def search(self, task, entry, config=None):
"""
Search for name from iptorrents
"""
categories = config.get('category', 'All')
# Make sure categories is a list
if not isinstance(categories, list):
categories = [categories]
# If there are any text categories, turn them into their id number
categories = [c if isinstance(c, int) else CATEGORIES[c]
for c in categories]
filter_url = '&'.join((str(c) + '=') for c in categories)
entries = set()
for search_string in entry.get('search_strings', [entry['title']]):
query = normalize_unicode(search_string)
query = quote_plus(query.encode('utf8'))
url = "{base_url}/t?{filter}&q={query}&qf=".format(base_url=BASE_URL, filter=filter_url, query=query)
log.debug('searching with url: %s' % url)
req = requests.get(url, cookies={'uid': str(config['uid']), 'pass': config['password']})
if '/u/' + str(config['uid']) not in req.text:
raise plugin.PluginError("Invalid cookies (user not logged in)...")
soup = get_soup(req.content, parser="html.parser")
torrents = soup.find('table', {'id': 'torrents'})
results = torrents.findAll('tr')
for torrent in results:
if torrent.th and 'ac' in torrent.th.get('class'):
# Header column
continue
if torrent.find('td', {'colspan': '99'}):
log.debug('No results found for search %s', search_string)
break
entry = Entry()
link = torrent.find('a', href=re.compile('download'))['href']
entry['url'] = "{base}{link}?torrent_pass={key}".format(
base=BASE_URL, link=link, key=config.get('rss_key'))
entry['title'] = torrent.find('a', href=re.compile('details')).text
seeders = torrent.findNext('td', {'class': 'ac t_seeders'}).text
leechers = torrent.findNext('td', {'class': 'ac t_leechers'}).text
entry['torrent_seeds'] = int(seeders)
entry['torrent_leeches'] = int(leechers)
entry['search_sort'] = torrent_availability(entry['torrent_seeds'],
entry['torrent_leeches'])
size = torrent.findNext(text=re.compile('^([\.\d]+) ([GMK]?)B$'))
size = re.search('^([\.\d]+) ([GMK]?)B$', size)
entry['content_size'] = parse_filesize(size.group(0))
log.debug('Found entry %s', entry)
entries.add(entry)
return entries
def url_rewrite(self, task, entry):
soup = self._get_soup(task, entry['url'])
# grab links from the main post:
link_elements = []
log.debug('Searching %s for a tags where the text matches one of: %s',
entry['url'], str(self.config.get('link_text_re')))
for regexp in self.config.get('link_text_re'):
link_elements.extend(soup.find_all('a', string=re.compile(regexp)))
log.debug('Original urls: %s', str(entry['urls']))
if entry['urls']:
urls = list(entry['urls'])
else:
urls = []
log.debug('Found link elements: %s', str(link_elements))
for element in link_elements:
if re.search('nfo1.rlsbb.(ru|com)', element['href']):
# grab multipart links
urls.extend(self.grab_multilinks(task, element['href']))
else:
urls.append(element['href'])
# grab links from comments
regexps = self.config.get('filehosters_re', [])
if self.config.get('parse_comments'):
comments = soup.find_all('div', id=re.compile("commentbody"))
log.debug('Comment parsing enabled: found %d comments.', len(comments))
if comments and not regexps:
log.warn('You have enabled comment parsing but you did not define any filehoster_re filter. You may get a lot of unwanted and potentially dangerous links from the comments.')
for comment in comments:
links = comment.find_all('a')
for link in links:
urls.append(link['href'])
# filter urls:
filtered_urls = []
for i, url in enumerate(urls):
urls[i] = normalize_unicode(url)
for regexp in regexps:
if re.search(regexp, urls[i]):
filtered_urls.append(urls[i])
log.debug('Url: "%s" matched filehoster filter: %s', urls[i], regexp)
break
else:
if regexps:
log.debug(
'Url: "%s" was discarded because it does not match any of the given filehoster filters: %s', urls[i], str(regexps))
if regexps:
log.debug('Using filehosters_re filters: %s', str(regexps))
urls = filtered_urls
else:
log.debug('No filehoster filters configured, using all found links.')
num_links = len(urls)
log.debug('Original urls: %s', str(entry['urls']))
log.verbose('Found %d links at %s.', num_links, entry['url'])
if num_links:
entry['urls'] = urls
entry['url'] = urls[0]
else:
raise UrlRewritingError('No useable links found at %s' % entry['url'])
def url_rewrite(self, task, entry):
soup = self._get_soup(task, entry['url'])
link_re = re.compile('rarefile\.net.*\.rar$')
# grab links from the main entry:
blog_entry = soup.find('div', class_="entry")
num_links = 0
link_list = None
for paragraph in blog_entry.find_all('p'):
links = paragraph.find_all('a', href=link_re)
if len(links) > num_links:
link_list = links
num_links = len(links)
if 'urls' in entry:
urls = list(entry['urls'])
else:
urls = []
if link_list is not None:
for link in link_list:
urls.append(normalize_unicode(link['href']))
else:
raise UrlRewritingError('No useable links found at %s' %
entry['url'])
num_links = len(urls)
log.verbose('Found %d links at %s.', num_links, entry['url'])
if num_links:
entry['urls'] = urls
entry['url'] = urls[0]
else:
raise UrlRewritingError('No useable links found at %s' %
entry['url'])
def search(self, task, entry, config=None):
from flexget.utils.template import environment
from flexget.manager import manager
search_strings = [
urllib.quote(normalize_unicode(s).encode("utf-8")) for s in entry.get("search_strings", [entry["title"]])
]
rss_plugin = plugin.get_plugin_by_name("rss")
entries = set()
rss_config = rss_plugin.instance.build_config(config)
try:
template = environment.from_string(rss_config["url"])
except TemplateSyntaxError as e:
raise plugin.PluginError("Invalid jinja template as rss url: %s" % e)
rss_config["all_entries"] = True
for search_string in search_strings:
rss_config["url"] = template.render({"search_term": search_string})
# TODO: capture some other_fields to try to find seed/peer/content_size numbers?
try:
results = rss_plugin.phase_handlers["input"](task, rss_config)
except plugin.PluginError as e:
log.error("Error attempting to get rss for %s: %s", rss_config["url"], e)
else:
entries.update(results)
return entries
def search(self, task, entry, config=None):
from flexget.utils.template import environment
search_strings = [
quote(normalize_unicode(s).encode('utf-8'))
for s in entry.get('search_strings', [entry['title']])
]
rss_plugin = plugin.get_plugin_by_name('rss')
entries = set()
rss_config = rss_plugin.instance.build_config(config)
try:
template = environment.from_string(rss_config['url'])
except TemplateSyntaxError as e:
raise plugin.PluginError('Invalid jinja template as rss url: %s' %
e)
rss_config['all_entries'] = True
for search_string in search_strings:
rss_config['url'] = template.render({'search_term': search_string})
# TODO: capture some other_fields to try to find seed/peer/content_size numbers?
try:
results = rss_plugin.phase_handlers['input'](task, rss_config)
except plugin.PluginError as e:
log.error('Error attempting to get rss for %s: %s',
rss_config['url'], e)
else:
entries.update(results)
return entries
def url_rewrite(self, task, entry):
soup = self._get_soup(task, entry['url'])
link_re = re.compile('rarefile\.net.*\.rar$')
# grab links from the main entry:
blog_entry = soup.find('div', class_="entry")
num_links = 0
link_list = None
for paragraph in blog_entry.find_all('p'):
links = paragraph.find_all('a', href=link_re)
if len(links) > num_links:
link_list = links
num_links = len(links)
if 'urls' in entry:
urls = list(entry['urls'])
else:
urls = []
if link_list is not None:
for link in link_list:
urls.append(normalize_unicode(link['href']))
else:
raise UrlRewritingError('No useable links found at %s' % entry['url'])
num_links = len(urls)
log.verbose('Found %d links at %s.', num_links, entry['url'])
if num_links:
entry['urls'] = urls
entry['url'] = urls[0]
else:
raise UrlRewritingError('No useable links found at %s' % entry['url'])
def search(self, task, entry, config=None):
"""
Search for entries on SceneAccess
"""
if not session.cookies:
log.debug('Logging in to %s...' % URL)
params = {'username': config['username'],
'password': config['password'],
'submit': 'come on in'}
session.post(URL + 'login', data=params)
if config.has_key('gravity_multiplier'):
multip = config['gravity_multiplier']
else:
multip = 1
# Prepare queries...
BASE_URLS = list()
entries = set()
for category in self.processCategories(config):
BASE_URLS.append(URL + '%(url_path)s?method=2%(category_url_string)s' % category)
# Search...
for search_string in entry.get('search_strings', [entry['title']]):
search_string_normalized = normalize_unicode(clean_title(search_string))
search_string_url_fragment = '&search=' + quote(search_string_normalized.encode('utf8'))
for url in BASE_URLS:
url += search_string_url_fragment
log.debug('Search URL for `%s`: %s' % (search_string, url))
page = session.get(url).content
soup = get_soup(page)
for result in soup.findAll('tr', attrs={'class': 'tt_row'}):
entry = Entry()
entry['title'] = result.find('a', href=re.compile(r'details\?id=\d+'))['title']
entry['url'] = URL + result.find('a', href=re.compile(r'.torrent$'))['href']
entry['torrent_seeds'] = result.find('td', attrs={'class': 'ttr_seeders'}).text
entry['torrent_leeches'] = result.find('td', attrs={'class': 'ttr_leechers'}).text
entry['search_sort'] = torrent_availability(entry['torrent_seeds'], entry['torrent_leeches'])*multip
size = result.find('td', attrs={'class': 'ttr_size'}).next
size = re.search('(\d+(?:[.,]\d+)*)\s?([KMG]B)', size)
if size:
if size.group(2) == 'GB':
entry['content_size'] = int(float(size.group(1)) * 1000 ** 3 / 1024 ** 2)
elif size.group(2) == 'MB':
entry['content_size'] = int(float(size.group(1)) * 1000 ** 2 / 1024 ** 2)
elif size.group(2) == 'KB':
entry['content_size'] = int(float(size.group(1)) * 1000 / 1024 ** 2)
else:
entry['content_size'] = int(float(size.group(1)) / 1024 ** 2)
entries.add(entry)
return entries
def search(self, entry, config):
# urllib.quote will crash if the unicode string has non ascii characters, so encode in utf-8 beforehand
name = normalize_unicode(entry["title"])
optionlist = [
"misc",
"movies",
"audio",
"tv",
"games",
"apps",
"pics",
"anime",
"comics",
"books",
"music video",
"unclassified",
"all",
]
url = "http://isohunt.com/js/rss/%s?iht=%s&noSL" % (
urllib.quote(name.encode("utf-8")),
optionlist.index(config),
)
log.debug("requesting: %s" % url)
rss = feedparser.parse(url)
entries = []
status = rss.get("status", False)
if status != 200:
raise PluginWarning("Search result not 200 (OK), received %s" % status)
ex = rss.get("bozo_exception", False)
if ex:
raise PluginWarning("Got bozo_exception (bad feed)")
for item in rss.entries:
entry = Entry()
entry["title"] = item.title
entry["url"] = item.link
m = re.search(r"Size: ([\d]+).*Seeds: (\d+).*Leechers: (\d+)", item.description, re.IGNORECASE)
if not m:
log.debug("regexp did not find seeds / peer data")
continue
else:
log.debug("regexp found size(%s), Seeds(%s) and Leeches(%s)" % (m.group(1), m.group(2), m.group(3)))
entry["content_size"] = int(m.group(1))
entry["torrent_seeds"] = int(m.group(2))
entry["torrent_leeches"] = int(m.group(3))
entry["search_sort"] = torrent_availability(entry["torrent_seeds"], entry["torrent_leeches"])
entries.append(entry)
# choose torrent
if not entries:
raise PluginWarning("No close matches for %s" % name, log, log_once=True)
entries.sort(reverse=True, key=lambda x: x.get("search_sort"))
return entries
def search(self, task, entry, config=None):
"""
Search for name from iptorrents
"""
categories = config.get('category', 'All')
# Make sure categories is a list
if not isinstance(categories, list):
categories = [categories]
# If there are any text categories, turn them into their id number
categories = [c if isinstance(c, int) else CATEGORIES[c]
for c in categories]
filter_url = '&'.join((str(c) + '=') for c in categories)
entries = set()
for search_string in entry.get('search_strings', [entry['title']]):
query = normalize_unicode(search_string)
query = quote_plus(query.encode('utf8'))
url = "{base_url}/t?{filter}&q={query}&qf=".format(base_url=BASE_URL, filter=filter_url, query=query)
log.debug('searching with url: %s' % url)
req = requests.get(url, cookies={'uid': str(config['uid']), 'pass': config['password']})
if '/u/' + str(config['uid']) not in req.text:
raise plugin.PluginError("Invalid cookies (user not logged in)...")
