def _get_sources(self, 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)
if link == []:
continue
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
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):
continue
if self.hdlr not in url:
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)) / div
size = '%.2f GB' % size
info.insert(0, size)
except:
pass
info = ' | '.join(info)
self.sources.append({
'source': 'torrent',
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True
})
except:
source_utils.scraper_error('BTSCENE')
pass
def get_sources(self, link):
try:
url = '%s%s' % (self.base_link, link)
result = client.request(url)
if result is None:
return
info_hash = re.findall('<kbd>(.+?)<', result, re.DOTALL)[0]
url = '%s%s' % ('magnet:?xt=urn:btih:', info_hash)
name = re.findall('<h3 class="card-title">(.+?)<', result,
re.DOTALL)[0]
name = urllib.unquote_plus(name).replace(' ', '.')
url = '%s%s%s' % (url, '&dn=', str(name))
if source_utils.remove_lang(name):
return
if url in str(self.sources):
return
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
size = re.findall(
'<div class="col-3">File size:</div><div class="col">(.+?)<',
result, re.DOTALL)[0]
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))',
size)[0]
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
isize = '0'
dsize = 0
pass
info = ' | '.join(info)
self.sources.append({
'source': 'torrent',
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True,
'size': dsize
})
except:
source_utils.scraper_error('YOURBITTORRENT')
pass
def _get_items(self, url):
try:
headers = {'User-Agent': client.agent()}
r = client.request(url, headers=headers)
if '<tbody' not in r:
return self.items
posts = client.parseDOM(r, 'tbody')[0]
posts = client.parseDOM(posts, 'tr')
for post in posts:
data = client.parseDOM(post, 'a', ret='href')[1]
link = urljoin(self.base_link, data)
try:
seeders = int(
client.parseDOM(post,
'td',
attrs={'class': 'coll-2 seeds'
})[0].replace(',', ''))
if self.min_seeders > seeders:
continue
except:
seeders = 0
pass
name = client.parseDOM(post, 'a')[1]
name = unquote_plus(name)
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
# 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:
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:
isize = '0'
dsize = 0
pass
self.items.append((name, link, isize, dsize, seeders))
return self.items
except:
source_utils.scraper_error('1337X')
return self.items
def _get_items(self, url):
try:
headers = {'User-Agent': client.agent()}
r = self.scraper.get(url, headers=headers).content
if not r:
return
posts = client.parseDOM(r, 'table', attrs={'class': 'table2'})[0]
posts = client.parseDOM(posts, 'tr')
for post in posts:
data = client.parseDOM(post, 'a', ret='href')[1]
if '/search/' in data:
continue
try:
data = data.encode('ascii', 'ignore')
except:
pass
data = re.sub('\s', '', data).strip()
link = urljoin(self.base_link, data)
name = client.parseDOM(post, 'a')[1]
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(self.title, name, self.hdlr,
self.year)
if not match:
continue
try:
seeders = int(
client.parseDOM(post, 'td',
attrs={'class':
'tdseed'})[0].replace(',', ''))
if self.min_seeders > seeders:
continue
except:
seeders = 0
pass
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:
isize = '0'
dsize = 0
pass
self.items.append((name, link, isize, dsize, seeders))
return self.items
except:
source_utils.scraper_error('LIMETORRENTS')
return self.items
def get_sources(self, url):
try:
r = client.request(url)
if r == str([]) or r == '' or r is None:
return
r = json.loads(r)
results = r['results']
for item in results:
try:
url = urllib.unquote_plus(item['magnet']).replace(' ', '.')
