[
'title']
title = title.replace('&', 'and').replace('Special Victims Unit',
'SVU')
hdlr = 'S%02dE%02d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else data['year']
query = '%s %s' % (title, hdlr)
query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query)
url = self.search_link % urllib.quote_plus(query)
url = urlparse.urljoin(self.base_link, url).replace('-', '+')
r = client.request(url)
if r is None and 'tvshowtitle' in data:
season = re.search('S(.*?)E', hdlr)
season = season.group(1)
url = title
r = client.request(url)
for loopCount in range(0, 2):
if loopCount == 1 or (r is None and 'tvshowtitle' in data):
r = client.request(url)
posts = client.parseDOM(r,
"h2",
attrs={"class": "entry-title"})
items = []
for post in posts:
try:
tit = client.parseDOM(post, "a")[0]
t = tit.split(hdlr)[0].replace(
data['year'],
'').replace('(',
'').replace(')',
'').replace('&', 'and')
if cleantitle.get(t) != cleantitle.get(title):
continue
if hdlr not in tit:
continue
u = client.parseDOM(post, 'a', ret='href')
for i in u:
name = str(i)
items.append(name)
except:
source_utils.scraper_error('SCENEDDL')
pass
if len(items) > 0:
break
for item in items:
try:
i = str(item)
r = client.request(i)
u = client.parseDOM(r,
"div",
attrs={"class": "entry-content"})
for t in u:
r = client.parseDOM(t, 'a', ret='href')
for url in r:
if '.rar' in url or 'imdb.com' in url:
continue
quality, info = source_utils.get_release_quality(
url)
valid, host = source_utils.is_host_valid(
url, hostDict)
if valid:
sources.append({
'source': host,
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True
})
except:
source_utils.scraper_error('SCENEDDL')
pass
return sources
except:
source_utils.scraper_error('SCENEDDL')
return sources
