def _get_items(self, url):
items = []
try:
headers = {'User-Agent': client.agent()}
r = client.request(url, headers=headers)
posts = client.parseDOM(r, 'tr', attrs={'class': 't-row'})
posts = [i for i in posts if not 'racker:' in i]
for post in posts:
data = client.parseDOM(post, 'a', ret='href')
url = [i for i in data if 'magnet:' in i][0]
name = client.parseDOM(post, 'a', ret='title')[0]
t = name.split(self.hdlr)[0]
if not cleantitle.get(re.sub('(|)', '', t)) == cleantitle.get(self.title): continue
try:
y = re.findall('[\.|\(|\[|\s|\_|\-](S\d+E\d+|S\d+)[\.|\)|\]|\s|\_|\-]', name, re.I)[-1].upper()
except BaseException:
y = re.findall('[\.|\(|\[|\s\_|\-](\d{4})[\.|\)|\]|\s\_|\-]', name, re.I)[-1].upper()
if not y == self.hdlr: continue
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)
except BaseException:
dsize, isize = 0.0, ''
items.append((name, url, isize, dsize))
return items
except:
log_utils.log('glodls2_exc', 1)
return items
def get_sources(self, url):
try:
r = client.request(url)
if not r:
return
div = client.parseDOM(r, 'div', attrs={'id': 'div2child'})
for row in div:
row = client.parseDOM(r, 'div', attrs={'class': 'resultdivbotton'})
if not row:
return
for post in row:
hash = re.findall('<div id="hideinfohash.+?" class="hideinfohash">(.+?)<', post, re.DOTALL)[0]
name = re.findall('<div id="hidename.+?" class="hideinfohash">(.+?)<', post, re.DOTALL)[0]
name = unquote_plus(name)
name = source_utils.clean_name(self.title, name)
if source_utils.remove_lang(name, self.episode_title):
continue
url = 'magnet:?xt=urn:btih:%s&dn=%s' % (hash, name)
if url in str(self.sources):
continue
if not source_utils.check_title(self.title, self.aliases, name, self.hdlr, self.year):
continue
# filter for episode multi packs (ex. S01E01-E17 is also returned in query)
if self.episode_title:
if not source_utils.filter_single_episodes(self.hdlr, name):
continue
try:
seeders = int(re.findall('<div class="resultdivbottonseed">([0-9]+|[0-9]+,[0-9]+)<', post, 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('<div class="resultdivbottonlength">(.+?)<', post)[0]
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
dsize = 0
pass
info = ' | '.join(info)
self.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('IDOPE')
pass
def _get_sources(self, name, url):
try:
headers = {'User-Agent': client.agent()}
r = cfScraper.get(url, headers=headers).content
r = ensure_text(r, errors='replace')
name = client.replaceHTMLCodes(name)
try:
_name = name.lower().replace('rr',
'').replace('nf', '').replace(
'ul', '').replace('cu', '')
except:
_name = name
l = dom_parser2.parse_dom(r, 'pre', {'class': 'links'})
s = ''
for i in l:
s += i.content
urls = re.findall(
r'''((?:http|ftp|https)://[\w_-]+(?:(?:\.[\w_-]+)+)[\w.,@?^=%&:/~+#-]*[\w@?^=%&/~+#-])''',
i.content,
flags=re.MULTILINE | re.DOTALL)
urls = [
i for i in urls if not i.endswith(('.rar', '.zip', '.iso',
'.idx', '.sub', '.srt'))
]
for url in urls:
if url in str(self.sources):
continue
valid, host = source_utils.is_host_valid(url, self.hostDict)
if not valid:
continue
host = client.replaceHTMLCodes(host)
#host = host.encode('utf-8')
quality, info = source_utils.get_release_quality(name, url)
try:
size = re.findall(
'((?:\d+\.\d+|\d+\,\d+|\d+)\s*(?:GiB|MiB|GB|MB))',
name)[0]
dsize, isize = source_utils._size(size)
except BaseException:
dsize, isize = 0.0, ''
info.insert(0, isize)
info = ' | '.join(info)
self.sources.append({
'source': host,
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True,
'size': dsize,
'name': _name
})
except:
log_utils.log('RMZ - Exception', 1)
pass
def sources(self, url, hostDict, hostprDict):
sources = []
try:
if debrid.status() is False:
return sources
if url is None:
return sources
data = parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data])
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(u'(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query).lower()
url = urljoin(self.base_link, self.search_link % query)
#r = client.request(url)
#r = requests.get(url).content
r = cfScraper.get(url).content
r = ensure_text(r, errors='replace').replace(' ', ' ')
r = client.parseDOM(r, 'div', attrs={'class': 'col s12'})
posts = client.parseDOM(r, 'div')[1:]
posts = [i for i in posts if 'magnet/' in i]
for post in posts:
links = client.parseDOM(post, 'a', ret='href')[0]
url = 'magnet:?xt=urn:btih:' + links.lstrip('magnet/')
try:
name = client.parseDOM(post, 'a', ret='title')[0]
if not query in cleantitle.get_title(name): continue
except:
name = ''
quality, info = source_utils.get_release_quality(name, name)
try:
size = re.findall(r'<b class="cpill .+?-pill">(.+?)</b>', post)[0]
dsize, isize = source_utils._size(size)
except:
dsize, isize = 0.0, ''
info.insert(0, isize)
info = ' | '.join(info)
