def parse_download_page(self, url):
txheaders = {'User-agent': 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'}
req = urllib2.Request(url, None, txheaders)
page = urlopener(req, log)
try:
soup = get_soup(page)
except Exception as e:
raise UrlRewritingError(e)
config = self.config or {}
config.setdefault('quality', 'hd')
links = soup.find_all('a', text="Descargar", href=re.compile("/subtitles"))
if not links:
raise UrlRewritingError('Unable to locate subtitle download link from url %s' % url)
subtitle_url = ''
for link in links:
sub_url = link['href']
log.verbose('Found url %s', sub_url)
if config['quality'] == 'hd' and re.search("720p|1080p",sub_url):
subtitle_url = 'http://www.argenteam.net' + sub_url
log.verbose('is a match')
break
if config['quality'] == 'sd' and re.search("720p|1080p",sub_url) == None:
subtitle_url = 'http://www.argenteam.net' + sub_url
log.verbose('is a match')
break
if subtitle_url == '':
raise UrlRewritingError('Unable to locate download link %s from url %s' % (config['quality'], url))
return subtitle_url
def get_json(url):
try:
log.debug('fetching json at %s' % url)
data = urlopener(url, log)
except URLError, e:
log.warning('Request failed %s' % url)
return
def nzbid_from_search(self, url, name, query):
"""Parses nzb download url from api results"""
import time
import difflib
matched_results = []
log.debug(
"Sleeping to respect nzbmatrix rules about hammering the API")
time.sleep(10)
apireturn = self.parse_nzb_matrix_api(
urlopener(url, log).read(), query)
if not apireturn:
return None
else:
names = []
for result in apireturn:
names.append(result["NZBNAME"])
matches = difflib.get_close_matches(name, names, 1, 0.3)
if len(matches) == 0:
return None
else:
for result in apireturn:
if result["NZBNAME"] == matches[0]:
break
for match in matches: # Already sorted
for result in apireturn:
if result.get(match, False):
matched_results.append(result)
return matched_results
def get_http_seeds(url, info_hash):
url = get_scrape_url(url, info_hash)
if not url:
log.debug('if not url is true returning 0')
return 0
log.debug('Checking for seeds from %s' % url)
data = None
try:
data = bdecode(urlopener(url, log, retries=1,
timeout=10).read()).get('files')
except URLError as e:
log.debug('Error scraping: %s' % e)
return 0
except SyntaxError as e:
log.warning('Error decoding tracker response: %s' % e)
return 0
except BadStatusLine as e:
log.warning('Error BadStatusLine: %s' % e)
return 0
except IOError as e:
log.warning('Server error: %s' % e)
return 0
if not data:
log.debug('No data received from tracker scrape.')
return 0
log.debug('get_http_seeds is returning: %s' % data.values()[0]['complete'])
return data.values()[0]['complete']
def get_file(self, only_cached=False):
"""Makes sure the poster is downloaded to the local cache (in userstatic folder) and
returns the path split into a list of directory and file components"""
from flexget.manager import manager
base_dir = os.path.join(manager.config_base, 'userstatic')
if self.file and os.path.isfile(os.path.join(base_dir, self.file)):
return self.file.split(os.sep)
elif only_cached:
return
# If we don't already have a local copy, download one.
log.debug('Downloading poster %s' % self.url)
dirname = os.path.join('tmdb', 'posters', str(self.movie_id))
# Create folders if they don't exist
fullpath = os.path.join(base_dir, dirname)
if not os.path.isdir(fullpath):
os.makedirs(fullpath)
filename = os.path.join(dirname, posixpath.basename(self.url))
thefile = file(os.path.join(base_dir, filename), 'wb')
thefile.write(urlopener(self.url, log).read())
self.file = filename
# If we are detached from a session, update the db
if not Session.object_session(self):
session = Session()
poster = session.query(TMDBPoster).filter(TMDBPoster.db_id == self.db_id).first()
if poster:
poster.file = filename
session.commit()
session.close()
return filename.split(os.sep)
def nzbid_from_search(self, url, name, query):
"""Parses nzb download url from api results"""
import time
import difflib
matched_results = []
log.debug("Sleeping to respect nzbmatrix rules about hammering the API")
time.sleep(10)
apireturn = self.parse_nzb_matrix_api(urlopener(url, log).read(),
query)
if not apireturn:
return None
else:
names = []
for result in apireturn:
names.append(result["NZBNAME"])
matches = difflib.get_close_matches(name, names, 1, 0.3)
if len(matches) == 0:
return None
else:
for result in apireturn:
if result["NZBNAME"] == matches[0]:
break
for match in matches: # Already sorted
for result in apireturn:
if result.get(match, False):
matched_results.append(result)
return matched_results
def on_task_output(self, task, config):
for entry in task.accepted:
if task.options.test:
log.info('Would add into sabnzbd: %s' % entry['title'])
continue
params = self.get_params(config)
# allow overriding the category
if 'category' in entry:
# Dirty hack over the next few lines to strip out non-ascii
# chars. We're going to urlencode this, which causes
# serious issues in python2.x if it's not ascii input.
params['cat'] = ''.join([x for x in entry['category'] if ord(x) < 128])
params['name'] = ''.join([x for x in entry['url'] if ord(x) < 128])
# add cleaner nzb name (undocumented api feature)
params['nzbname'] = ''.join([x for x in entry['title'] if ord(x) < 128])
request_url = config['url'] + urllib.urlencode(params)
log.debug('request_url: %s' % request_url)
try:
response = urlopener(request_url, log).read()
except Exception as e:
log.critical('Failed to use sabnzbd. Requested %s' % request_url)
log.critical('Result was: %s' % e)
entry.fail('sabnzbd unreachable')
if task.options.debug:
log.exception(e)
continue
if 'error' in response.lower():
entry.fail(response.replace('\n', ''))
else:
log.info('Added `%s` to SABnzbd' % (entry['title']))
def get_file(self, only_cached=False):
"""Makes sure the poster is downloaded to the local cache (in userstatic folder) and
returns the path split into a list of directory and file components"""
from flexget.manager import manager
base_dir = os.path.join(manager.config_base, 'userstatic')
if self.file and os.path.isfile(os.path.join(base_dir, self.file)):
return self.file.split(os.sep)
elif only_cached:
return
# If we don't already have a local copy, download one.
log.debug('Downloading poster %s' % self.url)
dirname = os.path.join('tmdb', 'posters', str(self.movie_id))
# Create folders if they don't exist
fullpath = os.path.join(base_dir, dirname)
if not os.path.isdir(fullpath):
os.makedirs(fullpath)
filename = os.path.join(dirname, posixpath.basename(self.url))
thefile = file(os.path.join(base_dir, filename), 'wb')
thefile.write(urlopener(self.url, log).read())
self.file = filename
# If we are detached from a session, update the db
if not Session.object_session(self):
session = Session()
poster = session.query(TMDBPoster).filter(
TMDBPoster.db_id == self.db_id).first()
if poster:
poster.file = filename
session.commit()
session.close()
return filename.split(os.sep)
def on_feed_output(self, feed, config):
for entry in feed.accepted:
if feed.manager.options.test:
log.info('Would add into sabnzbd: %s' % entry['title'])
continue
params = self.get_params(config)
# allow overriding the category
if 'category' in entry:
# Dirty hack over the next few lines to strip out non-ascii
# chars. We're going to urlencode this, which causes
# serious issues in python2.x if it's not ascii input.
params['cat'] = ''.join([x for x in entry['category'] if ord(x) < 128])
params['name'] = ''.join([x for x in entry['url'] if ord(x) < 128])
# add cleaner nzb name (undocumented api feature)
params['nzbname'] = ''.join([x for x in entry['title'] if ord(x) < 128])
request_url = config['url'] + urllib.urlencode(params)
log.debug('request_url: %s' % request_url)
try:
response = urlopener(request_url, log).read()
except Exception, e:
log.critical('Failed to use sabnzbd. Requested %s' % request_url)
log.critical('Result was: %s' % e)
feed.fail(entry, 'sabnzbd unreachable')
if feed.manager.options.debug:
log.exception(e)
continue
if 'error' in response.lower():
feed.fail(entry, response.replace('\n', ''))
else:
log.info('Added `%s` to SABnzbd' % (entry['title']))
def get_json(url):
try:
log.debug("fetching json at %s" % url)
data = urlopener(url, log)
except URLError, e:
log.warning("Request failed %s" % url)
return
def on_task_output(self, task, config):
for entry in task.accepted:
if task.options.test:
log.info("Would add into sabnzbd: %s" % entry["title"])
continue
params = self.get_params(config)
# allow overriding the category
if "category" in entry:
# Dirty hack over the next few lines to strip out non-ascii
# chars. We're going to urlencode this, which causes
# serious issues in python2.x if it's not ascii input.
params["cat"] = "".join([x for x in entry["category"] if ord(x) < 128])
params["name"] = "".join([x for x in entry["url"] if ord(x) < 128])
# add cleaner nzb name (undocumented api feature)
params["nzbname"] = "".join([x for x in entry["title"] if ord(x) < 128])
request_url = config["url"] + urllib.urlencode(params)
log.debug("request_url: %s" % request_url)
try:
response = urlopener(request_url, log).read()
except Exception as e:
log.critical("Failed to use sabnzbd. Requested %s" % request_url)
log.critical("Result was: %s" % e)
entry.fail("sabnzbd unreachable")
if task.options.debug:
log.exception(e)
continue
if "error" in response.lower():
entry.fail(response.replace("\n", ""))
else:
log.info("Added `%s` to SABnzbd" % (entry["title"]))
def search(self, task, entry, config=None):
txheaders = {
'User-Agent': 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Language': 'en-us,en;q=0.5',
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
'Keep-Alive': '300',
'Connection': 'keep-alive',
}
nzbs = set()
for search_string in entry.get('search_strings', [entry['title']]):
query = entry['title']
url = u'http://newzleech.com/?%s' % str(urllib.urlencode({'q': query.encode('latin1'),
'm': 'search', 'group': '', 'min': 'min',
'max': 'max', 'age': '', 'minage': '',
'adv': ''}))
# log.debug('Search url: %s' % url)
req = urllib2.Request(url, headers=txheaders)
page = urlopener(req, log)
soup = get_soup(page)
for item in soup.find_all('table', attrs={'class': 'contentt'}):
subject_tag = item.find('td', attrs={'class': 'subject'}).next
subject = ''.join(subject_tag.find_all(text=True))
complete = item.find('td', attrs={'class': 'complete'}).contents[0]
size = item.find('td', attrs={'class': 'size'}).contents[0]
nzb_url = 'http://newzleech.com/' + item.find('td', attrs={'class': 'get'}).next.get('href')
# generate regexp from entry title and see if it matches subject
regexp = query
wildcardize = [' ', '-']
for wild in wildcardize:
regexp = regexp.replace(wild, '.')
