def get_sources_packs(self, link):
# log_utils.log('link = %s' % str(link), __name__, log_utils.LOGDEBUG)
try:
r = client.request(link, timeout='5')
if not r: return
r = re.sub(r'\n', '', r)
r = re.sub(r'\t', '', r)
posts = re.compile(r'<table\s*class\s*=\s*["\']table2["\']\s*cellspacing\s*=\s*["\']\d+["\']>(.*?)</table>', re.I).findall(r)
posts = client.parseDOM(posts, 'tr')
except:
source_utils.scraper_error('TORRENTDOWNLOAD')
return
for post in posts:
try:
if '<th' in post: continue
links = re.compile(r'<a\s*href\s*=\s*["\'](.+?)["\']>.*?<td class\s*=\s*["\']tdnormal["\']>((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))</td><td class\s*=\s*["\']tdseed["\']>([0-9]+|[0-9]+,[0-9]+)</td>', re.I).findall(post)
for items in links:
link = items[0].split("/")
hash = link[1].lower()
name = link[2].replace('+MB+', '')
name = unquote_plus(name).replace('&', '&')
name = source_utils.clean_name(name)
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'
name_info = source_utils.info_from_name(name, self.title, self.year, season=self.season_x, pack=package)
if source_utils.remove_lang(name_info): continue
url = 'magnet:?xt=urn:btih:%s&dn=%s' % (hash, name)
try:
seeders = int(items[2].replace(',', ''))
if self.min_seeders > seeders: continue
except: seeders = 0
quality, info = source_utils.get_release_quality(name_info, url)
try:
size = re.findall(r'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))', items[1])[0]
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except: dsize = 0
info = ' | '.join(info)
item = {'provider': 'torrentdownload', 'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'name_info': name_info, '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('TORRENTDOWNLOAD')
def get_pack_sources(self, items):
try:
link = client.request(items[2], timeout='5')
if link is None: return
hash = re.findall(r'Infohash.*?>(?!<)(.+?)</', link, re.DOTALL | re.I)[0]
url = 'magnet:?xt=urn:btih:%s&dn=%s' % (hash, items[0])
if url in str(self.sources): return
try:
seeders = int(re.findall(r'Swarm.*?>(?!<)([0-9]+)</', link, re.DOTALL | re.I)[0].replace(',', ''))
if self.min_seeders > seeders: return
except: seeders = 0
quality, info = source_utils.get_release_quality(items[1], url)
try:
size = re.findall(r'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))', link)[0]
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except: dsize = 0
info = ' | '.join(info)
item = {'provider': 'torrentfunk', 'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': items[0], 'name_info': items[1], 'quality': quality,
'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize, 'package': items[3]}
if self.search_series: item.update({'last_season': items[4]})
self.sources.append(item)
except:
source_utils.scraper_error('TORRENTFUNK')
def sources(self, data, hostDict):
sources = []
if not data: return sources
try:
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
year = data['year']
hdlr = 'S%02dE%02d' % (int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else year
query = re.sub(r'[^A-Za-z0-9\s\.-]+', '', '%s %s' % (title, hdlr))
url = '%s%s' % (self.base_link, self.search_link % quote_plus(query))
# log_utils.log('url = %s' % url, log_utils.LOGDEBUG)
r = client.request(url, timeout='5')
if not r: return sources
if any(value in str(r) for value in ['something went wrong', 'Connection timed out', '521: Web server is down', '503 Service Unavailable']):
return sources
table = client.parseDOM(r, 'tbody')
rows = client.parseDOM(table, 'tr')
except:
source_utils.scraper_error('BITCQ')
return sources
for row in rows:
try:
if 'magnet' not in row: continue
url = re.findall(r'href="(magnet:.+?)"', row, re.DOTALL)[0]
url = unquote_plus(url).replace('&', '&').replace(' ', '.').split('&tr')[0]
url = source_utils.strip_non_ascii_and_unprintable(url)
hash = re.search(r'btih:(.*?)&', url, re.I).group(1)
name = source_utils.clean_name(url.split('&dn=')[1])
if not source_utils.check_title(title, aliases, name, hdlr, year): continue
name_info = source_utils.info_from_name(name, title, year, hdlr, episode_title)
if source_utils.remove_lang(name_info): continue
if not episode_title: # filter for eps returned in movie query (rare but movie and show exists for Run in 2020)
ep_strings = [r'(?:\.|\-)s\d{2}e\d{2}(?:\.|\-|$)', r'(?:\.|\-)s\d{2}(?:\.|\-|$)', r'(?:\.|\-)season(?:\.|\-)\d{1,2}(?:\.|\-|$)']
if any(re.search(item, name.lower()) for item in ep_strings): continue
try:
seeders = int(re.search(r'<td>(\d+)<', row).group(1))
if self.min_seeders > seeders: continue
except: seeders = 0
quality, info = source_utils.get_release_quality(name_info, url)
try:
size = re.search(r'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))', row).group(0)
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except: dsize = 0
info = ' | '.join(info)
sources.append({'provider': 'bitcq', 'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'name_info': name_info, 'quality': quality,
'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize})
except:
source_utils.scraper_error('BITCQ')
return sources
return sources
def get_sources_packs(self, link):
# log_utils.log('link = %s' % str(link), __name__, log_utils.LOGDEBUG)
try:
r = client.request(link, timeout='5')
if not r: return
if any(value in r for value in ['something went wrong', 'Connection timed out', '521: Web server is down', '503 Service Unavailable']):
return sources
table = client.parseDOM(r, 'table', attrs={'id': 'table'})
table_body = client.parseDOM(table, 'tbody')
rows = client.parseDOM(table_body, 'tr')
except:
source_utils.scraper_error('TORRENTZ2')
return
for row in rows:
try:
if 'magnet:' not in row: continue
url = re.findall(r'href\s*=\s*["\'](magnet:[^"\']+)["\']', row, re.DOTALL | re.I)[0]
url = unquote_plus(url).replace('&', '&').replace(' ', '.').split('&tr')[0]
url = source_utils.strip_non_ascii_and_unprintable(url)
hash = re.compile(r'btih:(.*?)&', re.I).findall(url)[0]
name = url.split('&dn=')[1]
name = source_utils.clean_name(name)
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'
name_info = source_utils.info_from_name(name, self.title, self.year, season=self.season_x, pack=package)
if source_utils.remove_lang(name_info): continue
try:
# seeders = int(client.parseDOM(row, 'td', attrs={'data-title': 'Seeds'})[0])
seeders = int(client.parseDOM(row, 'td', attrs={'data-title': 'Last Updated'})[0]) #keep an eye on this, looks like they gaffed their col's (seeders and size)
if self.min_seeders > seeders: continue
except: seeders = 0
quality, info = source_utils.get_release_quality(name_info, url)
try:
size = re.findall(r'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))', row.replace(u'\xa0', u' ').replace(u' ', u' '))[0]
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except: dsize = 0
info = ' | '.join(info)
item = {'provider': 'torrentz2', 'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'name_info': name_info, '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('TORRENTZ2')
def get_sources_packs(self, link):
# log_utils.log('link = %s' % str(link), __name__, log_utils.LOGDEBUG)
try:
r = client.request(link, timeout='5')
if not r: return
if any(value in str(r) for value in ['something went wrong', 'Connection timed out', '521: Web server is down', '503 Service Unavailable']):
return
table = client.parseDOM(r, 'tbody')
rows = client.parseDOM(table, 'tr')
except:
source_utils.scraper_error('BITCQ')
return
for row in rows:
try:
if 'magnet' not in row: continue
url = re.findall(r'href="(magnet:.+?)"', row, re.DOTALL)[0]
url = unquote_plus(url).replace('&', '&').replace(' ', '.').split('&tr')[0]
url = source_utils.strip_non_ascii_and_unprintable(url)
hash = re.search(r'btih:(.*?)&', url, re.I).group(1)
name = source_utils.clean_name(url.split('&dn=')[1])
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'
name_info = source_utils.info_from_name(name, self.title, self.year, season=self.season_x, pack=package)