sources.append({'source': 'Torrent', 'quality': quality, 'language': 'en', 'url': url, 'info': info,
'direct': False, 'debridonly': True, 'size': dsize, 'name': name})
return sources
except:
log_utils.log('bt4g3 - Exception', 1)
return sources
def sources(self, url, hostDict, hostprDict):
sources = []
try:
self.hostDict = hostDict + hostprDict
if url is None:
return sources
if debrid.status() is False: return
data = parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data])
self.title = data['tvshowtitle'] if 'tvshowtitle' in data else data['title']
self.title = cleantitle.get_query(self.title)
self.hdlr = 'S%02dE%02d' % (int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else data['year']
query = '%s S%02dE%02d' % (self.title, int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else '%s %s' % (self.title, data['year'])
query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query)
if 'tvshowtitle' in data:
url = self.tvsearch.format(quote(query))
url = urljoin(self.base_link, url)
else:
url = self.moviesearch.format(quote(query))
url = urljoin(self.base_link, url)
r = cfScraper.get(url).content
r = ensure_text(r, errors='ignore')
posts = client.parseDOM(r, 'table', attrs={'class': 'table2'})[0]
posts = client.parseDOM(posts, 'tr')
for post in posts:
link = client.parseDOM(post, 'a', ret='href')[0]
hash = re.findall(r'(\w{40})', link, re.I)
if hash:
url = 'magnet:?xt=urn:btih:' + hash[0]
name = link.split('title=')[1]
t = name.split(self.hdlr)[0]
if not cleantitle.get(re.sub('(|)', '', t)) == cleantitle.get(self.title): continue
try:
y = re.findall('[\.|\(|\[|\s|\_|\-](S\d+E\d+|S\d+)[\.|\)|\]|\s|\_|\-]', name, re.I)[-1].upper()
except:
y = re.findall('[\.|\(|\[|\s\_|\-](\d{4})[\.|\)|\]|\s\_|\-]', name, re.I)[-1].upper()
if not y == self.hdlr: continue
quality, info = source_utils.get_release_quality(name, name)
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)
except:
dsize, isize = 0.0, ''
info.insert(0, isize)
info = ' | '.join(info)
sources.append({'source': 'Torrent', 'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False,
'debridonly': True, 'size': dsize, 'name': name})
return sources
except:
log_utils.log('lime0 - Exception', 1)
return sources
def get_sources(self, row):
try:
if 'magnet' not in row:
return
url = re.findall('href="(magnet:.+?)"', row, re.DOTALL)[0]
url = unquote_plus(url).split('&tr')[0].replace('&', '&').replace(' ', '.')
if url in str(self.sources):
return
hash = re.compile('btih:(.*?)&').findall(url)[0]
name = url.split('&dn=')[1]
name = source_utils.clean_name(self.title, name)
if source_utils.remove_lang(name, self.episode_title):
return
if not source_utils.check_title(self.title, self.aliases, name, self.hdlr, self.year):
return
# filter for episode multi packs (ex. S01E01-E17 is also returned in query)
if self.episode_title:
if not source_utils.filter_single_episodes(self.hdlr, name):
return
try:
seeders = int(re.findall('<span style="color:#008000"><strong>\s*([0-9]+)\s*</strong>', row, re.DOTALL)[0].replace(',', ''))
if self.min_seeders > seeders:
return
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*(?:GB|GiB|Gb|MB|MiB|Mb))', row, re.DOTALL)[0]
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
dsize = 0
pass
info = ' | '.join(info)
self.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('MAGNET4YOU')
pass
def _get_items(self, url):
try:
r = cfScraper.get(url).content
r = ensure_text(r, errors='replace')
posts = client.parseDOM(r, 'tbody')[0]
posts = client.parseDOM(posts, 'tr')
for post in posts:
data = dom.parse_dom(post, 'a', req='href')[1]
link = urljoin(self.base_link, data.attrs['href'])
name = data.content
t = name.split(self.hdlr)[0]
if not cleantitle.get(re.sub('(|)', '', t)) == cleantitle.get(
self.title):
continue
try:
y = re.findall(
'[\.|\(|\[|\s|\_|\-](S\d+E\d+|S\d+)[\.|\)|\]|\s|\_|\-]',
name, re.I)[-1].upper()
except BaseException:
y = re.findall(
'[\.|\(|\[|\s\_|\-](\d{4})[\.|\)|\]|\s\_|\-]', name,
re.I)[-1].upper()
if not y == self.hdlr:
continue
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)
except BaseException:
dsize, isize = 0.0, ''
self.items.append((name, link, isize, dsize))
return self.items
except:
log_utils.log('1337x_exc0', 1)
return self.items
def get_sources(self, link):
try:
url = '%s%s' % (self.base_link, link)
result = client.request(url)
info_hash = re.findall('<kbd>(.+?)<', result, re.DOTALL)[0]
url = 'magnet:?xt=urn:btih:' + info_hash
name = re.findall('<h3 class="card-title">(.+?)<', result, re.DOTALL)[0]
name = unquote_plus(name).replace(' ', '.').replace('Original.Name:.', '').lower()
#url = '%s%s%s' % (url1, '&dn=', str(name))
t = name.split(self.hdlr)[0].replace(self.year, '').replace('(', '').replace(')', '').replace('&', 'and').replace('.US.', '.').replace('.us.', '.')
