def _find_season_quality(self, title, torrent_link, ep_number):
""" Return the modified title of a Season Torrent with the quality found inspecting torrent file list """
mediaExtensions = [
'avi', 'mkv', 'wmv', 'divx', 'vob', 'dvr-ms', 'wtv', 'ts'
'ogv', 'rar', 'zip', 'mp4'
]
quality = Quality.UNKNOWN
fileName = None
data = self.getURL(torrent_link)
if not data:
return None
try:
with BS4Parser(data, features=["html5lib", "permissive"]) as soup:
file_table = soup.find('table',
attrs={'class': 'torrentFileList'})
if not file_table:
return None
files = [
x.text for x in file_table.find_all(
'td', attrs={'class': 'torFileName'})
]
videoFiles = filter(
lambda x: x.rpartition(".")[2].lower() in mediaExtensions,
files)
#Filtering SingleEpisode/MultiSeason Torrent
if len(videoFiles) < ep_number or len(videoFiles) > float(
ep_number * 1.1):
logger.log(
u"Result " + title + " have " + str(ep_number) +
" episode and episodes retrived in torrent are " +
str(len(videoFiles)), logger.DEBUG)
logger.log(
u"Result " + title +
" Seem to be a Single Episode or MultiSeason torrent, skipping result...",
logger.DEBUG)
return None
if Quality.sceneQuality(title) != Quality.UNKNOWN:
return title
for fileName in videoFiles:
quality = Quality.sceneQuality(os.path.basename(fileName))
if quality != Quality.UNKNOWN: break
if fileName is not None and quality == Quality.UNKNOWN:
quality = Quality.assumeQuality(os.path.basename(fileName))
if quality == Quality.UNKNOWN:
logger.log(
u"Unable to obtain a Season Quality for " + title,
logger.DEBUG)
return None
try:
myParser = NameParser(showObj=self.show)
parse_result = myParser.parse(fileName)
except (InvalidNameException, InvalidShowException):
return None
logger.log(
u"Season quality for " + title + " is " +
Quality.qualityStrings[quality], logger.DEBUG)
if parse_result.series_name and parse_result.season_number:
title = parse_result.series_name + ' S%02d' % int(
parse_result.season_number
) + ' ' + self._reverseQuality(quality)
return title
except Exception, e:
logger.log(
u"Failed parsing " + self.name + " Traceback: " +
traceback.format_exc(), logger.ERROR)
def search(self, search_strings, age=0, ep_obj=None): # pylint: disable=too-many-locals
results = []
if not self.login():
return results
for mode in search_strings:
items = []
logger.log(u"Search Mode: {}".format(mode), logger.DEBUG)
for search_string in search_strings[mode]:
if mode != 'RSS':
logger.log(
u"Search string: {}".format(
search_string.decode("utf-8")), logger.DEBUG)
self.search_params['search'] = search_string
data = self.get_url(self.urls['search'],
params=self.search_params,
returns='text')
if not data:
continue
try:
with BS4Parser(data, 'html5lib') as html:
result_linkz = html.findAll(
'a', href=re.compile("torrents-details"))
if not result_linkz:
logger.log(
u"Data returned from provider do not contains any torrent",
logger.DEBUG)
continue
if result_linkz:
for link in result_linkz:
title = link.text
download_url = self.urls['base_url'] + link[
'href']
download_url = download_url.replace(
"torrents-details", "download")
# FIXME
size = -1
seeders = 1
leechers = 0
if not title or not download_url:
continue
# Filter unseeded torrent
# if seeders < self.minseed or leechers < self.minleech:
# if mode != 'RSS':
# logger.log(u"Discarding torrent because it doesn't meet the minimum seeders or leechers: {} (S:{} L:{})".format
# (title, seeders, leechers), logger.DEBUG)
# continue
item = {
'title': title,
'link': download_url,
'size': size,
'seeders': seeders,
'leechers': leechers,
'hash': None
}
if mode != 'RSS':
logger.log(u"Found result: %s " % title,
logger.DEBUG)
items.append(item)
except Exception:
logger.log(
u"Failed parsing provider. Traceback: %s" %
traceback.format_exc(), logger.ERROR)
# For each search mode sort all the items by seeders if available
items.sort(key=lambda d: try_int(d.get('seeders', 0)),
reverse=True)
results += items
return results
def search(self, search_strings, age=0, ep_obj=None): # pylint: disable=too-many-locals
results = []
for mode in search_strings:
items = []
logger.log("Search Mode: {0}".format(mode), logger.DEBUG)
for search_string in search_strings[mode]:
if mode != 'RSS':
logger.log(
"Search string: {0}".format(
search_string.decode("utf-8")), logger.DEBUG)
search_url = self.url + '/search_torrent/' + search_string.replace(
'.', '-').replace(' ', '-') + '.html,trie-seeds-d'
else:
search_url = self.url + '/torrents_series.html,trie-date-d'
data = self.get_url(search_url, returns='text')
if not data:
continue
with BS4Parser(data, 'html5lib') as html:
torrent_rows = html.findAll('tr')
for result in torrent_rows:
try:
title = result.find('a').get_text(
strip=False).replace("HDTV",
"HDTV x264-Torrent9")
title = re.sub(r' Saison',
' Season',
title,
flags=re.I)
tmp = result.find("a")['href'].split(
'/')[-1].replace('.html', '.torrent').strip()
download_url = (self.url +
'/get_torrent/{0}'.format(tmp) +
".torrent")
if not all([title, download_url]):
continue
seeders = try_int(
result.find(class_="seed_ok").get_text(
strip=True))
leechers = try_int(
result.find_all('td')[3].get_text(strip=True))
if seeders < self.minseed or leechers < self.minleech:
if mode != 'RSS':
logger.log(
"Discarding torrent because it doesn't meet the minimum seeders or leechers: {0} (S:{1} L:{2})"
.format(title, seeders,
leechers), logger.DEBUG)
continue
torrent_size = result.find_all('td')[1].get_text(
strip=True)
units = ['o', 'Ko', 'Mo', 'Go', 'To', 'Po']
size = convert_size(torrent_size,
units=units) or -1
item = {
'title': title,
'link': download_url,
'size': size,
'seeders': seeders,
'leechers': leechers,
'hash': ''
}
if mode != 'RSS':
logger.log(
"Found result: {0} with {1} seeders and {2} leechers"
.format(title, seeders,
leechers), logger.DEBUG)
items.append(item)
except StandardError:
continue
# For each search mode sort all the items by seeders if available
items.sort(key=lambda d: try_int(d.get('seeders', 0)),
reverse=True)
results += items
return results
def search(self, search_strings, age=0, ep_obj=None): # pylint: disable=too-many-locals, too-many-branches
results = []
if not self.login():
return results
# Search Params
search_params = {
'tags_type': 1,
'order_by': 'time',
'order_way': 'desc',
'action': 'basic',
'searchsubmit': 1,
'searchstr': ''
}
# Units
units = ['B', 'KB', 'MB', 'GB', 'TB', 'PB']
def process_column_header(td):
result = ''
if td.a and td.a.img:
result = td.a.img.get('title', td.a.get_text(strip=True))
if not result:
result = td.get_text(strip=True)
return result
for mode in search_strings:
items = []
logger.log("Search Mode: {0}".format(mode), logger.DEBUG)
for search_string in search_strings[mode]:
if mode != 'RSS':
logger.log("Search string: {0}".format
(search_string.decode("utf-8")), logger.DEBUG)
search_params['searchstr'] = search_string
data = self.get_url(self.urls['search'], params=search_params, returns='text')
if not data:
logger.log("No data returned from provider", logger.DEBUG)
continue
with BS4Parser(data, 'html5lib') as html:
torrent_table = html.find('table', class_='torrent_table')
torrent_rows = torrent_table('tr') if torrent_table else []
# Continue only if at least one Release is found
if len(torrent_rows) < 2:
logger.log("Data returned from provider does not contain any torrents", logger.DEBUG)
continue
labels = [process_column_header(label) for label in torrent_rows[0]('td')]
# Skip column headers
for result in torrent_rows[1:]:
try:
# skip if torrent has been nuked due to poor quality
if result.find('img', alt='Nuked'):
continue
title = result.find('a', title='View torrent').get_text(strip=True)
download_url = urljoin(self.url, result.find('span', title='Download').parent['href'])
if not all([title, download_url]):
continue
cells = result('td')
seeders = try_int(cells[labels.index('Seeders')].get_text(strip=True))
leechers = try_int(cells[labels.index('Leechers')].get_text(strip=True))
# Filter unseeded torrent
if seeders < self.minseed or leechers < self.minleech:
if mode != 'RSS':
logger.log("Discarding torrent because it doesn't meet the"
" minimum seeders or leechers: {0} (S:{1} L:{2})".format
(title, seeders, leechers), logger.DEBUG)
continue
torrent_size = cells[labels.index('Size')].get_text(strip=True)
size = convert_size(torrent_size, units=units) or -1
item = {'title': title, 'link': download_url, 'size': size, 'seeders': seeders, 'leechers': leechers, 'hash': ''}
if mode != 'RSS':
logger.log("Found result: {0} with {1} seeders and {2} leechers".format
(title, seeders, leechers), logger.DEBUG)
items.append(item)
except StandardError:
continue
# For each search mode sort all the items by seeders if available
items.sort(key=lambda d: try_int(d.get('seeders', 0)), reverse=True)
results += items
return results
def search(self, search_strings, age=0, ep_obj=None): # pylint: disable=too-many-locals, too-many-branches, too-many-statements
results = []
"""
205 = SD, 208 = HD, 200 = All Videos
https://pirateproxy.pl/s/?q=Game of Thrones&type=search&orderby=7&page=0&category=200
"""