if source_utils.remove_lang(name_info): continue
try:
seeders = int(re.search(r'<td>(\d+)<', row).group(1))
if self.min_seeders > seeders: continue
except: seeders = 0
quality, info = source_utils.get_release_quality(name_info, url)
try:
size = re.search(r'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))', row).group(0)
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except: dsize = 0
info = ' | '.join(info)
item = {'provider': 'bitcq', 'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'name_info': name_info, '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('BITCQ')
def get_sources_packs(self, link):
# log_utils.log('link = %s' % str(link), __name__, log_utils.LOGDEBUG)
try:
headers = {'User-Agent': client.agent()}
r = py_tools.ensure_str(self.scraper.get(link, headers=headers).content, errors='replace')
if not r or '<table' not in r: return
table = client.parseDOM(r, 'table', attrs={'class': 'table2'})[0]
rows = client.parseDOM(table, 'tr')
if not rows: return
except:
source_utils.scraper_error('LIMETORRENTS')
return
for row in rows:
try:
data = client.parseDOM(row, 'a', ret='href')[0]
if '/search/' in data: continue
data = re.sub(r'\s', '', data).strip()
hash = re.compile(r'/torrent/(.+?).torrent', re.I).findall(data)[0]
name = re.findall(r'title\s*=\s*(.+?)$', data, re.DOTALL | re.I)[0]
name = source_utils.clean_name(name)
url = 'magnet:?xt=urn:btih:%s&dn=%s' % (hash, name)
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'
name_info = source_utils.info_from_name(name, self.title, self.year, season=self.season_x, pack=package)
if source_utils.remove_lang(name_info): continue
try:
seeders = int(client.parseDOM(row, 'td', attrs={'class': 'tdseed'})[0].replace(',', ''))
if self.min_seeders > seeders: continue
except: seeders = 0
quality, info = source_utils.get_release_quality(name_info, url)
try:
size = re.findall(r'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))', row)[0]
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except: dsize = 0
info = ' | '.join(info)
item = {'provider': 'limetorrents', 'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'name_info': name_info, '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('LIMETORRENTS')
def get_sources_packs(self, link):
# log_utils.log('link = %s' % str(link), __name__, log_utils.LOGDEBUG)
try:
r = py_tools.ensure_str(self.scraper.get(link).content, errors='replace')
if not r: return
posts = client.parseDOM(r, 'div', attrs={'class': 'tgxtable'})
if not posts: return
except:
source_utils.scraper_error('TORRENTGALAXY')
return
for post in posts:
try:
links = zip(
re.findall(r'href\s*=\s*["\'](magnet:[^"\']+)["\']', post, re.DOTALL | re.I),
re.findall(r'<span\s*class\s*=\s*["\']badge\s*badge-secondary["\']\s*style\s*=\s*["\']border-radius:4px;["\']>(.*?)</span>', post, re.DOTALL | re.I),
re.findall(r'<span\s*title\s*=\s*["\']Seeders/Leechers["\']>\[<font\s*color\s*=\s*["\']green["\']><b>(.*?)<', post, re.DOTALL | re.I))
for link in links:
url = unquote_plus(link[0]).split('&tr')[0].replace(' ', '.')
url = source_utils.strip_non_ascii_and_unprintable(url)
hash = re.compile(r'btih:(.*?)&', re.I).findall(url)[0]
name = url.split('&dn=')[1]
name = source_utils.clean_name(name)
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'
name_info = source_utils.info_from_name(name, self.title, self.year, season=self.season_x, pack=package)
if source_utils.remove_lang(name_info): continue
try:
seeders = int(link[2])
if self.min_seeders > seeders: continue
except: seeders = 0
quality, info = source_utils.get_release_quality(name_info, url)
try:
dsize, isize = source_utils._size(link[1])
info.insert(0, isize)
except: dsize = 0
info = ' | '.join(info)
item = {'provider': 'torrentgalaxy', 'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'name_info': name_info, '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('TORRENTGALAXY')
def sources(self, url, hostDict):
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['title'].replace('&', 'and')
aliases = data['aliases']
hdlr = data['year']
year = data['year']
imdb = data['imdb']
url = self.search_link % imdb
api_url = urljoin(self.base_link, url)
# log_utils.log('api_url = %s' % api_url, log_utils.LOGDEBUG)
rjson = client.request(api_url, timeout='5')
if not rjson: return sources
files = jsloads(rjson)
if files.get('status') == 'error' or files.get('data').get('movie_count') == 0:
return sources
title_long = files.get('data').get('movies')[0].get('title_long').replace(' ', '.')
torrents = files.get('data').get('movies')[0].get('torrents')
except:
source_utils.scraper_error('YTSMX')
return sources
for torrent in torrents:
try:
quality = torrent.get('quality')
type = torrent.get('type')
hash = torrent.get('hash')
name = '%s.[%s].[%s].[YTS.MX]' % (title_long, quality, type)
url = 'magnet:?xt=urn:btih:%s&dn=%s' % (hash, name)
if not source_utils.check_title(title, aliases, name, hdlr, year): continue
name_info = source_utils.info_from_name(name, title, year, hdlr)
if source_utils.remove_lang(name_info): continue
try:
seeders = torrent.get('seeds')
if self.min_seeders > seeders: continue
except: seeders = 0
quality, info = source_utils.get_release_quality(name_info, url)
try:
size = torrent.get('size')
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except: dsize = 0
info = ' | '.join(info)
sources.append({'provider': 'ytsmx', 'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'name_info': name_info,
'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize})
except:
source_utils.scraper_error('YTSMX')
return sources
def get_sources_packs(self, link):
# log_utils.log('link = %s' % str(link), __name__, log_utils.LOGDEBUG)
try:
r = client.request(link, timeout='5')
if not r: return
posts = client.parseDOM(r, 'div', attrs={'class': 'media'})
except:
source_utils.scraper_error('BTDB')
return
for post in posts:
try:
if 'magnet:' not in post: continue
url = re.findall(r'href\s*=\s*["\'](magnet:[^"\']+)["\']', post, re.DOTALL | re.I)[0]
url = unquote_plus(url).replace('&', '&').replace(' ', '.').split('&tr')[0]
url = source_utils.strip_non_ascii_and_unprintable(url)
if url in str(self.sources): return
hash = re.compile(r'btih:(.*?)&', re.I).findall(url)[0]
name = url.split('&dn=')[1]
name = source_utils.clean_name(name)
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'
name_info = source_utils.info_from_name(name, self.title, self.year, season=self.season_x, pack=package)
if source_utils.remove_lang(name_info): continue
try:
seeders = int(re.findall(r'Seeders.*?["\']>([0-9]+|[0-9]+,[0-9]+)</strong>', post, re.DOTALL | re.I)[0].replace(',', ''))
if self.min_seeders > seeders: return
except: seeders = 0
quality, info = source_utils.get_release_quality(name_info, url)
try:
size = re.findall(r'((?:\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
info = ' | '.join(info)
item = {'provider': 'btdb', 'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'name_info': name_info, '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('BTDB')
def get_items(self, url):
try:
headers = {'User-Agent': client.agent()}
r = client.request(url, headers=headers, timeout='10')
if not r or '<tbody' not in r: return
posts = client.parseDOM(r, 'tbody')[0]
posts = client.parseDOM(posts, 'tr')
except:
source_utils.scraper_error('1337X')
return
for post in posts:
try:
data = client.parseDOM(post, 'a', ret='href')[1]
link = urljoin(self.base_link, data)
name = client.parseDOM(post, 'a')[1]
name = source_utils.clean_name(unquote_plus(name))
if not source_utils.check_title(self.title, self.aliases, name,
self.hdlr, self.year):
continue
name_info = source_utils.info_from_name(
name, self.title, self.year, self.hdlr, self.episode_title)
if source_utils.remove_lang(name_info): continue
if not self.episode_title: #filter for eps returned in movie query (rare but movie and show exists for Run in 2020)
ep_strings = [
r'[.-]s\d{2}e\d{2}([.-]?)', r'[.-]s\d{2}([.-]?)',
r'[.-]season[.-]?\d{1,2}[.-]?'