if cleantitle.get(t) != cleantitle.get(self.title):
return
if self.hdlr not in name:
return
quality, info = source_utils.get_release_quality(name, url)
try:
size = re.findall('<div class="col-3">File size:</div><div class="col">(.+?)<', result, re.DOTALL)[0]
size = re.findall('((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GiB|MiB|GB|MB))', size)[0]
dsize, isize = source_utils._size(size)
except:
dsize, isize = 0.0, ''
info.insert(0, isize)
info = ' | '.join(info)
self.sources.append({'source': 'torrent', 'quality': quality, 'language': 'en', 'url': url,
'info': info, 'direct': False, 'debridonly': True, 'size': dsize, 'name': name})
except:
log_utils.log('YourBT4 - Exception', 1)
pass
def sources(self, url, hostDict, hostprDict):
sources = []
try:
if debrid.status() is False:
return sources
if url is None:
return sources
data = parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '')
for i in data])
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(u'(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ',
query).lower()
url = urljoin(self.base_link, self.search_link % quote_plus(query))
r = client.request(url)
#r = cfScraper.get(url).content
r = ensure_text(r, errors='replace').strip()
posts = client.parseDOM(r,
'table',
attrs={
'class': 'table2',
'cellspacing': '0'
})[1]
posts = client.parseDOM(posts, 'tr')[1:]
for post in posts:
links = client.parseDOM(post, 'a', ret='href')[0]
links = client.replaceHTMLCodes(links).lstrip('/')
hash = links.split('/')[0]
name = links.split('/')[1]
url = 'magnet:?xt=urn:btih:{}'.format(hash)
if not query in cleantitle.get_title(name): continue
quality, info = source_utils.get_release_quality(name)
try:
size = client.parseDOM(post,
'td',
attrs={'class': 'tdnormal'})[1]
dsize, isize = source_utils._size(size)
except:
dsize, isize = 0.0, ''
info.insert(0, isize)
info = ' | '.join(info)
sources.append({
'source': 'Torrent',
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True,
'size': dsize,
'name': name
})
return sources
except:
log_utils.log('tdl3 - Exception', 1)
return sources
def get_sources_packs(self, url):
try:
r = client.request(url, timeout='5')
if not r:
return
r = client.parseDOM(r, 'table', attrs={'class': 'tmain'})[0]
links = re.findall('<a href="(/torrent/.+?)">(.+?)</a>', r, re.DOTALL)
for link in links:
try:
url = link[0].encode('ascii', errors='ignore').decode('ascii', errors='ignore').replace(' ', ' ')
except:
url = link[0].replace(' ', ' ')
if '/torrent/' not in url:
continue
try:
name = link[1].encode('ascii', errors='ignore').decode('ascii', errors='ignore').replace(' ', '.')
except:
name = link[1].replace(' ', '.')
if '<span' in name:
nam = name.split('<span')[0].replace(' ', '.')
span = client.parseDOM(name, 'span')[0].replace('-', '.')
name = '%s%s' % (nam, span)
name = source_utils.clean_name(self.title, name)
if source_utils.remove_lang(name):
continue
if not self.search_series:
if not self.bypass_filter:
if not source_utils.filter_season_pack(self.title, self.aliases, self.year, self.season_x, name):
continue
package = 'season'
elif self.search_series:
if not self.bypass_filter:
valid, last_season = source_utils.filter_show_pack(self.title, self.aliases, self.imdb, self.year, self.season_x, name, self.total_seasons)
if not valid:
continue
else:
last_season = self.total_seasons
package = 'show'
if not url.startswith('http'):
link = urljoin(self.base_link, url)
link = client.request(link, timeout='5')
if link is None:
continue
hash = re.findall('<b>Infohash</b></td><td valign=top>(.+?)</td>', link, re.DOTALL)[0]
url = 'magnet:?xt=urn:btih:%s&dn=%s' % (hash, name)
if url in str(self.sources):
continue
try:
seeders = int(re.findall('<b>Swarm:</b></td><td valign=top><font color=red>([0-9]+)</font>', link, re.DOTALL)[0].replace(',', ''))
if self.min_seeders > seeders: # site does not seem to report 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))', link)[0]
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
dsize = 0
pass
info = ' | '.join(info)
item = {'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'quality': quality,
'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize, 'package': package}
if self.search_series:
item.update({'last_season': last_season})
self.sources.append(item)
except:
source_utils.scraper_error('TORRENTFUNK')
pass
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 = 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 = cleantitle.get_query(title)
query = '%s S%02dE%02d' % (
title, int(data['season']), int(data['episode'])
) if 'tvshowtitle' in data else '%s %s' % (title, data['year'])
url = self.search_link % quote_plus(query)
url = urljoin(self.base_link, url).replace('%3A+', '+')
#r = client.request(url)
r = cfScraper.get(url).content
r = ensure_text(r, errors='replace')
posts = client.parseDOM(r, "div", attrs={"class": "postContent"})
items = []
for post in posts:
try:
p = client.parseDOM(post, "p", attrs={"dir": "ltr"})[1:]
for i in p:
items.append(i)
except:
pass
try:
for item in items:
u = client.parseDOM(item, 'a', ret='href')
name = re.findall('<strong>(.*?)</strong>', item,
re.DOTALL)[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
for url in u:
if any(x in url for x in ['.rar', '.zip', '.iso']):
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|gb|mb))',