url = re.sub(r'(&tr=.+)&dn=', '&dn=', url) # some links on solidtorrents &tr= before &dn=
hash = item['infohash']
name = item['title']
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 source_utils.remove_lang(name):
continue
match = source_utils.check_title(self.title, name, self.hdlr, self.year)
if not match:
continue
if url in str(self.sources):
continue
try:
seeders = int(item['swarm']['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(item["size"], to='GB')
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('SOLIDTORRENTS')
pass
except:
source_utils.scraper_error('SOLIDTORRENTS')
pass
def _get_items(self, url):
try:
headers = {'User-Agent': client.agent()}
r = client.request(url, headers=headers)
posts = client.parseDOM(r, 'table', attrs={'class': 'table2'})[0]
posts = client.parseDOM(posts, 'tr')
for post in posts:
data = client.parseDOM(post, 'a', ret='href')[1]
if '/search/' in data:
continue
# Remove non-ASCII characters...freakin limetorrents
try:
data = data.encode('ascii', 'ignore')
except:
pass
# some broken links with withespace
data = re.sub('\s', '', data).strip()
link = urlparse.urljoin(self.base_link, data)
name = client.parseDOM(post, 'a')[1]
name = urllib.unquote_plus(name).replace(' ', '.')
if source_utils.remove_lang(name):
continue
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):
continue
if self.hdlr not in name:
continue
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:
size = '0'
pass
self.items.append((name, link, size))
return self.items
except:
source_utils.scraper_error('LIMETORRENTS')
return self.items
def get_sources(self, link):
try:
url = re.compile('href="(.+?)"').findall(link)[0]
url = '%s%s' % (self.base_link, url)
result = client.request(url)
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('&xl=')[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(r'<b>Seeds: </b>.*?>([0-9]+|[0-9]+,[0-9]+)</font>', 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(r'<b>Total Size:</b></td><td>(.*?)</td>', result, re.DOTALL)[0].strip()
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('ETTV')
pass
def _get_sources(self, url):
try:
r = client.request(url)
div = client.parseDOM(r, 'div', attrs={'id': 'div2child'})
for row in div:
row = client.parseDOM(r, 'div', attrs={'class': 'resultdivbotton'})
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 = 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()
url = 'magnet:?xt=urn:btih:%s&dn=%s' % (hash, name)
if url in str(self.sources):
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
if source_utils.remove_lang(name):
continue
match = source_utils.check_title(self.title, name, self.hdlr, self.year)
if not match:
continue
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, 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:
ref = client.parseDOM(post, 'a', ret='href')
url = [i for i in ref if 'magnet:' in i][0]
name = client.parseDOM(post, 'a', ret='title')[0]
name = unquote_plus(name)
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
# 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(
"<td.*?<font color='green'><b>([0-9]+|[0-9]+,[0-9]+)</b>",
post)[0].replace(',', ''))
if self.min_seeders > seeders:
continue
except:
seeders = 0
pass
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:
isize = '0'
dsize = 0
pass
items.append((name, url, isize, dsize, seeders))
return items
except:
source_utils.scraper_error('GLODLS')
return items
def _get_items(self, r):
try:
try:
seeders = int(
re.search(r'<seeders>([\d]+)</seeders>',
r).groups()[0].replace(',', ''))
if seeders < self.min_seeders:
return
except:
seeders = 0
pass
hash = re.search(r'<info_hash>([a-zA-Z0-9]+)</info_hash>',
r).groups()[0]
name = re.search(r'<title>(.+?)</title>', r).groups()[0]
name = urllib.unquote_plus(name)
name = re.sub('[^A-Za-z0-9]+', '.', name).lstrip('.')
if source_utils.remove_lang(name):
return
match = source_utils.check_title(self.title, name, self.hdlr,
self.year)
if not match:
return
url = 'magnet:?xt=urn:btih:%s&dn=%s' % (hash, name)
quality, info = source_utils.get_release_quality(name, url)
try:
size = re.search(r'<size>([\d]+)</size>', r).groups()[0]
dsize, isize = source_utils.convert_size(float(size), to='GB')
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('TORRENTDOWNLOADS')
pass
def get_sources(self, url):
# log_utils.log('url = %s' % url, __name__, log_utils.LOGDEBUG)
try:
headers = {'User-Agent': client.agent()}
r = client.request(url, headers=headers)
if not r:
return
posts = client.parseDOM(r, 'tr', attrs={'id': 'torrent_latest_torrents'})
for post in posts:
ref = client.parseDOM(post, 'a', attrs={'title': 'Torrent magnet link'}, ret='href')[0]
link = ref.split('url=')[1]
url = unquote_plus(link).replace('&', '&').replace(' ', '.')