]
if any(
re.search(item, name.lower())
for item in ep_strings):
continue
try:
seeders = int(
client.parseDOM(post,
'td',
attrs={'class': 'coll-2 seeds'
})[0].replace(',', ''))
if self.min_seeders > seeders: continue
except:
seeders = 0
try:
size = re.findall(
r'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))',
post)[0]
dsize, isize = source_utils._size(size)
except:
isize = '0'
dsize = 0
self.items.append(
(name, name_info, link, isize, dsize, seeders))
except:
source_utils.scraper_error('1337X')
def sources(self, url, hostDict):
sources = []
if not url: return sources
try:
if cloudflare_worker_url == '': return sources
results = getResults(url)
if not results: return sources
if control.setting('gdrive.title.chk') == 'true':
simpleQuery = get_simple(url)
results = filteredResults(results, simpleQuery)
except:
source_utils.scraper_error('GDRIVE')
return sources
for result in results:
try:
link = result["link"]
name = unquote(link.rsplit("/")[-1])
# name_info = source_utils.info_from_name(name, title, year, hdlr, episode_title) # needs a decent rewrite to get this
release_title = name.lower().replace('&',
'and').replace("'", "")
release_title = re.sub(r'[^a-z0-9]+', '.', release_title)
quality, info = source_utils.get_release_quality(
release_title, link)
try:
size = str(result["size_gb"]) + ' GB'
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
source_utils.scraper_error('GDRIVE')
dsize = 0
info = ' | '.join(info)
sources.append({
'provider': 'gdrive',
'source': 'Google Drive',
'quality': quality,
'name': name,
'language': 'en',
'info': info,
'url': link,
'direct': True,
'debridonly': False,
'size': dsize
})
except:
source_utils.scraper_error('GDRIVE')
return sources
def get_sources(self, url):
try:
r = client.request(url, timeout='5')
if not r: return
r = re.sub(r'\n', '', r)
r = re.sub(r'\t', '', r)
posts = re.compile(r'<table\s*class\s*=\s*["\']table2["\']\s*cellspacing\s*=\s*["\']\d+["\']>(.*?)</table>', re.I).findall(r)
posts = client.parseDOM(posts, 'tr')
except:
source_utils.scraper_error('TORRENTDOWNLOAD')
return
for post in posts:
try:
if '<th' in post: continue
links = re.compile(r'<a\s*href\s*=\s*["\'](.+?)["\']>.*?<td class\s*=\s*["\']tdnormal["\']>((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))</td><td class\s*=\s*["\']tdseed["\']>([0-9]+|[0-9]+,[0-9]+)</td>', re.I).findall(post)
for items in links:
link = items[0].split("/")
hash = link[1].lower()
name = link[2].replace('+MB+', '')
name = unquote_plus(name).replace('&', '&')
name = source_utils.clean_name(name)
if not source_utils.check_title(self.title, self.aliases, name, self.hdlr, self.year): continue
name_info = source_utils.info_from_name(name, self.title, self.year, self.hdlr, self.episode_title)
if source_utils.remove_lang(name_info): continue
url = 'magnet:?xt=urn:btih:%s&dn=%s' % (hash, name)
if not self.episode_title: #filter for eps returned in movie query (rare but movie and show exists for Run in 2020)
ep_strings = [r'[.-]s\d{2}e\d{2}([.-]?)', r'[.-]s\d{2}([.-]?)', r'[.-]season[.-]?\d{1,2}[.-]?']
if any(re.search(item, name.lower()) for item in ep_strings): continue
try:
seeders = int(items[2].replace(',', ''))
if self.min_seeders > seeders: continue
except: seeders = 0
quality, info = source_utils.get_release_quality(name_info, url)
try:
size = re.findall(r'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))', items[1])[0]
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except: dsize = 0
info = ' | '.join(info)
self.sources.append({'provider': 'torrentdownload', 'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'name_info': name_info,
'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize})
except:
source_utils.scraper_error('TORRENTDOWNLOAD')
def get_sources(self, link):
# log_utils.log('link = %s' % link, log_utils.LOGDEBUG)
try:
headers = {'User-Agent': client.agent()}
r = py_tools.ensure_str(self.scraper.get(link, headers=headers).content, errors='replace')
if not r or '<table' not in r: return
table = client.parseDOM(r, 'table', attrs={'class': 'table2'})[0]
rows = client.parseDOM(table, 'tr')
if not rows: return
except:
source_utils.scraper_error('LIMETORRENTS')
return
for row in rows:
try:
data = client.parseDOM(row, 'a', ret='href')[0]
if '/search/' in data: continue
data = re.sub(r'\s', '', data).strip()
hash = re.compile(r'/torrent/(.+?).torrent', re.I).findall(data)[0]
name = re.findall(r'title\s*=\s*(.+?)$', data, re.DOTALL | re.I)[0]
name = source_utils.clean_name(name)
if not source_utils.check_title(self.title, self.aliases, name, self.hdlr, self.year): continue
name_info = source_utils.info_from_name(name, self.title, self.year, self.hdlr, self.episode_title)
if source_utils.remove_lang(name_info): continue
url = 'magnet:?xt=urn:btih:%s&dn=%s' % (hash, name)
if not self.episode_title: #filter for eps returned in movie query (rare but movie and show exists for Run in 2020)
ep_strings = [r'[.-]s\d{2}e\d{2}([.-]?)', r'[.-]s\d{2}([.-]?)', r'[.-]season[.-]?\d{1,2}[.-]?']
if any(re.search(item, name.lower()) for item in ep_strings): continue
try:
seeders = int(client.parseDOM(row, 'td', attrs={'class': 'tdseed'})[0].replace(',', ''))
if self.min_seeders > seeders: continue
except: seeders = 0
quality, info = source_utils.get_release_quality(name_info, url)
try:
size = re.findall(r'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))', row)[0]
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except: dsize = 0
info = ' | '.join(info)
self.sources.append({'provider': 'limetorrents', 'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'name_info': name_info,
'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize})
except:
source_utils.scraper_error('LIMETORRENTS')
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(name)
if not source_utils.check_title(self.title, self.aliases, name, self.hdlr, self.year): return
name_info = source_utils.info_from_name(name, self.title, self.year, self.hdlr, self.episode_title)
if source_utils.remove_lang(name_info): return
if not self.episode_title: #filter for eps returned in movie query (rare but movie and show exists for Run in 2020)
ep_strings = [r'[.-]s\d{2}e\d{2}([.-]?)', r'[.-]s\d{2}([.-]?)', r'[.-]season[.-]?\d{1,2}[.-]?']