item, re.DOTALL)[0]
dsize, isize = source_utils._size(size)
except:
dsize, isize = 0.0, ''
info.insert(0, isize)
info = ' | '.join(info)
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,
'size': dsize,
'name': name
})
except:
pass
return sources
except:
log_utils.log('max_rls Exception', 1)
return sources
def _get_sources(self, url, name, hostDict, hostprDict):
try:
urls = []
#result = client.request(url)
result = cfScraper.get(url).content
urls = [(client.parseDOM(result,
'a',
ret='href',
attrs={'class': 'dbuttn watch'})[0],
client.parseDOM(result,
'a',
ret='href',
attrs={'class': 'dbuttn blue'})[0],
client.parseDOM(result,
'a',
ret='href',
attrs={'class': 'dbuttn magnet'})[0])]
# '''<a class="dbuttn watch" href="https://www.linkomark.xyz/view/EnWNqSNeLw" target="_blank" rel="nofollow noopener">Watch Online Links</a>
# <a class="dbuttn blue" href="https://www.linkomark.xyz/view/3-Gjyz5Q2R" target="_blank" rel="nofollow noopener">Get Download Links</a>
# <a class="dbuttn magnet" href="https://torrentbox.site/save/2970fa51e8af52b7e2d1d5fa61a6005777d768ba" target="_blank" rel="nofollow noopener">Magnet Link</a>'''
quality, info = source_utils.get_release_quality(name, url)
try:
size = re.findall(
'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))',
result)[0]
dsize, isize = source_utils._size(size)
except:
dsize = 0.0
isize = ''
info.append(isize)
info = ' | '.join(info)
except:
failure = traceback.format_exc()
log_utils.log('mkvhub5 - Exception: \n' + str(failure))
return
for url in urls[0]:
try:
#r = client.request(url)
r = cfScraper.get(url).content
if r is None:
continue
if 'linkomark' in url:
p_link = client.parseDOM(r,
'link',
attrs={'rel': 'canonical'},
ret='href')[0]
#<input type="hidden" name="_csrf_token_" value=""/>
input_name = client.parseDOM(r, 'input', ret='name')[0]
input_value = client.parseDOM(r, 'input', ret='value')[0]
post = {input_name: input_value}
p_data = client.request(p_link, post=post)
links = client.parseDOM(p_data,
'a',
ret='href',
attrs={'target': '_blank'})
for i in links:
valid, host = source_utils.is_host_valid(i, hostDict)
if not valid:
valid, host = source_utils.is_host_valid(
i, hostprDict)
if not valid:
continue
else:
rd = True
else:
rd = False
if i in str(self._sources):
continue
if 'rapidgator' in i:
rd = True
if rd:
self._sources.append({
'source': host,
'quality': quality,
'language': 'en',
'url': i,
'info': info,
'direct': False,
'debridonly': True
})
else:
self._sources.append({
'source': host,
'quality': quality,
'language': 'en',
'url': i,
'info': info,
'direct': False,
'debridonly': False
})
elif 'torrent' in url:
data = client.parseDOM(r, 'a', ret='href')
url = [i for i in data if 'magnet:' in i][0]
url = url.split('&tr')[0]
self._sources.append({
'source': 'torrent',
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True,
'size': dsize
})
except:
failure = traceback.format_exc()
log_utils.log('mkvhub6 - Exception: \n' + str(failure))
pass
def sources(self, url, hostDict, hostprDict):
sources = []
if not url: return sources
try:
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 = cleantitle.get_query(title)
aliases = data['aliases']
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)
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(' ', '.').split('&tr')[0]
name = url.split('&dn=')[1]
quality, info = source_utils.get_release_quality(
name, url)
try:
size = link[1]
dsize, isize = source_utils._size(size)
except:
dsize, isize = 0.0, ''
pass
info.insert(0, isize)
info = ' | '.join(info)
sources.append({
'source': 'torrent',
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True,
'size': dsize,
'name': name
})
except:
log_utils.log('nyaa3 - Exception', 1)
return sources
return sources
except:
log_utils.log('nyaa4 - Exception', 1)
return sources
def sources(self, url, hostDict, hostprDict):
try:
sources = []
if url is None:
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 = cleantitle.get_query(title)
hdlr = 'S%02dE%02d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else data['year']
query = '%s S%02dE%02d' % (
title, int(data['season']), int(data['episode'])
) if 'tvshowtitle' in data else '%s %s' % (title, data['year'])
query = re.sub('(\\\|/| -|:|;|\*|\?|"|<|>|\|)', ' ', query)
url = self.search_link % quote_plus(query)
url = urljoin(self.base_link, url)
html = client.request(url)
if html is None:
return sources
html = html.replace(' ', ' ')
try:
rows = client.parseDOM(html,
'tr',
attrs={'id': 'torrent_latest_torrents'})
except Exception:
return sources
if rows is None:
#log_utils.log('KICKASS - No Torrents In Search Results')
return sources
for entry in rows:
try:
try:
name = re.findall('class="cellMainLink">(.+?)</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
try:
y = re.findall(
'[\.|\(|\[|\s|\_|\-](S\d+E\d+|S\d+)[\.|\)|\]|\s|\_|\-]',
name, re.I)[-1].upper()
except BaseException:
y = re.findall(
'[\.|\(|\[|\s](\d{4}|S\d*E\d*|S\d*)[\.|\)|\]|\s]',
name, re.I)[-1].upper()
if not y == hdlr:
continue
try:
link = 'magnet%s' % (re.findall(
'url=magnet(.+?)"', entry, re.DOTALL)[0])
link = str(
unquote(six.ensure_text(link)).split('&tr')[0])
except Exception:
continue
quality, info = source_utils.get_release_quality(
name, link)
try:
size = re.findall(