soup = get_soup(req.content, parser="html.parser")
torrents = soup.find('table', {'id': 'torrents'})
results = torrents.findAll('tr')
for torrent in results:
if torrent.th and 'ac' in torrent.th.get('class'):
# Header column
continue
if torrent.find('td', {'colspan': '99'}):
log.debug('No results found for search %s', search_string)
return
entry = Entry()
link = torrent.find('a', href=re.compile('download'))['href']
entry['url'] = "{base}{link}?torrent_pass={key}".format(
base=BASE_URL, link=link, key=config.get('rss_key'))
entry['title'] = torrent.find('a', href=re.compile('details')).text
seeders = torrent.findNext('td', {'class': 'ac t_seeders'}).text
leechers = torrent.findNext('td', {'class': 'ac t_leechers'}).text
entry['torrent_seeds'] = int(seeders)
entry['torrent_leeches'] = int(leechers)
entry['search_sort'] = torrent_availability(entry['torrent_seeds'],
entry['torrent_leeches'])
size = torrent.findNext(text=re.compile('^([\.\d]+) ([GMK]?)B$'))
size = re.search('^([\.\d]+) ([GMK]?)B$', size)
entry['content_size'] = parse_filesize(size.group(0))
log.debug('Found entry %s', entry)
entries.add(entry)
return entries
def search(self, entry, config=None):
from flexget.utils.template import environment
from flexget.manager import manager
search_strings = [
urllib.quote(normalize_unicode(s).encode('utf-8'))
for s in entry.get('search_strings', [entry['title']])
]
rss_plugin = plugin.get_plugin_by_name('rss')
entries = set()
rss_config = rss_plugin.instance.build_config(config)
template = environment.from_string(rss_config['url'])
rss_config['all_entries'] = True
for search_string in search_strings:
# Create a fake task to pass to the rss plugin input handler
task = Task(manager, 'search_rss_task', config={})
rss_config['url'] = template.render({'search_term': search_string})
# TODO: capture some other_fields to try to find seed/peer/content_size numbers?
try:
results = rss_plugin.phase_handlers['input'](task, rss_config)
except plugin.PluginError as e:
log.error('Error attempting to get rss for %s: %s',
rss_config['url'], e)
else:
entries.update(results)
return entries
def search(self, task, entry, config=None):
"""
Search for name from torrentleech.
"""
request_headers = {'User-Agent': 'curl/7.54.0'}
rss_key = config['rss_key']
# build the form request:
data = {'username': config['username'], 'password': config['password']}
# POST the login form:
try:
login = task.requests.post('https://www.torrentleech.org/user/account/login/', data=data,
headers=request_headers, allow_redirects=True)
except RequestException as e:
raise PluginError('Could not connect to torrentleech: %s', str(e))
if not isinstance(config, dict):
config = {}
# sort = SORT.get(config.get('sort_by', 'seeds'))
# if config.get('sort_reverse'):
# sort += 1
categories = config.get('category', 'all')
# Make sure categories is a list
if not isinstance(categories, list):
categories = [categories]
# If there are any text categories, turn them into their id number
categories = [c if isinstance(c, int) else CATEGORIES[c] for c in categories]
filter_url = '/categories/{}'.format(','.join(str(c) for c in categories))
entries = set()
for search_string in entry.get('search_strings', [entry['title']]):
query = normalize_unicode(search_string).replace(":", "")
# urllib.quote will crash if the unicode string has non ascii characters,
# so encode in utf-8 beforehand
url = ('https://www.torrentleech.org/torrents/browse/list/query/' +
quote(query.encode('utf-8')) + filter_url)
log.debug('Using %s as torrentleech search url', url)
results = task.requests.get(url, headers=request_headers, cookies=login.cookies).json()
for torrent in results['torrentList']:
entry = Entry()
entry['download_headers'] = request_headers
entry['title'] = torrent['name']
# construct download URL
torrent_url = 'https://www.torrentleech.org/rss/download/{}/{}/{}'.format(torrent['fid'], rss_key,
torrent['filename'])
log.debug('RSS-ified download link: %s', torrent_url)
entry['url'] = torrent_url
# seeders/leechers
entry['torrent_seeds'] = torrent['seeders']
entry['torrent_leeches'] = torrent['leechers']
entry['search_sort'] = torrent_availability(entry['torrent_seeds'], entry['torrent_leeches'])
entry['content_size'] = parse_filesize(str(torrent['size']) + ' b')
entries.add(entry)
return sorted(entries, reverse=True, key=lambda x: x.get('search_sort'))
def url_rewrite(self, task, entry):
soup = self._get_soup(task, entry['url'])
# grab link from filehosters_re
link_elements = []
log.debug('Searching %s for a tags where the text matches one of: %s',
entry['url'], str(self.config.get('filehosters_re')))
regexps = self.config.get('filehosters_re', [])
if self.config.get('parse'):
link_elements = soup.find_all('div',
class_=re.compile("mag_details"))
log.debug(
'filehosters_re parsing enabled: found %d filehosters_re.',
len(link_elements))
log.debug('Original urls: %s', str(entry['urls']))
if 'urls' in entry:
urls = list(entry['urls'])
log.debug('Original urls: %s', str(entry['urls']))
else:
urls = []
log.debug('link_elements parsing enabled: found %d link_elements.',
len(link_elements))
if link_elements and not regexps:
log.warn('There are not in filehosters_re.')
for target in link_elements:
links = target.find_all('a')
for link in links:
if re.search('novafile.com', link['href']):
urls.append(link['href'])
# filter urls:
filtered_urls = []
for i, url in enumerate(urls):
urls[i] = normalize_unicode(url)
for regexp in regexps:
if re.search(regexp, urls[i]):
filtered_urls.append(urls[i])
log.debug('Url: "%s" matched filehoster filter: %s',
urls[i], regexp)
break
else:
if regexps:
log.debug(
'Url: "%s" was discarded because it does not match any of the given filehoster filters: %s',
urls[i], str(regexps))
if regexps:
log.debug('Using filehosters_re filters: %s', str(regexps))
urls = filtered_urls
else:
log.debug(
'No filehoster filters configured, using all found links.')
num_links = len(urls)
log.verbose('Found %d links at %s.', num_links, entry['url'])
if num_links:
entry['urls'] = urls
entry['url'] = urls[0]
else:
raise UrlRewritingError('No useable links found at %s' %
entry['url'])
def search(self, task, entry, config=None):
config = self.process_config(config)
feed = REPUTATIONS[config['reputation']]
entries = set()
for search_string in entry.get('search_strings', [entry['title']]):
query = normalize_unicode(search_string +
config.get('extra_terms', ''))
for domain in ['eu', 'me', 'ch', 'in']:
# urllib.quote will crash if the unicode string has non ascii characters, so encode in utf-8 beforehand
url = 'http://torrentz.%s/%s?q=%s' % (
domain, feed, quote(query.encode('utf-8')))
log.debug('requesting: %s' % url)
try:
r = task.requests.get(url)
break
except requests.ConnectionError as err:
# The different domains all resolve to the same ip, so only try more if it was a dns error
log.warning('torrentz.%s connection failed. Error: %s' %
(domain, err))
continue
except requests.RequestException as err:
raise plugin.PluginError(
'Error getting torrentz search results: %s' % err)
else:
raise plugin.PluginError(
'Error getting torrentz search results')
if not r.content.strip():
raise plugin.PluginError(
'No data from %s. Maybe torrentz is blocking the FlexGet User-Agent'
% url)
rss = feedparser.parse(r.content)
if rss.get('bozo_exception'):
raise plugin.PluginError('Got bozo_exception (bad rss feed)')
for item in rss.entries:
m = re.search(
r'Size: ([\d]+) Mb Seeds: ([,\d]+) Peers: ([,\d]+) Hash: ([a-f0-9]+)',
item.description, re.IGNORECASE)
if not m:
log.debug('regexp did not find seeds / peer data')
continue
entry = Entry()
entry['title'] = item.title
entry['url'] = item.link
entry['content_size'] = int(m.group(1))
entry['torrent_seeds'] = int(m.group(2).replace(',', ''))
entry['torrent_leeches'] = int(m.group(3).replace(',', ''))
entry['torrent_info_hash'] = m.group(4).upper()
entry['search_sort'] = torrent_availability(
entry['torrent_seeds'], entry['torrent_leeches'])
entries.add(entry)
log.debug('Search got %d results' % len(entries))
return entries
def search(self, task, entry, config=None):
"""
Search for name from piratebay.
"""
if not isinstance(config, dict):
config = {}
sort = SORT.get(config.get('sort_by', 'seeds'))
if config.get('sort_reverse'):
sort += 1
if isinstance(config.get('category'), int):
category = config['category']
else:
category = CATEGORIES.get(config.get('category', 'all'))
filter_url = '/0/%d/%d' % (sort, category)
entries = set()
for search_string in entry.get('search_strings', [entry['title']]):
query = normalize_unicode(search_string)
# TPB search doesn't like dashes
query = query.replace('-', ' ')
# urllib.quote will crash if the unicode string has non ascii characters, so encode in utf-8 beforehand
url = 'http://thepiratebay.%s/search/%s%s' % (
CUR_TLD, quote(query.encode('utf-8')), filter_url)
log.debug('Using %s as piratebay search url' % url)
page = requests.get(url).content
soup = get_soup(page)
for link in soup.find_all('a', attrs={'class': 'detLink'}):
entry = Entry()
entry['title'] = self.extract_title(link)
if not entry['title']:
log.error(
'Malformed search result. No title or url found. Skipping.'
)
continue
entry['url'] = 'http://thepiratebay.%s%s' % (CUR_TLD,
link.get('href'))
tds = link.parent.parent.parent.find_all('td')
entry['torrent_seeds'] = int(tds[-2].contents[0])
entry['torrent_leeches'] = int(tds[-1].contents[0])
entry['search_sort'] = torrent_availability(
entry['torrent_seeds'], entry['torrent_leeches'])
# Parse content_size
size = link.find_next(attrs={'class': 'detDesc'}).contents[0]
size = re.search('Size ([\.\d]+)\xa0([GMK])iB', size)
if size:
if size.group(2) == 'G':
entry['content_size'] = int(
float(size.group(1)) * 1000**3 / 1024**2)
elif size.group(2) == 'M':
entry['content_size'] = int(
float(size.group(1)) * 1000**2 / 1024**2)
else:
entry['content_size'] = int(
float(size.group(1)) * 1000 / 1024**2)
entries.add(entry)
return sorted(entries,
reverse=True,
key=lambda x: x.get('search_sort'))
def search(self, task, entry, config=None):
"""
Search for name from torrentleech.
