def get_sources(self, item):
try:
quality, info = source_utils.get_release_quality(item[1], item[2])
if item[3] != '0': info.insert(0, item[3])
info = ' | '.join(info)
data = client.request(item[2], timeout='10')
data = client.parseDOM(data, 'a', ret='href')
if not data: return
url = [i for i in data if 'magnet:' in 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]
self.sources.append({
'provider': '1337x',
'source': 'torrent',
'seeders': item[5],
'hash': hash,
'name': item[0],
'name_info': item[1],
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True,
'size': item[4]
})
except:
source_utils.scraper_error('1337X')
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:
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 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_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, 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, 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, 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 get_sources_packs(self, link):
try:
# log_utils.log('link = %s' % link)
r = py_tools.ensure_str(self.scraper.get(link).content,
errors='replace')
if not r: return
posts = client.parseDOM(r, 'tr', attrs={'class': 'tlr'})
posts += client.parseDOM(r, 'tr', attrs={'class': 'tlz'})
except:
source_utils.scraper_error('EXTRATORRENT')
return
for post in posts:
try:
post = re.sub(r'\n', '', post)
post = re.sub(r'\t', '', post)
url = re.search(r'href\s*=\s*["\'](magnet:[^"\']+)["\']', post,
re.I).group(1)
url = unquote_plus(url).replace('&', '&').replace(
' ', '.').split('&tr')[0]
url = source_utils.strip_non_ascii_and_unprintable(url)
if url in str(self.sources): continue
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(post, 'td',
attrs={'class':
'sn'})[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))',
post).group(0)
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
dsize = 0
info = ' | '.join(info)
item = {
'provider': 'extratorrent',
'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('EXTRATORRENT')
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 get_sources_packs(self, link, url):
try:
self.headers.update({'Referer': link})
query_data = {
'query': url,
'offset': 0,
'limit': 99,
'filters[field]': 'seeds',
'filters[sort]': 'desc',
'filters[time]': 4,
'filters[category]': 4,
'filters[adult]': False,
'filters[risky]': False}
api_url = '%s%s' % (self.base_link, self.api_search_link)
rjson = client.request(api_url, post=query_data, headers=self.headers, timeout='5')
if not rjson: return
files = jsloads(rjson)
error = files.get('error')
if error: return
except:
source_utils.scraper_error('BITLORD')
return
for file in files.get('content'):
try:
name = source_utils.clean_name(file.get('name'))
url = unquote_plus(file.get('magnet')).replace('&', '&').replace(' ', '.')
url = re.sub(r'(&tr=.+)&dn=', '&dn=', url) # some links on bitlord &tr= before &dn=
url = url.split('&tr=')[0].split('&xl=')[0]
url = source_utils.strip_non_ascii_and_unprintable(url)
hash = re.search(r'btih:(.*?)&', url, re.I).group(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 = file.get('seeds')
if self.min_seeders > seeders: continue
except: seeders = 0
quality, info = source_utils.get_release_quality(name_info, url)
try:
size = file.get('size')
size = str(size) + ' GB' if len(str(size)) <= 2 else str(size) + ' MB' # bitlord size is all over the place between MB and GB
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except: dsize = 0
info = ' | '.join(info)
item = {'provider': 'bitlord', '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('BITLORD')
def get_sources(self, link):
try:
url = re.findall(r'href\s*=\s*["\'](magnet:[^"\']+)["\']', link,
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 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(
client.parseDOM(link, 'td',
attrs={'class': 'sy'})[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': 'extratorrent',
'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('EXTRATORRENT')
def get_sources(self, url):
try:
r = client.request(url, timeout='5')
if not r: return
results = jsloads(r)['results']
except:
source_utils.scraper_error('SOLIDTORRENTS')
return
for item in results:
try:
url = unquote_plus(item['magnet']).replace(' ', '.')