# oder_by is 7 in browse for seeders, but 8 in search!
search_params = {
"q": "",
"type": "search",
"orderby": 8,
"page": 0,
"category": 200
}
# Units
units = ["B", "KIB", "MIB", "GIB"]
def process_column_header(th):
text = ""
if th.a:
text = th.a.get_text(strip=True)
if not text:
text = th.get_text(strip=True)
return text
for mode in search_strings:
items = []
logger.log("Search Mode: {0}".format(mode), logger.DEBUG)
for search_string in search_strings[mode]:
search_urls = (self.urls["search"],
self.urls["rss"])[mode == "RSS"]
if not isinstance(search_urls, list):
search_urls = [search_urls]
for search_url in search_urls:
if self.custom_url:
if not validators.url(self.custom_url):
logger.log(
"Invalid custom url: {0}".format(
self.custom_url), logger.WARNING)
return results
search_url = urljoin(self.custom_url,
search_url.split(self.url)[1])
if mode != "RSS":
search_params["q"] = search_string
logger.log(
"Search string: {}".format(
search_string.decode("utf-8")), logger.DEBUG)
# Prevents a 302 redirect, since there is always a 301 from .se to the best mirror having an extra
# redirect is excessive on the provider and spams the debug log unnecessarily
search_url, params = self.convert_url(
search_url, search_params)
data = self.get_url(search_url,
params=params,
returns="text")
else:
data = self.get_url(search_url, returns="text")
if not data:
logger.log(
"URL did not return data, maybe try a custom url, or a different one",
logger.DEBUG)
continue
with BS4Parser(data, "html5lib") as html:
torrent_table = html.find("table", id="searchResult")
torrent_rows = torrent_table(
"tr") if torrent_table else []
# Continue only if at least one Release is found
if len(torrent_rows) < 2:
logger.log(
"Data returned from provider does not contain any torrents",
logger.DEBUG)
continue
labels = [
process_column_header(label)
for label in torrent_rows[0]("th")
]
# Skip column headers
for result in torrent_rows[1:]:
try:
cells = result("td")
# Funky js on page messing up titles, this fixes that
title = result.find(
class_="detLink")['title'].split(
'Details for ', 1)[-1]
download_url = result.find(
title="Download this torrent using magnet"
)["href"] + self._custom_trackers
if not self.magnet_regex.match(download_url):
logger.log(
"Got an invalid magnet: {0}".format(
download_url))
logger.log(
"Invalid ThePirateBay proxy please try another one",
logger.DEBUG)
continue
if not all([title, download_url]):
continue
seeders = try_int(
cells[labels.index("SE")].get_text(
strip=True))
leechers = try_int(
cells[labels.index("LE")].get_text(
strip=True))
# Filter unseeded torrent
if seeders < self.minseed or leechers < self.minleech:
if mode != "RSS":
logger.log(
"Discarding torrent because it doesn't meet the minimum seeders or leechers: {0} (S:{1} L:{2})"
.format(title, seeders,
leechers), logger.DEBUG)
continue
# Accept Torrent only from Good People for every Episode Search
if self.confirmed and not result.find(
alt=re.compile(r"VIP|Trusted")):
if mode != "RSS":
logger.log(
"Found result: {0} but that doesn't seem like a trusted result so I'm ignoring it"
.format(title), logger.DEBUG)
continue
# Convert size after all possible skip scenarios
torrent_size = re.sub(
r".*Size ([\d.]+).+([KMGT]iB).*", r"\1 \2",
result.find(class_="detDesc").get_text(
strip=True))
size = convert_size(torrent_size,
units=units) or -1
item = {
'title': title,
'link': download_url,
'size': size,
'seeders': seeders,
'leechers': leechers,
'hash': ''
}
if mode != "RSS":
logger.log(
"Found result: {0} with {1} seeders and {2} leechers"
.format(title, seeders,
leechers), logger.DEBUG)
items.append(item)
except StandardError:
continue
# For each search mode sort all the items by seeders if available
items.sort(key=lambda d: try_int(d.get('seeders', 0)),
reverse=True)
results += items
return results
def _search_provider(self, search_params, **kwargs):
results = []
if not self._authorised():
return results
items = {'Cache': [], 'Season': [], 'Episode': [], 'Propers': []}
rc = dict((k, re.compile('(?i)' + v)) for (k, v) in {
'info': 'detail',
'get': 'download'
}.items())
for mode in search_params.keys():
for search_string in search_params[mode]:
search_string = isinstance(
search_string,
unicode) and unidecode(search_string) or search_string
# URL with 50 tv-show results, or max 150 if adjusted in IPTorrents profile
search_url = self.urls['search'] % (
self._categories_string(mode, '%s', ';'), search_string,
(';free', '')[not self.freeleech],
(';o=seeders', '')['Cache' == mode])
html = self.get_url(search_url)
if self.should_skip():
return results
cnt = len(items[mode])
try:
if not html or self._has_no_results(html):
raise generic.HaltParseException
with BS4Parser(html, features=['html5lib',
'permissive']) as soup:
torrent_table = soup.find(id='torrents') or soup.find(
'table', class_='torrents')
torrent_rows = [] if not torrent_table else torrent_table.find_all(
'tr')
if 2 > len(torrent_rows):
raise generic.HaltParseException
head = None
for tr in torrent_rows[1:]:
cells = tr.find_all('td')
if 5 > len(cells):
continue
try:
head = head if None is not head else self._header_row(
tr,
header_strip=
'(?i)(?:leechers|seeders|size);')
seeders, leechers = [
tryInt(
tr.find('td', class_='t_' +
x).get_text().strip())
for x in 'seeders', 'leechers'
]
if self._reject_item(seeders, leechers):
continue
info = tr.find('a', href=rc['info'])
title = (info.attrs.get('title')
or info.get_text()).strip()
size = cells[head['size']].get_text().strip()
download_url = self._link(
tr.find('a', href=rc['get'])['href'])
except (AttributeError, TypeError, ValueError):
continue
if title and download_url:
items[mode].append(
(title, download_url, seeders,
self._bytesizer(size)))
except generic.HaltParseException:
pass
except (StandardError, Exception):
logger.log(
u'Failed to parse. Traceback: %s' %
traceback.format_exc(), logger.ERROR)
self._log_search(mode, len(items[mode]) - cnt, search_url)
results = self._sort_seeding(mode, results + items[mode])
return results
def search(self, search_params, age=0, ep_obj=None):
results = []
items = {'Season': [], 'Episode': [], 'RSS': []}
freeleech = '3' if self.freeleech else '0'
if not self.login():
return results
for mode in search_params.keys():
logger.log(u"Search Mode: %s" % mode, logger.DEBUG)
for search_string in search_params[mode]:
if mode != 'RSS':
logger.log(u"Search string: %s " % search_string,
logger.DEBUG)
searchURL = self.urls['search'] % (freeleech, search_string)
logger.log(u"Search URL: %s" % searchURL, logger.DEBUG)
init_html = self.get_url(searchURL)
max_page_number = 0
if not init_html:
logger.log(u"No data returned from provider", logger.DEBUG)
continue
try:
with BS4Parser(init_html, 'html5lib') as init_soup:
# Check to see if there is more than 1 page of results
pager = init_soup.find('div', {'class': 'pager'})
if pager:
page_links = pager.find_all('a', href=True)
else:
page_links = []
if len(page_links) > 0:
for lnk in page_links:
link_text = lnk.text.strip()
if link_text.isdigit():
page_int = int(link_text)
if page_int > max_page_number:
max_page_number = page_int
# limit page number to 15 just in case something goes wrong
if max_page_number > 15:
max_page_number = 15
# limit RSS search
if max_page_number > 3 and mode == 'RSS':
max_page_number = 3
except Exception:
logger.log(
u"Failed parsing provider. Traceback: %s" %
traceback.format_exc(), logger.ERROR)
continue
data_response_list = [init_html]
# Freshon starts counting pages from zero, even though it displays numbers from 1
if max_page_number > 1:
for i in range(1, max_page_number):
time.sleep(1)
page_searchURL = searchURL + '&page=' + str(i)
# '.log(u"Search string: " + page_searchURL, logger.DEBUG)
page_html = self.get_url(page_searchURL)
if not page_html:
continue
data_response_list.append(page_html)
try:
for data_response in data_response_list:
with BS4Parser(data_response, 'html5lib') as html:
torrent_rows = html.findAll(
"tr", {"class": re.compile('torrent_[0-9]*')})
# Continue only if a Release is found
if len(torrent_rows) == 0:
logger.log(
u"Data returned from provider does not contain any torrents",
logger.DEBUG)
continue
for individual_torrent in torrent_rows:
# skip if torrent has been nuked due to poor quality
if individual_torrent.find(
'img', alt='Nuked') is not None:
continue
try:
title = individual_torrent.find(
'a', {'class': 'torrent_name_link'
})['title']
except Exception:
logger.log(
u"Unable to parse torrent title. Traceback: %s "
% traceback.format_exc(),
logger.WARNING)
continue
try:
details_url = individual_torrent.find(
'a',
{'class': 'torrent_name_link'})['href']
torrent_id = int((re.match(
'.*?([0-9]+)$',
details_url).group(1)).strip())
download_url = self.urls['download'] % (
str(torrent_id))
seeders = try_int(
individual_torrent.find(
'td', {
'class': 'table_seeders'
}).find('span').text.strip(), 1)
leechers = try_int(
individual_torrent.find(
'td', {
'class': 'table_leechers'
}).find('a').text.strip(), 0)
# FIXME
size = -1
except Exception:
continue
if not all([title, download_url]):
continue
# Filter unseeded torrent
if seeders < self.minseed or leechers < self.minleech:
if mode != 'RSS':
logger.log(
u"Discarding torrent because it doesn't meet the minimum seeders or leechers: {0} (S:{1} L:{2})"
.format(title, seeders,
leechers), logger.DEBUG)
continue
item = title, download_url, size, seeders, leechers
if mode != 'RSS':
logger.log(u"Found result: %s " % title,
logger.DEBUG)
items[mode].append(item)
except Exception:
logger.log(
u"Failed parsing provider. Traceback: %s" %