"""
request_headers = {'User-Agent': 'curl/7.54.0'}
rss_key = config['rss_key']
# build the form request:
data = {'username': config['username'], 'password': config['password']}
# POST the login form:
try:
login = task.requests.post('https://www.torrentleech.org/user/account/login/', data=data,
headers=request_headers, allow_redirects=True)
except RequestException as e:
raise PluginError('Could not connect to torrentleech: %s' % str(e))
if not isinstance(config, dict):
config = {}
# sort = SORT.get(config.get('sort_by', 'seeds'))
# if config.get('sort_reverse'):
# sort += 1
categories = config.get('category', 'all')
# Make sure categories is a list
if not isinstance(categories, list):
categories = [categories]
# If there are any text categories, turn them into their id number
categories = [c if isinstance(c, int) else CATEGORIES[c] for c in categories]
filter_url = '/categories/{}'.format(','.join(str(c) for c in categories))
entries = set()
for search_string in entry.get('search_strings', [entry['title']]):
query = normalize_unicode(search_string).replace(":", "")
# urllib.quote will crash if the unicode string has non ascii characters,
# so encode in utf-8 beforehand
url = ('https://www.torrentleech.org/torrents/browse/list/query/' +
quote(query.encode('utf-8')) + filter_url)
log.debug('Using %s as torrentleech search url', url)
results = task.requests.get(url, headers=request_headers, cookies=login.cookies).json()
for torrent in results['torrentList']:
entry = Entry()
entry['download_headers'] = request_headers
entry['title'] = torrent['name']
# construct download URL
torrent_url = 'https://www.torrentleech.org/rss/download/{}/{}/{}'.format(torrent['fid'], rss_key,
torrent['filename'])
log.debug('RSS-ified download link: %s', torrent_url)
entry['url'] = torrent_url
# seeders/leechers
entry['torrent_seeds'] = torrent['seeders']
entry['torrent_leeches'] = torrent['leechers']
entry['search_sort'] = torrent_availability(entry['torrent_seeds'], entry['torrent_leeches'])
entry['content_size'] = parse_filesize(str(torrent['size']) + ' b')
entries.add(entry)
return sorted(entries, reverse=True, key=lambda x: x.get('search_sort'))
def search(self, task, entry, config=None):
"""
Search for entries on SceneAccess
"""
session = task.requests
if 'sceneaccess.eu' not in session.domain_limiters:
session.add_domain_limiter(TimedLimiter('sceneaccess.eu', '7 seconds'))
if not session.cookies:
log.debug('Logging in to %s...' % URL)
params = {'username': config['username'],
'password': config['password'],
'submit': 'come on in'}
session.post(URL + 'login', data=params)
if 'gravity_multiplier' in config:
multip = config['gravity_multiplier']
else:
multip = 1
# Prepare queries...
base_urls = list()
entries = set()
for category in self.process_categories(config):
base_urls.append(URL + '%(url_path)s?method=2%(category_url_string)s' % category)
# Search...
for search_string in entry.get('search_strings', [entry['title']]):
search_string_normalized = normalize_unicode(clean_title(search_string))
search_string_url_fragment = '&search=' + quote(search_string_normalized.encode('utf8'))
for url in base_urls:
url += search_string_url_fragment
log.debug('Search URL for `%s`: %s' % (search_string, url))
page = session.get(url).content
soup = get_soup(page)
for result in soup.findAll('tr', attrs={'class': 'tt_row'}):
entry = Entry()
entry['title'] = result.find('a', href=re.compile(r'details\?id=\d+'))['title']
entry['url'] = URL + result.find('a', href=re.compile(r'.torrent$'))['href']
entry['torrent_seeds'] = result.find('td', attrs={'class': 'ttr_seeders'}).text
entry['torrent_leeches'] = result.find('td', attrs={'class': 'ttr_leechers'}).text
entry['search_sort'] = torrent_availability(entry['torrent_seeds'],
entry['torrent_leeches']) * multip
size = result.find('td', attrs={'class': 'ttr_size'}).text
size = re.search('(\d+(?:[.,]\d+)*)\s?([KMG]B)', size)
entry['content_size'] = parse_filesize(size.group(0))
entries.add(entry)
return entries
def search(self, task, entry, config=None):
"""
Search for name from iptorrents
"""
categories = config.get('category', 'all')
# Make sure categories is a list
if not isinstance(categories, list):
categories = [categories]
# If there are any text categories, turn them into their id number
categories = [c if isinstance(c, int) else CATEGORIES[c]
for c in categories]
filter_url = '&'.join((str(c) + '=') for c in categories)
entries = set()
for search_string in entry.get('search_strings', [entry['title']]):
query = normalize_unicode(search_string)
query = quote_plus(query.encode('utf8'))
url = "{base_url}/t?{filter}&q={query}&qf=".format(base_url=BASE_URL, filter=filter_url, query=query)
log.debug('searching with url: %s' % url)
req = requests.get(url, cookies={'uid': str(config['uid']), 'pass': config['password']})
if '/u/' + str(config.get('uid')) not in req.content:
raise plugin.PluginError("Invalid cookies (user not logged in)...")
soup = get_soup(req.content, parser="html.parser")
torrents = soup.find('table', {'class': 'torrents'})
for torrent in torrents.findAll('a', href=re.compile('\.torrent$')):
entry = Entry()
entry['url'] = "{base}{link}?torrent_pass={key}".format(
base=BASE_URL, link=torrent['href'], key=config.get('rss_key'))
entry['title'] = torrent.findPrevious("a", attrs={'class': 't_title'}).text
seeders = torrent.findNext('td', {'class': 'ac t_seeders'}).text
leechers = torrent.findNext('td', {'class': 'ac t_leechers'}).text
entry['torrent_seeds'] = int(seeders)
entry['torrent_leeches'] = int(leechers)
entry['search_sort'] = torrent_availability(entry['torrent_seeds'],
entry['torrent_leeches'])
size = torrent.findNext(text=re.compile('^([\.\d]+) ([GMK]?)B$'))
size = re.search('^([\.\d]+) ([GMK]?)B$', size)
if size:
if size.group(2) == 'G':
entry['content_size'] = int(float(size.group(1)) * 1000 ** 3 / 1024 ** 2)
elif size.group(2) == 'M':
entry['content_size'] = int(float(size.group(1)) * 1000 ** 2 / 1024 ** 2)
elif size.group(2) == 'K':
entry['content_size'] = int(float(size.group(1)) * 1000 / 1024 ** 2)
else:
entry['content_size'] = int(float(size.group(1)) / 1024 ** 2)
entries.add(entry)
return entries
def entries_from_search(self, name, url=None):
"""Parses torrent download url from search results"""
name = normalize_unicode(name)
if not url:
url = 'http://www.newtorrents.info/search/%s' % quote(
name.encode('utf-8'), safe=b':/~?=&%')
log.debug('search url: %s' % url)
html = requests.get(url).text
# fix </SCR'+'IPT> so that BS does not crash
# TODO: should use beautifulsoup massage
html = re.sub(r'(</SCR.*?)...(.*?IPT>)', r'\1\2', html)
soup = get_soup(html)
# saving torrents in dict
torrents = []
for link in soup.find_all('a', attrs={'href': re.compile('down.php')}):
torrent_url = 'http://www.newtorrents.info%s' % link.get('href')
release_name = link.parent.next.get('title')
# quick dirty hack
seed = link.find_next('td', attrs={
'class': re.compile('s')
}).renderContents()
if seed == 'n/a':
seed = 0
else:
try:
seed = int(seed)
except ValueError:
log.warning(
'Error converting seed value (%s) from newtorrents to integer.'
% seed)
seed = 0
# TODO: also parse content_size and peers from results
torrents.append(
Entry(title=release_name,
url=torrent_url,
torrent_seeds=seed,
search_sort=torrent_availability(seed, 0)))
# sort with seed number Reverse order
torrents.sort(reverse=True, key=lambda x: x.get('search_sort', 0))
# choose the torrent
if not torrents:
dashindex = name.rfind('-')
if dashindex != -1:
return self.entries_from_search(name[:dashindex])
else:
return torrents
else:
if len(torrents) == 1:
log.debug('found only one matching search result.')
else:
log.debug(
'search result contains multiple matches, sorted %s by most seeders'
% torrents)
return torrents
def search(self, task, entry, config=None):
"""
Search for name from torrentday.
"""
categories = config.get('category', 'all')
# Make sure categories is a list
if not isinstance(categories, list):
categories = [categories]
# If there are any text categories, turn them into their id number
categories = [c if isinstance(c, int) else CATEGORIES[c] for c in categories]
params = { 'cata': 'yes', 'c%s' % ','.join(str(c) for c in categories): 1, 'clear-new': 1}
entries = set()
for search_string in entry.get('search_strings', [entry['title']]):
url = 'https://www.torrentday.com/browse.php'
params['search'] = normalize_unicode(search_string).replace(':', '')
cookies = { 'uid': config['uid'], 'pass': config['passkey'], '__cfduid': config['cfduid'] }
try:
page = requests.get(url, params=params, cookies=cookies).content
except RequestException as e:
raise PluginError('Could not connect to torrentday: %s' % e)
soup = get_soup(page)
for tr in soup.find_all('tr', { 'class': 'browse' }):
entry = Entry()
# find the torrent names
title = tr.find('a', { 'class': 'torrentName' })
entry['title'] = title.contents[0]
log.debug('title: %s', title.contents[0])
# find download link
torrent_url = tr.find('td', { 'class': 'dlLinksInfo' })
torrent_url = torrent_url.find('a').get('href')
# construct download URL
torrent_url = ( 'https://www.torrentday.com/' + torrent_url + '?torrent_pass='******'rss_key'] )
log.debug('RSS-ified download link: %s', torrent_url)
entry['url'] = torrent_url
# us tr object for seeders/leechers
seeders, leechers = tr.find_all('td', { 'class': ['seedersInfo', 'leechersInfo']})
entry['torrent_seeds'] = int(seeders.contents[0].replace(',', ''))
entry['torrent_leeches'] = int(leechers.contents[0].replace(',', ''))
entry['search_sort'] = torrent_availability(entry['torrent_seeds'], entry['torrent_leeches'])
# use tr object for size
size = tr.find('td', text=re.compile('([\.\d]+) ([TGMKk]?)B')).contents[0]
size = re.search('([\.\d]+) ([TGMKk]?)B', str(size))
entry['content_size'] = parse_filesize(size.group(0))
entries.add(entry)
return sorted(entries, reverse=True, key=lambda x: x.get('search_sort'))
def search(self, task, entry, config):
search_strings = [normalize_unicode(s).lower() for s in entry.get('search_strings', [entry['title']])]
entries = set()
for search_string in search_strings:
search_string = clean_title(search_string)
search_string_url_fragment = search_string
params = {'rss': 1}
if config.get('verified'):
search_string_url_fragment += ' verified:1'
url = 'https://kat.cr/usearch/%s/' % quote(search_string_url_fragment.encode('utf-8'))
if config.get('category', 'all') != 'all':
params['category'] = config['category']
sorters = [{'field': 'time_add', 'sorder': 'desc'},
{'field': 'seeders', 'sorder': 'desc'}]
for sort in sorters:
params.update(sort)
log.debug('requesting: %s' % url)
try:
r = task.requests.get(url, params=params, raise_status=False)
except RequestException as e:
log.warning('Search resulted in: %s' % e)
continue
if not r.content:
log.debug('No content returned from search.')
continue
elif r.status_code != 200:
log.warning('Search returned %s response code' % r.status_code)
continue
rss = feedparser.parse(r.content)
ex = rss.get('bozo_exception', False)
if ex:
log.warning('Got bozo_exception (bad feed)')
continue
for item in rss.entries:
entry = Entry()
entry['title'] = item.title
if not item.get('enclosures'):
log.warning('Could not get url for entry from KAT. Maybe plugin needs updated?')