url = re.sub(
r'(&tr=.+)&dn=', '&dn=',
url) # some links on solidtorrents &tr= before &dn=
url = source_utils.strip_non_ascii_and_unprintable(url)
hash = item['infohash'].lower()
if url in str(self.sources): continue
name = source_utils.clean_name(item['title'])
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(item['swarm']['seeders'])
if self.min_seeders > seeders: continue
except:
seeders = 0
quality, info = source_utils.get_release_quality(
name_info, url)
try:
dsize, isize = source_utils.convert_size(item["size"],
to='GB')
info.insert(0, isize)
except:
dsize = 0
info = ' | '.join(info)
self.sources.append({
'provider': 'solidtorrents',
'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('SOLIDTORRENTS')
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'[^A-Za-z0-9\s\.-]+', '', query)
url = '%s%s' % (self.base_link, self.search_link % quote_plus(query))
# log_utils.log('url = %s' % url, __name__, log_utils.LOGDEBUG)
api_url = '%s%s' % (self.base_link, self.api_search_link)
headers = cache.get(self._get_token_and_cookies, 1)
if not headers: return sources
headers.update({'Referer': url})
query_data = {
'query': query,
'offset': 0,
'limit': 99,
'filters[field]': 'seeds',
'filters[sort]': 'desc',
'filters[time]': 4,
'filters[category]': 3 if 'tvshowtitle' not in data else 4,
'filters[adult]': False,
'filters[risky]': False}
rjson = client.request(api_url, post=query_data, headers=headers, timeout='5')
if not rjson: return sources
files = jsloads(rjson)
error = files.get('error')
if error: return sources
except:
source_utils.scraper_error('BITLORD')
return sources
for file in files.get('content'):
try:
name = source_utils.clean_name(file.get('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
url = unquote_plus(file.get('magnet')).replace('&', '&').replace(' ', '.')
url = re.sub(r'(&tr=.+)&dn=', '&dn=', url) # some links on bitlord &tr= before &dn=
url = url.split('&tr=')[0].split('&xl=')[0]
url = source_utils.strip_non_ascii_and_unprintable(url)
hash = re.search(r'btih:(.*?)&', url, re.I).group(1)
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 = file.get('seeds')
if self.min_seeders > seeders: continue
except: seeders = 0
quality, info = source_utils.get_release_quality(name_info, url)
try:
size = file.get('size')
size = str(size) + ' GB' if len(str(size)) <= 2 else str(size) + ' MB' # bitlord size is all over the place between MB and GB
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except: dsize = 0
info = ' | '.join(info)
sources.append({'provider': 'bitlord', '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('BITLORD')
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 = 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, timeout='5')
if not r: return sources
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 sources
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 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(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)
sources.append({'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})
except:
source_utils.scraper_error('TORRENTZ2')
return sources
def sources(self, url, hostDict):
sources = []
if not url: return sources
try:
scraper = cfscrape.create_scraper(delay=5)
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
isSeasonQuery = False
query = '%s %s' % (title, hdlr)
query = re.sub(r'(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '', query)
# query = re.sub(r'[^A-Za-z0-9\s\.-]+', '', query)
query = re.sub(r'\s', '-', query)
if int(year) >= 2021: self.base_link = self.base_new
else: self.base_link = self.base_old
url = urljoin(self.base_link, query)
# 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')
if not r or 'nothing was found' in r:
if 'tvshowtitle' in data:
season = re.search(r'S(.*?)E', hdlr).group(1)
query = re.sub(r'(\\\|/| -|:|;|\*|\?|"|\'|<|>|\|)', '',
title)
# query = re.sub(r'[^A-Za-z0-9\s\.-]+', '', title)
query = re.sub(r'\s', '-', query)
query = query + "-S" + season
url = urljoin(self.base_link, query)
# r = scraper.get(url).content
r = py_tools.ensure_str(scraper.get(url).content,
errors='replace')
isSeasonQuery = True
else:
return sources
if not r or 'nothing was found' in r: return sources
# may need to add fallback to use self.search_link if nothing found
posts = client.parseDOM(r, "div", attrs={"class": "content"})
if not posts: return sources
except:
source_utils.scraper_error('RLSBB')
return sources
release_title = re.sub(r'[^A-Za-z0-9\s\.-]+', '',
title).replace(' ', '.')