traceback.format_exc(), logger.ERROR)
# For each search mode sort all the items by seeders if available
items[mode].sort(key=lambda tup: tup[3], reverse=True)
results += items[mode]
return results
def search(self, search_params, age=0, ep_obj=None): # pylint: disable=too-many-locals, too-many-branches, too-many-statements
results = []
if not self.login():
return results
freeleech = '&free=on' if self.freeleech else ''
for mode in search_params:
items = []
logger.log(u"Search Mode: {0}".format(mode), logger.DEBUG)
for search_string in search_params[mode]:
if mode != 'RSS':
logger.log(
u"Search string: {0}".format(
search_string.decode("utf-8")), logger.DEBUG)
# URL with 50 tv-show results, or max 150 if adjusted in IPTorrents profile
search_url = self.urls['search'] % (self.categories, freeleech,
search_string)
search_url += ';o=seeders' if mode != 'RSS' else ''
if self.custom_url:
if not validators.url(self.custom_url):
logger.log(
"Invalid custom url: {0}".format(self.custom_url),
logger.WARNING)
return results
search_url = urljoin(self.custom_url,
search_url.split(self.url)[1])
data = self.get_url(search_url, returns='text')
if not data:
continue
try:
data = re.sub(r'(?im)<button.+?</button>', '', data, 0)
with BS4Parser(data, 'html5lib') as html:
if not html:
logger.log(u"No data returned from provider",
logger.DEBUG)
continue
if html.find(text='No Torrents Found!'):
logger.log(
u"Data returned from provider does not contain any torrents",
logger.DEBUG)
continue
torrent_table = html.find('table', id='torrents')
torrents = torrent_table('tr') if torrent_table else []
# Continue only if one Release is found
if len(torrents) < 2:
logger.log(
u"Data returned from provider does not contain any torrents",
logger.DEBUG)
continue
for result in torrents[1:]:
try:
title = result('td')[1].find('a').text
download_url = urljoin(
search_url,
result('td')[3].find('a')['href'])
seeders = int(
result.find('td',
class_='ac t_seeders').text)
leechers = int(
result.find('td',
class_='ac t_leechers').text)
torrent_size = result('td')[5].text
size = convert_size(torrent_size) or -1
except (AttributeError, TypeError, KeyError):
continue
if not all([title, download_url]):
continue
# Filter unseeded torrent
if seeders < self.minseed or leechers < self.minleech:
if mode != 'RSS':
logger.log(
u"Discarding torrent because it doesn't meet the minimum seeders or leechers: {0} (S:{1} L:{2})"
.format(title, seeders,
leechers), logger.DEBUG)
continue
item = {
'title': title,
'link': download_url,
'size': size,
'seeders': seeders,
'leechers': leechers,
'hash': ''
}
if mode != 'RSS':
logger.log(
u"Found result: {0} with {1} seeders and {2} leechers"
.format(title, seeders,
leechers), logger.DEBUG)
items.append(item)
except Exception as e:
logger.log(
u"Failed parsing provider. Error: {0!r}".format(ex(e)),
logger.ERROR)
# For each search mode sort all the items by seeders if available
items.sort(key=lambda d: try_int(d.get('seeders', 0)),
reverse=True)
results += items
return results
def search(self, search_params, age=0, ep_obj=None): # pylint: disable=too-many-locals, too-many-branches, too-many-statements
results = []
for mode in search_params:
items = []
logger.log(u'Search Mode: {0}'.format(mode), logger.DEBUG)
for search_string in search_params[mode]:
self.page = 1
last_page = 0
y = int(self.page)
if search_string == '':
continue
search_string = str(search_string).replace('.', ' ')
for x in range(0, y):
if last_page:
break
search_url = self.urls['search_page'].format(
search_string, x)
logger.log(
u'Search string: {0}'.format(
search_string.decode('utf-8')), logger.DEBUG)
data = self.get_url(search_url, returns='text')
if not data:
logger.log(u'No data returned from provider',
logger.DEBUG)
continue
try:
with BS4Parser(data, 'html5lib') as html:
table_header = html.find('tr', class_='bordo')
torrent_table = table_header.find_parent(
'table') if table_header else None
if not torrent_table:
logger.log(u'Could not find table of torrents',
logger.ERROR)
continue
torrent_rows = torrent_table('tr')
# Continue only if one Release is found
if (len(torrent_rows) < 6) or (len(
torrent_rows[2]('td')) == 1):
logger.log(
u'Data returned from provider does not contain any torrents',
logger.DEBUG)
last_page = 1
continue
if len(torrent_rows) < 45:
last_page = 1
for result in torrent_rows[2:-3]:
try:
link = result('td')[1].find('a')['href']
title = re.sub(
' +', ' ',
link.rsplit('/',
1)[-1].replace('_', ' '))
hash = result('td')[3].find(
'input',
class_='downarrow')['value'].upper()
seeders = try_int(result('td')[5].text)
leechers = try_int(result('td')[6].text)
torrent_size = result('td')[2].string
size = convert_size(torrent_size) or -1
# Download Urls
download_url = self.urls['download'] % hash
if urllib.urlopen(
download_url).getcode() == 404:
logger.log(
u'Torrent hash not found in itorrents.org, searching for magnet',
logger.DEBUG)
data_detail = self.get_url(
link, returns='text')
with BS4Parser(
data_detail,
'html5lib') as html_detail:
sources_row = html_detail.find(
'td', class_='header2').parent
source_magnet = sources_row(
'td')[1].find('a',
class_='forbtn',
title='Magnet')
if source_magnet and not source_magnet == 'None':
download_url = source_magnet[
'href']
else:
continue
except (AttributeError, TypeError):
continue
filename_qt = self._reverseQuality(
self._episodeQuality(result))
for text in self.hdtext:
title1 = title
title = title.replace(text, filename_qt)
if title != title1:
break
if Quality.nameQuality(
title) == Quality.UNKNOWN:
title += filename_qt
if not self._is_italian(
title) and not self.subtitle:
logger.log(
u'Torrent is subtitled, skipping: {0} '
.format(title), logger.DEBUG)
continue
if self.engrelease and not self._is_english(
title):
logger.log(
u'Torrent isnt english audio/subtitled , skipping: {0} '
.format(title), logger.DEBUG)
continue
search_show = re.split(r'([Ss][\d{1,2}]+)',
search_string)[0]
show_title = search_show
ep_params = ''
rindex = re.search(r'([Ss][\d{1,2}]+)', title)
if rindex:
show_title = title[:rindex.start()]
ep_params = title[rindex.start():]
if show_title.lower() != search_show.lower(
) and search_show.lower() in show_title.lower(
):
new_title = search_show + ep_params
title = new_title
if not all([title, download_url]):
continue
if self._is_season_pack(title):
title = re.sub(r'([Ee][\d{1,2}\-?]+)', '',
title)
# Filter unseeded torrent
if seeders < self.minseed or leechers < self.minleech:
logger.log(
u'Discarding torrent because it doesn\'t meet the minimum seeders or leechers: {0} (S:{1} L:{2})'
.format(title, seeders,
leechers), logger.DEBUG)
continue
item = {
'title': title,
'link': download_url,
'size': size,
'seeders': seeders,
'leechers': leechers,
'hash': ''
}
if mode != 'RSS':
logger.log(
u'Found result: {0} with {1} seeders and {2} leechers'
.format(title, seeders,
leechers), logger.DEBUG)
items.append(item)
except Exception:
logger.log(
u'Failed parsing provider. Traceback: {0}'.format(
traceback.format_exc()), logger.ERROR)
# For each search mode sort all the items by seeders if available
items.sort(key=lambda d: try_int(d.get('seeders', 0)),
reverse=True)
results += items
return results
def _search_provider(self, search_params, **kwargs):
results = []
if not self.url:
return results
items = {'Cache': [], 'Season': [], 'Episode': [], 'Propers': []}
rc = dict((k, re.compile('(?i)' + v)) for (k, v) in {
'info': r'torrent.?(\d+)',
'versrc': r'ver\.',
'verified': 'Verified'
}.iteritems())
for mode in search_params.keys():
for search_string in search_params[mode]:
search_string = isinstance(
search_string,
unicode) and unidecode(search_string) or search_string
search_url = self.urls['browse'] if 'Cache' == mode \
else self.urls['search'] % (urllib.quote_plus(search_string).replace('+', '-'))
html = self.get_url(search_url)
if self.should_skip():
return results
cnt = len(items[mode])
try:
if not html or self._has_no_results(html):
raise generic.HaltParseException
with BS4Parser(html.replace('thead', 'tr')) as soup:
tbl = soup.find(
'div',
class_=('panel panel-default',
'table-responsive')['Cache' == mode])
if None is tbl:
raise generic.HaltParseException
tbl = tbl.find(
'table',
class_=
'table table-striped table-bordered table-hover table-condensed'
)
tbl_rows = [] if not tbl else tbl.find_all('tr')
if 2 > len(tbl_rows):
raise generic.HaltParseException
head = None
for tr in tbl_rows[1:]:
cells = tr.find_all('td')
if 5 > len(cells):
continue
try:
head = head if None is not head else self._header_row(
tr)
seeders, leechers, size = [
tryInt(n, n) for n in [
cells[head[x]].get_text().strip()
for x in 'seed', 'leech', 'size'
]
]
if self._reject_item(
seeders,
leechers,
verified=self.confirmed and not (
tr.find('img', src=rc['versrc'])
or tr.find('img',
title=rc['verified']))):
continue
info = tr.find('a', href=rc['info']) or {}
title = info and info.get_text().strip()
tid_href = info and tryInt(rc['info'].findall(
info['href'])[0])
download_url = tid_href and self._link(
tid_href)
except (AttributeError, TypeError, ValueError,
IndexError):
continue
if title and download_url:
items[mode].append(
(title, download_url, seeders,
self._bytesizer(size)))
def _doSearch(self,
search_strings,
search_mode='eponly',
epcount=0,
age=0,
epObj=None):
results = []
items = {'Season': [], 'Episode': [], 'RSS': []}
if not self._doLogin():
return results
for mode in search_strings.keys():
logger.log(u"Search Mode: %s" % mode, logger.DEBUG)
for search_string in search_strings[mode]:
if mode != 'RSS':