continue
entry['url'] = item.enclosures[0]['url']
entry['torrent_seeds'] = int(item.torrent_seeds)
entry['torrent_leeches'] = int(item.torrent_peers)
entry['search_sort'] = torrent_availability(entry['torrent_seeds'], entry['torrent_leeches'])
entry['content_size'] = int(item.torrent_contentlength) / 1024 / 1024
entry['torrent_info_hash'] = item.torrent_infohash
entries.add(entry)
if len(rss.entries) < 25:
break
return entries
def prepare_search_query(self, search_string):
query = normalize_unicode(search_string)
se = re.findall('((((|S)[\d]+(E|x)[\d]+)|(|S)[\d]+))$', query)[0][0]
query = re.sub(se, '', query).strip()
self.se = se
self.query = query
return query
def search(self, task, entry, config=None):
"""
Search for entries on PublicHD
"""
categories = config.get('category', 'all')
# Ensure categories a list
if not isinstance(categories, list):
categories = [categories]
# Convert named category to its respective category id number
categories = [c if isinstance(c, int) else CATEGORIES[c] for c in categories]
category_url_fragment = '&category=%s' % urllib.quote(';'.join(str(c) for c in categories))
base_url = 'http://publichd.se/index.php?page=torrents&active=0'
entries = set()
for search_string in entry.get('search_strings', [entry['title']]):
query = normalize_unicode(search_string)
query_url_fragment = '&search=' + urllib.quote(query.encode('utf8'))
# http://publichd.se/index.php?page=torrents&active=0&category=5;15&search=QUERY
url = (base_url + category_url_fragment + query_url_fragment)
log.debug('PublicHD search url: %s' % url)
page = requests.get(url).content
soup = get_soup(page)
for result in soup.findAll('a', href=re.compile('page=torrent-details')):
entry = Entry()
entry['title'] = result.text
# Expand the selection to whole row
result = result.findPrevious('tr')
download_url = result.find('a', href=re.compile('\.torrent$'))['href']
torrent_hash = re.search(r'/([0-9a-fA-F]{5,40})/', download_url).group(1)
entry['url'] = 'http://publichd.se/download.php?id=%s' % torrent_hash
seeds, leeches = result.findAll('td', text=re.compile('^\d+$'))
entry['torrent_seeds'] = int(seeds.text)
entry['torrent_leeches'] = int(leeches.text)
entry['search_sort'] = torrent_availability(entry['torrent_seeds'], entry['torrent_leeches'])
size = result.find("td", text=re.compile('(\d+(?:[.,]\d+)*)\s?([KMG]B)')).text
size = re.search('(\d+(?:[.,]\d+)*)\s?([KMG]B)', size)
if size:
if size.group(2) == 'GB':
entry['content_size'] = int(float(size.group(1).replace(',', '')) * 1000 ** 3 / 1024 ** 2)
elif size.group(2) == 'MB':
entry['content_size'] = int(float(size.group(1).replace(',', '')) * 1000 ** 2 / 1024 ** 2)
elif size.group(2) == 'KB':
entry['content_size'] = int(float(size.group(1).replace(',', '')) * 1000 / 1024 ** 2)
else:
entry['content_size'] = int(float(size.group(1).replace(',', '')) / 1024 ** 2)
entries.add(entry)
return entries
def search(self, task, entry, config=None):
"""
Search for entries on PublicHD
"""
categories = config.get('category', 'all')
# Ensure categories a list
if not isinstance(categories, list):
categories = [categories]
# Convert named category to its respective category id number
categories = [c if isinstance(c, int) else CATEGORIES[c] for c in categories]
category_url_fragment = '&category=%s' % urllib.parse.quote(';'.join(str(c) for c in categories))
base_url = 'http://publichd.se/index.php?page=torrents&active=0'
entries = set()
for search_string in entry.get('search_strings', [entry['title']]):
query = normalize_unicode(search_string)
query_url_fragment = '&search=' + urllib.parse.quote(query.encode('utf8'))
# http://publichd.se/index.php?page=torrents&active=0&category=5;15&search=QUERY
url = (base_url + category_url_fragment + query_url_fragment)
log.debug('PublicHD search url: %s' % url)
page = requests.get(url).content
soup = get_soup(page)
for result in soup.findAll('a', href=re.compile('page=torrent-details')):
entry = Entry()
entry['title'] = result.text
# Expand the selection to whole row
result = result.findPrevious('tr')
download_url = result.find('a', href=re.compile('\.torrent$'))['href']
torrent_hash = re.search(r'/([0-9a-fA-F]{5,40})/', download_url).group(1)
entry['url'] = 'http://publichd.se/download.php?id=%s' % torrent_hash
seeds, leeches = result.findAll('td', text=re.compile('^\d+$'))
entry['torrent_seeds'] = int(seeds.text)
entry['torrent_leeches'] = int(leeches.text)
entry['search_sort'] = torrent_availability(entry['torrent_seeds'], entry['torrent_leeches'])
size = result.find("td", text=re.compile('(\d+(?:[.,]\d+)*)\s?([KMG]B)')).text
size = re.search('(\d+(?:[.,]\d+)*)\s?([KMG]B)', size)
if size:
if size.group(2) == 'GB':
entry['content_size'] = int(float(size.group(1).replace(',', '')) * 1000 ** 3 / 1024 ** 2)
elif size.group(2) == 'MB':
entry['content_size'] = int(float(size.group(1).replace(',', '')) * 1000 ** 2 / 1024 ** 2)
elif size.group(2) == 'KB':
entry['content_size'] = int(float(size.group(1).replace(',', '')) * 1000 / 1024 ** 2)
else:
entry['content_size'] = int(float(size.group(1).replace(',', '')) / 1024 ** 2)
entries.add(entry)
return entries
def search(self, entry, config=None):
config = self.process_config(config)
feed = REPUTATIONS[config['reputation']]
entries = set()
for search_string in entry.get('search_string', [entry['title']]):
query = normalize_unicode(search_string +
config.get('extra_terms', ''))
# urllib.quote will crash if the unicode string has non ascii characters, so encode in utf-8 beforehand
url = 'http://torrentz.eu/%s?q=%s' % (
feed, urllib.quote(query.encode('utf-8')))
log.debug('requesting: %s' % url)
try:
opened = urllib2.urlopen(url)
except urllib2.URLError as err:
url = 'http://torrentz.me/%s?q=%s' % (
feed, urllib.quote(query.encode('utf-8')))
log.warning(
'torrentz.eu failed, trying torrentz.me. Error: %s' % err)
try:
opened = urllib2.urlopen(url)
except urllib2.URLError as err:
raise plugin.PluginWarning('Error requesting URL: %s' %
err)
rss = feedparser.parse(opened)
status = rss.get('status', False)
if status != 200:
raise plugin.PluginWarning(
'Search result not 200 (OK), received %s %s' %
(status, opened.msg))
ex = rss.get('bozo_exception', False)
if ex:
raise plugin.PluginWarning('Got bozo_exception (bad feed)')
for item in rss.entries:
m = re.search(
r'Size: ([\d]+) Mb Seeds: ([,\d]+) Peers: ([,\d]+) Hash: ([a-f0-9]+)',
item.description, re.IGNORECASE)
if not m:
log.debug('regexp did not find seeds / peer data')
continue
entry = Entry()
entry['title'] = item.title
entry['url'] = item.link
entry['content_size'] = int(m.group(1))
entry['torrent_seeds'] = int(m.group(2).replace(',', ''))
entry['torrent_leeches'] = int(m.group(3).replace(',', ''))
entry['torrent_info_hash'] = m.group(4).upper()
entry['search_sort'] = torrent_availability(
entry['torrent_seeds'], entry['torrent_leeches'])
entries.add(entry)
log.debug('Search got %d results' % len(entries))
return entries
def search(self, task, entry, config=None):
"""
Search for name from fuzer.
"""
self.rss_key = config['rss_key']
username = config['username']
password = hashlib.md5(config['password'].encode('utf-8')).hexdigest()
# build the form request:
data = {'cookieuser': '******',
'do': 'login',
's': '',
'securitytoken': 'guest',
'vb_login_username': username,
'vb_login_password': '',
'vb_login_md5password': password,
'vb_login_md5password_utf': password
}
# POST the login form:
try:
login = requests.post('https://www.fuzer.me/login.php?do=login', data=data)
except RequestException as e:
raise PluginError('Could not connect to fuzer: %s' % str(e))
login_check_phrases = ['ההתחברות נכשלה', 'banned']
if any(phrase in login.text for phrase in login_check_phrases):
raise PluginError('Login to Fuzer failed, check credentials')
self.user_id = requests.cookies.get('fzr2userid')
category = config.get('category', [0])
# Make sure categories is a list
if not isinstance(category, list):
category = [category]
# If there are any text categories, turn them into their id number
categories = [c if isinstance(c, int) else CATEGORIES[c] for c in category]
c_list = []
for c in categories:
c_list.append('c{}={}'.format(quote_plus('[]'), c))
entries = []
if entry.get('imdb_id'):
log.debug('imdb_id {} detected, using in search.'.format(entry['imdb_id']))
soup = self.get_fuzer_soup(entry['imdb_id'], c_list)
entries = self.extract_entry_from_soup(soup)
if entries:
for e in list(entries):
e['imdb_id'] = entry.get('imdb_id')
else:
for search_string in entry.get('search_strings', [entry['title']]):
query = normalize_unicode(search_string).replace(":", "")
text = quote_plus(query.encode('windows-1255'))
soup = self.get_fuzer_soup(text, c_list)
entries += self.extract_entry_from_soup(soup)
return sorted(entries, reverse=True, key=lambda x: x.get('search_sort')) if entries else []
def search(self, task, entry, config):
"""
Search for entries on RarBG
"""
categories = config.get('category', 'all')
# Ensure categories a list
if not isinstance(categories, list):
categories = [categories]
# Convert named category to its respective category id number
categories = [c if isinstance(c, int) else CATEGORIES[c] for c in categories]
category_url_fragment = ';'.join(str(c) for c in categories)
entries = set()
token = self.get_token()
if not token:
log.error('No token set. Exiting RARBG search.')
return entries
params = {'mode': 'search', 'token': token, 'ranked': int(config['ranked']),
'min_seeders': config['min_seeders'], 'min_leechers': config['min_leechers'],
'sort': config['sorted_by'], 'category': category_url_fragment, 'format': 'json'}
for search_string in entry.get('search_strings', [entry['title']]):
params.pop('search_string', None)
params.pop('search_imdb', None)
if entry.get('movie_name'):
params['search_imdb'] = entry.get('imdb_id')
else:
query = normalize_unicode(search_string)
query_url_fragment = query.encode('utf8')
params['search_string'] = query_url_fragment
if config['use_tvdb']:
plugin.get_plugin_by_name('thetvdb_lookup').instance.lazy_series_lookup(entry)
params['search_tvdb'] = entry.get('tvdb_id')
log.debug('Using tvdb id %s' % entry.get('tvdb_id'))
page = requests.get(self.base_url, params=params)
log.debug('requesting: %s' % page.url)
try:
r = page.json()
except ValueError:
log.debug(page.text)
continue
for result in r:
e = Entry()
e['title'] = result.get('f')
e['url'] = result.get('d')
entries.add(e)
return entries
def search(self, entry, config):
search_strings = [normalize_unicode(s).lower() for s in entry.get('search_strings', [entry['title']])]
entries = set()
for search_string in search_strings:
search_string_url_fragment = search_string
if config.get('verified'):
search_string_url_fragment += ' verified:1'
url = 'http://kickass.to/search/%s/?rss=1' % urllib.quote(search_string_url_fragment.encode('utf-8'))
if config.get('category', 'all') != 'all':
url += '&category=%s' % config['category']
sorters = [{'field': 'time_add', 'sorder': 'desc'},
{'field': 'seeders', 'sorder': 'desc'}]
for sort in sorters:
url += '&field=%(field)s&sorder=%(sorder)s' % sort
log.debug('requesting: %s' % url)
rss = feedparser.parse(url)
status = rss.get('status', False)
if status == 404:
# Kat returns status code 404 when no results found for some reason...
log.debug('No results found for search query: %s' % search_string)
continue
elif status not in [200, 301]:
log.warning('Search result not 200 (OK), received %s' % status)
continue
ex = rss.get('bozo_exception', False)
if ex:
log.warning('Got bozo_exception (bad feed)')
continue
for item in rss.entries:
entry = Entry()
entry['title'] = item.title
if not item.get('enclosures'):
log.warning('Could not get url for entry from KAT. Maybe plugin needs updated?')