items = []
count = 0
for post in posts:
if count >= 300:
break # to limit large link list and slow scrape time
try:
post_titles = re.findall(
r'(?:.*>|>\sRelease Name.*|\s)(%s.*?)<' % release_title,
post, re.I
) #parse all matching release_titles in each post(content) group
items = []
if len(post_titles) > 1:
index = 0
for name in post_titles:
start = post_titles[index].replace('[', '\\[').replace(
'(', '\\(').replace(')', '\\)').replace(
'+', '\\+').replace(' \\ ', ' \\\\ ')
end = (post_titles[index + 1].replace(
'[', '\\[').replace('(', '\\(').replace(
')', '\\)').replace('+', '\\+')).replace(
' \\ ', ' \\\\ '
) if index + 1 < len(post_titles) else ''
try:
container = re.findall(
r'(?:%s)([\S\s]+)(?:%s)' % (start, end), post,
re.I
)[0] #parse all data between release_titles in multi post(content) group
except:
source_utils.scraper_error('RLSBB')
continue
try:
size = re.findall(
r'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))',
container)[0].replace(',', '.')
except:
size = '0'
container = client.parseDOM(container, 'a', ret='href')
items.append((name, size, container))
index += 1
elif len(post_titles) == 1:
name = post_titles[0]
container = client.parseDOM(
post, 'a', ret='href'
) #parse all links in a single post(content) group
try:
size = re.findall(
r'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))',
post)[0].replace(',', '.')
except:
size = '0'
items.append((name, size, container))
else:
continue
for group_name, size, links in items:
for i in links:
name = group_name
# if isSeasonQuery and hdlr not in name.upper():
# name = i.rsplit("/", 1)[-1]
# if hdlr not in name.upper(): continue
if hdlr not in name.upper():
name = i.rsplit("/", 1)[-1]
if hdlr not in name.upper(): continue
name = client.replaceHTMLCodes(name)
name = source_utils.strip_non_ascii_and_unprintable(
name)
name_info = source_utils.info_from_name(
name, title, year, hdlr, episode_title)
url = py_tools.ensure_text(client.replaceHTMLCodes(
str(i)),
errors='replace')
if url in str(sources): continue
if url.endswith(('.rar', '.zip', '.iso', '.part',
'.png', '.jpg', '.bmp', '.gif')):
continue
valid, host = source_utils.is_host_valid(url, hostDict)
if not valid: continue
quality, info = source_utils.get_release_quality(
name, url)
try:
if size == '0':
try:
size = re.findall(
r'((?:\d+\,\d+\.\d+|\d+\.\d+|\d+\,\d+|\d+)\s*(?:GB|GiB|Gb|MB|MiB|Mb))',
name)[0].replace(',', '.')
except:
raise Exception()
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
dsize = 0
info = ' | '.join(info)
sources.append({
'provider': 'rlsbb',
'source': host,
'name': name,
'name_info': name_info,
'quality': quality,
'language': 'en',
'url': url,
'info': info,
'direct': False,
'debridonly': True,
'size': dsize
})
count += 1
except:
source_utils.scraper_error('RLSBB')
return sources
def get_sources_packs(self, link):
# log_utils.log('link = %s' % str(link), __name__, log_utils.LOGDEBUG)
try:
# For some reason Zooqle returns 404 even though the response has a body.
# This is probably a bug on Zooqle's server and the error should just be ignored.
html = client.request(link, ignoreErrors=404, timeout='5')
if not html: return
html = html.replace(' ', ' ')
try:
table = client.parseDOM(
html,
'table',
attrs={
'class': 'table table-condensed table-torrents vmiddle'
})[0]
except:
return
rows = client.parseDOM(table, 'tr')
if not rows: return
except:
source_utils.scraper_error('ZOOQLE')
return
for row in rows:
try:
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)
if url in str(self.sources): continue
except:
continue
hash = re.compile(r'btih:(.*?)&', re.I).findall(url)[0]
try:
name = re.findall(r'<a class\s*=\s*["\'].+?>(.+?)</a>',
row, re.DOTALL | re.I)[0]
name = client.cleanHTML(name)
name = unquote_plus(name)
name = source_utils.clean_name(name)
except:
continue
# some titles have foreign title translation in front so remove it
if './.' in name: name = name.split('./.', 1)[1]
if '.com.' in name.lower():
try:
name = re.sub(r'(.*?)\W{2,10}', '', name)
except:
name = name.split('-.', 1)[1].lstrip()
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:\s*([0-9]+|[0-9]+,[0-9]+)\s*\|',
row, re.DOTALL | re.I)[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)[-1]
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
dsize = 0
info = ' | '.join(info)
item = {
'provider': 'zooqle',
'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('ZOOQLE')
def get_sources(self, url):
try:
# For some reason Zooqle returns 404 even though the response has a body.
# This is probably a bug on Zooqle's server and the error should just be ignored.
html = client.request(url, ignoreErrors=404, timeout='5')
if not html: return
html = html.replace(' ', ' ')
try:
table = client.parseDOM(
html,
'table',
attrs={
'class': 'table table-condensed table-torrents vmiddle'
})[0]
except:
return
rows = client.parseDOM(table, 'tr')
if not rows: return
except:
source_utils.scraper_error('ZOOQLE')
return
for row in rows:
try:
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)
if url in str(self.sources): continue
except:
continue
hash = re.compile(r'btih:(.*?)&', re.I).findall(url)[0]
try:
name = re.findall(r'<a class\s*=\s*["\'].+?>(.+?)</a>',
row, re.DOTALL | re.I)[0]
name = client.cleanHTML(name)
name = unquote_plus(name)
name = source_utils.clean_name(name)
except:
continue
# some titles have foreign title translation in front so remove it
if './.' in name: name = name.split('./.', 1)[1]
if '.com.' in name.lower():
try:
name = re.sub(r'(.*?)\W{2,10}', '', name)
except:
name = name.split('-.', 1)[1].lstrip()
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:\s*([0-9]+|[0-9]+,[0-9]+)\s*\|',
row, re.DOTALL | re.I)[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)[-1]
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
dsize = 0
info = ' | '.join(info)
self.sources.append({
'provider': 'zooqle',
'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('ZOOQLE')
def get_sources(self, row):
row = re.sub(r'\n', '', row)
row = re.sub(r'\t', '', row)
data = re.compile(
r'<a\s*href\s*=\s*["\'](/torrent_details/.+?)["\']><span>(.+?)</span>.*?<td\s*class\s*=\s*["\']size-row["\']>(.+?)</td><td\s*class\s*=\s*["\']sn["\']>([0-9]+)</td>'
).findall(row)
if not data: return
for items in data:
try:
# 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='5')
if not link or 'Download Magnet link' not in link: continue
link = unquote_plus(
client.parseDOM(link,
'a',
attrs={'title': 'Download Magnet link'},
ret='href')[0])
if not link: continue
url = re.compile(r'(magnet:.*)').findall(link)[0].replace(
'&', '&').replace(' ', '.').split('&tr')[0]
url = source_utils.strip_non_ascii_and_unprintable(
unquote_plus(
url)) # many links dbl quoted so we must unquote again
hash = re.compile(r'btih:(.*?)&', re.I).findall(url)[0]
name = unquote_plus(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(items[3].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[2])[0]
dsize, isize = source_utils._size(size)
info.insert(0, isize)
except:
dsize = 0
info = ' | '.join(info)
self.sources.append({
'provider': 'isohunt2',
'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('ISOHUNT2')
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 get_sources_packs(self, link):
# log_utils.log('link = %s' % str(link))
try:
r = client.request(link, timeout='5')
if not r: return
results = jsloads(r)['results']
except:
source_utils.scraper_error('SOLIDTORRENTS')
return
for item in results:
try:
url = unquote_plus(item['magnet']).replace(' ', '.')
url = re.sub(
r'(&tr=.+)&dn=', '&dn=',
url) # some links on solidtorrents &tr= before &dn=
url = source_utils.strip_non_ascii_and_unprintable(url)
hash = item['infohash'].lower()
if url in str(self.sources): continue
name = source_utils.clean_name(item['title'])
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(item['swarm']['seeders'])
if self.min_seeders > seeders: continue
except:
seeders = 0
quality, info = source_utils.get_release_quality(
name_info, url)
try:
dsize, isize = source_utils.convert_size(item["size"],
to='GB')
info.insert(0, isize)
except:
dsize = 0
info = ' | '.join(info)
item = {
'provider': 'solidtorrents',
'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('SOLIDTORRENTS')