logger.log(u"Search string: %s " % search_string,
logger.DEBUG)
self.search_params['searchstr'] = search_string
data = self.getURL(self.urls['search'],
params=self.search_params)
strTableStart = "<table class=\"torrent_table"
startTableIndex = data.find(strTableStart)
trimmedData = data[startTableIndex:]
if not trimmedData:
continue
try:
with BS4Parser(trimmedData,
features=["html5lib",
"permissive"]) as html:
result_table = html.find('table',
{'id': 'torrent_table'})
if not result_table:
logger.log(
u"Data returned from provider does not contain any torrents",
logger.DEBUG)
continue
result_tbody = result_table.find('tbody')
entries = result_tbody.contents
del entries[1::2]
for result in entries[1:]:
torrent = result.find_all('td')
if len(torrent) <= 1:
break
allAs = (torrent[1]).find_all('a')
try:
link = self.urls['base_url'] + allAs[2].attrs[
'href']
#url = result.find('td', attrs={'class': 'quickdownload'}).find('a')
title = allAs[2].string
#Trimming title so accepted by scene check(Feature has been rewuestet i forum)
title = title.replace("custom.", "")
title = title.replace("CUSTOM.", "")
title = title.replace("Custom.", "")
title = title.replace("dk", "")
title = title.replace("DK", "")
title = title.replace("Dk", "")
title = title.replace("subs.", "")
title = title.replace("SUBS.", "")
title = title.replace("Subs.", "")
download_url = self.urls['base_url'] + allAs[
0].attrs['href']
id = link.replace(
self.urls['base_url'] + 'torrents.php?id=',
'')
#FIXME
size = -1
seeders = 1
leechers = 0
except (AttributeError, TypeError):
continue
if not title or not download_url:
continue
#Filter unseeded torrent
#if seeders < self.minseed or leechers < self.minleech:
# if mode != 'RSS':
# logger.log(u"Discarding torrent because it doesn't meet the minimum seeders or leechers: {0} (S:{1} L:{2})".format(title, seeders, leechers), logger.DEBUG)
# continue
item = title, download_url, size, seeders, leechers
if mode != 'RSS':
logger.log(u"Found result: %s " % title,
logger.DEBUG)
items[mode].append(item)
except Exception, e:
logger.log(
u"Failed parsing provider. Traceback: %s" %
traceback.format_exc(), logger.ERROR)
#For each search mode sort all the items by seeders if available
items[mode].sort(key=lambda tup: tup[3], reverse=True)
results += items[mode]
def search(self, search_params, age=0, ep_obj=None): # pylint: disable=too-many-locals, too-many-branches, too-many-statements
results = []
if not self.login():
return results
self.categories = "cat=" + str(self.cat)
for mode in search_params:
items = []
logger.log("Search Mode: {0}".format(mode), logger.DEBUG)
for search_string in search_params[mode]:
if mode == 'RSS':
self.page = 2
last_page = 0
y = int(self.page)
if search_string == '':
continue
search_string = str(search_string).replace('.', ' ')
for x in range(0, y):
z = x * 20
if last_page:
break
if mode != 'RSS':
search_url = (self.urls['search_page'] + '&filter={2}').format(z, self.categories, search_string)
else:
search_url = self.urls['search_page'].format(z, self.categories)
if mode != 'RSS':
logger.log("Search string: {0}".format
(search_string.decode("utf-8")), logger.DEBUG)
data = self.get_url(search_url, returns='text')
if not data:
logger.log("No data returned from provider", logger.DEBUG)
continue
try:
with BS4Parser(data, 'html5lib') as html:
torrent_table = html.find('table', class_='copyright')
torrent_rows = torrent_table('tr') if torrent_table else []
# Continue only if one Release is found
if len(torrent_rows) < 3:
logger.log("Data returned from provider does not contain any torrents", logger.DEBUG)
last_page = 1
continue
if len(torrent_rows) < 42:
last_page = 1
for result in torrent_table('tr')[2:]:
try:
link = result.find('td').find('a')
title = link.string
download_url = self.urls['download'] % result('td')[8].find('a')['href'][-8:]
leechers = result('td')[3]('td')[0].text
leechers = int(leechers.strip('[]'))
seeders = result('td')[3]('td')[1].text
seeders = int(seeders.strip('[]'))
torrent_size = result('td')[3]('td')[3].text.strip('[]') + " GB"
size = convert_size(torrent_size) or -1
except (AttributeError, TypeError):
continue
filename_qt = self._reverseQuality(self._episodeQuality(result))
for text in self.hdtext:
title1 = title
title = title.replace(text, filename_qt)
if title != title1:
break
if Quality.nameQuality(title) == Quality.UNKNOWN:
title += filename_qt
if not self._is_italian(result) and not self.subtitle:
logger.log("Torrent is subtitled, skipping: {0} ".format(title), logger.DEBUG)
continue
if self.engrelease and not self._is_english(result):
logger.log("Torrent isnt english audio/subtitled , skipping: {0} ".format(title), logger.DEBUG)
continue
search_show = re.split(r'([Ss][\d{1,2}]+)', search_string)[0]
show_title = search_show
rindex = re.search(r'([Ss][\d{1,2}]+)', title)
if rindex:
show_title = title[:rindex.start()]
ep_params = title[rindex.start():]
if show_title.lower() != search_show.lower() and search_show.lower() in show_title.lower():
new_title = search_show + ep_params
title = new_title
if not all([title, download_url]):
continue
if self._is_season_pack(title):
title = re.sub(r'([Ee][\d{1,2}\-?]+)', '', title)
# Filter unseeded torrent
if seeders < self.minseed or leechers < self.minleech:
if mode != 'RSS':
logger.log("Discarding torrent because it doesn't meet the minimum seeders or leechers: {0} (S:{1} L:{2})".format
(title, seeders, leechers), logger.DEBUG)
continue
item = {'title': title, 'link': download_url, 'size': size, 'seeders': seeders, 'leechers': leechers, 'hash': ''}
if mode != 'RSS':
logger.log("Found result: {0} with {1} seeders and {2} leechers".format(title, seeders, leechers), logger.DEBUG)
items.append(item)
except Exception:
logger.log("Failed parsing provider. Traceback: {0}".format(traceback.format_exc()), logger.ERROR)
# For each search mode sort all the items by seeders if available if available
items.sort(key=lambda d: try_int(d.get('seeders', 0)), reverse=True)
results += items
return results
def search(self, search_strings, age=0, ep_obj=None): # pylint: disable=too-many-locals, too-many-branches
results = []
lang_info = '' if not ep_obj or not ep_obj.show else ep_obj.show.lang
"""
Search query:
http://www.elitetorrent.net/torrents.php?cat=4&modo=listado&orden=fecha&pag=1&buscar=fringe
cat = 4 => Shows
modo = listado => display results mode
orden = fecha => order
buscar => Search show
pag = 1 => page number
"""
search_params = {
'cat': 4,
'modo': 'listado',
'orden': 'fecha',
'pag': 1,
'buscar': ''
}
for mode in search_strings:
items = []
logger.log(u"Search Mode: {0}".format(mode), logger.DEBUG)
# Only search if user conditions are true
if self.onlyspasearch and lang_info != 'es' and mode != 'RSS':
logger.log(u"Show info is not spanish, skipping provider search", logger.DEBUG)
continue
for search_string in search_strings[mode]:
if mode != 'RSS':
logger.log(u"Search string: {0}".format
(search_string.decode("utf-8")), logger.DEBUG)
search_string = re.sub(r'S0*(\d*)E(\d*)', r'\1x\2', search_string)
search_params['buscar'] = search_string.strip() if mode != 'RSS' else ''
time.sleep(cpu_presets[sickbeard.CPU_PRESET])
data = self.get_url(self.urls['search'], params=search_params, returns='text')
if not data:
continue
try:
with BS4Parser(data, 'html5lib') as html:
torrent_table = html.find('table', class_='fichas-listado')
torrent_rows = torrent_table('tr') if torrent_table else []
if len(torrent_rows) < 2:
logger.log(u"Data returned from provider does not contain any torrents", logger.DEBUG)
continue
for row in torrent_rows[1:]:
try:
download_url = self.urls['base_url'] + row.find('a')['href']
title = self._processTitle(row.find('a', class_='nombre')['title'])
seeders = try_int(row.find('td', class_='semillas').get_text(strip=True))
leechers = try_int(row.find('td', class_='clientes').get_text(strip=True))
# Provider does not provide size
size = -1
except (AttributeError, TypeError, KeyError, ValueError):
continue
if not all([title, download_url]):
continue
# Filter unseeded torrent
if seeders < self.minseed or leechers < self.minleech:
if mode != 'RSS':
logger.log(u"Discarding torrent because it doesn't meet the minimum seeders or leechers: {0} (S:{1} L:{2})".format
(title, seeders, leechers), logger.DEBUG)
continue
item = {'title': title, 'link': download_url, 'size': size, 'seeders': seeders, 'leechers': leechers, 'hash': ''}
if mode != 'RSS':
logger.log(u"Found result: {0} with {1} seeders and {2} leechers".format(title, seeders, leechers), logger.DEBUG)
items.append(item)
except Exception:
logger.log(u"Failed parsing provider. Traceback: {0}".format(traceback.format_exc()), logger.WARNING)
# For each search mode sort all the items by seeders if available
items.sort(key=lambda d: try_int(d.get('seeders', 0)), reverse=True)
results += items
return results
def _doSearch(self, search_params, search_mode='eponly', epcount=0, age=0):
results = []
items = {'Season': [], 'Episode': [], 'RSS': []}
for mode in search_params.keys():
for search_string in search_params[mode]:
for url in self.urls:
if mode != 'RSS':
searchURL = url + 'usearch/%s/?field=seeders&sorder=desc' % (
urllib.quote(unidecode(search_string)))
logger.log(u"Search string: " + searchURL,
logger.DEBUG)
else:
searchURL = url + 'tv/?field=time_add&sorder=desc'
logger.log(u"KAT cache update URL: " + searchURL,
logger.DEBUG)
html = self.getURL(searchURL)
if html:
self.url = url
break
if not html:
continue
try:
with BS4Parser(html, features=["html5lib",
"permissive"]) as soup:
torrent_table = soup.find('table',