regexp = '.*' + regexp + '.*'
# log.debug('Title regexp: %s' % regexp)
if re.match(regexp, subject):
log.debug('%s matches to regexp' % subject)
if complete != u'100':
log.debug('Match is incomplete %s from newzleech, skipping ..' % query)
continue
log.info('Found \'%s\'' % query)
try:
size_num = float(size[:-3])
except (ValueError, TypeError):
log.error('Failed to parse_size %s' % size)
size_num = 0
# convert into megabytes
if 'GB' in size:
size_num *= 1024
if 'KB' in size:
size_num /= 1024
# choose largest file
nzbs.add(Entry(title=subject, url=nzb_url, content_size=size_num, search_sort=size_num))
return nzbs
def on_feed_input(self, feed, config):
config = self.build_config(config)
log.debug('InputPlugin html requesting url %s' % config['url'])
if config.get('username') and config.get('password'):
log.debug('Basic auth enabled. User: %s Password: %s' % (config['username'], config['password']))
passman = urllib2.HTTPPasswordMgrWithDefaultRealm()
passman.add_password(None, config['url'], config['username'], config['password'])
handlers = [urllib2.HTTPBasicAuthHandler(passman)]
else:
handlers = None
page = urlopener(config['url'], log, handlers=handlers)
soup = get_soup(page)
log.debug('Detected encoding %s' % soup.originalEncoding)
# dump received content into a file
if 'dump' in config:
name = config['dump']
log.info('Dumping %s into %s' % (config['url'], name))
data = soup.prettify()
f = open(name, 'w')
f.write(data)
f.close()
return self.create_entries(config['url'], soup, config)
def on_task_input(self, task, config):
config = self.build_config(config)
log.debug('InputPlugin html requesting url %s' % config['url'])
if config.get('username') and config.get('password'):
log.debug('Basic auth enabled. User: %s Password: %s' %
(config['username'], config['password']))
passman = urllib2.HTTPPasswordMgrWithDefaultRealm()
passman.add_password(None, config['url'], config['username'],
config['password'])
handlers = [urllib2.HTTPBasicAuthHandler(passman)]
else:
handlers = None
page = urlopener(config['url'], log, handlers=handlers)
soup = get_soup(page)
log.debug('Detected encoding %s' % soup.originalEncoding)
# dump received content into a file
if 'dump' in config:
name = config['dump']
log.info('Dumping %s into %s' % (config['url'], name))
data = soup.prettify()
f = open(name, 'w')
f.write(data)
f.close()
return self.create_entries(config['url'], soup, config)
def get_http_seeds(url, info_hash):
url = get_scrape_url(url, info_hash)
if not url:
log.debug('if not url is true returning 0')
return 0
log.debug('Checking for seeds from %s' % url)
data = None
try:
data = bdecode(urlopener(url, log, retries=1, timeout=10).read()).get('files')
except URLError as e:
log.debug('Error scraping: %s' % e)
return 0
except SyntaxError as e:
log.warning('Error decoding tracker response: %s' % e)
return 0
except BadStatusLine as e:
log.warning('Error BadStatusLine: %s' % e)
return 0
except IOError as e:
log.warning('Server error: %s' % e)
return 0
if not data:
log.debug('No data received from tracker scrape.')
