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, 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 sources(self, url, hostDict, hostprDict):
sources = []
try:
if url is None:
return sources
if debrid.status() is False:
return sources
data = parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '')
for i in data])
title = data['tvshowtitle'] if 'tvshowtitle' in data else data[
'title']
title = title.replace('&', 'and').replace('Special Victims Unit',
'SVU')
aliases = data['aliases']
episode_title = data['title'] if 'tvshowtitle' in data else None
hdlr = 'S%02dE%02d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else data['year']
query = '%s %s' % (title, hdlr)
query = re.sub('[^A-Za-z0-9\s\.-]+', '', query)
url = self.search_link % quote_plus(query)
url = urljoin(self.base_link, url)
# log_utils.log('url = %s' % url, log_utils.LOGDEBUG)
r = client.request(url)
if '<tbody' not in r:
return sources
posts = client.parseDOM(r, 'tbody')[0]
posts = client.parseDOM(posts, 'tr')
except:
source_utils.scraper_error('SKYTORRENTS')
return sources
for post in posts:
try:
post = re.sub(r'\n', '', post)
post = re.sub(r'\t', '', post)
link = re.findall(
'href="(magnet:.+?)".+<td style="text-align: center;color:green;">([0-9]+|[0-9]+,[0-9]+)</td>',
post, re.DOTALL)
for url, seeders, in link:
url = unquote_plus(url).split('&tr')[0].replace(
'&', '&').replace(' ', '.')
url = source_utils.strip_non_ascii_and_unprintable(url)
if url in str(self.sources):
return
hash = re.compile('btih:(.*?)&').findall(url)[0]
name = url.split('&dn=')[1]
name = source_utils.clean_name(title, name)
if source_utils.remove_lang(name, episode_title):
continue
if not source_utils.check_title(title, aliases, name, hdlr,
data['year']):
continue
# filter for episode multi packs (ex. S01E01-E17 is also returned in query)
if episode_title:
if not source_utils.filter_single_episodes(hdlr, name):
continue
try:
seeders = int(seeders)
if self.min_seeders > seeders:
continue
except:
seeders = 0
pass
quality, info = source_utils.get_release_quality(name, url)
try:
size = re.findall(
'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GiB|MiB|GB|MB))',
post)[0]
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
dsize = 0
pass
info = ' | '.join(info)
sources.append({
'source': 'torrent',
'seeders': seeders,
'hash': hash,
'name': name,
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True,
'size': dsize
})
except:
source_utils.scraper_error('SKYTORRENTS')
return sources
return sources
def sources(self, url, hostDict, hostprDict):
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(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:
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
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 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 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