attrs={'class': 'data'})
torrent_rows = torrent_table.find_all(
'tr') if torrent_table else []
#Continue only if one Release is found
if len(torrent_rows) < 2:
logger.log(
u"The data returned from " + self.name +
" does not contain any torrents",
logger.WARNING)
continue
for tr in torrent_rows[1:]:
try:
link = urlparse.urljoin(
self.url, (tr.find('div', {
'class': 'torrentname'
}).find_all('a')[1])['href'])
id = tr.get('id')[-7:]
title = (tr.find('div', {'class': 'torrentname'}).find_all('a')[1]).text \
or (tr.find('div', {'class': 'torrentname'}).find_all('a')[2]).text
url = tr.find('a', 'imagnet')['href']
verified = True if tr.find(
'a', 'iverify') else False
trusted = True if tr.find(
'img', {'alt': 'verified'}) else False
seeders = int(tr.find_all('td')[-2].text)
leechers = int(tr.find_all('td')[-1].text)
except (AttributeError, TypeError):
continue
if mode != 'RSS' and (seeders < self.minseed
or leechers < self.minleech):
continue
if self.confirmed and not verified:
logger.log(
u"KAT Provider found result " + title +
" but that doesn't seem like a verified result so I'm ignoring it",
logger.DEBUG)
continue
#Check number video files = episode in season and find the real Quality for full season torrent analyzing files in torrent
if mode == 'Season' and search_mode == 'sponly':
ep_number = int(
epcount /
len(set(allPossibleShowNames(self.show))))
title = self._find_season_quality(
title, link, ep_number)
if not title or not url:
continue
item = title, url, id, seeders, leechers
items[mode].append(item)
except Exception, e:
logger.log(
u"Failed to parsing " + self.name + " Traceback: " +
traceback.format_exc(), logger.ERROR)
#For each search mode sort all the items by seeders
items[mode].sort(key=lambda tup: tup[3], reverse=True)
results += items[mode]
def _doSearch(self,
search_params,
search_mode='eponly',
epcount=0,
age=0,
epObj=None):
results = data = []
if not self._doLogin():
return results
for search_string in [search_params]:
if isinstance(search_string, unicode):
search_string = unidecode(search_string)
searchURLS = []
if search_mode == 'sponly':
searchURLS += [
self.urls['archive'] % (urllib.quote(search_string))
]
else:
searchURLS += [
self.urls['search'] %
(urllib.quote(search_string), self.categories)
]
searchURLS += [
self.urls['nonscene'] % (urllib.quote(search_string))
]
searchURLS += [
self.urls['foreign'] % (urllib.quote(search_string))
]
for searchURL in searchURLS:
logger.log(u"Search string: " + searchURL, logger.DEBUG)
try:
data = self.getURL(searchURL)
time.sleep(cpu_presets[sickbeard.CPU_PRESET])
except Exception as e:
logger.log(
u"Unable to fetch data reason: {0}".format(str(e)),
logger.WARNING)
if not data:
continue
with BS4Parser(data, features=["html5lib",
"permissive"]) as html:
torrent_table = html.find('table',
attrs={'id': 'torrents-table'})
torrent_rows = torrent_table.find_all(
'tr') if torrent_table else []
#Continue only if at least one Release is found
if len(torrent_rows) < 2:
info = u'The Data returned from %s does not contain any torrent' % self.name
if html.title:
info += ' (%s)' % html.title
logger.log(info, logger.DEBUG)
continue
for result in torrent_table.find_all('tr')[1:]:
try:
link = result.find('td',
attrs={
'class': 'ttr_name'
}).find('a')
all_urls = result.find('td',
attrs={
'class': 'td_dl'
}).find_all('a', limit=2)
# Foreign section contain two links, the others one
if self._isSection('Foreign', data):
url = all_urls[1]
else:
url = all_urls[0]
title = link.string
if re.search('\.\.\.', title):
data = self.getURL(self.url + "/" +
link['href'])
if data:
with BS4Parser(data) as details_html:
title = re.search(
'(?<=").+(?<!")',
details_html.title.string).group(0)
download_url = self.urls['download'] % url['href']
id = int(link['href'].replace('details?id=', ''))
seeders = int(
result.find('td',
attrs={
'class': 'ttr_seeders'
}).string)
leechers = int(
result.find('td',
attrs={
'class': 'ttr_leechers'
}).string)
except (AttributeError, TypeError):
continue
if not title or not download_url or seeders < self.minseed or leechers < self.minleech:
continue
item = title, download_url, id, seeders, leechers
logger.log(
u"Found result: " + title.replace(' ', '.') +
" (" + searchURL + ")", logger.DEBUG)
results.append(item)
results.sort(key=lambda tup: tup[3], reverse=True)
return results
def _search_provider(self, search_params, **kwargs):
results = []
if not self._authorised():
return results
items = {'Cache': [], 'Season': [], 'Episode': [], 'Propers': []}
rc = dict((k, re.compile('(?i)' + v)) for (k, v) in {
'info': 'torrents',
'get': '(.*?download)_check(.*)'
}.items())
log = ''
if self.filter:
non_marked = 'f0' in self.filter
# if search_any, use unselected to exclude, else use selected to keep
filters = ([f for f in self.may_filter if f in self.filter],
[f for f in self.may_filter
if f not in self.filter])[non_marked]
filters += (
((all([x in filters for x in 'free', 'double', 'feat'])
and ['freedoublefeat'] or []) +
(all([x in filters
for x in 'free', 'double']) and ['freedouble'] or []) +
(all([x in filters
for x in 'feat', 'double']) and ['featdouble'] or [])),
((not all([x not in filters for x in 'free', 'double', 'feat'])
and ['freedoublefeat'] or []) +
(not all([x not in filters
for x in 'free', 'double']) and ['freedouble']
or []) +
(not all([x not in filters
for x in 'feat', 'double']) and ['featdouble']
or [])))[non_marked]
rc['filter'] = re.compile('(?i)^(%s)$' % '|'.join([
'%s' % f for f in filters
if (f in self.may_filter and self.may_filter[f][1]) or f
]))
log = '%sing (%s) ' % (('keep', 'skipp')[non_marked], ', '.join([
f in self.may_filter and self.may_filter[f][0] or f
for f in filters
]))
for mode in search_params.keys():
if mode in ['Season', 'Episode']:
show_type = self.show.air_by_date and 'Air By Date' \
or self.show.is_sports and 'Sports' or None
if show_type:
logger.log(
u'Provider does not carry shows of type: [%s], skipping'
% show_type, logger.DEBUG)
return results
for search_string in search_params[mode]:
search_string = isinstance(
search_string,
unicode) and unidecode(search_string) or search_string
search_url = self.urls['search'] % (self.token, '+'.join(
search_string.split()), self._categories_string(
mode, ''), '', '', '')
resp = self.get_url(search_url, json=True)
if self.should_skip():
return results
cnt = len(items[mode])
try:
if not resp or not resp.get('rows'):
raise generic.HaltParseException
html = '<html><body>%s</body></html>' % \
self.resp.replace('</tbody>', '%s</tbody>' % ''.join(resp.get('result', [])))
with BS4Parser(html, features=['html5lib',
'permissive']) as soup:
torrent_table = soup.find('table', class_='table')
torrent_rows = [] if not torrent_table else torrent_table.find_all(
'tr')
if 2 > len(torrent_rows):
raise generic.HaltParseException
head = None
for tr in torrent_rows[1:]:
cells = tr.find_all('td')
if 5 > len(cells):
continue
if any(self.filter):
marked = ','.join([
x.attrs.get('data-original-title',
'').lower()
for x in tr.find_all(
'i',
attrs={
'class': [
'text-gold', 'fa-diamond',
'fa-certificate'
]
})
])
# noinspection PyTypeChecker
munged = ''.join(
filter(marked.__contains__,
['free', 'double', 'feat']))
if ((non_marked
and rc['filter'].search(munged)) or
(not non_marked
and not rc['filter'].search(munged))):
continue
try:
head = head if None is not head else self._header_row(
tr, {
'seed': r'circle-up',
'leech': r'circle-down',
'size': r'fa-file'
})
seeders, leechers, size = [
tryInt(n, n) for n in [
cells[head[x]].get_text().strip()
for x in 'seed', 'leech', 'size'
]
]
if self._peers_fail(mode, seeders, leechers):
continue
title = tr.find(
'a',
href=rc['info'])['data-original-title']
download_url = self._link(rc['get'].sub(
r'\1\2',
tr.find('a', href=rc['get'])['href']))
except (AttributeError, TypeError, ValueError,
IndexError):
continue
if title and download_url:
items[mode].append(
(title, download_url, seeders,
self._bytesizer(size)))
def _doSearch(self,
search_params,
search_mode='eponly',
epcount=0,
age=0,
epObj=None):
logger.log(u"_doSearch started with ..." + str(search_params),
logger.DEBUG)
results = []
items = {'Season': [], 'Episode': [], 'RSS': []}
# check for auth
if not self._doLogin():
return False
for mode in search_params.keys():
for search_string in search_params[mode]:
if isinstance(search_string, unicode):
search_string = unidecode(search_string)
searchURL = self.urls['search'] % (urllib.quote(search_string),
self.categories)
logger.log(u"Search string: " + searchURL, logger.DEBUG)
r = self.opener.open(searchURL)
with BS4Parser(r, features=["html5lib", "permissive"]) as html:
resultsTable = html.find("div", {"class": "DataGrid"})
logger.log(u"Page opened", logger.DEBUG)
if resultsTable:
logger.log(u"We have results ", logger.DEBUG)
rows = resultsTable.findAll("ul")
for row in rows:
link = row.find("a", title=True)
title = link['title']
autogetURL = self.url + '/' + (row.find(
"li", {
"class": "torrents_name"
}).find('a')['href'][1:]).replace(
'#FTD_MENU', '&menu=4')
r = self.opener.open(autogetURL, 'wb').read()
with BS4Parser(r,
features=["html5lib",
"permissive"]) as html:
downloadURL = html.find(
"div", {
"class": "autoget"
}).find('a')['href']
item = title, downloadURL
logger.log(u"Download URL : " + downloadURL,
logger.DEBUG)
items[mode].append(item)
results += items[mode]
return results
def search(self, search_strings, age=0, ep_obj=None): # pylint: disable=too-many-locals, too-many-branches, too-many-statements
results = []
if not self.login():
return results