return 0
log.debug('get_http_seeds is returning: %s' % data.values()[0]['complete'])
return data.values()[0]['complete']
def search(self, entry, config):
url = "https://tehconnection.eu/torrents.php?searchstr=%s" \
% entry.get("imdb_id");
page = urlopener(url, log)
soup = get_soup(page)
results = set()
for row in soup.find_all("tr", class_="group_torrent"):
link = row.find(title="Download")
info = row.find(colspan="1").contents[3].contents[0].strip()
seeders = int(row.find_all("td")[6].contents[0].strip())
leechers = int(row.find_all("td")[7].contents[0].strip())
result = Entry();
result["title"] = entry.get("title") + " / " + info
result["imdb_id"] = entry.get("imdb_id")
result["url"] = "https://tehconnection.eu" + link.get("href")
result["torrent_seeds"] = seeders
result["torrent_leeches"] = leechers
result["search_sort"] = torrent_availability(result['torrent_seeds'],
result['torrent_leeches'])
results.add(result)
return results
def search(self, entry, config=None):
txheaders = {
'User-Agent': 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Language': 'en-us,en;q=0.5',
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
'Keep-Alive': '300',
'Connection': 'keep-alive',
}
nzbs = set()
for search_string in entry.get('search_strings', [entry['title']]):
query = entry['title']
url = u'http://newzleech.com/?%s' % str(urllib.urlencode({'q': query.encode('latin1'),
'm': 'search', 'group': '', 'min': 'min',
'max': 'max', 'age': '', 'minage': '', 'adv': ''}))
#log.debug('Search url: %s' % url)
req = urllib2.Request(url, headers=txheaders)
page = urlopener(req, log)
soup = get_soup(page)
for item in soup.find_all('table', attrs={'class': 'contentt'}):
subject_tag = item.find('td', attrs={'class': 'subject'}).next
subject = ''.join(subject_tag.find_all(text=True))
complete = item.find('td', attrs={'class': 'complete'}).contents[0]
size = item.find('td', attrs={'class': 'size'}).contents[0]
nzb_url = 'http://newzleech.com/' + item.find('td', attrs={'class': 'get'}).next.get('href')
# generate regexp from entry title and see if it matches subject
regexp = query
wildcardize = [' ', '-']
for wild in wildcardize:
regexp = regexp.replace(wild, '.')
regexp = '.*' + regexp + '.*'
#log.debug('Title regexp: %s' % regexp)
if re.match(regexp, subject):
log.debug('%s matches to regexp' % subject)
if complete != u'100':
log.debug('Match is incomplete %s from newzleech, skipping ..' % query)
continue
log.info('Found \'%s\'' % query)
try:
size_num = float(size[:-3])
except (ValueError, TypeError):
log.error('Failed to parse_size %s' % size)
size_num = 0
# convert into megabytes
if 'GB' in size:
size_num *= 1024
if 'KB' in size:
size_num /= 1024
# choose largest file
nzbs.add(Entry(title=subject, url=nzb_url, content_size=size_num, search_sort=size_num))
return nzbs
def parse_download_page(self, url):
txheaders = {'User-agent': 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'}
req = urllib2.Request(url, None, txheaders)
page = urlopener(req, log)
try:
soup = get_soup(page)
except Exception, e:
raise UrlRewritingError(e)
def parse_download_page(self, url):
page = urlopener(url, log)
log.debug('%s opened', url)
try:
soup = get_soup(page)
torrent_url = 'http://www.t411.me' + soup.find(text='Télécharger').findParent().get('href')
except Exception, e:
raise UrlRewritingError(e)
def parse_download_page(self, url):
txheaders = {'User-agent': 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'}
req = urllib2.Request(url, None, txheaders)
page = urlopener(req, log)
try:
soup = get_soup(page)
except Exception, e:
raise UrlRewritingError(e)
def process_invalid_content(self, feed, url):
"""If feedparser reports error, save the received data and log error."""
log.critical('Invalid XML received from feed %s' % feed.name)
try:
req = urlopener(url, log)
except ValueError, exc:
log.debug('invalid url `%s` due to %s (ok for a file)' % (url, exc))
return
def search_title(self, name, comparator=StringComparator(), url=None):
"""
Search for name from piratebay.
If optional search :url: is passed it will be used instead of internal search.
"""
comparator.set_seq1(name)
name = comparator.search_string()
if not url:
# urllib.quote will crash if the unicode string has non ascii characters, so encode in utf-8 beforehand
url = 'http://thepiratebay.org/search/' + urllib.quote(name.encode('utf-8'))
log.debug('Using %s as piratebay search url' % url)
page = urlopener(url, log)
soup = get_soup(page)
entries = []
for link in soup.findAll('a', attrs={'class': 'detLink'}):
comparator.set_seq2(link.contents[0])
log.debug('name: %s' % comparator.a)
log.debug('found name: %s' % comparator.b)
log.debug('confidence: %s' % comparator.ratio())
if not comparator.matches():
continue
entry = Entry()
entry['title'] = link.contents[0]
entry['url'] = 'http://thepiratebay.org' + link.get('href')
tds = link.parent.parent.parent.findAll('td')
entry['torrent_seeds'] = int(tds[-2].contents[0])
entry['torrent_leeches'] = int(tds[-1].contents[0])
entry['search_ratio'] = comparator.ratio()
entry['search_sort'] = torrent_availability(entry['torrent_seeds'], entry['torrent_leeches'])
# Parse content_size
size = link.findNext(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.append(entry)
if not entries:
dashindex = name.rfind('-')
if dashindex != -1:
return self.search_title(name[:dashindex], comparator=comparator)
else:
raise PluginWarning('No close matches for %s' % name, log, log_once=True)
def score(a):
return torrent_availability(a['torrent_seeds'], a['torrent_leeches'])