url = url.split('&tr')[0]
hash = re.compile('btih:(.*?)&').findall(url)[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
# 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('<td class="green center">([0-9]+|[0-9]+,[0-9]+)</td>', 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('((?:\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)
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('KICKASS2')
pass
def get_sources(self, url):
try:
r = client.request(url)
if not r:
return
posts = client.parseDOM(r, 'tr')
for post in posts:
link = re.findall('a title="Download Torrent Magnet" href="(magnet:.+?)"', post, re.DOTALL)
if not link:
continue
for url in link:
url = unquote_plus(url).split('&tr')[0].replace('&', '&').replace(' ', '.')
url = source_utils.strip_non_ascii_and_unprintable(url)
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):
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(client.parseDOM(post, 'td', attrs={'class': 'seeds is-hidden-sm-mobile'})[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+|\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)
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('BTSCENE')
pass
def _get_items(self, url):
try:
headers = {'User-Agent': client.agent()}
r = client.request(url, headers=headers)
posts = client.parseDOM(r,
'tr',
attrs={'id': 'torrent_latest_torrents'})
for post in posts:
ref = client.parseDOM(post,
'a',
attrs={'title': 'Torrent magnet link'},
ret='href')[0]
link = urllib.unquote(ref).decode('utf8').replace(
'https://mylink.me.uk/?url=',
'').replace('https://mylink.cx/?url=', '')
name = urllib.unquote_plus(
re.search('dn=([^&]+)', link).groups()[0])
name = re.sub('[^A-Za-z0-9]+', '.', name).lstrip('.')
if source_utils.remove_lang(name):
continue
match = source_utils.check_title(self.title, name, self.hdlr,
self.year)
if not match:
continue
try:
seeders = int(
re.findall(
'<td class="green center">([0-9]+|[0-9]+,[0-9]+)</td>',
post, re.DOTALL)[0].replace(',', ''))
if self.min_seeders > seeders:
continue
except:
seeders = 0
pass
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:
isize = '0'
dsize = 0
pass
self.items.append((name, link, isize, dsize, seeders))
return self.items
except:
source_utils.scraper_error('KICKASS2')
return self.items
def _get_items(self, url):
try:
headers = {'User-Agent': client.agent()}
r = client.request(url, headers=headers)
if '<tbody' not in r:
return self.items
posts = client.parseDOM(r, 'tbody')[0]
posts = client.parseDOM(posts, 'tr')
for post in posts:
data = client.parseDOM(post, 'a', ret='href')[1]
link = urlparse.urljoin(self.base_link, data)
try:
seeders = int(
client.parseDOM(post,
'td',
attrs={'class': 'coll-2 seeds'
})[0].replace(',', ''))
if self.min_seeders > seeders:
continue
except:
seeders = 0
pass
name = client.parseDOM(post, 'a')[1]
name = urllib.unquote_plus(name)
name = re.sub('[^A-Za-z0-9]+', '.', name).lstrip('.')
if source_utils.remove_lang(name):
continue
match = source_utils.check_title(self.title, name, self.hdlr,
self.year)
if not match:
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:
isize = '0'
dsize = 0
pass
self.items.append((name, link, isize, dsize, seeders))
return self.items
except:
source_utils.scraper_error('1337X')
return self.items
def _get_items(self, url):
try:
headers = {'User-Agent': client.agent()}
r = client.request(url, headers=headers)
posts = client.parseDOM(r,
'tr',
attrs={'id': 'torrent_latest_torrents'})
for post in posts:
ref = client.parseDOM(post,
'a',
attrs={'title': 'Torrent magnet link'},
ret='href')[0]
link = urllib.unquote(ref).decode('utf8').replace(
'https://mylink.me.uk/?url=',
'').replace('https://mylink.cx/?url=', '')
name = urllib.unquote_plus(
re.search('dn=([^&]+)', link).groups()[0])
name = name.replace(' ', '.')