'((?:\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|MB|MiB))',
entry)[-1]
dsize, isize = source_utils._size(size)
except Exception:
dsize, isize = 0.0, ''
info.insert(0, isize)
info = ' | '.join(info)
sources.append({
'source': 'Torrent',
'quality': quality,
'language': 'en',
'url': link,
'info': info,
'direct': False,
'debridonly': True,
'size': dsize,
'name': name
})
except Exception:
continue
check = [i for i in sources if not i['quality'] == 'CAM']
if check:
sources = check
return sources
except:
log_utils.log('kickass_exc', 1)
return sources
def sources(self, url, hostDict, hostprDict):
sources = []
try:
if debrid.status() is False:
return sources
if url is None:
return sources
data = parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '')
for i in data])
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(u'(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ',
query).lower()
url = urljoin(self.base_link, self.search_link % quote_plus(query))
#r = client.request(url)
#r = requests.get(url).content
r = cfScraper.get(url).content
r = ensure_text(r, errors='replace').replace(' ', ' ')
r = client.parseDOM(
r,
'div',
attrs={'style': 'display:table;width:100%;text-align:left'})
posts = client.parseDOM(r, 'div', attrs={'class': 'one_result'})
#log_utils.log('posts_is: '+str(posts))
for post in posts:
links = client.parseDOM(post,
'div',
attrs={'class': 'fa fa-magnet'})[0]
url = client.parseDOM(links, 'a', ret='href')[0]
url = client.replaceHTMLCodes(url).split('&tr=')[0]
name = url.split('&dn=')[1]
if not query in cleantitle.get_title(name): continue
quality, info = source_utils.get_release_quality(name, url)
try:
size = client.parseDOM(post,
'span',
attrs={'class': 'torrent_size'})[0]
dsize, isize = source_utils._size(size)
except:
dsize, isize = 0.0, ''
info.insert(0, isize)
info = ' | '.join(info)
sources.append({
'source': 'Torrent',
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True,
'size': dsize,
'name': name
})
return sources
except:
log_utils.log('btdig3 - Exception', 1)
return sources
def sources(self, url, hostDict, hostprDict):
sources = []
try:
if url is None:
return sources
if debrid.status() is False:
raise Exception()
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']
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 % quote_plus(query)
url = urljoin(self.base_link, url)
try:
r = client.request(url)
posts = client.parseDOM(r, 'tr')
for post in posts:
link = re.findall(
'a title="Download Torrent Magnet" href="(magnet:.+?)"',
post, re.DOTALL)
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)
except BaseException:
dsize, isize = 0.0, ''
for url in link:
url = unquote_plus(url).split('&tr')[0].replace(
'&', '&').replace(' ', '.')
if hdlr not in url:
continue
name = url.split('&dn=')[1]
quality, info = source_utils.get_release_quality(
name, url)
if any(x in url for x in [
'FRENCH', 'Ita', 'italian', 'TRUEFRENCH',
'-lat-', 'Dublado'
]):
continue
info.insert(0, isize)
info = ' | '.join(info)
sources.append({
'source': 'Torrent',
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True,
'size': dsize,
'name': name
})
except:
return
return sources
except:
return sources
def get_sources(self, url):
try:
r = client.request(url, timeout='10')
if not r:
return
posts = client.parseDOM(r, 'tbody')[0]
posts = client.parseDOM(posts, 'tr')
for post in posts:
post = re.sub(r'\n', '', post)
post = re.sub(r'\t', '', post)
links = re.compile(
'<a href="(/torrent_details/.+?)"><span>(.+?)</span>.*?<td class="size-row">(.+?)</td><td class="sn">([0-9]+)</td>'
).findall(post)
for items in links:
# item[1] does not contain full info like the &dn= portion of magnet
link = urljoin(self.base_link, items[0])
link = client.request(link, timeout='10')
if not link:
continue
magnet = re.compile('(magnet.+?)"').findall(link)[0]
url = unquote_plus(magnet).replace('&',
'&').replace(' ', '.')
url = url.split('&tr')[0]
name = unquote_plus(url.split('&dn=')[1])
name = source_utils.clean_name(self.title, name)
if source_utils.remove_lang(name, self.episode_title):
continue
if not source_utils.check_title(self.title, self.aliases,
name, self.hdlr,
self.year):
continue
hash = re.compile('btih:(.*?)&').findall(url)[0]
# filter for episode multi packs (ex. S01E01-E17 is also returned in query)
if self.episode_title:
if not source_utils.filter_single_episodes(
self.hdlr, name):
continue
try:
seeders = int(items[3].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+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))',
items[2])[0]
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
dsize = 0
pass
info = ' | '.join(info)
self.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('ISOHUNT2')
pass
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 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)
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
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 = int(link[1])
size = str(size) + ' GB' if len(str(size)) == 1 else str(size) + ' MB'
dsize, isize = source_utils._size(size)
except:
dsize, isize = 0, ''
info.insert(0, isize)
info = ' | '.join(info)
sources.append({'source': 'torrent', 'quality': quality, 'language': 'en', 'url': url,
'info': info, 'direct': False, 'debridonly': True, 'size': dsize})