if any(re.search(item, name.lower()) for item in ep_strings): 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(r'Infohash.*?>(?!<)(.+?)</', link, re.DOTALL | re.I)[0]
url = 'magnet:?xt=urn:btih:%s&dn=%s' % (hash, name)
if url in str(self.sources): return
try:
seeders = int(re.findall(r'Swarm.*?>(?!<)([0-9]+)</', link, re.DOTALL | re.I)[0].replace(',', ''))
if self.min_seeders > seeders: return
except: seeders = 0
quality, info = source_utils.get_release_quality(name_info, url)
try:
size = re.findall(r'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))', link)[0]
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except: dsize = 0
info = ' | '.join(info)
self.sources.append({'provider': 'torrentfunk', 'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'name_info': name_info,
'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize})
except:
source_utils.scraper_error('TORRENTFUNK')
def get_sources(self, url):
try:
r = client.request(url, timeout='5')
if not r: return
posts = client.parseDOM(r, 'div', attrs={'class': 'media'})
except:
source_utils.scraper_error('BTDB')
return
for post in posts:
try:
if 'magnet:' not in post: continue
url = re.findall(r'href\s*=\s*["\'](magnet:[^"\']+)["\']', post, re.DOTALL | re.I)[0]
url = unquote_plus(url).replace('&', '&').replace(' ', '.').split('&tr')[0]
url = source_utils.strip_non_ascii_and_unprintable(url)
hash = re.compile(r'btih:(.*?)&', re.I).findall(url)[0]
name = url.split('&dn=')[1]
name = source_utils.clean_name(name)
if not source_utils.check_title(self.title, self.aliases, name, self.hdlr, self.year): continue
name_info = source_utils.info_from_name(name, self.title, self.year, self.hdlr, self.episode_title)
if source_utils.remove_lang(name_info): continue
if not self.episode_title: #filter for eps returned in movie query (rare but movie and show exists for Run in 2020)
ep_strings = [r'[.-]s\d{2}e\d{2}([.-]?)', r'[.-]s\d{2}([.-]?)', r'[.-]season[.-]?\d{1,2}[.-]?']
if any(re.search(item, name.lower()) for item in ep_strings): continue
try:
seeders = int(re.findall(r'Seeders.*?["\']>([0-9]+|[0-9]+,[0-9]+)</strong>', post, re.DOTALL | re.I)[0].replace(',', ''))
if self.min_seeders > seeders: return
except: seeders = 0
quality, info = source_utils.get_release_quality(name_info, url)
try:
size = re.findall(r'((?:\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
info = ' | '.join(info)
self.sources.append({'provider': 'btdb', 'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'name_info': name_info,
'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize})
except:
source_utils.scraper_error('BTDB')
def get_sources(self, link):
try:
url = re.compile(r'href\s*=\s*["\'](.+?)["\']', re.I).findall(link)[0]
url = urljoin(self.base_link, url)
result = client.request(url, timeout='10')
if not result or 'magnet' not in result: return
url = re.findall(r'href\s*=\s*["\'](magnet:[^"\']+)["\']', result, re.DOTALL | re.I)[0]
url = unquote_plus(url).replace('&', '&').replace(' ', '.').split('&xl=')[0]
url = source_utils.strip_non_ascii_and_unprintable(url)
if url in str(self.sources): return
hash = re.compile(r'btih:(.*?)&', re.I).findall(url)[0]
name = url.split('&dn=')[1]
name = source_utils.clean_name(name)
if not source_utils.check_title(self.title, self.aliases, name, self.hdlr, self.year): return
name_info = source_utils.info_from_name(name, self.title, self.year, self.hdlr, self.episode_title)
if source_utils.remove_lang(name_info): return
if not self.episode_title: #filter for eps returned in movie query (rare but movie and show exists for Run in 2020)
ep_strings = [r'[.-]s\d{2}e\d{2}([.-]?)', r'[.-]s\d{2}([.-]?)', r'[.-]season[.-]?\d{1,2}[.-]?']
if any(re.search(item, name.lower()) for item in ep_strings): return
try:
seeders = int(re.findall(r'>Seeds:.*?["\']>([0-9]+|[0-9]+,[0-9]+)</', result, re.DOTALL | re.I)[0].replace(',', ''))
if self.min_seeders > seeders: return
except: seeders = 0
quality, info = source_utils.get_release_quality(name_info, url)
try:
size = re.findall(r'>Total Size:.*>(\d.*?)<', result, re.I)[0].strip()
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except: dsize = 0
info = ' | '.join(info)
self.sources.append({'provider': 'ettv', 'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'name_info': name_info,
'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize})
except:
source_utils.scraper_error('ETTV')
def sources(self, url, hostDict):
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 = title.replace('&', 'and').replace('Special Victims Unit',
'SVU')
aliases = data['aliases']
episode_title = data['title'] if 'tvshowtitle' in data else None
year = data['year']
hdlr = 'S%02dE%02d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else year
query = '%s %s' % (title, hdlr)
query = re.sub(r'[^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, __name__, log_utils.LOGDEBUG)
r = client.request(url, timeout='5')
if not r or 'did not match any documents' in r: return sources
r = r.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]
except:
source_utils.scraper_error('BT4G')
return sources
for post in posts:
try:
name = client.parseDOM(post, 'a', ret='title')[0]
name = source_utils.clean_name(name)
if not source_utils.check_title(title, aliases, name, hdlr,
year):
continue
name_info = source_utils.info_from_name(
name, title, year, hdlr, episode_title)
if source_utils.remove_lang(name_info): continue
hash = client.parseDOM(post, 'a',
ret='href')[0].split('magnet/')[1]
url = 'magnet:?xt=urn:btih:%s&dn=%s' % (hash, name)
if not episode_title: #filter for eps returned in movie query (rare but movie and show exists for Run in 2020)
ep_strings = [
r'[.-]s\d{2}e\d{2}([.-]?)', r'[.-]s\d{2}([.-]?)',
r'[.-]season[.-]?\d{1,2}[.-]?'
]
if any(
re.search(item, name.lower())
for item in ep_strings):
continue
try:
seeders = int(
client.parseDOM(post, 'b',
attrs={'id':
'seeders'})[0].replace(',', ''))
if self.min_seeders > seeders: return
except:
seeders = 0
quality, info = source_utils.get_release_quality(
name_info, url)
try:
size = re.findall(
r'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))',
post
)[0] #lot of combo S01E01-E08 so parse episode item for size instead, it's closer
# size = re.findall(r'<b class\s*=\s*["\']cpill .+?-pill["\']>(.+?)</b>', post, re.I)[0]
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
dsize = 0
info = ' | '.join(info)
sources.append({
'provider': 'bt4g',
'source': 'torrent',
'seeders': seeders,
'hash': hash,
'name': name,
'name_info': name_info,
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True,
'size': dsize
})
except:
source_utils.scraper_error('BT4G')
return sources
return sources
def sources(self, url, hostDict):
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 = title.replace('&', 'and').replace('Special Victims Unit',
'SVU')
aliases = data['aliases']
episode_title = data['title'] if 'tvshowtitle' in data else None
year = data['year']
hdlr = 'S%02dE%02d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else ('(' + year +
')')
query = title
query = re.sub(r'[^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, timeout='5')
if not r: return sources
r = r.replace('\r', '').replace('\n', '').replace('\t', '')
r = client.parseDOM(r, 'div', attrs={'class': 'card'})
if not r: return sources
except:
source_utils.scraper_error('TOPNOW')
return sources
for i in r:
try:
if 'magnet:' not in i: continue
name = client.parseDOM(i,
'img',
attrs={'class': 'thumbnails'},
ret='alt')[0].replace(u'\xa0', u' ')
if not source_utils.check_title(
title, aliases, name,
hdlr.replace('(', '').replace(')', ''), year):
continue
url = re.search(r'href\s*=\s*["\'](magnet:[^"\']+)["\']', i,
re.DOTALL | re.I).group(1)
try:
url = unquote_plus(url).decode('utf8').replace(
'&', '&').replace(' ', '.')