if source_utils.remove_lang(name):
continue
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):
continue
if self.hdlr not in name:
continue
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:
size = '0'
pass
self.items.append((name, link, size))
return self.items
except:
source_utils.scraper_error('KICKASS2')
return self.items
def get_sources(self, link):
try:
url = re.compile('href="(.+?)"').findall(link)[0]
url = '%s%s' % (self.base_link, url)
result = client.request(url)
if 'magnet' not in result:
return
url = 'magnet:%s' % (re.findall('a href="magnet:(.+?)"', result, re.DOTALL)[0])
url = urllib.unquote(url).decode('utf8').replace('&', '&')
url = url.split('&xl=')[0]
if url in str(self.sources):
return
size_list = client.parseDOM(result, "td", attrs={"class": "table_col2"})
name = url.split('&dn=')[1]
name = urllib.unquote_plus(urllib.unquote_plus(name)).replace(' ', '.')
if source_utils.remove_lang(name):
return
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)
for match in size_list:
try:
size = re.findall('((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GiB|MiB|GB|MB))', match)[0]
div = 1 if size.endswith('GB') else 1024
size = float(re.sub('[^0-9|/.|/,]', '', size.replace(',', '.'))) / div
size = '%.2f GB' % size
info.insert(0, size)
if size:
break
except:
size = '0'
pass
info = ' | '.join(info)
self.sources.append({'source': 'torrent', 'quality': quality, 'language': 'en', 'url': url,
'info': info, 'direct': False, 'debridonly': True})
except:
source_utils.scraper_error('ETTV')
pass
def _get_items(self, r):
try:
size = re.search(r'<size>([\d]+)</size>', r).groups()[0]
seeders = re.search(r'<seeders>([\d]+)</seeders>', r).groups()[0]
_hash = re.search(r'<info_hash>([a-zA-Z0-9]+)</info_hash>',
r).groups()[0]
name = re.search(r'<title>(.+?)</title>', r).groups()[0]
name = urllib.unquote_plus(name).replace(' ', '.')
if source_utils.remove_lang(name):
return
url = 'magnet:?xt=urn:btih:%s&dn=%s' % (_hash.upper(),
urllib.quote_plus(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, name)
try:
div = 1000**3
dsize = float(size) / div
isize = '%.2f GB' % dsize
info.insert(0, isize)
except:
pass
info = ' | '.join(info)
if seeders > self.min_seeders:
self._sources.append({
'source': 'torrent',
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True,
'size': dsize
})
except:
source_utils.scraper_error('TORRENTDOWNLOADS')
pass
def get_sources(self, link):
try:
url = 'magnet:%s' % (re.findall('a href="magnet:(.+?)"', link, re.DOTALL)[0])
url = unquote_plus(url).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 source_utils.remove_lang(name):
return
match = source_utils.check_title(self.title, name, self.hdlr, self.year)
if not match:
return
if url in str(self.sources):
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_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:
ref = client.parseDOM(post, 'a', ret='href')
url = [i for i in ref if 'magnet:' in i][0]
name = client.parseDOM(post, 'a', ret='title')[0]
name = urllib.unquote_plus(name)
name = re.sub('[^A-Za-z0-9]+', '.', name).lstrip('.')
if source_utils.remove_lang(name):
continue
match = source_utils.check_title(self.title, name, self.hdlr,
self.year)
if not match:
continue
try:
seeders = int(
re.findall(
"<td.*?<font color='green'><b>([0-9]+|[0-9]+,[0-9]+)</b>",
post)[0].replace(',', ''))
if self.min_seeders > seeders:
continue
except:
seeders = 0
pass
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:
isize = '0'
dsize = 0
pass
items.append((name, url, isize, dsize, seeders))
return items
except:
source_utils.scraper_error('GLODLS')
return items
def sources(self, url, hostDict, hostprDict):
self._sources = []
try:
self.scraper = cfscrape.create_scraper()
if url is None:
return self._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%02d' % (int(data['season'])) 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)
r = self.scraper.get(url).content
posts = client.parseDOM(r, 'figure')
items = []
for post in posts:
try:
url = client.parseDOM(post, 'a', ret='href')[0]
name = client.parseDOM(post, 'img', ret='title')[0].replace(' ', '.')