continue
entry['url'] = item.enclosures[0]['url']
entry['torrent_seeds'] = int(item.torrent_seeds)
entry['torrent_leeches'] = int(item.torrent_peers)
entry['search_sort'] = torrent_availability(entry['torrent_seeds'], entry['torrent_leeches'])
entry['content_size'] = int(item.torrent_contentlength) / 1024 / 1024
entry['torrent_info_hash'] = item.torrent_infohash
entries.add(entry)
if len(rss.entries) < 25:
break
return entries
def search(self, task, entry, config=None):
"""
Search for entries on Serienjunkies
"""
base_url = 'http://serienjunkies.org/search/'
mull = {
"Dauer:", "Download:", "Uploader:", u"Größe:", u"Tonhöhe:",
"Sprache:", "Format:", "HQ-Cover:"
}
self.config = task.config.get('searchSerienjunkies') or {}
self.config.setdefault('hoster', DEFHOS)
self.config.setdefault('language', DEFLANG)
entries = set()
for search_string in entry.get('search_strings', [entry['title']]):
query = normalize_unicode(search_string)
query_url_fragment = urllib.quote(query.encode('utf8'))
# http://serienjunkies.org/search/QUERY
url = (base_url + query_url_fragment)
log.debug('Serienjunkies search url: %s' % url)
page = requests.get(url).content
soup = get_soup(page)
hoster = self.config['hoster']
if self.config['language'] == 'english':
english = True
else:
english = None
for p in soup.find_all('p'):
entry = Entry()
if p.strong is not None and p.strong.text not in mull:
if english:
try:
if not p.strong.find(text=re.compile(
"german", flags=re.IGNORECASE)):
link = p.find(
text=re.compile(hoster)).find_previous('a')
entry['title'] = p.strong.text
entry['url'] = link.get('href')
entries.add(entry)
except:
pass
else:
try:
if p.strong.find(text=re.compile(
"german", flags=re.IGNORECASE)):
link = p.find(
text=re.compile(hoster)).find_previous('a')
entry['title'] = p.strong.text
entry['url'] = link.get('href')
entries.add(entry)
except:
pass
return entries
def search(self, task, entry, config):
"""Search interface"""
self.setup(task, config)
entries = set()
params = self.params_from_config(config)
for search_string in entry.get('search_strings', [entry['title']]):
query = normalize_unicode(search_string)
params[self._key('search')] = query
entries.update(self.get_entries(self.search_results(params)))
return entries
def search(self, task, entry, config=None):
"""
Search for name from piratebay.
"""
if not isinstance(config, dict):
config = {}
self.set_urls(config.get('url', URL))
sort = SORT.get(config.get('sort_by', 'seeds'))
if config.get('sort_reverse'):
sort += 1
if isinstance(config.get('category'), int):
category = config['category']
else:
category = CATEGORIES.get(config.get('category', 'all'))
filter_url = '/0/%d/%d' % (sort, category)
entries = set()
for search_string in entry.get('search_strings', [entry['title']]):
query = normalize_unicode(search_string)
# TPB search doesn't like dashes or quotes
query = query.replace('-', ' ').replace("'", " ")
# urllib.quote will crash if the unicode string has non ascii characters, so encode in utf-8 beforehand
url = '%s/search/%s%s' % (self.url, quote(query.encode('utf-8')), filter_url)
log.debug('Using %s as piratebay search url' % url)
page = task.requests.get(url).content
soup = get_soup(page)
for link in soup.find_all('a', attrs={'class': 'detLink'}):
entry = Entry()
entry['title'] = self.extract_title(link)
if not entry['title']:
log.error('Malformed search result. No title or url found. Skipping.')
continue
href = link.get('href')
if href.startswith('/'): # relative link?
href = self.url + href
entry['url'] = href
tds = link.parent.parent.parent.find_all('td')
entry['torrent_seeds'] = int(tds[-2].contents[0])
entry['torrent_leeches'] = int(tds[-1].contents[0])
entry['search_sort'] = torrent_availability(entry['torrent_seeds'], entry['torrent_leeches'])
# Parse content_size
size_text = link.find_next(attrs={'class': 'detDesc'}).get_text()
if size_text:
size = re.search('Size (\d+(\.\d+)?\xa0(?:[PTGMK])?i?B)', size_text)
if size:
entry['content_size'] = parse_filesize(size.group(1))
else:
log.error('Malformed search result? Title: "%s", No size? %s', entry['title'], size_text)
entries.add(entry)
return sorted(entries, reverse=True, key=lambda x: x.get('search_sort'))
def search(self, arg_entry, config=None):
"""
Search for name from piratebay.
"""
if not isinstance(config, dict):
config = {}
sort = SORT.get(config.get('sort_by', 'seeds'))
if config.get('sort_reverse'):
sort += 1
if isinstance(config.get('category'), int):
category = config['category']
else:
category = CATEGORIES.get(config.get('category', 'all'))
filter_url = '/0/%d/%d' % (sort, category)
entries = set()
for search_string in arg_entry.get('search_string',
[arg_entry['title']]):
query = normalize_unicode(search_string)
# TPB search doesn't like dashes
query = query.replace('-', ' ')
# urllib.quote will crash if the unicode string has non ascii characters, so encode in utf-8 beforehand
url = 'http://thepiratebay.%s/search/%s%s' % (
CUR_TLD, urllib.quote(query.encode('utf-8')), filter_url)
log.debug('Using %s as piratebay search url' % url)
page = requests.get(url).content
soup = get_soup(page)
for link in soup.find_all('a', attrs={'class': 'detLink'}):
entry = Entry()
entry['title'] = link.contents[0]
entry['url'] = 'http://thepiratebay.%s%s' % (CUR_TLD,
link.get('href'))
tds = link.parent.parent.parent.find_all('td')
entry['torrent_seeds'] = int(tds[-2].contents[0])
entry['torrent_leeches'] = int(tds[-1].contents[0])
entry['search_sort'] = torrent_availability(
entry['torrent_seeds'], entry['torrent_leeches'])
# Parse content_size
size = link.find_next(attrs={'class': 'detDesc'}).contents[0]
size = re.search('Size ([\.\d]+)\xa0([GMK])iB', size)
if size:
if size.group(2) == 'G':
entry['content_size'] = int(
float(size.group(1)) * 1000**3 / 1024**2)
elif size.group(2) == 'M':
entry['content_size'] = int(
float(size.group(1)) * 1000**2 / 1024**2)
else:
entry['content_size'] = int(
float(size.group(1)) * 1000 / 1024**2)
entries.add(entry)
return sorted(
entries, reverse=True, key=lambda x: x.get('search_sort'))
def search(self, entry, config):
# urllib.quote will crash if the unicode string has non ascii characters, so encode in utf-8 beforehand
name = normalize_unicode(entry['title'])
optionlist = [
'misc', 'movies', 'audio', 'tv', 'games', 'apps', 'pics', 'anime',
'comics', 'books', 'music video', 'unclassified', 'all'
]
url = 'http://isohunt.com/js/rss/%s?iht=%s&noSL' % (urllib.quote(
name.encode('utf-8')), optionlist.index(config))
log.debug('requesting: %s' % url)
rss = feedparser.parse(url)
entries = []
status = rss.get('status', False)
if status != 200:
raise PluginWarning('Search result not 200 (OK), received %s' %
status)
ex = rss.get('bozo_exception', False)
if ex:
raise PluginWarning('Got bozo_exception (bad feed)')
for item in rss.entries:
entry = Entry()
entry['title'] = item.title
entry['url'] = item.link
m = re.search(r'Size: ([\d]+).*Seeds: (\d+).*Leechers: (\d+)',
item.description, re.IGNORECASE)
if not m:
log.debug('regexp did not find seeds / peer data')
continue
else:
log.debug('regexp found size(%s), Seeds(%s) and Leeches(%s)' %
(m.group(1), m.group(2), m.group(3)))
entry['content_size'] = int(m.group(1))
entry['torrent_seeds'] = int(m.group(2))
entry['torrent_leeches'] = int(m.group(3))
entry['search_sort'] = torrent_availability(
entry['torrent_seeds'], entry['torrent_leeches'])
entries.append(entry)
# choose torrent
if not entries:
raise PluginWarning('No close matches for %s' % name,
log,
log_once=True)
entries.sort(reverse=True, key=lambda x: x.get('search_sort'))
return entries
def search(self, task, entry, config=None):
config = self.prepare_config(config)
if not session.cookies:
log.debug('Logging in to %s...' % URL)
params = {
'username': config['username'],
'password': config['password'],
'keeplogged': '1',
'login': '******'
}
session.post(URL + 'login.php', data=params)
cat = ''.join([
'&' + ('filter_cat[%s]' % id) + '=1' for id in config['category']
])
rls = 'release_type=' + config['type']
url_params = rls + cat
multip = config['gravity_multiplier']
entries = set()
for search_string in entry.get('search_strings', [entry['title']]):
srch = normalize_unicode(clean_title(search_string))
srch = '&searchstr=' + quote(srch.encode('utf8'))
url = URL + 'torrents.php?' + url_params + srch
log.debug('Fetching URL for `%s`: %s' % (search_string, url))
page = session.get(url).content
soup = get_soup(page)
for result in soup.findAll('tr', attrs={'class': 'torrent'}):
entry = Entry()
entry['title'] = result.find('span',
attrs={
'class': 'torrent_name_link'
}).text
entry['url'] = URL + result.find(
'a', href=re.compile(
'torrents\.php\?action=download')).get('href')
entry['torrent_seeds'], entry['torrent_leeches'] = [
r.text for r in result.findAll('td')[-2:]
]
entry['search_sort'] = torrent_availability(
entry['torrent_seeds'], entry['torrent_leeches']) * multip
size = result.findAll('td')[-4].text
size = re.search('(\d+(?:[.,]\d+)*)\s?([KMG]B)', size)
entry['content_size'] = parse_filesize(size.group(0))
entries.add(entry)
return entries
def search(self, task, entry, config=None):
if not config:
log.debug('Divxatope disabled')
return set()
log.debug('Search DivxATope')
url_search = 'http://divxatope1.com/buscar/descargas'
results = set()
for search_string in entry.get('search_strings', [entry['title']]):
query = normalize_unicode(search_string)
query = re.sub(' \(\d\d\d\d\)$', '', query)
log.debug('Searching DivxATope %s' % query)
query = query.encode('utf8', 'ignore')
data = {'q': query}
try:
response = task.requests.post(url_search, data=data)
except requests.RequestException as e:
log.error('Error searching DivxATope: %s' % e)
return
content = response.content
soup = get_soup(content)
if 'divxatope1.com' in url_search:
soup2 = soup.find('ul', attrs={'class': 'buscar-list'})
else:
soup2 = soup.find('ul', attrs={'class': 'peliculas-box'})
children = soup2.findAll('a', href=True)
for child in children:
entry = Entry()
entry['url'] = child['href']
entry_title = child.find('h2')
if entry_title is None:
continue
entry_title = entry_title.contents