except:
url = unquote_plus(url).replace('&',
'&').replace(' ', '.')
url = re.sub(r'(&tr=.+)&dn=', '&dn=',
url) # some links on topnow &tr= before &dn=
url = url.split('&tr=')[0].replace(' ', '.')
url = source_utils.strip_non_ascii_and_unprintable(url)
hash = re.compile(r'btih:(.*?)&', re.I).findall(url)[0]
release_name = url.split('&dn=')[1]
release_name = source_utils.clean_name(release_name)
name_info = source_utils.info_from_name(
release_name, title, year, hdlr, episode_title)
if source_utils.remove_lang(name_info): continue
seeders = 0 # seeders not available on topnow
quality, info = source_utils.get_release_quality(
name_info, url)
try:
size = re.findall(
r'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))',
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
info = ' | '.join(info)
sources.append({
'provider': 'topnow',
'source': 'torrent',
'seeders': seeders,
'hash': hash,
'name': release_name,
'name_info': name_info,
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True,
'size': dsize
})
except:
source_utils.scraper_error('TOPNOW')
return sources
def sources(self, url, hostDict):
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 = title.replace('&', 'and').replace('Special Victims Unit',
'SVU')
aliases = data['aliases']
episode_title = data['title'] if 'tvshowtitle' in data else None
year = data['year']
hdlr = 'S%02dE%02d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else year
query = '%s %s' % (title, hdlr)
query = re.sub(r'(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', 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 not r: return sources
posts = client.parseDOM(r, 'h2')
urls = []
for item in posts:
if not item.startswith('<a href'): continue
try:
name = client.parseDOM(item, "a")[0]
if not source_utils.check_title(title, aliases, name, hdlr,
year):
continue
name_info = source_utils.info_from_name(
name, title, year, hdlr, episode_title)
if source_utils.remove_lang(name_info): continue
quality, info = source_utils.get_release_quality(
name_info, item[0])
try:
size = re.findall(
r'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))',
item)[0]
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
dsize = 0
info = ' | '.join(info)
item = client.parseDOM(item, 'a', ret='href')
url = item
links = self.links(url)
if links is None: continue
urls += [(i, name, name_info, quality, info, dsize)
for i in links]
except:
source_utils.scraper_error('300MBFILMS')
for item in urls:
if 'earn-money' in item[0]: continue
url = py_tools.ensure_text(client.replaceHTMLCodes(item[0]),
errors='replace')
valid, host = source_utils.is_host_valid(url, hostDict)
if not valid: continue
sources.append({
'provider': '300mbfilms',
'source': host,
'name': item[1],
'name_info': item[2],
'quality': item[3],
'language': 'en',
'url': url,
'info': item[4],
'direct': False,
'debridonly': True,
'size': item[5]
})
return sources
except:
source_utils.scraper_error('300MBFILMS')
return sources
def get_sources_packs(self, link):
# log_utils.log('link = %s' % str(link), __name__, log_utils.LOGDEBUG)
try:
r = client.request(link, timeout='5')
if not r or '<table' not in r: return
table = client.parseDOM(r, 'table', attrs={'class': 'rtable'})
rows = client.parseDOM(table, 'tr')
except:
source_utils.scraper_error('BTSCENE')
return
for row in rows:
try:
if 'magnet:' not in row: continue
url = re.search(r'href\s*=\s*["\'](magnet:[^"\']+)["\']', row,
re.I).group(1)
url = unquote_plus(url).replace('&', '&').replace(
' ', '.').split('&tr')[0]
url = source_utils.strip_non_ascii_and_unprintable(url)
hash = re.search(r'btih:(.*?)&', url, re.I).group(1)
name = url.split('&dn=')[1]
name = source_utils.clean_name(name)
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'
name_info = source_utils.info_from_name(name,
self.title,
self.year,
season=self.season_x,
pack=package)
if source_utils.remove_lang(name_info): continue
try:
seeders = int(
client.parseDOM(row,
'td',
attrs={
'class':
'seeds is-hidden-sm-mobile'
})[0].replace(',', ''))
if self.min_seeders > seeders: continue
except:
seeders = 0
quality, info = source_utils.get_release_quality(
name_info, url)
try:
size = re.search(
r'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))',
row).group(0)
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
dsize = 0
info = ' | '.join(info)
item = {
'provider': 'btscene',
'source': 'torrent',
'seeders': seeders,
'hash': hash,
'name': name,
'name_info': name_info,
'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('BTSCENE')
def sources(self, data, hostDict):
sources = []
if not data: return sources
try:
self.title = data[
'tvshowtitle'] if 'tvshowtitle' in data else data['title']
self.title = self.title.replace('&', 'and').replace(
'Special Victims Unit', 'SVU')
self.aliases = data['aliases']
self.episode_title = data[
'title'] if 'tvshowtitle' in data else None
self.year = data['year']
self.hdlr = 'S%02dE%02d' % (
int(data['season']),
int(data['episode'])) if 'tvshowtitle' in data else self.year
query = '%s %s' % (self.title, self.hdlr)
query = re.sub(r'[^A-Za-z0-9\s\.-]+', '', query)
if 'tvshowtitle' in data:
url = self.tvsearch.format(quote_plus(query))
else:
url = self.moviesearch.format(quote_plus(query))
url = '%s%s' % (self.base_link, url)
# log_utils.log('url = %s' % url)
headers = {'User-Agent': client.agent()}
result = client.request(url, headers=headers, timeout='5')
if not result: return sources
rows = client.parseDOM(result, 'tr', attrs={'class': 't-row'})
if not rows: return sources
rows = [i for i in rows if 'racker:' not in i]
except:
source_utils.scraper_error('GLODLS')
return sources
for row in rows:
try:
ref = client.parseDOM(row, 'a', ret='href')
url = [i for i in ref if 'magnet:' in i][0]
url = unquote_plus(url).replace('&', '&').replace(
' ', '.').split('&tr')[0]
hash = re.search(r'btih:(.*?)&', url, re.I).group(1).lower()
name = unquote_plus(client.parseDOM(row, 'a', ret='title')[0])
name = source_utils.clean_name(name)
if not source_utils.check_title(self.title, self.aliases, name,
self.hdlr, self.year):
continue
name_info = source_utils.info_from_name(
name, self.title, self.year, self.hdlr, self.episode_title)
if source_utils.remove_lang(name_info): continue
if not self.episode_title: #filter for eps returned in movie query (rare but movie and show exists for Run in 2020)
ep_strings = [
r'[.-]s\d{2}e\d{2}([.-]?)', r'[.-]s\d{2}([.-]?)',
r'[.-]season[.-]?\d{1,2}[.-]?'