# TV, Episodes, BoxSets, Episodes HD, Animation, Anime, Cartoons
# 2,26,27,32,7,34,35
# Units
units = ["B", "KB", "MB", "GB", "TB", "PB"]
def process_column_header(td):
result = ""
if td.a:
result = td.a.get("title")
if not result:
result = td.get_text(strip=True)
return result
for mode in search_strings:
items = []
logger.log("Search Mode: {}".format(mode), logger.DEBUG)
for search_string in search_strings[mode]:
if mode != "RSS":
logger.log(
"Search string: {}".format(
search_string.decode("utf-8")), logger.DEBUG)
categories = ["2", "7", "35"]
categories += ["26", "32"] if mode == "Episode" else ["27"]
if self.show and self.show.is_anime:
categories += ["34"]
else:
categories = ["2", "26", "27", "32", "7", "34", "35"]
search_params = {
"categories": ",".join(categories),
"query": search_string
}
data = self.get_url(self.urls["search"],
params=search_params,
returns="text")
if not data:
logger.log("No data returned from provider", logger.DEBUG)
continue
with BS4Parser(data, "html5lib") as html:
torrent_table = html.find("table", id="torrenttable")
torrent_rows = torrent_table.find_all(
"tr") if torrent_table else []
# Continue only if at least one Release is found
if len(torrent_rows) < 2:
logger.log(
"Data returned from provider does not contain any torrents",
logger.DEBUG)
continue
labels = [
process_column_header(label)
for label in torrent_rows[0].find_all("th")
]
# Skip column headers
for result in torrent_rows[1:]:
try:
title = result.find(
"td",
class_="name").find("a").get_text(strip=True)
download_url = urljoin(
self.url,
result.find(
"td",
class_="quickdownload").find("a")["href"])
if not all([title, download_url]):
continue
seeders = try_int(
result.find(
"td",
class_="seeders").get_text(strip=True))
leechers = try_int(
result.find(
"td",
class_="leechers").get_text(strip=True))
# Filter unseeded torrent
if seeders < self.minseed or leechers < self.minleech:
if mode != "RSS":
logger.log(
"Discarding torrent because it doesn't meet the"
" minimum seeders or leechers: {} (S:{} L:{})"
.format(title, seeders,
leechers), logger.DEBUG)
continue
torrent_size = result.find_all("td")[labels.index(
"Size")].get_text()
size = convert_size(torrent_size,
units=units) or -1
item = {
'title': title,
'link': download_url,
'size': size,
'seeders': seeders,
'leechers': leechers,
'hash': None
}
if mode != "RSS":
logger.log(
"Found result: {} with {} seeders and {} leechers"
.format(title, seeders,
leechers), logger.DEBUG)
items.append(item)
except StandardError:
continue
# For each search mode sort all the items by seeders if available
items.sort(key=lambda d: try_int(d.get('seeders', 0)),
reverse=True)
results += items
return results
def _doSearch(self, search_params, search_mode='eponly', epcount=0, age=0, epObj=None):
results = []
items = {'Season': [], 'Episode': [], 'RSS': []}
if not self._doLogin():
return results
for mode in search_params.keys():
for search_string in search_params[mode]:
if isinstance(search_string, unicode):
search_string = unidecode(search_string)
searchURL = self.urls['search'] % (search_string, self.catagories)
data = self.getURL(searchURL)
if not data:
continue
try:
with BS4Parser(data, features=["html5lib", "permissive"]) as html:
torrent_table = html.find('table', attrs={'id': 'torrent_table'})
torrent_rows = torrent_table.find_all('tr') if torrent_table else []
#Continue only if one Release is found
if len(torrent_rows) < 2:
logger.log(u"The Data returned from " + self.name + " does not contain any torrents",
logger.DEBUG)
continue
for result in torrent_rows[1:]:
cells = result.find_all('td')
link = result.find('a', attrs = {'dir': 'ltr'})
url = result.find('a', attrs = {'title': 'Download'})
try:
title = link.contents[0]
download_url = self.urls['download'] % (url['href'])
id = link['href'][-6:]
seeders = cells[len(cells)-2].contents[0]
leechers = cells[len(cells)-1].contents[0]
except (AttributeError, TypeError):
continue
#Filter unseeded torrent
if mode != 'RSS' and (seeders < self.minseed or leechers < self.minleech):
continue
if not title or not download_url:
continue
item = title, download_url, id, seeders, leechers
logger.log(u"Found result: " + title + "(" + searchURL + ")", logger.DEBUG)
items[mode].append(item)
except Exception, e:
logger.log(u"Failed parsing " + self.name + " Traceback: " + traceback.format_exc(), logger.ERROR)
#For each search mode sort all the items by seeders
items[mode].sort(key=lambda tup: tup[3], reverse=True)
results += items[mode]
def _doSearch(self,
search_params,
search_mode='eponly',
epcount=0,
age=0,
epObj=None):
results = []
items = {'Season': [], 'Episode': [], 'RSS': []}
if not self._doLogin():
return results
for mode in search_params.keys():
for search_string in search_params[mode]:
if isinstance(search_string, unicode):
search_string = unidecode(search_string)
searchURL = self.urls['search'] % (urllib.quote(search_string),
self.categories)
logger.log(u"Search string: " + searchURL, logger.DEBUG)
data = self.getURL(searchURL)
if not data:
continue
try:
with BS4Parser(data, "html.parser") as html:
torrent_table = html.find('table',
attrs={'class': 'koptekst'})
torrent_rows = torrent_table.find_all(
'tr') if torrent_table else []
#Continue only if one Release is found
if len(torrent_rows) < 2:
logger.log(
u"The Data returned from " + self.name +
" do not contains any torrent", logger.DEBUG)
continue
for result in torrent_rows[1:]:
cells = result.find_all('td')
link = cells[1].find('a')
download_url = self.urls['download'] % cells[
2].find('a')['href']
id = link['href']
id = id.replace('details.php?id=', '')
id = id.replace('&hit=1', '')
try:
title = link.getText()
id = int(id)
seeders = int(cells[10].getText())
leechers = int(cells[11].getText())
except (AttributeError, TypeError):
continue
#Filter unseeded torrent
if mode != 'RSS' and (seeders < self.minseed
or leechers < self.minleech):
continue
if not title or not download_url:
continue
item = title, download_url, id, seeders, leechers
logger.log(
u"Found result: " + title.replace(' ', '.') +
" (" + searchURL + ")", logger.DEBUG)
items[mode].append(item)
except Exception, e:
logger.log(
u"Failed parsing " + self.name + " Traceback: " +
traceback.format_exc(), logger.ERROR)
#For each search mode sort all the items by seeders
items[mode].sort(key=lambda tup: tup[3], reverse=True)
results += items[mode]
def search(self, search_strings, age=0, ep_obj=None):
results = []
items = {'Season': [], 'Episode': [], 'RSS': []}
if not self.login():
return results
for mode in search_strings.keys():
logger.log(u"Search Mode: %s" % mode, logger.DEBUG)
for search_string in search_strings[mode]:
if mode != 'RSS':
logger.log(u"Search string: %s " % search_string,
logger.DEBUG)
self.search_params['search'] = search_string
data = self.get_url(self.urls['search'],
params=self.search_params)
if not data:
continue
try:
with BS4Parser(data, 'html5lib') as html:
result_linkz = html.findAll(
'a', href=re.compile("torrents-details"))
if not result_linkz:
logger.log(
u"Data returned from provider do not contains any torrent",
logger.DEBUG)
continue
if result_linkz:
for link in result_linkz:
title = link.text
download_url = self.urls['base_url'] + link[
'href']
download_url = download_url.replace(
"torrents-details", "download")
# FIXME
size = -1
seeders = 1
leechers = 0
if not title or not download_url:
continue
# Filter unseeded torrent
# if seeders < self.minseed or leechers < self.minleech:
# if mode != 'RSS':
# logger.log(u"Discarding torrent because it doesn't meet the minimum seeders or leechers: {0} (S:{1} L:{2})".format(title, seeders, leechers), logger.DEBUG)
# continue
item = title, download_url, size, seeders, leechers
if mode != 'RSS':
logger.log(u"Found result: %s " % title,
logger.DEBUG)
items[mode].append(item)
except Exception as e:
logger.log(
u"Failed parsing provider. Traceback: %s" %
traceback.format_exc(), logger.ERROR)
# For each search mode sort all the items by seeders if available
items[mode].sort(key=lambda tup: tup[3], reverse=True)
results += items[mode]
return results
def search(self, search_strings, age=0, ep_obj=None): # pylint: disable=too-many-branches, too-many-locals, too-many-statements
results = []
anime = (self.show and self.show.anime) or (ep_obj and ep_obj.show and ep_obj.show.anime) or False
search_params = {
"q": "",
"field": "seeders",
"sorder": "desc",
"rss": 1,
"category": ("tv", "anime")[anime]
}
for mode in search_strings:
items = []
logger.log("Search Mode: {}".format(mode), logger.DEBUG)
for search_string in search_strings[mode]:
search_params["q"] = search_string if mode != "RSS" else ""
search_params["field"] = "seeders" if mode != "RSS" else "time_add"
if mode != "RSS":
logger.log("Search string: {}".format(search_string.decode("utf-8")),
logger.DEBUG)
search_url = self.urls["search"] % ("usearch" if mode != "RSS" else search_string)
if self.custom_url:
if not validators.url(self.custom_url):
logger.log("Invalid custom url: {}".format(self.custom_url), logger.WARNING)
return results
search_url = urljoin(self.custom_url, search_url.split(self.url)[1])
data = self.get_url(search_url, params=search_params, returns="text")
if not data:
logger.log("URL did not return data, maybe try a custom url, or a different one", logger.DEBUG)
continue
if not data.startswith("<?xml"):
logger.log("Expected xml but got something else, is your mirror failing?", logger.INFO)
continue
with BS4Parser(data, "html5lib") as html:
for item in html.find_all("item"):
try:
title = item.title.get_text(strip=True)