entries.sort(reverse=True, key=lambda x: x.get('search_sorted'))
#for torrent in torrents:
# log.debug('%s link: %s' % (torrent, torrent['link']))
return entries
def parse_site(self, url, task):
"""Parse configured url and return releases array"""
page = urlopener(url, log)
soup = get_soup(page)
releases = []
for entry in soup.find_all('div', attrs={'class': 'entry'}):
release = {}
title = entry.find('h2')
if not title:
log.debug('No h2 entrytitle')
continue
release['title'] = title.a.contents[0].strip()
log.debug('Processing title %s' % (release['title']))
for link in entry.find_all('a'):
# no content in the link
if not link.contents:
continue
link_name = link.contents[0]
if link_name is None:
continue
if not isinstance(link_name, NavigableString):
continue
link_name = link_name.strip().lower()
if link.has_attr('href'):
link_href = link['href']
else:
continue
log.debug('found link %s -> %s' % (link_name, link_href))
# handle imdb link
if link_name.lower() == 'imdb':
log.debug('found imdb link %s' % link_href)
release['imdb_url'] = link_href
# test if entry with this url would be rewritable by known plugins (ie. downloadable)
temp = {}
temp['title'] = release['title']
temp['url'] = link_href
urlrewriting = plugin.get_plugin_by_name('urlrewriting')
if urlrewriting['instance'].url_rewritable(task, temp):
release['url'] = link_href
log.trace('--> accepting %s (resolvable)' % link_href)
else:
log.trace('<-- ignoring %s (non-resolvable)' % link_href)
# reject if no torrent link
if not 'url' in release:
from flexget.utils.log import log_once
log_once(
'%s skipped due to missing or unsupported (unresolvable) download link'
% (release['title']), log)
else:
releases.append(release)
return releases
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 get_first_result(tmdb_function, value):
if isinstance(value, basestring):
value = value.replace(' ', '+').encode('utf-8')
url = '%s/2.1/Movie.%s/%s/json/%s/%s' % (server, tmdb_function, lang, api_key, value)
try:
data = urlopener(url, log)
except URLError, e:
log.warning('Request failed %s' % url)
return
def parse_site(self, url, task):
"""Parse configured url and return releases array"""
page = urlopener(url, log)
soup = get_soup(page)
releases = []
for entry in soup.find_all('div', attrs={'class': 'entry'}):
release = {}
title = entry.find('h2')
if not title:
log.debug('No h2 entrytitle')
continue
release['title'] = title.a.contents[0].strip()
log.debug('Processing title %s' % (release['title']))
for link in entry.find_all('a'):
# no content in the link
if not link.contents:
continue
link_name = link.contents[0]
if link_name is None:
continue
if not isinstance(link_name, NavigableString):
continue
link_name = link_name.strip().lower()
if link.has_attr('href'):
link_href = link['href']
else:
continue
log.debug('found link %s -> %s' % (link_name, link_href))
# handle imdb link
if link_name.lower() == 'imdb':
log.debug('found imdb link %s' % link_href)
release['imdb_url'] = link_href
# test if entry with this url would be rewritable by known plugins (ie. downloadable)
temp = {}
temp['title'] = release['title']
temp['url'] = link_href
urlrewriting = plugin.get_plugin_by_name('urlrewriting')
if urlrewriting['instance'].url_rewritable(task, temp):
release['url'] = link_href
log.trace('--> accepting %s (resolvable)' % link_href)
else:
log.trace('<-- ignoring %s (non-resolvable)' % link_href)
# reject if no torrent link
if not 'url' in release:
from flexget.utils.log import log_once
log_once('%s skipped due to missing or unsupported (unresolvable) download link' % (release['title']), log)
else:
releases.append(release)
return releases
def get_tracker_seeds(self, url, info_hash):
url = self.get_scrape_url(url)
if not url:
return 0
log.debug('Checking for seeds from %s' % url)
url += '?info_hash=%s' % quote(info_hash.decode('hex'))
data = bdecode(urlopener(url, log, retries=2).read())['files']
if not data:
return 0
return data.values()[0]['complete']
def get_tracker_seeds(self, url, info_hash):
url = self.get_scrape_url(url)
if not url:
return 0
log.debug('Checking for seeds from %s' % url)
url += '?info_hash=%s' % quote(info_hash.decode('hex'))
try:
data = bdecode(urlopener(url, log, retries=2).read()).get('files')
except SyntaxError, e:
log.warning('Error bdecoding tracker response: %s' % e)
return 0
def get_tracker_seeds(url, info_hash):
url = get_scrape_url(url, info_hash)
if not url:
log.debug('if not url is true returning 0')
return 0
log.debug('Checking for seeds from %s' % url)
try:
data = bdecode(urlopener(url, log, retries=1, timeout=10).read()).get('files')
except SyntaxError, e:
log.warning('Error decoding tracker response: %s' % e)
return 0
def on_task_input(self, task, config, session=None):
account_id = str(config['account_id'])
# Get the cache for this user
user_favorites = session.query(ThetvdbFavorites).filter(
ThetvdbFavorites.account_id == account_id).first()
if user_favorites and user_favorites.updated > datetime.now(
) - timedelta(minutes=10):
log.debug(
'Using cached thetvdb favorite series information for account ID %s'
% account_id)
else:
try:
url = 'http://thetvdb.com/api/User_Favorites.php?accountid=%s' % account_id
log.debug('requesting %s' % url)
data = ElementTree.fromstring(urlopener(url, log).read())
favorite_ids = []
for i in data.findall('Series'):
if i.text:
favorite_ids.append(i.text)
except (urllib2.URLError, IOError, AttributeError):
import traceback
# If there are errors getting the favorites or parsing the xml, fall back on cache
log.error(
'Error retrieving favorites from thetvdb, using cache.')