]
if any(
re.search(item, name.lower())
for item in ep_strings):
continue
try:
seeders = int(
re.search(
r'<td.*?<font\s*color\s*=\s*["\'].+?["\']><b>([0-9]+|[0-9]+,[0-9]+)</b>',
row).group(1).replace(',', ''))
if self.min_seeders > seeders: continue
except:
seeders = 0
quality, info = source_utils.get_release_quality(
name_info, url)
try:
size = re.search(
r'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))',
row).group(0)
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
dsize = 0
info = ' | '.join(info)
sources.append({
'provider': 'glodls',
'source': 'torrent',
'seeders': seeders,
'hash': hash,
'name': name,
'name_info': name_info,
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True,
'size': dsize
})
except:
source_utils.scraper_error('GLODLS')
return sources
def get_sources(self, name, url):
try:
# r = self.scraper.get(url, headers=self.headers).content
r = py_tools.ensure_str(self.scraper.get(
url, headers=self.headers).content,
errors='replace')
name = client.replaceHTMLCodes(name)
if name.startswith('['): name = name.split(']')[1]
name = name.strip().replace(' ', '.')
name_info = source_utils.info_from_name(name, self.title,
self.year, self.hdlr,
self.episode_title)
if source_utils.remove_lang(name_info): return self.sources
l = dom_parser.parse_dom(r, 'pre', {'class': 'links'})
if l == []: return
s = ''
for i in l:
s += i.content
urls = re.findall(
r'''((?:http|ftp|https)://[\w_-]+(?:(?:\.[\w_-]+)+)[\w.,@?^=%&:/~+#-]*[\w@?^=%&/~+#-])''',
i.content,
flags=re.M | re.S)
urls = [
i for i in urls if not i.endswith(('.rar', '.zip', '.iso',
'.idx', '.sub', '.srt'))
]
for link in urls:
url = py_tools.ensure_text(client.replaceHTMLCodes(str(link)),
errors='replace')
if url in str(self.sources): continue
valid, host = source_utils.is_host_valid(url, self.hostDict)
if not valid: continue
quality, info = source_utils.get_release_quality(name, url)
try:
size = re.search(
r'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))',
name).group(0)
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
dsize = 0
info = ' | '.join(info)
self.sources.append({
'provider': 'rapidmoviez',
'source': host,
'name': name,
'name_info': name_info,
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True,
'size': dsize
})
except:
source_utils.scraper_error('RAPIDMOVIEZ')
def sources(self, url, hostDict):
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 = title.replace('&', 'and').replace('Special Victims Unit',
'SVU')
aliases = data['aliases']
year = data['year']
hdlr = 'S%02dE%02d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else year
hdlr2 = 'S%d - %d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else year
query = '%s %s' % (title, hdlr)
query = re.sub(r'(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query)
query2 = '%s %s' % (title, hdlr2)
query2 = re.sub(r'(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query2)
urls = []
url = self.search_link % quote_plus(query)
url = urljoin(self.base_link, url)
urls.append(url)
url2 = self.search_link % quote_plus(query2)
url2 = urljoin(self.base_link, url2)
urls.append(url2)
# log_utils.log('urls = %s' % urls, log_utils.LOGDEBUG)
except:
source_utils.scraper_error('NYYAA')
return sources
for url in urls:
try:
r = client.request(url, timeout='5')
if not r or '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(r'href\s*=\s*["\'](magnet:[^"\']+)["\']',
row, re.DOTALL | re.I),
re.findall(
r'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))',
row, re.DOTALL),
[
re.findall(
r'<td class\s*=\s*["\']text-center["\']>([0-9]+)</td>',
row, re.DOTALL)
])
for link in links:
url = unquote_plus(link[0]).replace(
'&', '&').replace(' ', '.').split('&tr')[0]
url = source_utils.strip_non_ascii_and_unprintable(url)
hash = re.compile(r'btih:(.*?)&', re.I).findall(url)[0]
name = url.split('&dn=')[1]
name = source_utils.clean_name(name)
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(year, '').replace(
'(',
'').replace(')',
'').replace('&', 'and').replace(
'.US.',
'.').replace('.us.', '.')
if hdlr2 in name:
t = name.split(hdlr2)[0].replace(year, '').replace(
'(',
'').replace(')',
'').replace('&', 'and').replace(
'.US.',
'.').replace('.us.', '.')
# if cleantitle.get(t) != cleantitle.get(title): continue # Anime title matching is a bitch!
try:
seeders = int(link[2][0])
if self.min_seeders > seeders: continue
except:
seeders = 0
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
info = ' | '.join(info)
sources.append({
'provider': 'nyaa',
'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
def sources(self, url, hostDict):
sources = []
if not url: return sources
try:
scraper = cfscrape.create_scraper()
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
year = data['year']
hdlr = 'S%02dE%02d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else year
query = '%s %s' % (title, hdlr)
query = re.sub(r'(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', 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
r = py_tools.ensure_str(scraper.get(url).content, errors='replace')
posts = client.parseDOM(r, 'div', attrs={'class': 'post'})
if not posts: return sources
except:
source_utils.scraper_error('SCENERLS')
return sources
items = []
for post in posts:
try:
content = client.parseDOM(post,
"div",
attrs={"class": "postContent"})
size = re.findall(
r'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))',
content[0])[0]
u = client.parseDOM(content, "h2")
u = client.parseDOM(u, 'a', ret='href')
u = [(i.strip('/').split('/')[-1], i, size) for i in u]
items += u
except:
source_utils.scraper_error('SCENERLS')
return sources
for item in items:
try:
name = item[0]
name = client.replaceHTMLCodes(name)
if not source_utils.check_title(title, aliases, name, hdlr,
year):
continue
name_info = source_utils.info_from_name(
name, title, year, hdlr, episode_title)
if source_utils.remove_lang(name_info): continue
# check year for reboot/remake show issues if year is available-crap shoot
# if 'tvshowtitle' in data:
# if re.search(r'([1-3][0-9]{3})', name):
# if not any(value in name for value in [year, str(int(year)+1), str(int(year)-1)]):
# continue
url = py_tools.ensure_text(client.replaceHTMLCodes(str(
item[1])),
errors='replace')
if url in str(sources): continue
valid, host = source_utils.is_host_valid(url, hostDict)
if not valid: continue
quality, info = source_utils.get_release_quality(
name_info, url)
try:
dsize, isize = source_utils._size(item[2])
info.insert(0, isize)
except:
dsize = 0
info = ' | '.join(info)
sources.append({
'provider': 'scenerls',
'source': host,
'name': name,
'name_info': name_info,
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True,
'size': dsize
})
except:
source_utils.scraper_error('SCENERLS')
return sources
def get_sources_packs(self, link):
# log_utils.log('link = %s' % str(link))
try:
# headers = {'User-Agent': client.agent()}
headers = {'User-Agent': client.randomagent()}
result = client.request(link, headers=headers, timeout='5')
if not result: return
rows = client.parseDOM(result, 'tr', attrs={'class': 't-row'})
if not rows: return
rows = [i for i in rows if 'racker:' not in i]
except:
source_utils.scraper_error('GLODLS')
return
for row in rows:
try:
ref = client.parseDOM(row, 'a', ret='href')
url = [i for i in ref if 'magnet:' in i][0]
url = unquote_plus(url).replace('&', '&').replace(
' ', '.').split('&tr')[0]
hash = re.search(r'btih:(.*?)&', url, re.I).group(1).lower()
name = unquote_plus(client.parseDOM(row, 'a', ret='title')[0])
name = source_utils.clean_name(name)
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'
name_info = source_utils.info_from_name(name,
self.title,
self.year,
season=self.season_x,
pack=package)
if source_utils.remove_lang(name_info): continue