# Use the torcache link kat provides,
# unless it is not torcache or we are not using blackhole
# because we want to use magnets if connecting direct to client
# so that proxies work.
download_url = item.enclosure["url"]
if sickbeard.TORRENT_METHOD != "blackhole" or "torcache" not in download_url:
download_url = item.find("torrent:magneturi").next.replace("CDATA", "").strip("[!]") + self._custom_trackers
if not (title and download_url):
continue
seeders = try_int(item.find("torrent:seeds").get_text(strip=True))
leechers = try_int(item.find("torrent:peers").get_text(strip=True))
# Filter unseeded torrent
if seeders < self.minseed or leechers < self.minleech:
if mode != "RSS":
logger.log("Discarding torrent because it doesn't meet the minimum seeders or leechers: {} (S:{} L:{})".format
(title, seeders, leechers), logger.DEBUG)
continue
verified = bool(try_int(item.find("torrent:verified").get_text(strip=True)))
if self.confirmed and not verified:
if mode != "RSS":
logger.log("Found result " + title + " but that doesn't seem like a verified result so I'm ignoring it", logger.DEBUG)
continue
torrent_size = item.find("torrent:contentlength").get_text(strip=True)
size = convert_size(torrent_size) or -1
info_hash = item.find("torrent:infohash").get_text(strip=True)
item = {'title': title, 'link': download_url, 'size': size, 'seeders': seeders, 'leechers': leechers, 'hash': info_hash}
if mode != "RSS":
logger.log("Found result: %s with %s seeders and %s leechers" % (title, seeders, leechers), logger.DEBUG)
items.append(item)
except (AttributeError, TypeError, KeyError, ValueError):
continue
# For each search mode sort all the items by seeders if available
items.sort(key=lambda d: try_int(d.get('seeders', 0)), reverse=True)
results += items
return results
def search(self, search_strings, age=0, ep_obj=None): # pylint: disable=too-many-branches, too-many-locals, too-many-statements
results = []
if not self.login():
return results
for mode in search_strings:
items = []
for search_string in search_strings[mode]:
if mode != 'RSS':
logger.log(
"Search string: {0}".format(
search_string.decode("utf-8")), logger.DEBUG)
search_params = {
'searchtext': search_string,
'filter_freeleech': (0, 1)[self.freeleech is True],
'order_by': ('seeders', 'time')[mode == 'RSS'],
"order_way": "desc"
}
if not search_string:
del search_params['searchtext']
data = self.get_url(self.urls['search'],
params=search_params,
returns='text')
if not data:
logger.log("No data returned from provider", logger.DEBUG)
continue
try:
with BS4Parser(data, 'html5lib') as html:
torrent_table = html.find('table',
{'id': 'torrent_table'})
if not torrent_table:
logger.log(
"Data returned from {0} does not contain any torrents"
.format(self.name), logger.DEBUG)
continue
labels = [
x.get_text(strip=True) or x.a.img.get('alt')
for x in torrent_table.find(
'tr', class_='colhead').find_all('td')
]
torrent_rows = torrent_table('tr', class_='torrent')
# Continue only if one Release is found
if not torrent_rows:
logger.log(
"Data returned from {0} does not contain any torrents"
.format(self.name), logger.DEBUG)
continue
for torrent_row in torrent_rows:
freeleech = torrent_row.find(
'img', alt="Freeleech") is not None
if self.freeleech and not freeleech:
continue
# Normal Download Link
download_item = torrent_row.find(
'a', {'title': 'Download Torrent'})
if not download_item:
# If the user has downloaded it
download_item = torrent_row.find(
'a', {
'title':
'Previously Grabbed Torrent File'
})
if not download_item:
# If the user is seeding
download_item = torrent_row.find(
'a',
{'title': 'Currently Seeding Torrent'})
if not download_item:
# If the user is leeching
download_item = torrent_row.find(
'a',
{'title': 'Currently Leeching Torrent'})
if not download_item:
# If there are none
continue
download_url = urljoin(self.url,
download_item['href'])
temp_anchor = torrent_row.find(
'a', {"data-src": True})
title = temp_anchor['data-src'].rsplit('.', 1)[0]
if not all([title, download_url]):
continue
cells = torrent_row('td')
seeders = try_int(
cells[labels.index('Seeders')].text.strip())
leechers = try_int(
cells[labels.index('Leechers')].get_text(
strip=True))
# Filter unseeded torrent
if seeders < self.minseed or leechers < self.minleech:
if mode != 'RSS':
logger.log(
"Discarding torrent because it doesn't meet the"
" minimum seeders or leechers: {0} (S:{1} L:{2})"
.format(title, seeders,
leechers), logger.DEBUG)
continue
size = temp_anchor['data-filesize'] or -1
item = {
'title': title,
'link': download_url,
'size': size,
'seeders': seeders,
'leechers': leechers,
'hash': ''
}
if mode != 'RSS':
logger.log(
"Found result: {0} with {1} seeders and {2} leechers"
.format(title, seeders,
leechers), logger.DEBUG)
items.append(item)
except Exception:
logger.log(
"Failed parsing provider. Traceback: {0}".format(
traceback.format_exc()), logger.ERROR)
# For each search mode sort all the items by seeders
items.sort(key=lambda d: try_int(d.get('seeders', 0)),
reverse=True)
results += items
return results
def _doSearch(self, search_params, search_mode='eponly', epcount=0, age=0):
results = []
items = {'Season': [], 'Episode': [], 'RSS': []}
freeleech = '3' if self.freeleech else '0'
if not self._doLogin():
return results
for mode in search_params.keys():
for search_string in search_params[mode]:
if isinstance(search_string, unicode):
search_string = unidecode(search_string)
searchURL = self.urls['search'] % (freeleech, search_string)
logger.log(u"Search string: " + searchURL, logger.DEBUG)
# returns top 15 results by default, expandable in user profile to 100
data = self.getURL(searchURL)
if not data:
continue
try:
with BS4Parser(data, features=["html5lib",
"permissive"]) as html:
torrent_table = html.find('table',
attrs={'class': 'frame'})
torrent_rows = torrent_table.findChildren(
'tr') if torrent_table else []
#Continue only if one Release is found
if len(torrent_rows) < 2:
logger.log(
u"The Data returned from " + self.name +
" do not contains any torrent", logger.DEBUG)
continue
# skip colheader
for result in torrent_rows[1:]:
cells = result.findChildren('td')
link = cells[1].find(
'a', attrs={'class': 'torrent_name_link'})
#skip if torrent has been nuked due to poor quality
if cells[1].find('img', alt='Nuked') != None:
continue
torrent_id = link['href'].replace(
'/details.php?id=', '')
try:
if link.has_key('title'):
title = cells[1].find(
'a', {'class': 'torrent_name_link'
})['title']
else:
title = link.contents[0]
download_url = self.urls['download'] % (
torrent_id)
id = int(torrent_id)
seeders = int(cells[8].find(
'a', {
'class': 'link'
}).span.contents[0].strip())
leechers = int(cells[9].find(
'a', {
'class': 'link'
}).contents[0].strip())
except (AttributeError, TypeError):
continue
#Filter unseeded torrent
if mode != 'RSS' and (seeders < self.minseed
or leechers < self.minleech):
continue
if not title or not download_url:
continue
item = title, download_url, id, seeders, leechers
logger.log(
u"Found result: " + title + "(" + searchURL +
")", logger.DEBUG)
items[mode].append(item)
except Exception, e:
logger.log(
u"Failed parsing " + self.name + " Traceback: " +
traceback.format_exc(), logger.ERROR)
#For each search mode sort all the items by seeders
items[mode].sort(key=lambda tup: tup[3], reverse=True)
results += items[mode]
def search(self, search_params, age=0, ep_obj=None): # pylint: disable=too-many-locals, too-many-branches, too-many-statements
results = []
for mode in search_params:
items = []
logger.log(u'Search Mode: {0}'.format(mode), logger.DEBUG)
for search_string in search_params[mode]:
if search_string == '':
continue
search_string = six.text_type(search_string).replace('.', ' ')
logger.log(
u'Search string: {0}'.format(
search_string.decode('utf-8')), logger.DEBUG)
last_page = False
for page in range(0, self.max_pages):
if last_page:
break
logger.log('Processing page {0} of results'.format(page),
logger.DEBUG)
search_url = self.urls['search'].format(
search_string, page)
data = self.get_url(search_url, returns='text')
if not data:
logger.log(u'No data returned from provider',
logger.DEBUG)
continue
try:
with BS4Parser(data, 'html5lib') as html:
table_header = html.find('tr', class_='bordo')
torrent_table = table_header.find_parent(
'table') if table_header else None
if not torrent_table:
logger.log(u'Could not find table of torrents',
logger.ERROR)
continue
torrent_rows = torrent_table('tr')
# Continue only if one Release is found
if len(torrent_rows) < 6 or len(
torrent_rows[2]('td')) == 1:
logger.log(
u'Data returned from provider does not contain any torrents',
logger.DEBUG)
last_page = True
continue
if len(torrent_rows) < 45:
last_page = True
for result in torrent_rows[2:-3]:
result_cols = result('td')
if len(result_cols) == 1:
# Ignore empty rows in the middle of the table
continue
try:
info_link = result('td')[1].find(
'a')['href']
title = re.sub(
' +', ' ',
info_link.rsplit('/', 1)[-1].replace(
'_', ' '))
info_hash = result('td')[3].find(
'input',
class_='downarrow')['value'].upper()
download_url = self._magnet_from_result(
info_hash, title)
seeders = try_int(result('td')[5].text)
leechers = try_int(result('td')[6].text)
torrent_size = result('td')[2].string
size = convert_size(torrent_size) or -1
except (AttributeError, IndexError, TypeError):
continue
filename_qt = self._reverseQuality(
self._episodeQuality(result))
for text in self.hdtext:
title1 = title
title = title.replace(text, filename_qt)
if title != title1:
break
if Quality.nameQuality(
title) == Quality.UNKNOWN:
title += filename_qt
if not self._is_italian(
title) and not self.subtitle:
logger.log(
u'Torrent is subtitled, skipping: {0}'.
format(title), logger.DEBUG)
continue
if self.engrelease and not self._is_english(
title):
logger.log(
u'Torrent isn\'t english audio/subtitled, skipping: {0}'
.format(title), logger.DEBUG)
continue
search_show = re.split(r'([Ss][\d{1,2}]+)',
search_string)[0]
show_title = search_show
ep_params = ''
rindex = re.search(r'([Ss][\d{1,2}]+)', title)
if rindex:
show_title = title[:rindex.start()]
ep_params = title[rindex.start():]
if show_title.lower() != search_show.lower(
) and search_show.lower() in show_title.lower(
):
new_title = search_show + ep_params
title = new_title
if not all([title, download_url]):
continue
if self._is_season_pack(title):
title = re.sub(r'([Ee][\d{1,2}\-?]+)', '',
title)
# Filter unseeded torrent
if seeders < self.minseed or leechers < self.minleech:
logger.log(
u'Discarding torrent because it doesn\'t meet the minimum'
u' seeders or leechers: {0} (S:{1} L:{2})'
.format(title, seeders,
leechers), logger.DEBUG)
continue
item = {
'title': title,
'link': download_url,
'size': size,
'seeders': seeders,
'leechers': leechers,
'hash': info_hash
}
if mode != 'RSS':
logger.log(
u'Found result: {0} with {1} seeders and {2} leechers'
.format(title, seeders,
leechers), logger.DEBUG)
items.append(item)
except Exception as error:
logger.log(
u'Failed parsing provider. Error: {0}'.format(
error), logger.ERROR)
# For each search mode sort all the items by seeders if available
items.sort(key=lambda d: try_int(d.get('seeders', 0)),
reverse=True)
results += items
return results
def search(self, search_strings, age=0, ep_obj=None): # pylint: disable=too-many-locals
results = []
for mode in search_strings:
items = []
logger.log(u"Search Mode: {0}".format(mode), logger.DEBUG)
for search_string in search_strings[mode]:
search_url = self.urls[
'verified'] if self.confirmed else self.urls['feed']
if mode != 'RSS':
logger.log(
u"Search string: {0}".format(
search_string.decode("utf-8")), logger.DEBUG)
data = self.get_url(search_url,
params={'q': search_string},
returns='text')
if not data:
logger.log(u"No data returned from provider", logger.DEBUG)
continue
if not data.startswith("<?xml"):
logger.log(
u"Expected xml but got something else, is your mirror failing?",
logger.INFO)
continue
try:
with BS4Parser(data, 'html5lib') as parser:
for item in parser('item'):
if item.category and 'tv' not in item.category.get_text(
strip=True):
continue
title = item.title.text.rsplit(' ', 1)[0].replace(
' ', '.')