log.debug(traceback.format_exc())
else:
# Successfully updated from tvdb, update the database
log.debug('Successfully updated favorites from thetvdb.com')
if not user_favorites:
user_favorites = ThetvdbFavorites(account_id, favorite_ids)
else:
user_favorites.series_ids = favorite_ids
user_favorites.updated = datetime.now()
session.merge(user_favorites)
if not user_favorites.series_ids:
log.warning('Didn\'t find any thetvdb.com favorites.')
return
# Construct list of entries with our series names
entries = []
for series_id in user_favorites.series_ids:
# Lookup the series name from the id
try:
series = lookup_series(tvdb_id=series_id)
except LookupError as e:
log.error('Error looking up %s from thetvdb: %s' %
(series_id, e.message))
else:
series_name = series.seriesname
if config.get('strip_dates'):
# Remove year from end of series name if present
series_name = re.sub(r'\s+\(\d{4}\)$', '', series_name)
entries.append(Entry(series_name, '', tvdb_id=series.id))
return entries
def parse_download_page(self, url):
page = urlopener(url, log)
try:
soup = get_soup(page)
tag_div = soup.find('div', attrs={'class': 'download'})
if not tag_div:
raise UrlRewritingError('Unable to locate download link from url %s' % url)
tag_a = tag_div.find('a')
torrent_url = tag_a.get('href')
return torrent_url
except Exception, e:
raise UrlRewritingError(e)
def parse_download_page(self, url):
txheaders = {'User-agent': 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'}
req = urllib2.Request(url, None, txheaders)
page = urlopener(req, log)
try:
soup = get_soup(page)
except Exception as e:
raise UrlRewritingError(e)
down_link = soup.find('a', attrs={'href': re.compile("download/\d+/.*\.torrent")})
if not down_link:
raise UrlRewritingError('Unable to locate download link from url %s' % url)
return 'http://www.deadfrog.us/' + down_link.get('href')
def on_task_input(self, task, config):
# use rss plugin
rss_config = {'url': self.rss_url}
rss_entries = super(AppleTrailers,
self).on_task_input(task, rss_config)
# Multiple entries can point to the same movie page (trailer 1, clip
# 1, etc.)
entries = {}
for entry in rss_entries:
url = entry['original_url']
if url in entries:
continue
else:
title = entry['title']
entries[url] = title[:title.rfind('-')].rstrip()
result = []
for url, title in entries.iteritems():
inc_url = url + 'includes/playlists/web.inc'
try:
page = urlopener(inc_url, log)
except HTTPError, err:
log.warning("HTTPError when opening playlist page: %d %s" %
(err.code, err.reason))
continue
soup = get_soup(page)
links = soup.find_all('a',
attrs={
'class': 'target-quicktimeplayer',
'href': re.compile(r'_h?480p\.mov$')
})
for link in links:
url = link.get('href')
url = url[:url.rfind('_')]
quality = self.quality.lower()
if quality == 'ipod':
url += '_i320.m4v'
else:
url += '_h' + quality + '.mov'
entry = Entry()
entry['url'] = url
entry['title'] = title
match = re.search(r'.*/([^?#]*)', url)
entry['filename'] = match.group(1)
result.append(entry)
log.debug('found trailer %s', url)
def on_task_input(self, task):
pageurl = "http://tvtorrents.com/loggedin/recently_aired.do"
log.debug("InputPlugin tvtorrents requesting url %s" % pageurl)
page = urlopener(pageurl, log)
soup = get_soup(page)
hscript = soup.find('script', src=None).contents[0]
hlines = hscript.splitlines()
hash = hlines[15].strip().split("'")[1]
digest = hlines[16].strip().split("'")[1]
hurl = hlines[17].strip().split("'")
hashurl = hurl[1] + "%s" + hurl[3] + digest + hurl[5] + hash
for link in soup.find_all('a'):
if not 'href' in link:
continue
url = link['href']
title = link.contents[0]
if link.has_attr(
'onclick') and link['onclick'].find("loadTorrent") != -1:
infohash = link['onclick'].split("'")[1]
td = link.parent.parent.contents[4]
sname = td.contents[0].strip()
epi = td.contents[2].contents[0].strip()
title = "%s - %s" % (sname, epi)
url = hashurl % (infohash, )
else:
continue
if title is None:
continue
title = title.strip()
if not title:
continue
# fix broken urls
if url.startswith('//'):
url = "http:" + url
elif not url.startswith('http://') or not url.startswith(
'https://'):
url = urlparse.urljoin(pageurl, url)
# in case the title contains xxxxxxx.torrent - foooo.torrent clean it a bit (get upto first .torrent)
if title.lower().find('.torrent') > 0:
title = title[:title.lower().find(".torrent")]
entry = Entry()
entry['url'] = url
entry['title'] = title
task.entries.append(entry)
def on_task_input(self, task, config):
account_id = str(config['account_id'])
favorite_ids = []
# Get the cache for this user
with Session() as session:
user_favorites = session.query(ThetvdbFavorites).filter(ThetvdbFavorites.account_id == account_id).first()
if user_favorites:
favorite_ids = user_favorites.series_ids
if user_favorites and user_favorites.updated > datetime.now() - timedelta(minutes=10):
log.debug('Using cached thetvdb favorite series information for account ID %s' % account_id)
else:
try:
url = 'http://thetvdb.com/api/User_Favorites.php?accountid=%s' % account_id
log.debug('requesting %s' % url)
data = ElementTree.fromstring(urlopener(url, log).read())
favorite_ids = []
for i in data.findall('Series'):
if i.text:
favorite_ids.append(i.text)
except (urllib2.URLError, IOError, AttributeError):
import traceback
# If there are errors getting the favorites or parsing the xml, fall back on cache
log.error('Error retrieving favorites from thetvdb, using cache.')