return sources
except:
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 = 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 = cleantitle.get_query(title)
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)
html = client.request(url)
html = html.replace(' ', ' ')
try:
results = client.parseDOM(html, 'table', attrs={'id': 'searchResult'})
except:
return sources
url2 = url.replace('/1/', '/2/')
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:
try:
try:
url = 'magnet:%s' % (re.findall('a href="magnet:(.+?)"', entry, re.DOTALL)[0])
url = str(client.replaceHTMLCodes(url).split('&tr')[0])
except:
continue
try:
name = re.findall('class="detLink" title=".+?">(.+?)</a>', entry, re.DOTALL)[0]
name = client.replaceHTMLCodes(name)
name = unquote_plus(name).replace(' ', '.').lower()
t = name.split(hdlr)[0].replace(data['year'], '').replace('(', '').replace(')', '').replace('&', 'and').replace('.US.', '.').replace('.us.', '.').lower()
if cleantitle.get(t) != cleantitle.get(title):
continue
except:
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+)\s*(?:GB|GiB|MB|MiB))', entry)[-1]
dsize, isize = source_utils._size(size)
except:
dsize, isize = 0.0, ''
info.insert(0, isize)
info = ' | '.join(info)
sources.append({'source': 'torrent', 'quality': quality, 'language': 'en', 'url': url,
'info': info, 'direct': False, 'debridonly': True, 'size': dsize, 'name': name})
except:
continue
return sources
except:
log_utils.log('tpb_exc', 1)
return sources
def sources(self, url, hostDict, hostprDict):
sources = []
try:
if url is None:
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']
hdlr = 'S%02dE%02d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else data['year']
query = '%s S%02dE%02d' % (
title, int(data['season']), int(data['episode'])
) if 'tvshowtitle' in data else '%s %s' % (title, data['year'])
query = re.sub('(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query)
#r = client.request(self.base_link)
#search_base = client.parseDOM(r, 'form', ret='action')[0]
#log_utils.log(search_base)
#url = urljoin(search_base, self.search_link)
url = urljoin(self.base_link, self.search_link)
url = url % quote_plus(query)
r = client.request(url)
r = client.parseDOM(r, 'h2')
z = zip(client.parseDOM(r, 'a', ret='href'),
client.parseDOM(r, 'a'))
if 'tvshowtitle' in data:
posts = [(i[1], i[0]) for i in z]
else:
posts = [(i[1], i[0]) for i in z]
host_dict = hostprDict + hostDict
items = []
for post in posts:
try:
r = client.request(post[1])
r = ensure_text(r, errors='replace')
r = client.parseDOM(r,
'div',
attrs={'class': 'entry-content cf'})[0]
if 'tvshowtitle' in data:
z = zip(
re.findall(r'<p><b>(%s.+?)</b>' % title, r,
re.I | re.S),
re.findall(r'<ul>(.+?)</ul>', r, re.S))
for f in z:
u = re.findall(r'\'(http.+?)\'',
f[1]) + re.findall(
r'\"(http.+?)\"', f[1])
u = [i for i in u if '/embed/' not in i]
t = f[0]
try:
s = re.findall(
r'((?:\d+\.\d+|\d+\,\d+|\d+|\d+\,\d+\.\d+)\s*(?:GB|GiB|MB|MiB))',
t)[0]
except:
s = '0'
items += [(t, i, s) for i in u]
else:
t = ensure_text(post[0], errors='replace')
u = re.findall(r'\'(http.+?)\'', r) + re.findall(
'\"(http.+?)\"', r)
u = [i for i in u if '/embed/' not in i]
try:
s = re.findall(
r'((?:\d+\.\d+|\d+\,\d+|\d+|\d+\,\d+\.\d+)\s*(?:GB|GiB|MB|MiB))',
r)[0]
except:
s = '0'
items += [(t, i, s) for i in u]
except:
log_utils.log('MYVIDEOLINK ERROR', 1)
pass
for item in items:
try:
url = ensure_text(item[1])
url = client.replaceHTMLCodes(url)
void = ('.rar', '.zip', '.iso', '.part', '.png', '.jpg',
'.bmp', '.gif', 'sub', 'srt')
if url.endswith(void):
continue
name = ensure_text(item[0], errors='replace')
name = client.replaceHTMLCodes(name)
t = re.sub(
r'(\.|\(|\[|\s)(\d{4}|S\d*E\d*|S\d*|3D)(\.|\)|\]|\s|)(.+|)',
'', name, re.I)
if not cleantitle.get(t) == cleantitle.get(title):
continue
y = re.findall(
r'[\.|\(|\[|\s](\d{4}|S\d*E\d*|S\d*)[\.|\)|\]|\s]',
name)[-1].upper()
if not y == hdlr:
continue
valid, host = source_utils.is_host_valid(url, host_dict)
if not valid:
continue
host = client.replaceHTMLCodes(host)
quality, info = source_utils.get_release_quality(name, url)
try:
size = item[2]
dsize, isize = source_utils._size(size)
except:
dsize, isize = 0.0, ''
info.insert(0, isize)
info = ' | '.join(info)
sources.append({
'source': host,
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': False,
'size': dsize,
'name': name
})
except:
log_utils.log('MYVIDEOLINK ERROR', 1)
pass
return sources
except:
log_utils.log('MYVIDEOLINK ERROR', 1)
return sources
def sources(self, url, hostDict, hostprDict):
sources = []
try:
if debrid.status() is False:
return sources
if url is None:
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']
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 % quote_plus(query)
url = urljoin(self.base_link, url)
r = client.request(url)
posts = re.findall('<h2 class="title">(.+?)</h2>', r,
re.IGNORECASE)
hostDict = hostprDict + hostDict
urls = []
for item in posts:
try:
link, name = re.findall('href="(.+?)" title="(.+?)"', item,
re.IGNORECASE)[0]
if not cleantitle.get(title) in cleantitle.get(name):
continue
name = client.replaceHTMLCodes(name)
try:
_name = name.lower().replace('permalink to', '')
except:
_name = name
quality, info = source_utils.get_release_quality(
name, link)
try:
size = re.findall(