if not entry_title:
continue
else:
entry_title = entry_title[0]
quality_lan = child.find('strong')
if quality_lan is None:
continue
quality_lan = quality_lan.contents
if len(quality_lan) > 2:
if (isinstance(quality_lan[0], Tag)):
entry_quality_lan = quality_lan[1]
else:
entry_quality_lan = quality_lan[0] + ' ' + quality_lan[
2]
elif len(quality_lan) == 2:
entry_quality_lan = quality_lan[1]
entry['title'] = entry_title + ' ' + entry_quality_lan
results.add(entry)
log.debug('Finish search DivxATope with %d entries' % len(results))
return results
def search(self, task, entry, config=None):
if not config:
log.debug('Divxatope disabled')
return set()
log.debug('Search DivxATope')
url_search = 'http://divxatope1.com/buscar/descargas'
results = set()
for search_string in entry.get('search_strings', [entry['title']]):
query = normalize_unicode(search_string)
query = re.sub(' \(\d\d\d\d\)$', '', query)
log.debug('Searching DivxATope %s' % query)
query = query.encode('utf8', 'ignore')
data = {'q': query}
try:
response = task.requests.post(url_search, data=data)
except requests.RequestException as e:
log.error('Error searching DivxATope: %s' % e)
return
content = response.content
soup = get_soup(content)
if 'divxatope1.com' in url_search:
soup2 = soup.find('ul', attrs={'class': 'buscar-list'})
else:
soup2 = soup.find('ul', attrs={'class': 'peliculas-box'})
children = soup2.findAll('a', href=True)
for child in children:
entry = Entry()
entry['url'] = child['href']
entry_title = child.find('h2')
if entry_title is None:
continue
entry_title = entry_title.contents
if not entry_title:
continue
else:
entry_title = entry_title[0]
quality_lan = child.find('strong')
if quality_lan is None:
continue
quality_lan = quality_lan.contents
if len(quality_lan) > 2:
if (isinstance(quality_lan[0], Tag)):
entry_quality_lan = quality_lan[1]
else:
entry_quality_lan = quality_lan[0] + ' ' + quality_lan[2]
elif len(quality_lan) == 2:
entry_quality_lan = quality_lan[1]
entry['title'] = entry_title + ' ' + entry_quality_lan
results.add(entry)
log.debug('Finish search DivxATope with %d entries' % len(results))
return results
def search(self, task, entry, config=None):
config = self.prepare_config(config)
if not session.cookies:
log.debug('Logging in to %s...' % URL)
params = {
'username': config['username'],
'password': config['password'],
'keeplogged': '1',
'login': '******'
}
session.post(URL + 'login.php', data=params)
cat = ''.join(['&' + ('filter_cat[%s]' % id) + '=1' for id in config['category']])
rls = 'release_type=' + config['type']
url_params = rls + cat
multip = config['gravity_multiplier']
entries = set()
for search_string in entry.get('search_strings', [entry['title']]):
srch = normalize_unicode(clean_title(search_string))
srch = '&searchstr=' + quote(srch.encode('utf8'))
url = URL + 'torrents.php?' + url_params + srch
log.debug('Fetching URL for `%s`: %s' % (search_string, url))
page = session.get(url).content
soup = get_soup(page)
for result in soup.findAll('tr', attrs={'class': 'torrent'}):
entry = Entry()
entry['title'] = result.find('span', attrs={'class': 'torrent_name_link'}).text
entry['url'] = URL + result.find('a', href=re.compile('torrents\.php\?action=download')).get('href')
entry['torrent_seeds'], entry['torrent_leeches'] = [r.text for r in result.findAll('td')[-2:]]
entry['search_sort'] = torrent_availability(entry['torrent_seeds'], entry['torrent_leeches']) * multip
size = result.findAll('td')[-4].text
size = re.search('(\d+(?:[.,]\d+)*)\s?([KMG]B)', size)
if size:
if size.group(2) == 'GB':
entry['content_size'] = int(float(size.group(1).replace(',', '')) * 1000 ** 3 / 1024 ** 2)
elif size.group(2) == 'MB':
entry['content_size'] = int(float(size.group(1).replace(',', '')) * 1000 ** 2 / 1024 ** 2)
elif size.group(2) == 'KB':
entry['content_size'] = int(float(size.group(1).replace(',', '')) * 1000 / 1024 ** 2)
else:
entry['content_size'] = int(float(size.group(1).replace(',', '')) / 1024 ** 2)
entries.add(entry)
return entries
def entries_from_search(self, name, url=None):
"""Parses torrent download url from search results"""
name = normalize_unicode(name)
if not url:
url = "http://www.newtorrents.info/search/%s" % urllib.quote(name.encode("utf-8"), safe=b":/~?=&%")
log.debug("search url: %s" % url)
html = urlopener(url, log).read()
# fix </SCR'+'IPT> so that BS does not crash
# TODO: should use beautifulsoup massage
html = re.sub(r"(</SCR.*?)...(.*?IPT>)", r"\1\2", html)
soup = get_soup(html)
# saving torrents in dict
torrents = []
for link in soup.find_all("a", attrs={"href": re.compile("down.php")}):
torrent_url = "http://www.newtorrents.info%s" % link.get("href")
release_name = link.parent.next.get("title")
# quick dirty hack
seed = link.find_next("td", attrs={"class": re.compile("s")}).renderContents()
if seed == "n/a":
seed = 0
else:
try:
seed = int(seed)
except ValueError:
log.warning("Error converting seed value (%s) from newtorrents to integer." % seed)
seed = 0
# TODO: also parse content_size and peers from results
torrents.append(
Entry(
title=release_name, url=torrent_url, torrent_seeds=seed, search_sort=torrent_availability(seed, 0)
)
)
# sort with seed number Reverse order
torrents.sort(reverse=True, key=lambda x: x.get("search_sort", 0))
# choose the torrent
if not torrents:
dashindex = name.rfind("-")
if dashindex != -1:
return self.entries_from_search(name[:dashindex])
else:
return torrents
else:
if len(torrents) == 1:
log.debug("found only one matching search result.")
else:
log.debug("search result contains multiple matches, sorted %s by most seeders" % torrents)
return torrents
def search(self, task, entry, config=None):
config = self.process_config(config)
feed = REPUTATIONS[config['reputation']]
entries = set()
for search_string in entry.get('search_strings', [entry['title']]):
query = normalize_unicode(search_string + config.get('extra_terms', ''))
for domain in ['eu', 'me', 'ch', 'in']:
# urllib.quote will crash if the unicode string has non ascii characters, so encode in utf-8 beforehand
url = 'http://torrentz.%s/%s?q=%s' % (domain, feed, quote(query.encode('utf-8')))
log.debug('requesting: %s' % url)
try:
r = task.requests.get(url)
break
except requests.ConnectionError as err:
# The different domains all resolve to the same ip, so only try more if it was a dns error
log.warning('torrentz.%s connection failed. Error: %s' % (domain, err))
continue
except requests.RequestException as err:
raise plugin.PluginError('Error getting torrentz search results: %s' % err)
else:
raise plugin.PluginError('Error getting torrentz search results')
if not r.content.strip():
raise plugin.PluginError('No data from %s. Maybe torrentz is blocking the FlexGet User-Agent' % url)
rss = feedparser.parse(r.content)
if rss.get('bozo_exception'):
raise plugin.PluginError('Got bozo_exception (bad rss feed)')
for item in rss.entries:
m = re.search(r'Size: ([\d]+) Mb Seeds: ([,\d]+) Peers: ([,\d]+) Hash: ([a-f0-9]+)',
item.description, re.IGNORECASE)
if not m:
log.debug('regexp did not find seeds / peer data')
continue
entry = Entry()
entry['title'] = item.title
entry['url'] = item.link
entry['content_size'] = int(m.group(1))
entry['torrent_seeds'] = int(m.group(2).replace(',', ''))
entry['torrent_leeches'] = int(m.group(3).replace(',', ''))
entry['torrent_info_hash'] = m.group(4).upper()
entry['search_sort'] = torrent_availability(entry['torrent_seeds'], entry['torrent_leeches'])
entries.add(entry)
log.debug('Search got %d results' % len(entries))
return entries
def search(self, entry, config=None):
if config:
feed = REPUTATIONS[config]
else:
feed = REPUTATIONS['good']
query = normalize_unicode(entry['title'])
# urllib.quote will crash if the unicode string has non ascii characters, so encode in utf-8 beforehand
url = 'http://torrentz.eu/%s?q=%s' % (
feed, urllib.quote(query.encode('utf-8')))
log.debug('requesting: %s' % url)
rss = feedparser.parse(url)
entries = []
status = rss.get('status', False)
if status != 200:
raise PluginWarning('Search result not 200 (OK), received %s' %
status)
ex = rss.get('bozo_exception', False)
if ex:
raise PluginWarning('Got bozo_exception (bad feed)')
for item in rss.entries:
m = re.search(
r'Size: ([\d]+) Mb Seeds: ([,\d]+) Peers: ([,\d]+) Hash: ([a-f0-9]+)',
item.description, re.IGNORECASE)
if not m:
log.debug('regexp did not find seeds / peer data')
continue
entry = Entry()
entry['title'] = item.title
entry['url'] = item.link
entry['content_size'] = int(m.group(1))
entry['torrent_seeds'] = int(m.group(2).replace(',', ''))
entry['torrent_leeches'] = int(m.group(3).replace(',', ''))
entry['torrent_info_hash'] = m.group(4).upper()
entry['search_sort'] = torrent_availability(
entry['torrent_seeds'], entry['torrent_leeches'])
entries.append(entry)
# choose torrent
if not entries:
raise PluginWarning('No close matches for %s' % query,
log,
log_once=True)
entries.sort(reverse=True, key=lambda x: x.get('search_sort'))
log.debug('Search got %d results' % len(entries))
return entries
def search(self, task, entry, config=None):
"""
Search for name from piratebay.
"""
if not isinstance(config, dict):
config = {}
sort = SORT.get(config.get("sort_by", "seeds"))
if config.get("sort_reverse"):
sort += 1
if isinstance(config.get("category"), int):
category = config["category"]
else:
category = CATEGORIES.get(config.get("category", "all"))
filter_url = "/0/%d/%d" % (sort, category)
entries = set()
for search_string in entry.get("search_strings", [entry["title"]]):
query = normalize_unicode(search_string)
# TPB search doesn't like dashes
query = query.replace("-", " ")
# urllib.quote will crash if the unicode string has non ascii characters, so encode in utf-8 beforehand
url = "http://thepiratebay.%s/search/%s%s" % (CUR_TLD, quote(query.encode("utf-8")), filter_url)
log.debug("Using %s as piratebay search url" % url)
page = requests.get(url).content
soup = get_soup(page)
for link in soup.find_all("a", attrs={"class": "detLink"}):
entry = Entry()
entry["title"] = self.extract_title(link)
if not entry["title"]:
log.error("Malformed search result. No title or url found. Skipping.")