log.debug(traceback.format_exc())
else:
# Successfully updated from tvdb, update the database
log.debug('Successfully updated favorites from thetvdb.com')
if not user_favorites:
user_favorites = ThetvdbFavorites(account_id, favorite_ids)
else:
user_favorites.series_ids = favorite_ids
user_favorites.updated = datetime.now()
session.merge(user_favorites)
if not favorite_ids:
log.warning('Didn\'t find any thetvdb.com favorites.')
return
# Construct list of entries with our series names
entries = []
for series_id in favorite_ids:
# Lookup the series name from the id
try:
series = lookup_series(tvdb_id=series_id)
except LookupError as e:
log.error('Error looking up %s from thetvdb: %s' % (series_id, e.args[0]))
else:
series_name = series.seriesname
if config.get('strip_dates'):
# Remove year from end of series name if present
series_name = re.sub(r'\s+\(\d{4}\)$', '', series_name)
entries.append(Entry(series_name, '', tvdb_id=series.id))
return entries
def entries_from_search(self, name, url=None, comparator=StringComparator(cutoff=0.9)):
"""Parses torrent download url from search results"""
comparator.set_seq1(name)
name = comparator.search_string()
if not url:
url = 'http://www.newtorrents.info/search/%s' % urllib.quote(name, 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.findAll('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.findNext('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
if comparator.matches(release_name):
torrents.append(Entry(title=release_name, url=torrent_url, torrent_seeds=seed,
search_ratio=comparator.ratio(), search_sort=torrent_availability(seed, 0)))
else:
log.debug('rejecting search result: %s !~ %s' % (release_name, name))
# 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], comparator=comparator)
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 get_json(url):
try:
log.debug('fetching json at %s' % url)
data = urlopener(url, log)
except URLError as e:
log.warning('Request failed %s' % url)
return
try:
result = json.load(data)
except ValueError:
log.warning('Rotten Tomatoes returned invalid json at: %s' % url)
return
return result
def parse_download_page(self, url):
txheaders = {'User-agent': 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'}
req = urllib2.Request(url, None, txheaders)
page = urlopener(req, log)
try:
soup = get_soup(page)
except Exception as e:
raise UrlRewritingError(e)
tag_a = soup.find('a', attrs={'class': 'download_link'})
if not tag_a:
raise UrlRewritingError('Unable to locate download link from url %s' % url)
torrent_url = 'http://www.bakabt.com' + tag_a.get('href')
return torrent_url
def parse_download_page(self, url):
txheaders = {'User-agent': 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'}
req = urllib2.Request(url, None, txheaders)
page = urlopener(req, log)
try:
soup = get_soup(page)
except Exception as e:
raise UrlRewritingError(e)
tag_a = soup.find('a', attrs={'class': 'download_link'})
if not tag_a:
raise UrlRewritingError('Unable to locate download link from url %s' % url)
torrent_url = 'http://www.bakabt.com' + tag_a.get('href')
return torrent_url
def parse_download_page(self, url):
txheaders = {"User-agent": "Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)"}
req = urllib2.Request(url, None, txheaders)
page = urlopener(req, log)
try:
soup = get_soup(page)
except Exception as e:
raise UrlRewritingError(e)
tag_a = soup.find("a", attrs={"class": "download_link"})
if not tag_a:
raise UrlRewritingError("Unable to locate download link from url %s" % url)
torrent_url = "http://www.bakabt.com" + tag_a.get("href")
return torrent_url
def get_json(url):
try:
log.debug('fetching json at %s' % url)
data = urlopener(url, log)
except URLError as e:
log.warning('Request failed %s' % url)
return
try:
result = json.load(data)
except ValueError:
log.warning('Rotten Tomatoes returned invalid json at: %s' % url)
return
return result
def parse_download_page(self, url):
page = urlopener(url, log)
log.debug('%s opened', url)
try:
soup = get_soup(page)
torrent_url = 'http://www.t411.me' + soup.find(text='Télécharger').findParent().get('href')
except Exception as e:
raise UrlRewritingError(e)
if not torrent_url:
raise UrlRewritingError('Unable to locate download link from url %s' % url)
return torrent_url
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 on_feed_input(self, feed):
pageurl = "http://tvtorrents.com/loggedin/recently_aired.do"