'((?:\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|MB|MiB))',
name)[-1]
dsize, isize = source_utils._size(size)
except Exception:
dsize, isize = 0.0, ''
info.insert(0, isize)
info = ' | '.join(info)
links = self.links(link)
urls += [(i, quality, info) for i in links]
except Exception:
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')
url = ensure_text(url)
valid, host = source_utils.is_host_valid(url, hostDict)
if not valid:
continue
host = client.replaceHTMLCodes(host)
#host = host.encode('utf-8')
host = ensure_text(host)
sources.append({
'source': host,
'quality': item[1],
'language': 'en',
'url': url,
'info': item[2],
'direct': False,
'debridonly': True,
'size': dsize,
'name': _name
})
return sources
except Exception:
return sources
def sources(self, url, hostDict, hostprDict):
sources = []
try:
if debrid.status() is False:
return sources
if url is None:
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 = cleantitle.get_query(title)
hdlr = 'S%02dE%02d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else data['year']
query = '%s s%02de%02d' % (title, int(data['season']), int(data['episode']))\
if 'tvshowtitle' in data else '%s %s' % (title, data['year'])
query = re.sub(u'(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', ' ', query)
url = urljoin(
self.base_link,
self.search_link.format(query[0].lower(),
cleantitle.geturl(query)))
r = client.request(url)
r = client.parseDOM(r, 'tbody')[0]
posts = client.parseDOM(r, 'tr')
posts = [i for i in posts if 'magnet:' in i]
for post in posts:
post = post.replace(' ', ' ')
name = client.parseDOM(post, 'a', ret='title')[1]
t = name.split(hdlr)[0]
if not cleantitle.get(re.sub(r'(|)', '',
t)) == cleantitle.get(title):
continue
try:
y = re.findall(
u'[\.|\(|\[|\s|\_|\-](S\d+E\d+|S\d+)[\.|\)|\]|\s|\_|\-]',
name, re.I)[-1].upper()
except BaseException:
y = re.findall(
u'[\.|\(|\[|\s\_|\-](\d{4})[\.|\)|\]|\s\_|\-]', name,
re.I)[-1].upper()
if not y == hdlr: continue
links = client.parseDOM(post, 'a', ret='href')
magnet = [
i.replace('&', '&') for i in links if 'magnet:' in i
][0]
url = magnet.split('&tr')[0]
quality, info = source_utils.get_release_quality(name, url)
try:
size = re.findall(
r'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GiB|MiB|GB|MB))',
post)[0]
dsize, isize = source_utils._size(size)
except:
dsize, isize = 0.0, ''
info.insert(0, isize)
info = ' | '.join(info)
sources.append({
'source': 'Torrent',
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True,
'size': dsize,
'name': name
})
return sources
except:
log_utils.log('Magnetdl - Exception', 1)
return sources
def get_sources_packs(self, link):
# log_utils.log('link = %s' % str(link), __name__, log_utils.LOGDEBUG)
try:
r = client.request(link)
if not r:
return
if '<tbody' not in r:
return
posts = client.parseDOM(r, 'tbody')[0]
posts = client.parseDOM(posts, 'tr')
except:
source_utils.scraper_error('SKYTORRENTS')
return
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(self.title, name)
if source_utils.remove_lang(name):
continue
if not self.search_series:
if not self.bypass_filter:
if not source_utils.filter_season_pack(
self.title, self.aliases, self.year,
self.season_x, name):
continue
package = 'season'
elif self.search_series:
if not self.bypass_filter:
valid, last_season = source_utils.filter_show_pack(
self.title, self.aliases, self.imdb, self.year,
self.season_x, name, self.total_seasons)
if not valid:
continue
else:
last_season = self.total_seasons
package = 'show'
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)
item = {
'source': 'torrent',
'seeders': seeders,
'hash': hash,
'name': name,
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True,
'size': dsize,
'package': package
}
if self.search_series:
item.update({'last_season': last_season})
self.sources.append(item)
except:
source_utils.scraper_error('SKYTORRENTS')
pass
def get_sources(self, link):
try:
url = 'magnet:%s' % (re.findall('a href="magnet:(.+?)"', link,
re.DOTALL)[0])
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(self.title, name)
if source_utils.remove_lang(name, self.episode_title):
return
if not source_utils.check_title(self.title, self.aliases, name,
self.hdlr, self.year):
return
# filter for episode multi packs (ex. S01E01-E17 is also returned in query)
if self.episode_title:
if not source_utils.filter_single_episodes(self.hdlr, name):
return
try:
seeders = int(
client.parseDOM(link, 'td',
attrs={'class': 'sy'})[0].replace(',', ''))
if self.min_seeders > seeders:
return
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))',
link)[0]
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
source_utils.scraper_error('EXTRATORRENT')
dsize = 0
pass
info = ' | '.join(info)
self.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('EXTRATORRENT')
pass
def get_sources(self, link):
try:
try:
url = link[0].encode('ascii', errors='ignore').decode('ascii', errors='ignore').replace(' ', ' ')
except:
url = link[0].replace(' ', ' ')
if '/torrent/' not in url:
return
try:
name = link[1].encode('ascii', errors='ignore').decode('ascii', errors='ignore').replace(' ', '.')
except:
name = link[1].replace(' ', '.')
if '<span' in name:
nam = name.split('<span')[0].replace(' ', '.')
span = client.parseDOM(name, 'span')[0].replace('-', '.')