if source_utils.remove_lang(name):
continue
match = source_utils.check_title(title, name, hdlr, data['year'])
if not match:
continue
items.append((url, name))
except:
source_utils.scraper_error('MKVHUB')
pass
threads = []
for i in items:
threads.append(workers.Thread(self._get_sources, i[0], i[1], hostDict, hostprDict))
[i.start() for i in threads]
[i.join() for i in threads]
return self._sources
except:
source_utils.scraper_error('MKVHUB')
return self._sources
def _get_sources(self, 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)
if link == []:
continue
for url in link:
try:
seeders = int(client.parseDOM(post, 'td', attrs={'class': 'seeds is-hidden-sm-mobile'})[0].replace(',', ''))
if self.min_seeders > seeders:
continue
except:
seeders = 0
pass
url = urllib.unquote_plus(url).replace('&', '&').replace(' ', '.')
url = url.split('&tr')[0]
hash = re.compile('btih:(.*?)&').findall(url)[0]
name = url.split('&dn=')[1]
name = re.sub('[^A-Za-z0-9]+', '.', name).lstrip('.')
if source_utils.remove_lang(name):
continue
match = source_utils.check_title(self.title, name, self.hdlr, self.year)
if not match:
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]
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('BTSCENE')
pass
def _get_items(self, url):
try:
headers = {'User-Agent': client.agent()}
r = client.request(url, headers=headers)
if '<tbody' not in r:
return self.items
posts = client.parseDOM(r, 'tbody')[0]
posts = client.parseDOM(posts, 'tr')
for post in posts:
data = client.parseDOM(post, 'a', ret='href')[1]
link = urlparse.urljoin(self.base_link, data)
name = client.parseDOM(post, 'a')[1]
name = urllib.unquote_plus(name).replace(' ', '.')
if source_utils.remove_lang(name):
return
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):
continue
if self.hdlr not in name:
continue
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:
size = '0'
pass
self.items.append((name, link, size))
return self.items
except:
source_utils.scraper_error('1337X')
return self.items
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:
ref = client.parseDOM(post, 'a', ret='href')
url = [i for i in ref if 'magnet:' in i][0]
name = client.parseDOM(post, 'a', ret='title')[0]
name = urllib.unquote_plus(name).replace(' ', '.')
if source_utils.remove_lang(name):
continue
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):
continue
if self.hdlr not in name:
continue
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:
size = '0'
pass
items.append((name, url, size))
return items
except:
source_utils.scraper_error('GLODLS')
return items
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:
size = link[1]
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:
size = '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
})
except:
source_utils.scraper_error('DDLSPOT')
pass
return sources
except:
source_utils.scraper_error('DDLSPOT')
return
def get_sources(self, item):
try:
name = item[0].replace(' ', '.')
url = item[1]
r = self.scraper.get(url, headers=self.headers).content
r = re.sub(r'\n', '', r)
r = re.sub(r'\t', '', r)
list = client.parseDOM(r, 'div', attrs={'id': 'content'})
# log_utils.log('list = %s' % list, log_utils.LOGDEBUG)
if 'tvshowtitle' in self.data:
regex = '(<p><strong>(.*?)</strong><br />([A-Z]*)\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 />.*<strong>Size:</strong>\s*((\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))?<br />(.*\s)*)'
# regex = '(<strong>Release Name:</strong>\s*(.*?)<br />.*<strong>Size:</strong>\s*((\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))?<br />.*<strong>Audio:</strong>\s*[A-Z]*[a-z]*\s*\|\s*([A-z]*[0-9]*)(.*\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(self.hdlr)[0].replace(self.year, '').replace(
'(', '').replace(')', '').replace('&', 'and')
if cleantitle.get(t) != cleantitle.get(self.title):
continue
if self.hdlr not in name:
continue
if source_utils.remove_lang(name):
continue
if 'tvshowtitle' in self.data:
size = str(match.group(5))
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(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)
if 'tvshowtitle' in self.data:
info.append(str(match.group(4)))
try:
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
dsize = 0
pass
info = ' | '.join(info)
self.sources.append({
'source': host,
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True,
'size': dsize
})
except:
source_utils.scraper_error('TVDOWNLOADS')
pass
return self.sources
except:
source_utils.scraper_error('TVDOWNLOADS')
pass
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']
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 % urllib.quote_plus(query)
url = urlparse.urljoin(self.base_link, url)
urls.append(url)
url2 = self.search_link % urllib.quote_plus(query2)
url2 = urlparse.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 = urllib.unquote_plus(link[0]).replace(
'&', '&').replace(' ', '.')