try:
seeders = int(
re.search(
r'<td.*?<font\s*color\s*=\s*["\'].+?["\']><b>([0-9]+|[0-9]+,[0-9]+)</b>',
row).group(1).replace(',', ''))
if self.min_seeders > seeders: continue
except:
seeders = 0
quality, info = source_utils.get_release_quality(
name_info, url)
try:
size = re.search(
r'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))',
row).group(0)
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
dsize = 0
info = ' | '.join(info)
item = {
'provider': 'glodls',
'source': 'torrent',
'seeders': seeders,
'hash': hash,
'name': name,
'name_info': name_info,
'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('GLODLS')
def sources(self, url, hostDict):
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'].replace('&', 'and').replace('Special Victims Unit', 'SVU')
aliases = data['aliases']
episode_title = data['title']
year = data['year']
hdlr = 'S%02dE%02d' % (int(data['season']), int(data['episode']))
query = '%s %s' % (title, hdlr)
# query = re.sub(r'[^A-Za-z0-9\s\.-]+', '', query) #eztv has issues with dashes in titles
query = re.sub(r'[^A-Za-z0-9\s\.]+', '', query)
url = self.search_link % (quote_plus(query).replace('+', '-'))
url = urljoin(self.base_link, url)
# log_utils.log('url = %s' % url, log_utils.LOGDEBUG)
html = client.request(url, timeout='5')
try:
tables = client.parseDOM(html, 'table', attrs={'class': 'forum_header_border'})
if not tables: return sources
for table in tables:
if 'magnet:' not in table: continue
else: break
except:
source_utils.scraper_error('EZTV')
return sources
rows = re.findall(r'<tr\s*name\s*=\s*["\']hover["\']\s*class\s*=\s*["\']forum_header_border["\']>(.+?)</tr>', table, re.DOTALL | re.I)
if not rows: return sources
except:
source_utils.scraper_error('EZTV')
return sources
for row in rows:
try:
try:
columns = re.findall(r'<td\s.+?>(.+?)</td>', row, re.DOTALL)
link = re.findall(r'href\s*=\s*["\'](magnet:[^"\']+)["\'].*title\s*=\s*["\'](.+?)["\']', columns[2], re.DOTALL | re.I)[0]
except: continue
url = str(client.replaceHTMLCodes(link[0]).split('&tr')[0])
try: url = unquote(url).decode('utf8')
except: pass
hash = re.compile(r'btih:(.*?)&', re.I).findall(url)[0]
name = link[1].split(' [eztv]')[0].split(' Torrent:')[0]
name = source_utils.clean_name(name)
if not source_utils.check_title(title, aliases, name, hdlr, year): continue
name_info = source_utils.info_from_name(name, title, year, hdlr, episode_title)
if source_utils.remove_lang(name_info): continue
try:
seeders = int(re.findall(r'<font\s*color\s*=\s*["\'].+?["\']>(\d+|\d+\,\d+)</font>', columns[5], re.DOTALL)[0].replace(',', ''))
if self.min_seeders > seeders: continue
except: seeders = 0
quality, info = source_utils.get_release_quality(name_info, url)
try:
size = re.findall(r'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))', columns[3])[-1]
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except: dsize = 0
info = ' | '.join(info)
sources.append({'provider': 'eztv', 'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'name_info': name_info,
'quality': quality, 'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize})
except:
source_utils.scraper_error('EZTV')
return sources
def sources(self, data, hostDict):
sources = []
if not data: return sources
try:
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
year = data['year']
hdlr = 'S%02dE%02d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else year
query = '%s %s' % (title, hdlr)
query = re.sub(r'(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query)
url = '%s%s' % (self.base_link,
self.search_link % quote_plus(query))
# log_utils.log('url = %s' % url, __name__, log_utils.LOGDEBUG)
r = client.request(url, timeout='5')
if not r or 'Error 404' in r: return sources
r = client.parseDOM(r, 'div', attrs={'id': 'content'})
r1 = client.parseDOM(r, 'h2')
posts = zip(client.parseDOM(r1, 'a', ret='href'),
client.parseDOM(r1, 'a'))
except:
source_utils.scraper_error('MYVIDEOLINK')
return sources
items = []
for post in posts:
try:
name = source_utils.strip_non_ascii_and_unprintable(post[1])
if '<' in name: name = re.sub(r'<.*?>', '', name)
name = client.replaceHTMLCodes(name)
name = source_utils.clean_name(name)
if 'tvshowtitle' in data:
if not source_utils.check_title(title, aliases, name, hdlr,
year):
if not source_utils.check_title(
title, aliases, name,
'S%02d' % int(data['season']), year):
if not source_utils.check_title(
title, aliases, name,
'Season.%d' % int(data['season']), year):
if not source_utils.check_title(
title, aliases, name,
'S%d' % int(data['season']), year):
continue
else:
if not source_utils.check_title(title, aliases, name, hdlr,
year):
continue
name_info = source_utils.info_from_name(
name, title, year, hdlr, episode_title)
link = post[0]
results = client.request(link, timeout='5')
results = client.parseDOM(results,
'div',
attrs={'class':
'entry-content cf'})[0]
if 'tvshowtitle' in data:
isSeasonList = False
if 'Season' in name or 'S%02d' % int(
data['season']) in name:
isSeasonList = True
results = re.sub(r'\n', '', results)
results = re.sub(r'\t', '', results).replace('> <', '><')
test = re.findall(
r'<p><b>(.*?)</ul>', results, re.DOTALL
) # parsing this site for episodes is a bitch, f**k it this is close as I'm doing
for x in test:
test2 = re.search(r'(.*?)</b>', x).group(1)
if hdlr in test2:
if isSeasonList:
name = re.sub(r'\.Season\.\d+',
'.%s.' % test2.replace(' ', '.'),
name)
name = re.sub(r'\.S\d+',
'.%s' % test2.replace(' ', '.'),
name)
else:
name = test2
links = client.parseDOM(x, 'a', ret='href')
break
else:
try:
test3 = re.search(r'<p><b>(.*?)</b></p>',
x).group(1)
except:
continue
if hdlr in test3:
if isSeasonList:
name = re.sub(
r'\.Season\.\d+',
'.%s.' % test3.replace(' ', '.'), name)
name = re.sub(
r'\.S\d+',
'.%s' % test3.replace(' ', '.'), name)
else:
name = test3
links = client.parseDOM(x, 'a', ret='href')
break
else:
links = client.parseDOM(results,
'a',
attrs={'class': 'autohyperlink'},
ret='href')
for link in links:
try:
url = py_tools.ensure_text(client.replaceHTMLCodes(
str(link)),
errors='replace')
if url.endswith(('.rar', '.zip', '.iso', '.part',
'.png', '.jpg', '.bmp', '.gif')):
continue
if url in str(sources): continue
valid, host = source_utils.is_host_valid(url, hostDict)
if not valid: continue
quality, info = source_utils.get_release_quality(
name_info, url)
try:
size = re.search(
r'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))',
results).group(0)
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
dsize = 0
info = ' | '.join(info)
sources.append({
'provider': 'myvideolink',
'source': host,
'name': name,
'name_info': name_info,
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True,
'size': dsize
})
except:
source_utils.scraper_error('MYVIDEOLINK')
except:
source_utils.scraper_error('MYVIDEOLINK')
return sources
def get_sources_packs(self, url):
# log_utils.log('url = %s' % str(url), __name__, log_utils.LOGDEBUG)
try:
r = client.request(url, timeout='5')
if not r or '<tbody' not in r: return
r = client.parseDOM(r, 'tbody')[0]
results = client.parseDOM(r, 'tr')
posts = [i for i in results if 'magnet:' in i]
except:
source_utils.scraper_error('MAGNETDL')
return
try:
next_page = [i for i in results if 'Next Page' in i]
if not next_page: raise Exception()
page = client.parseDOM(next_page,
'a',
ret='href',
attrs={'title': 'Downloads | Page 2'})[0]
r2 = client.request(self.base_link + page)
results2 = client.parseDOM(r2, 'tr')
posts += [i for i in results2 if 'magnet:' in i]
except:
pass
for post in posts:
try:
post = post.replace(' ', ' ')
links = client.parseDOM(post, 'a', ret='href')
magnet = [
i.replace('&', '&') for i in links if 'magnet:' in i
][0]
url = unquote_plus(magnet).split('&tr')[0].replace(' ', '.')