t_hash = item.guid.text.rsplit('/', 1)[-1]
if not all([title, t_hash]):
continue
download_url = "magnet:?xt=urn:btih:" + t_hash + "&dn=" + title + self._custom_trackers
torrent_size, seeders, leechers = self._split_description(
item.find('description').text)
size = convert_size(torrent_size) or -1
# Filter unseeded torrent
if seeders < self.minseed or leechers < self.minleech:
if mode != 'RSS':
logger.log(
u"Discarding torrent because it doesn't meet the minimum seeders or leechers: {0} (S:{1} L:{2})"
.format(title, seeders,
leechers), logger.DEBUG)
continue
result = {
'title': title,
'link': download_url,
'size': size,
'seeders': seeders,
'leechers': leechers,
'hash': t_hash
}
items.append(result)
except StandardError:
logger.log(
u"Failed parsing provider. Traceback: {0!r}".format(
traceback.format_exc()), logger.ERROR)
# For each search mode sort all the items by seeders if available
items.sort(key=lambda d: try_int(d.get('seeders', 0)),
reverse=True)
results += items
return results
def search(self, search_strings, age=0, ep_obj=None):
results = []
if not self.login():
return results
# Search Params
search_params = {
"searchstr": "",
"filter_cat[1]": 1,
"filter_cat[2]": 1,
"filter_cat[3]": 1,
"filter_cat[4]": 1,
"filter_cat[5]": 1
}
# Units
units = ["B", "KB", "MB", "GB", "TB", "PB"]
def process_column_header(td):
result = ""
if td.a and td.a.img:
result = td.a.img.get("title", td.a.get_text(strip=True))
if not result:
result = td.get_text(strip=True)
return result
for mode in search_strings:
items = []
logger.log("Search Mode: {0}".format(mode), logger.DEBUG)
for search_string in search_strings[mode]:
if mode != "RSS":
logger.log(
"Search string: {0}".format(
search_string.decode("utf-8")), logger.DEBUG)
search_params["searchstr"] = search_string
search_url = self.urls["search"]
data = self.get_url(search_url,
params=search_params,
returns="text")
if not data:
logger.log("No data returned from provider", logger.DEBUG)
continue
with BS4Parser(data, "html5lib") as html:
torrent_table = html.find("table", id="torrent_table")
torrent_rows = torrent_table("tr") if torrent_table else []
# Continue only if at least one Release is found
if len(torrent_rows) < 2:
logger.log(
"Data returned from provider does not contain any torrents",
logger.DEBUG)
continue
# "", "", "Name /Year", "Files", "Time", "Size", "Snatches", "Seeders", "Leechers"
labels = [
process_column_header(label)
for label in torrent_rows[0]("td")
]
# Skip column headers
for result in torrent_rows[1:]:
cells = result("td")
if len(cells) < len(labels):
continue
try:
title = cells[labels.index("Name /Year")].find(
"a", dir="ltr").get_text(strip=True)
download_url = urljoin(
self.url,
cells[labels.index("Name /Year")].find(
"a", title="Download")["href"])
if not all([title, download_url]):
continue
seeders = try_int(
cells[labels.index("Seeders")].get_text(
strip=True))
leechers = try_int(
cells[labels.index("Leechers")].get_text(
strip=True))
# Filter unseeded torrent
if seeders < self.minseed or leechers < self.minleech:
if mode != "RSS":
logger.log(
"Discarding torrent because it doesn't meet the"
" minimum seeders or leechers: {0} (S:{1} L:{2})"
.format(title, seeders,
leechers), logger.DEBUG)
continue
torrent_size = cells[labels.index(
"Size")].get_text(strip=True)
size = convert_size(torrent_size,
units=units) or -1
item = {
'title': title,
'link': download_url,
'size': size,
'seeders': seeders,
'leechers': leechers,
'hash': ''
}
if mode != "RSS":
logger.log(
"Found result: {0} with {1} seeders and {2} leechers"
.format(title, seeders,
leechers), logger.DEBUG)
items.append(item)
except StandardError:
continue
# For each search mode sort all the items by seeders if available
items.sort(key=lambda d: try_int(d.get('seeders', 0)),
reverse=True)
results += items
return results
def search(self, search_strings, age=0, ep_obj=None): # pylint: disable=too-many-locals, too-many-branches
results = []
if not self.login():
return results
# http://speed.cd/browse.php?c49=1&c50=1&c52=1&c41=1&c55=1&c2=1&c30=1&freeleech=on&search=arrow&d=on
# Search Params
search_params = {
'c2': 1, # TV/Episodes
'c30': 1, # Anime
'c41': 1, # TV/Packs
'c49': 1, # TV/HD
'c50': 1, # TV/Sports
'c52': 1, # TV/B-Ray
'c55': 1, # TV/Kids
'search': '',
}
# Units
units = ['B', 'KB', 'MB', 'GB', 'TB', 'PB']
def process_column_header(td):
result = ''
if td.a and td.a.img:
result = td.a.img.get('alt', td.a.get_text(strip=True))
if td.img and not result:
result = td.img.get('alt', '')
if not result:
result = td.get_text(strip=True)
return result
if self.freeleech:
search_params['freeleech'] = 'on'
for mode in search_strings:
items = []
logger.log(u"Search Mode: {}".format(mode), logger.DEBUG)
for search_string in search_strings[mode]:
if mode != 'RSS':
logger.log(
u"Search string: {}".format(
search_string.decode("utf-8")), logger.DEBUG)
search_params['search'] = search_string
search_url = "%s?%s" % (self.urls['search'],
urlencode(search_params))
logger.log(u"Search URL: %s" % search_url, logger.DEBUG)
data = self.get_url(search_url)
if not data:
continue
with BS4Parser(data, 'html5lib') as html:
torrent_table = html.find(
'div', class_='boxContent').find('table')
torrent_rows = torrent_table.find_all(
'tr') if torrent_table else []
# Continue only if at least one Release is found
if len(torrent_rows) < 2:
logger.log(
u"Data returned from provider does not contain any torrents",
logger.DEBUG)
continue
labels = [
process_column_header(label)
for label in torrent_rows[0].find_all('th')
]
# Skip column headers
for result in torrent_rows[1:]:
try:
cells = result.find_all('td')
title = cells[labels.index('Title')].find(
'a', class_='torrent').get_text()
download_url = self.url + cells[labels.index(
'Download')].find(
title='Download').parent['href']
if not all([title, download_url]):
continue
seeders = try_int(
cells[labels.index('Seeders')].get_text(
strip=True))
leechers = try_int(
cells[labels.index('Leechers')].get_text(
strip=True))
# Filter unseeded torrent
if seeders < self.minseed or leechers < self.minleech:
if mode != 'RSS':
logger.log(
u"Discarding torrent because it doesn't meet the minimum seeders or leechers: {} (S:{} L:{})"
.format(title, seeders,
leechers), logger.DEBUG)
continue
torrent_size = cells[labels.index(
'Size')].get_text()
# TODO: Make convert_size work with 123.12GB
torrent_size = torrent_size[:
-2] + ' ' + torrent_size[
-2:]
size = convert_size(torrent_size,
units=units) or -1
item = title, download_url, size, seeders, leechers
if mode != 'RSS':
logger.log(
u"Found result: %s with %s seeders and %s leechers"
% (title, seeders, leechers), logger.DEBUG)
items.append(item)
except StandardError:
continue
# For each search mode sort all the items by seeders if available
items.sort(key=lambda tup: tup[3], reverse=True)
results += items
return results
def _doSearch(self, search_params, search_mode='eponly', epcount=0, age=0):
results = []
items = {'Season': [], 'Episode': [], 'RSS': []}
if not self._doLogin():
return []
for mode in search_params.keys():
for search_string in search_params[mode]:
if isinstance(search_string, unicode):
search_string = unidecode(search_string)
searchURL = self.urls['search'] % (search_string, self.categories)
logger.log(u"Search string: " + searchURL, logger.DEBUG)
data = self.getURL(searchURL)
if not data:
continue
try:
with BS4Parser(data, features=["html5lib", "permissive"]) as html:
torrent_table = html.find('table', attrs={'border': '1'})
torrent_rows = torrent_table.find_all('tr') if torrent_table else []
#Continue only if one Release is found
if len(torrent_rows) < 2:
logger.log(u"The Data returned from " + self.name + " do not contains any torrent",
logger.DEBUG)
continue
for result in torrent_rows[1:]:
cells = result.find_all('td')
link = cells[1].find('a', attrs={'class': 'index'})
full_id = link['href'].replace('details.php?id=', '')
torrent_id = full_id.split("&")[0]
try:
if link.has_key('title'):
title = cells[1].find('a', {'class': 'index'})['title']
else:
title = link.contents[0]
download_url = self.urls['download'] % (torrent_id, link.contents[0])
id = int(torrent_id)
seeders = int(cells[8].find('span').contents[0])
leechers = int(cells[9].find('span').contents[0])
except (AttributeError, TypeError):
continue
#Filter unseeded torrent
if mode != 'RSS' and (seeders < self.minseed or leechers < self.minleech):
continue
if not title or not download_url:
continue
item = title, download_url, id, seeders, leechers
logger.log(u"Found result: " + title + "(" + searchURL + ")", logger.DEBUG)
items[mode].append(item)
except Exception, e:
logger.log(u"Failed parsing " + self.name + " Traceback: " + traceback.format_exc(), logger.ERROR)
#For each search mode sort all the items by seeders
items[mode].sort(key=lambda tup: tup[3], reverse=True)
results += items[mode]
def search(self, search_strings, age=0, ep_obj=None):
results = []
items = {'Season': [], 'Episode': [], 'RSS': []}
if not self.login():
return results
for mode in search_strings.keys():
logger.log(u"Search Mode: %s" % mode, logger.DEBUG)
for search_string in search_strings[mode]:
if mode != 'RSS':
logger.log(u"Search string: %s " % search_string,
logger.DEBUG)
searchURL = self.urls['search'] % (search_string,
self.categories)
logger.log(u"Search URL: %s" % searchURL, logger.DEBUG)
data = self.get_url(searchURL)
if not data:
continue
try:
with BS4Parser(data, 'html5lib') as html:
torrent_table = html.find(
'table', attrs={'id': 'torrent_table'})
torrent_rows = torrent_table.find_all(
'tr') if torrent_table else []
# Continue only if one Release is found
if len(torrent_rows) < 2:
logger.log(
u"Data returned from provider does not contain any torrents",
logger.DEBUG)
continue
for result in torrent_rows[1:]:
cells = result.find_all('td')
link = result.find('a', attrs={'dir': 'ltr'})
url = result.find('a', attrs={'title': 'Download'})
try:
title = link.contents[0]
download_url = self.urls['download'] % (
url['href'])
seeders = cells[len(cells) - 2].contents[0]
leechers = cells[len(cells) - 1].contents[0]
# FIXME
size = -1
except (AttributeError, TypeError):
continue
if not all([title, download_url]):
continue
# Filter unseeded torrent
if seeders < self.minseed or leechers < self.minleech:
if mode != 'RSS':
logger.log(
u"Discarding torrent because it doesn't meet the minimum seeders or leechers: {0} (S:{1} L:{2})"
.format(title, seeders,
leechers), logger.DEBUG)
continue
item = title, download_url, size, seeders, leechers
if mode != 'RSS':
logger.log(u"Found result: %s " % title,
logger.DEBUG)
items[mode].append(item)
except Exception:
logger.log(
u"Failed parsing provider. Traceback: %s" %
traceback.format_exc(), logger.WARNING)
# For each search mode sort all the items by seeders if available
items[mode].sort(key=lambda tup: tup[3], reverse=True)
results += items[mode]
return results