continue
entry["url"] = "http://thepiratebay.%s%s" % (CUR_TLD, link.get("href"))
tds = link.parent.parent.parent.find_all("td")
entry["torrent_seeds"] = int(tds[-2].contents[0])
entry["torrent_leeches"] = int(tds[-1].contents[0])
entry["search_sort"] = torrent_availability(entry["torrent_seeds"], entry["torrent_leeches"])
# Parse content_size
size = link.find_next(attrs={"class": "detDesc"}).contents[0]
size = re.search("Size ([\.\d]+)\xa0([GMK])iB", size)
if size:
if size.group(2) == "G":
entry["content_size"] = int(float(size.group(1)) * 1000 ** 3 / 1024 ** 2)
elif size.group(2) == "M":
entry["content_size"] = int(float(size.group(1)) * 1000 ** 2 / 1024 ** 2)
else:
entry["content_size"] = int(float(size.group(1)) * 1000 / 1024 ** 2)
entries.add(entry)
return sorted(entries, reverse=True, key=lambda x: x.get("search_sort"))
def search(self, entry, config=None):
config = self.process_config(config)
feed = REPUTATIONS[config['reputation']]
entries = set()
for search_string in entry.get('search_string', [entry['title']]):
query = normalize_unicode(search_string+config.get('extra_terms', ''))
# urllib.quote will crash if the unicode string has non ascii characters, so encode in utf-8 beforehand
url = 'http://torrentz.eu/%s?q=%s' % (feed, urllib.quote(query.encode('utf-8')))
log.debug('requesting: %s' % url)
try:
opened = urllib2.urlopen(url)
except urllib2.URLError as err:
url = 'http://torrentz.me/%s?q=%s' % (feed, urllib.quote(query.encode('utf-8')))
log.warning('torrentz.eu failed, trying torrentz.me. Error: %s' % err)
try:
opened = urllib2.urlopen(url)
except urllib2.URLError as err:
raise plugin.PluginWarning('Error requesting URL: %s' % err)
rss = feedparser.parse(opened)
status = rss.get('status', False)
if status != 200:
raise plugin.PluginWarning(
'Search result not 200 (OK), received %s %s' %
(status, opened.msg))
ex = rss.get('bozo_exception', False)
if ex:
raise plugin.PluginWarning('Got bozo_exception (bad feed)')
for item in rss.entries:
m = re.search(r'Size: ([\d]+) Mb Seeds: ([,\d]+) Peers: ([,\d]+) Hash: ([a-f0-9]+)',
item.description, re.IGNORECASE)
if not m:
log.debug('regexp did not find seeds / peer data')
continue
entry = Entry()
entry['title'] = item.title
entry['url'] = item.link
entry['content_size'] = int(m.group(1))
entry['torrent_seeds'] = int(m.group(2).replace(',', ''))
entry['torrent_leeches'] = int(m.group(3).replace(',', ''))
entry['torrent_info_hash'] = m.group(4).upper()
entry['search_sort'] = torrent_availability(entry['torrent_seeds'], entry['torrent_leeches'])
entries.add(entry)
log.debug('Search got %d results' % len(entries))
return entries
def search(self, entry, config=None):
config = self.process_config(config)
feed = REPUTATIONS[config['reputation']]
entries = set()
for search_string in entry.get('search_string', [entry['title']]):
query = normalize_unicode(search_string +
config.get('extra_terms', ''))
for domain in ['eu', 'me']:
# urllib.quote will crash if the unicode string has non ascii characters, so encode in utf-8 beforehand
url = 'http://torrentz.%s/%s?q=%s' % (
domain, feed, urllib.quote(query.encode('utf-8')))
log.debug('requesting: %s' % url)
try:
r = requests.get(url)
break
except requests.RequestException as err:
log.warning('torrentz.%s failed. Error: %s' %
(domain, err))
else:
raise plugin.PluginWarning(
'Error getting torrentz search results')
rss = feedparser.parse(r.content)
ex = rss.get('bozo_exception', False)
if ex:
raise plugin.PluginWarning('Got bozo_exception (bad feed)')
for item in rss.entries:
m = re.search(
r'Size: ([\d]+) Mb Seeds: ([,\d]+) Peers: ([,\d]+) Hash: ([a-f0-9]+)',
item.description, re.IGNORECASE)
if not m:
log.debug('regexp did not find seeds / peer data')
continue
entry = Entry()
entry['title'] = item.title
entry['url'] = item.link
entry['content_size'] = int(m.group(1))
entry['torrent_seeds'] = int(m.group(2).replace(',', ''))
entry['torrent_leeches'] = int(m.group(3).replace(',', ''))
entry['torrent_info_hash'] = m.group(4).upper()
entry['search_sort'] = torrent_availability(
entry['torrent_seeds'], entry['torrent_leeches'])
entries.add(entry)
log.debug('Search got %d results' % len(entries))
return entries
def search(self, entry, config=None):
from flexget.utils.template import environment
from flexget.manager import manager
query = entry['title']
search_string = urllib.quote(normalize_unicode(query).encode('utf-8'))
rss_plugin = get_plugin_by_name('rss')
# Create a fake task to pass to the rss plugin input handler
task = Task(manager, 'search_rss_task', {})
# Use a copy of the config, so we don't overwrite jinja url when filling in search term
config = rss_plugin.instance.build_config(config).copy()
template = environment.from_string(config['url'])
config['url'] = template.render({'search_term': search_string})
config['all_entries'] = True
# TODO: capture some other_fields to try to find seed/peer/content_size numbers?
return rss_plugin.phase_handlers['input'](task, config)
def search(self, task, entry, config=None):
"""
Search for entries on Serienjunkies
"""
base_url = 'http://serienjunkies.org/search/'
mull = {"Dauer:", "Download:", "Uploader:", u"Größe:", u"Tonhöhe:", "Sprache:", "Format:", "HQ-Cover:"}
self.config = task.config.get('searchSerienjunkies') or {}
self.config.setdefault('hoster', DEFHOS)
self.config.setdefault('language', DEFLANG)
entries = set()
for search_string in entry.get('search_strings', [entry['title']]):
query = normalize_unicode(search_string)
query_url_fragment = urllib.quote(query.encode('utf8'))
# http://serienjunkies.org/search/QUERY
url = (base_url + query_url_fragment)
log.debug('Serienjunkies search url: %s' % url)
page = requests.get(url).content
soup = get_soup(page)
hoster = self.config['hoster']
if self.config['language'] == 'english':
english = True
else:
english = None
for p in soup.find_all('p'):
entry = Entry()
if p.strong is not None and p.strong.text not in mull:
if english:
try:
if not p.strong.find(text=re.compile("german", flags=re.IGNORECASE)):
link = p.find(text=re.compile(hoster)).find_previous('a')
entry['title'] = p.strong.text
entry['url'] = link.get('href')
entries.add(entry)
except:
pass
else:
try:
if p.strong.find(text=re.compile("german", flags=re.IGNORECASE)):
link = p.find(text=re.compile(hoster)).find_previous('a')
entry['title'] = p.strong.text
entry['url'] = link.get('href')
entries.add(entry)
except:
pass
return entries
def entries_from_search(self, name, url=None):
"""Parses torrent download url from search results"""
name = normalize_unicode(name)
if not url:
url = 'http://www.newtorrents.info/search/%s' % urllib.quote(name.encode('utf-8'), safe=':/~?=&%')
log.debug('search url: %s' % url)
html = urlopener(url, log).read()
# fix </SCR'+'IPT> so that BS does not crash
# TODO: should use beautifulsoup massage
html = re.sub(r'(</SCR.*?)...(.*?IPT>)', r'\1\2', html)
soup = get_soup(html)
# saving torrents in dict
torrents = []
for link in soup.find_all('a', attrs={'href': re.compile('down.php')}):
torrent_url = 'http://www.newtorrents.info%s' % link.get('href')
release_name = link.parent.next.get('title')
# quick dirty hack
seed = link.find_next('td', attrs={'class': re.compile('s')}).renderContents()
if seed == 'n/a':
seed = 0
else:
try:
seed = int(seed)
except ValueError:
log.warning('Error converting seed value (%s) from newtorrents to integer.' % seed)
seed = 0
#TODO: also parse content_size and peers from results
torrents.append(Entry(title=release_name, url=torrent_url, torrent_seeds=seed,
search_sort=torrent_availability(seed, 0)))
# sort with seed number Reverse order
torrents.sort(reverse=True, key=lambda x: x.get('search_sort', 0))
# choose the torrent
if not torrents:
dashindex = name.rfind('-')
if dashindex != -1:
return self.entries_from_search(name[:dashindex])
else:
raise PluginWarning('No matches for %s' % name, log, log_once=True)
else:
if len(torrents) == 1:
log.debug('found only one matching search result.')
else:
log.debug('search result contains multiple matches, sorted %s by most seeders' % torrents)
return torrents
def search(self, entry, config=None):
config = self.process_config(config)
feed = REPUTATIONS[config["reputation"]]
entries = set()
for search_string in entry.get("search_strings", [entry["title"]]):
query = normalize_unicode(search_string + config.get("extra_terms", ""))
for domain in ["eu", "me"]:
# urllib.quote will crash if the unicode string has non ascii characters, so encode in utf-8 beforehand
url = "http://torrentz.%s/%s?q=%s" % (domain, feed, urllib.quote(query.encode("utf-8")))
log.debug("requesting: %s" % url)
try:
r = requests.get(url, headers={"User-Agent": "FlexGet/%s" % flexget.__version__})
break
except requests.RequestException as err:
log.warning("torrentz.%s failed. Error: %s" % (domain, err))
else:
raise plugin.PluginError("Error getting torrentz search results")
if not r.content.strip():
raise plugin.PluginError("No data from %s. Maybe torrentz is blocking the FlexGet User-Agent" % url)
rss = feedparser.parse(r.content)
if rss.get("bozo_exception"):
raise plugin.PluginError("Got bozo_exception (bad rss feed)")
for item in rss.entries:
m = re.search(
r"Size: ([\d]+) Mb Seeds: ([,\d]+) Peers: ([,\d]+) Hash: ([a-f0-9]+)",
item.description,
re.IGNORECASE,
)
if not m:
log.debug("regexp did not find seeds / peer data")
continue
entry = Entry()
entry["title"] = item.title
entry["url"] = item.link
entry["content_size"] = int(m.group(1))
entry["torrent_seeds"] = int(m.group(2).replace(",", ""))
entry["torrent_leeches"] = int(m.group(3).replace(",", ""))
entry["torrent_info_hash"] = m.group(4).upper()
entry["search_sort"] = torrent_availability(entry["torrent_seeds"], entry["torrent_leeches"])
entries.add(entry)
log.debug("Search got %d results" % len(entries))
return entries
def search(self, entry, config):
search_strings = [
normalize_unicode(s).lower()
for s in entry.get('search_strings', [entry['title']])
]
entries = set()
for search_string in search_strings:
if config.get('verified'):
search_string += ' verified:1'
url = 'http://kickass.to/search/%s/?rss=1' % urllib.quote(
search_string.encode('utf-8'))
if config.get('category', 'all') != 'all':
url += '&category=%s' % config['category']
log.debug('requesting: %s' % url)
rss = feedparser.parse(url)
status = rss.get('status', False)
if status != 200:
raise plugin.PluginWarning(
'Search result not 200 (OK), received %s' % status)
ex = rss.get('bozo_exception', False)
if ex:
raise plugin.PluginWarning('Got bozo_exception (bad feed)')
for item in rss.entries:
entry = Entry()
entry['title'] = item.title
if not item.get('enclosures'):
log.warning(
'Could not get url for entry from KAT. Maybe plugin needs updated?'