if url in str(self.sources): continue
hash = re.compile(r'btih:(.*?)&', re.I).findall(url)[0]
name = client.parseDOM(post, 'a',
ret='title')[1].replace('–', '-')
name = source_utils.clean_name(unquote_plus(name))
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'
name_info = source_utils.info_from_name(name,
self.title,
self.year,
season=self.season_x,
pack=package)
if source_utils.remove_lang(name_info): continue
try:
seeders = int(
client.parseDOM(post, 'td',
attrs={'class':
's'})[0].replace(',', ''))
if self.min_seeders > seeders: continue
except:
seeders = 0
quality, info = source_utils.get_release_quality(
name_info, url)
try:
size = re.findall(
r'((?:\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
info = ' | '.join(info)
item = {
'provider': 'magnetdl',
'source': 'torrent',
'seeders': seeders,
'hash': hash,
'name': name,
'name_info': name_info,
'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('MAGNETDL')
def sources(self, url, hostDict):
sources = []
if not url: return sources
try:
scraper = cfscrape.create_scraper()
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
year = data['year']
hdlr = 'S%02dE%02d' % (int(data['season']), int(data['episode'])) if 'tvshowtitle' in data else year
if 'tvshowtitle' in data:
query = '%s %s' % (title, hdlr)
query = re.sub(r'[^A-Za-z0-9\s\.-]+', '', query)
url = self.search_link % quote_plus(query)
else:
url = self.search_link % data['imdb']
url = urljoin(self.base_link, url)
# log_utils.log('url = %s' % url, log_utils.LOGDEBUG)
r = py_tools.ensure_str(scraper.get(url).content, errors='replace')
posts = client.parseDOM(r, 'div', attrs={'class': 'tgxtable'})
if not posts: return sources
except:
source_utils.scraper_error('TORRENTGALAXY')
return sources
for post in posts:
try:
links = zip(
re.findall(r'href\s*=\s*["\'](magnet:[^"\']+)["\']', post, re.DOTALL | re.I),
re.findall(r'<span\s*class\s*=\s*["\']badge\s*badge-secondary["\']\s*style\s*=\s*["\']border-radius:4px;["\']>(.*?)</span>', post, re.DOTALL | re.I),
re.findall(r'<span\s*title\s*=\s*["\']Seeders/Leechers["\']>\[<font\s*color\s*=\s*["\']green["\']><b>(.*?)<', post, re.DOTALL | re.I))
for link in links:
url = unquote_plus(link[0]).split('&tr')[0].replace(' ', '.')
url = source_utils.strip_non_ascii_and_unprintable(url)
hash = re.compile(r'btih:(.*?)&', re.I).findall(url)[0]
name = url.split('&dn=')[1]
name = source_utils.clean_name(name)
if not source_utils.check_title(title, aliases, name, hdlr, year): continue
name_info = source_utils.info_from_name(name, title, year, hdlr, episode_title)
if source_utils.remove_lang(name_info): continue
if not episode_title: #filter for eps returned in movie query (rare but movie and show exists for Run in 2020)
ep_strings = [r'[.-]s\d{2}e\d{2}([.-]?)', r'[.-]s\d{2}([.-]?)', r'[.-]season[.-]?\d{1,2}[.-]?']
if any(re.search(item, name.lower()) for item in ep_strings): continue
try:
seeders = int(link[2])
if self.min_seeders > seeders: continue
except: seeders = 0
quality, info = source_utils.get_release_quality(name_info, url)
try:
dsize, isize = source_utils._size(link[1])
info.insert(0, isize)
except: dsize = 0
info = ' | '.join(info)
sources.append({'provider': 'torrentgalaxy', 'source': 'torrent', 'seeders': seeders, 'hash': hash, 'name': name, 'name_info': name_info, 'quality': quality,
'language': 'en', 'url': url, 'info': info, 'direct': False, 'debridonly': True, 'size': dsize})
except:
source_utils.scraper_error('TORRENTGALAXY')
return sources
def sources(self, url, hostDict):
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 = title.replace('&', 'and').replace('Special Victims Unit',
'SVU')
aliases = data['aliases']
episode_title = data['title'] if 'tvshowtitle' in data else None
year = data['year']
hdlr = 'S%02dE%02d' % (int(data['season']), int(
data['episode'])) if 'tvshowtitle' in data else year
query = '%s %s' % (title, hdlr)
query = re.sub(r'[^A-Za-z0-9\s\.-]+', '', query)
url = urljoin(
self.base_link,
self.search_link.format(query[0].lower(),
cleantitle.geturl(query)))
# log_utils.log('url = %s' % url, __name__, log_utils.LOGDEBUG)
r = client.request(url, timeout='5')
if not r or '<tbody' not in r: return sources
r = client.parseDOM(r, 'tbody')[0]
results = client.parseDOM(r, 'tr')
posts = [i for i in results if 'magnet:' in i]
except:
source_utils.scraper_error('MAGNETDL')
return sources
try:
next_page = [i for i in results if 'Next Page' in i]
if not next_page: raise Exception()
page = client.parseDOM(next_page,
'a',
ret='href',
attrs={'title': 'Downloads | Page 2'})[0]
r2 = client.request(self.base_link + page)
results2 = client.parseDOM(r2, 'tr')
posts += [i for i in results2 if 'magnet:' in i]
except:
pass
for post in posts:
try:
post = post.replace(' ', ' ')
links = client.parseDOM(post, 'a', ret='href')
magnet = [
i.replace('&', '&') for i in links if 'magnet:' in i
][0]
url = unquote_plus(magnet).split('&tr')[0].replace(' ', '.')
if url in str(sources): continue
hash = re.compile(r'btih:(.*?)&', re.I).findall(url)[0]
name = client.parseDOM(post, 'a',
ret='title')[1].replace('–', '-')
name = source_utils.clean_name(unquote_plus(name))
if not source_utils.check_title(title, aliases, name, hdlr,
year):
continue
name_info = source_utils.info_from_name(
name, title, year, hdlr, episode_title)
if source_utils.remove_lang(name_info): continue
elif not episode_title: #filter for eps returned in movie query (rare but movie and show exists for Run in 2020)
ep_strings = [
r'[.-]s\d{2}e\d{2}([.-]?)', r'[.-]s\d{2}([.-]?)',
r'[.-]season[.-]?\d{1,2}[.-]?'
]
if any(
re.search(item, name.lower())
for item in ep_strings):
continue
try:
seeders = int(
client.parseDOM(post, 'td',
attrs={'class':
's'})[0].replace(',', ''))
if self.min_seeders > seeders: continue
except:
seeders = 0
quality, info = source_utils.get_release_quality(
name_info, url)
try:
size = re.findall(
r'((?:\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
info = ' | '.join(info)
sources.append({
'provider': 'magnetdl',
'source': 'torrent',
'seeders': seeders,
'hash': hash,
'name': name,
'name_info': name_info,
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True,
'size': dsize
})
except:
source_utils.scraper_error('MAGNETDL')
return sources