name = '%s%s' % (nam, span)
name = source_utils.clean_name(self.title, name)
if source_utils.remove_lang(name, self.episode_title):
return
if not source_utils.check_title(self.title, self.aliases, name, self.hdlr, self.year):
return
# filter for episode multi packs (ex. S01E01-E17 is also returned in query)
if self.episode_title:
if not source_utils.filter_single_episodes(self.hdlr, name):
return
if not url.startswith('http'):
link = urljoin(self.base_link, url)
link = client.request(link, timeout='5')
if link is None:
return
hash = re.findall('<b>Infohash</b></td><td valign=top>(.+?)</td>', link, re.DOTALL)[0]
url = 'magnet:?xt=urn:btih:%s&dn=%s' % (hash, name)
if url in str(self.sources):
return
try:
seeders = int(re.findall('<b>Swarm:</b></td><td valign=top><font color=red>([0-9]+)</font>', link, re.DOTALL)[0].replace(',', ''))
if self.min_seeders > seeders: # site does not seem to report seeders
return
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))', link)[0]
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
dsize = 0
pass
info = ' | '.join(info)
self.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('TORRENTFUNK')
pass
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
data = parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '')
for i in data])
title = data['title']
aliases = data['aliases']
episode_title = data['title'] if 'tvshowtitle' in data else None
year = data['year']
query = re.sub('[^A-Za-z0-9\s\.-]+', '', title)
url = self.search_link % quote_plus(query)
url = urljoin(self.base_link, url)
# log_utils.log('url = %s' % url, log_utils.LOGDEBUG)
try:
r = scraper.get(url).content
if not r:
return sources
if any(value in str(r) for value in [
'No movies found', 'something went wrong',
'Connection timed out'
]):
return sources
r = json.loads(r)
id = ''
for i in r:
if i['original_title'] == title and i[
'release_date'] == year:
id = i['id']
break
if id == '':
return sources
link = '%s%s%s' % (self.base_link, '/movies/torrents?id=', id)
result = scraper.get(link).content
if 'magnet' not in result:
return sources
result = re.sub(r'\n', '', result)
links = re.findall(
r'<tr>.*?<a title="Download:\s*(.+?)"href="(magnet:.+?)">.*?title="File Size">\s*(.+?)\s*</td>.*?title="Seeds">([0-9]+|[0-9]+,[0-9]+)\s*<',
result)
for link in links:
name = link[0]
name = unquote_plus(name)
name = source_utils.clean_name(title, name)
if source_utils.remove_lang(name, episode_title):
continue
if not source_utils.check_title(title.replace('&', 'and'),
aliases, name, year, year):
continue
url = link[1]
try:
url = unquote_plus(url).decode('utf8').replace(
'&', '&').replace(' ', '.')
except:
url = unquote_plus(url).replace('&',
'&').replace(' ', '.')
url = url.split('&tr')[0]
hash = re.compile('btih:(.*?)&').findall(url)[0]
quality, info = source_utils.get_release_quality(name, url)
try:
size = link[2]
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
dsize = 0
pass
info = ' | '.join(info)
try:
seeders = int(link[3].replace(',', ''))
if self.min_seeders > seeders:
continue
except:
seeders = 0
pass
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('MOVIEMAGNET')
return sources
except:
source_utils.scraper_error('MOVIEMAGNET')
return sources
def get_sources_packs(self, link):
# log_utils.log('link = %s' % str(link), __name__, log_utils.LOGDEBUG)
try:
r = client.request(link)
if not r:
return
div = client.parseDOM(r, 'div', attrs={'id': 'div2child'})
for row in div:
row = client.parseDOM(r, 'div', attrs={'class': 'resultdivbotton'})
if not row:
return
for post in row:
hash = re.findall('<div id="hideinfohash.+?" class="hideinfohash">(.+?)<', post, re.DOTALL)[0]
name = re.findall('<div id="hidename.+?" class="hideinfohash">(.+?)<', post, re.DOTALL)[0]
name = unquote_plus(name)
name = source_utils.clean_name(self.title, name)
if source_utils.remove_lang(name):
continue
url = 'magnet:?xt=urn:btih:%s&dn=%s' % (hash, name)
if url in str(self.sources):
continue
if not self.search_series:
if not self.bypass_filter:
if not source_utils.filter_season_pack(self.title, self.aliases, self.year, self.season_x, name):
continue
package = 'season'
elif self.search_series:
if not self.bypass_filter:
valid, last_season = source_utils.filter_show_pack(self.title, self.aliases, self.imdb, self.year, self.season_x, name, self.total_seasons)
if not valid:
continue
else:
last_season = self.total_seasons
package = 'show'
try:
seeders = int(re.findall('<div class="resultdivbottonseed">([0-9]+|[0-9]+,[0-9]+)<', post, 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('<div class="resultdivbottonlength">(.+?)<', post)[0]
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
dsize = 0
pass
info = ' | '.join(info)
item = {'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'quality': quality,
'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize, 'package': package}
if self.search_series:
item.update({'last_season': last_season})
self.sources.append(item)
except:
source_utils.scraper_error('IDOPE')
pass
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 get_sources(self, link):
try:
url = '%s%s' % (self.base_link, link)
result = client.request(url, timeout='5')
if result is None:
return
if 'magnet' not in result:
return
url = 'magnet:%s' % (re.findall('a href="magnet:(.+?)"', result,
re.DOTALL)[0])
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(self.title, name)
if source_utils.remove_lang(name, self.episode_title):
return
if not source_utils.check_title(self.title, self.aliases, name,
self.hdlr, self.year):
return
# filter for episode multi packs (ex. S01E01-E17 is also returned in query)
if self.episode_title:
if not source_utils.filter_single_episodes(self.hdlr, name):
return
try:
seeders = int(
re.findall('<dt>SWARM</dt><dd>.*?>([0-9]+)</b>', result,
re.DOTALL)[0].replace(',', ''))
if self.min_seeders > seeders:
return
except:
seeders = 0
pass
quality, info = source_utils.get_release_quality(name, url)
try:
size = re.findall('<dt>SIZE</dt><dd>(.*? [a-zA-Z]{2})', result,
re.DOTALL)[0]
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
dsize = 0
pass
info = ' | '.join(info)
self.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('TORLOCK')
pass