url = url.split('&tr')[0]
url = url.encode('ascii', errors='ignore').decode(
'ascii', errors='ignore')
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):
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['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_plus(query)
url = 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': 'tgxtable'})
for post in posts:
links = zip(
re.findall('a href="(magnet:.+?)"', post, re.DOTALL),
re.findall(
r"<span class='badge badge-secondary' style='border-radius:4px;'>(.*?)</span>",
post, re.DOTALL),
re.findall(
r"<span title='Seeders/Leechers'>\[<font color='green'><b>(.*?)<",
post, re.DOTALL))
for link in links:
url = unquote_plus(link[0]).split('&tr')[0].replace(
' ', '.')
hash = re.compile('btih:(.*?)&').findall(url)[0]
name = url.split('&dn=')[1]
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(link[2])
if self.min_seeders > seeders:
continue
except:
seeders = 0
pass
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)
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('TORRENTGALAXY')
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])
try:
url = unquote_plus(url).decode('utf8').replace('&', '&')
except:
url = unquote_plus(url).replace('&', '&')
url = url.split('&tr=')[0].replace(' ', '.')
if url in str(self.sources):
return
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 source_utils.remove_lang(name):
return
match = source_utils.check_title(self.title, name, self.hdlr,
self.year)
if not match:
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
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 '<kbd>' not in result:
return
hash = re.findall('<kbd>(.+?)<', result, re.DOTALL)[0]
url = '%s%s' % ('magnet:?xt=urn:btih:', hash)
name = re.findall('<h3 class="card-title">(.+?)<', result,
re.DOTALL)[0].replace('Original Name: ', '')
name = unquote_plus(name)
name = re.sub('[^A-Za-z0-9]+', '.', name).lstrip('.')
if source_utils.remove_lang(name):
return
match = source_utils.check_title(self.title, name, self.hdlr,
self.year)
if not match:
return
url = '%s%s%s' % (url, '&dn=', str(name))
if url in str(self.sources):
return
size = re.findall(
'<div class="col-3">File size:</div><div class="col">(.+?)<',
result, re.DOTALL)[0]
quality, info = source_utils.get_release_quality(name, url)
try:
seeders = int(
re.findall(
'<div class="col-3">Seeders:</div><div class="col"><span style="color:green">([0-9]+|[0-9]+,[0-9]+)<',
result, re.DOTALL)[0].replace(',', ''))
if self.min_seeders > seeders:
return
except:
seeders = 0
pass
try:
size = re.findall(
'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))',
size)[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('YOURBITTORRENT')
pass
def get_sources(self, url):
try:
scraper = cfscrape.create_scraper()
r = scraper.get(url).content
if not r:
return
posts = client.parseDOM(r, 'div', attrs={'class': 'media'})
for post in posts:
# file_name = client.parseDOM(post, 'span', attrs={'class': 'file-name'}) # file_name and &dn= differ 25% of the time. May add check
try:
seeders = int(
re.findall(
r'Seeders\s+:\s+<strong class="text-success">([0-9]+|[0-9]+,[0-9]+)</strong>',
post, re.DOTALL)[0].replace(',', ''))
if self.min_seeders > seeders:
return
except:
seeders = 0
pass
link = re.findall('<a href="(magnet:.+?)"', post, re.DOTALL)
for url in link:
url = unquote_plus(url).split('&tr')[0].replace(
'&', '&').replace(' ', '.')
url = source_utils.strip_non_ascii_and_unprintable(url)
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):
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
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))',
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('BTDB')
pass