)
continue
entry['url'] = item.enclosures[0]['url']
entry['torrent_seeds'] = int(item.torrent_seeds)
entry['torrent_leeches'] = int(item.torrent_peers)
entry['search_sort'] = torrent_availability(
entry['torrent_seeds'], entry['torrent_leeches'])
entry['content_size'] = int(
item.torrent_contentlength) / 1024 / 1024
entry['torrent_info_hash'] = item.torrent_infohash
entries.add(entry)
return entries
def url_rewrite(self, task, entry):
try:
page = task.requests.get(entry['url'])
except RequestException as e:
raise UrlRewritingError(str(e))
try:
soup = get_soup(page.text)
except Exception as e:
raise UrlRewritingError(str(e))
link_elements = soup.find_all('pre', class_='links')
if 'urls' in entry:
urls = list(entry['urls'])
else:
urls = []
for element in link_elements:
urls.extend(element.text.splitlines())
regexps = self.config.get('filehosters_re', [])
filtered_urls = []
for i, url in enumerate(urls):
urls[i] = normalize_unicode(url)
for regexp in regexps:
if re.search(regexp, urls[i]):
filtered_urls.append(urls[i])
log.debug('Url: "%s" matched filehoster filter: %s',
urls[i], regexp)
break
else:
if regexps:
log.debug(
'Url: "%s" does not match any of the given filehoster filters: %s',
urls[i], str(regexps))
if regexps:
log.debug('Using filehosters_re filters: %s', str(regexps))
urls = filtered_urls
else:
log.debug(
'No filehoster filters configured, using all found links.')
num_links = len(urls)
log.verbose('Found %d links at %s.', num_links, entry['url'])
if num_links:
entry['urls'] = urls
entry['url'] = urls[0]
else:
raise UrlRewritingError('No useable links found at %s' %
entry['url'])
def search(self, task, entry, config=None):
if not config:
log.debug('NewPCT disabled')
return set()
log.debug('Search NewPCT')
url_search = 'http://newpct1.com/buscar'
results = set()
for search_string in entry.get('search_strings', [entry['title']]):
query = normalize_unicode(search_string)
query = re.sub(' \(\d\d\d\d\)$', '', query)
log.debug('Searching NewPCT %s', query)
query = unicodedata.normalize('NFD',
query).encode('ascii', 'ignore')
data = {'q': query}
try:
response = task.requests.post(url_search, data=data)
except requests.RequestException as e:
log.error('Error searching NewPCT: %s', e)
return results
content = response.content
soup = get_soup(content)
soup2 = soup.find('ul', attrs={'class': 'buscar-list'})
children = soup2.findAll('a', href=True)
for child in children:
entry = Entry()
entry['url'] = child['href']
entry_title = child.find('h2')
if entry_title is None:
log.debug('Ignore empty entry')
continue
entry_title = entry_title.text
if not entry_title:
continue
try:
entry_quality_lan = re.search(
'.+ \[([^\]]+)\](\[[^\]]+\])+$', entry_title).group(1)
except AttributeError:
log.debug('Quality not found')
continue
entry_title = re.sub(' \[.+]$', '', entry_title)
entry['title'] = entry_title + ' ' + entry_quality_lan
results.add(entry)
log.debug('Finish search NewPCT with %d entries', len(results))
return results
def search(self, entry, config=None):
if config:
feed = REPUTATIONS[config]
else:
feed = REPUTATIONS['good']
query = normalize_unicode(entry['title'])
# urllib.quote will crash if the unicode string has non ascii characters, so encode in utf-8 beforehand
url = 'http://torrentz.eu/%s?q=%s' % (feed, urllib.quote(query.encode('utf-8')))
log.debug('requesting: %s' % url)
rss = feedparser.parse(url)
entries = []
status = rss.get('status', False)
if status != 200:
raise PluginWarning('Search result not 200 (OK), received %s' % status)
ex = rss.get('bozo_exception', False)
if ex:
raise PluginWarning('Got bozo_exception (bad feed)')
for item in rss.entries:
m = re.search(r'Size: ([\d]+) Mb Seeds: ([,\d]+) Peers: ([,\d]+) Hash: ([a-f0-9]+)',
item.description, re.IGNORECASE)
if not m:
log.debug('regexp did not find seeds / peer data')
continue
entry = Entry()
entry['title'] = item.title
entry['url'] = item.link
entry['content_size'] = int(m.group(1))
entry['torrent_seeds'] = int(m.group(2).replace(',', ''))
entry['torrent_leeches'] = int(m.group(3).replace(',', ''))
entry['torrent_info_hash'] = m.group(4).upper()
entry['search_sort'] = torrent_availability(entry['torrent_seeds'], entry['torrent_leeches'])
entries.append(entry)
# choose torrent
if not entries:
raise PluginWarning('No close matches for %s' % query, log, log_once=True)
entries.sort(reverse=True, key=lambda x: x.get('search_sort'))
log.debug('Search got %d results' % len(entries))
return entries
def search(self, task, entry, config=None):
"""
Search for name from fuzer.
"""
self.rss_key = config['rss_key']
self.user_id = config['user_id']
self.cookies = {
'fzr2lastactivity': '0',
'fzr2lastvisit': '',
'fzr2password': config['cookie_password'],
'fzr2sessionhash': '',
'fzr2userid': str(self.user_id)
}
category = config.get('category', [0])
# Make sure categories is a list
if not isinstance(category, list):
category = [category]
# If there are any text categories, turn them into their id number
categories = [
c if isinstance(c, int) else CATEGORIES[c] for c in category
]
c_list = ['c{}={}'.format(quote_plus('[]'), c) for c in categories]
entries = []
if entry.get('imdb_id'):
log.debug("imdb_id '%s' detected, using in search.",
entry['imdb_id'])
soup = self.get_fuzer_soup(entry['imdb_id'], c_list)
entries = self.extract_entry_from_soup(soup)
if entries:
for e in list(entries):
e['imdb_id'] = entry.get('imdb_id')
else:
for search_string in entry.get('search_strings', [entry['title']]):
query = normalize_unicode(search_string).replace(":", "")
text = quote_plus(query.encode('windows-1255'))
soup = self.get_fuzer_soup(text, c_list)
entries += self.extract_entry_from_soup(soup)
return sorted(entries,
reverse=True,
key=lambda x: x.get('search_sort')) if entries else []
def search(self, entry, config=None):
config = self.process_config(config)
feed = REPUTATIONS[config['reputation']]
entries = set()
for search_string in entry.get('search_string', [entry['title']]):
query = normalize_unicode(search_string+config.get('extra_terms', ''))
for domain in ['eu', 'me']:
# urllib.quote will crash if the unicode string has non ascii characters, so encode in utf-8 beforehand
url = 'http://torrentz.%s/%s?q=%s' % (domain, feed, urllib.quote(query.encode('utf-8')))
log.debug('requesting: %s' % url)
try:
r = requests.get(url)
break
except requests.RequestException as err:
log.warning('torrentz.%s failed. Error: %s' % (domain, err))
else:
raise plugin.PluginWarning('Error getting torrentz search results')
rss = feedparser.parse(r.content)
ex = rss.get('bozo_exception', False)
if ex:
raise plugin.PluginWarning('Got bozo_exception (bad feed)')
for item in rss.entries:
m = re.search(r'Size: ([\d]+) Mb Seeds: ([,\d]+) Peers: ([,\d]+) Hash: ([a-f0-9]+)',
item.description, re.IGNORECASE)
if not m:
log.debug('regexp did not find seeds / peer data')
continue
entry = Entry()
entry['title'] = item.title
entry['url'] = item.link
entry['content_size'] = int(m.group(1))
entry['torrent_seeds'] = int(m.group(2).replace(',', ''))
entry['torrent_leeches'] = int(m.group(3).replace(',', ''))
entry['torrent_info_hash'] = m.group(4).upper()
entry['search_sort'] = torrent_availability(entry['torrent_seeds'], entry['torrent_leeches'])
entries.add(entry)
log.debug('Search got %d results' % len(entries))
return entries
def search(self, task, entry, config=None):
entries = set()
search_strings = [normalize_unicode(s) for s in entry.get('search_strings', [entry['title']])]
for search_string in search_strings:
url = 'https://yts.am/api/v2/list_movies.json?query_term=%s' % (
urllib.quote(search_string.encode('utf-8')))
log.debug('requesting: %s' % url)
try:
result = requests.get(url)
try:
data = result.json()
except ValueError:
log.debug('Could not decode json from response: %s', result.text)
raise plugin.PluginError('Error getting result from yts.')
except requests.RequestException as e:
raise plugin.PluginError('Could not retrieve query from yts (%s)' % e.args[0])
if not data['status'] == 'ok':
raise plugin.PluginError('failed to query YTS')
try:
if data['data']['movie_count'] > 0:
for item in data['data']['movies']:
for torrent in item['torrents']:
entry = Entry()
entry['title'] = item['title']
entry['year'] = item['year']
entry['url'] = torrent['url']
entry['content_size'] = parse_filesize(str(torrent['size_bytes']) + "b")
entry['torrent_seeds'] = torrent['seeds']
entry['torrent_leeches'] = torrent['peers']
entry['torrent_info_hash'] = torrent['hash']
entry['search_sort'] = torrent_availability(entry['torrent_seeds'], entry['torrent_leeches'])
entry['quality'] = torrent['quality']
entry['imdb_id'] = item['imdb_code']
if entry.isvalid():
entries.add(entry)
except Exception:
log.debug('invalid return structure from YTS')
log.debug('Search got %d results' % len(entries))
return entries
def search(self, task, entry, config=None):
if not isinstance(config, dict):
config = {}
category = CATEGORIES.get(config.get('category', 'all'), None)
category_query = '&cid=%d' % category if category else ''
entries = set()
for search_string in entry.get('search_strings', [entry['title']]):
query = normalize_unicode(search_string)
search_query = '&search=%s' % quote(query.encode('utf-8'))
url = ('http://extratorrent.cc/rss.xml?type=search%s%s' %
(category_query, search_query))
log.debug('Using %s as extratorrent search url' % url)
rss = feedparser.parse(url)
status = rss.get('status', False)
if status != 200:
log.debug('Search result not 200 (OK), received %s' % status)
if not status or status >= 400:
continue
for item in rss.entries:
entry = Entry()
entry['title'] = item.title
entry['url'] = item.link
entry['content_size'] = int(item.size) / 1024 / 1024
entry['torrent_info_hash'] = item.info_hash
if isinstance(item.seeders, int):
entry['torrent_seeds'] = int(item.seeders)
if isinstance(item.leechers, int):
entry['torrent_leeches'] = int(item.leechers)
entries.add(entry)
return entries
def search(self, task, entry, config):
if not isinstance(config, dict):
config = {'category': config}
config.setdefault('category', 'anime eng')
config.setdefault('filter', 'all')
entries = set()
for search_string in entry.get('search_strings', [entry['title']]):
name = normalize_unicode(search_string)
url = 'https://www.nyaa.si/?page=rss&q=%s&c=%s&f=%s' % (
quote(name.encode('utf-8')), CATEGORIES[config['category']],
FILTERS.index(config['filter']))
log.debug('requesting: %s' % url)
rss = feedparser.parse(url)
status = rss.get('status', False)
if status != 200:
log.debug('Search result not 200 (OK), received %s' % status)
if status >= 400:
continue
ex = rss.get('bozo_exception', False)
if ex:
log.error('Got bozo_exception (bad feed) on %s' % url)
continue
for item in rss.entries:
entry = Entry()
entry['title'] = item.title
entry['url'] = item.link
entry['torrent_seeds'] = int(item.nyaa_seeders)
entry['torrent_leeches'] = int(item.nyaa_leechers)
entry['torrent_info_hash'] = item.nyaa_infohash
entry['search_sort'] = torrent_availability(
entry['torrent_seeds'], entry['torrent_leeches'])
if item.nyaa_size:
entry['content_size'] = parse_filesize(item.nyaa_size)
entries.add(entry)
return entries
def search(self, entry, config):
if not isinstance(config, dict):
config = {'category': config}
config.setdefault('category', 'anime')
config.setdefault('filter', 'all')
entries = set()
for search_string in entry.get('search_strings', [entry['title']]):
name = normalize_unicode(search_string)
url = 'http://www.nyaa.se/?page=rss&cats=%s&filter=%s&term=%s' % (
CATEGORIES[config['category']], FILTERS.index(
config['filter']), urllib.quote(name.encode('utf-8')))
log.debug('requesting: %s' % url)
rss = feedparser.parse(url)
status = rss.get('status', False)
if status != 200:
log.debug('Search result not 200 (OK), received %s' % status)
if status >= 400:
continue
ex = rss.get('bozo_exception', False)
if ex:
log.error('Got bozo_exception (bad feed) on %s' % url)
continue
for item in rss.entries:
entry = Entry()
entry['title'] = item.title
entry['url'] = item.link
# TODO: parse some shit
#entry['torrent_seeds'] = int(item.seeds)
#entry['torrent_leeches'] = int(item.leechs)
#entry['search_sort'] = torrent_availability(entry['torrent_seeds'], entry['torrent_leeches'])
#entry['content_size'] = int(item.size) / 1024 / 1024
entries.add(entry)
return entries