log.debug("InputPlugin tvtorrents requesting url %s" % pageurl)
page = urlopener(pageurl, log)
soup = get_soup(page)
hscript = soup.find('script', src=None).contents[0]
hlines = hscript.splitlines()
hash = hlines[15].strip().split("'")[1]
digest = hlines[16].strip().split("'")[1]
hurl = hlines[17].strip().split("'")
hashurl = hurl[1] + "%s" + hurl[3] + digest + hurl[5] + hash
for link in soup.findAll('a'):
if not 'href' in link:
continue
url = link['href']
title = link.contents[0]
if link.has_key('onclick') and link['onclick'].find("loadTorrent") != -1:
infohash = link['onclick'].split("'")[1]
td = link.parent.parent.contents[4]
sname = td.contents[0].strip()
epi = td.contents[2].contents[0].strip()
title = "%s - %s" % (sname, epi)
url = hashurl % (infohash,)
else:
continue
if title is None:
continue
title = title.strip()
if not title:
continue
# fix broken urls
if url.startswith('//'):
url = "http:" + url
elif not url.startswith('http://') or not url.startswith('https://'):
url = urlparse.urljoin(pageurl, url)
# in case the title contains xxxxxxx.torrent - foooo.torrent clean it a bit (get upto first .torrent)
if title.lower().find('.torrent') > 0:
title = title[:title.lower().find(".torrent")]
entry = Entry()
entry['url'] = url
entry['title'] = title
feed.entries.append(entry)
def on_task_input(self, task, config):
entries = []
page = urlopener(config['url'], log)
for row in csv.reader(page):
if not row:
continue
entry = Entry()
for name, index in config.get('values', {}).items():
try:
entry[name] = row[index - 1]
except IndexError:
raise Exception('Field `%s` index is out of range' % name)
entries.append(entry)
return entries
def url_from_page(self, url):
"""Parses torrent url from newtorrents download page"""
try:
page = urlopener(url, log)
data = page.read()
except urllib2.URLError:
raise UrlRewritingError('URLerror when retrieving page')
p = re.compile("copy\(\'(.*)\'\)", re.IGNORECASE)
f = p.search(data)
if not f:
# the link in which plugin relies is missing!
raise UrlRewritingError('Failed to get url from download page. Plugin may need a update.')
else:
return f.group(1)
def url_from_page(self, url):
"""Parses torrent url from newtorrents download page"""
try:
page = urlopener(url, log)
data = page.read()
except urllib2.URLError:
raise UrlRewritingError('URLerror when retrieving page')
p = re.compile("copy\(\'(.*)\'\)", re.IGNORECASE)
f = p.search(data)
if not f:
# the link in which plugin relies is missing!
raise UrlRewritingError('Failed to get url from download page. Plugin may need a update.')
else:
return f.group(1)
def update_rated(self, task, config):
"""Update my movies list"""
# set first last_time into past so we trigger update on first run
next_time = task.simple_persistence.setdefault('next_time',
datetime.datetime.min)
log.debug('next_time: %s' % next_time)
if not datetime.datetime.now() > next_time:
return
task.simple_persistence['next_time'] = datetime.datetime.now(
) + datetime.timedelta(hours=4)
log.debug('updating my movies from %s' % config['url'])
massage = []
# fix imdb html, just enough to pass parser
#
# <td class=list bgcolor="#CCCCCC"} colspan="4">
# ^ god damn noobs
massage.append((re.compile('"}'), lambda match: '"'))
# onclick="(new Image()).src='/rg/home/navbar/images/b.gif?link=/'"">IMDb</a>
# ^ are you even trying?
massage.append((re.compile('/\'""'), lambda match: '/\'"'))
# <table class="footer" id="amazon-affiliates"">
# ^ ffs, I don't think they are even trying ...
massage.append((re.compile('amazon-affiliates""'),
lambda match: 'amazon-affiliates"'))
data = urlopener(config['url'], log)
soup = BeautifulSoup(data)
count = 0
for a_imdb_link in soup.find_all(
'a', attrs={'href': re.compile(r'/title/tt\d+')}):
imdb_url = 'http://www.imdb.com%s' % a_imdb_link.get('href')
if not task.session.query(ImdbRated).filter(ImdbRated.url == config['url']).\
filter(ImdbRated.imdb_url == imdb_url).first():
rated = ImdbRated(config['url'], imdb_url)
task.session.add(rated)
log.debug('adding %s' % rated)
count += 1
if count > 0:
log.info('Added %s new movies' % count)
def parse_download_page(self, url):
txheaders = {
'User-agent': 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
}
req = urllib2.Request(url, None, txheaders)
page = urlopener(req, log)
try:
soup = get_soup(page)
except Exception as e:
raise UrlRewritingError(e)
down_link = soup.find('a', attrs={'href': re.compile(".+mp4")})
if not down_link:
raise UrlRewritingError(
'Unable to locate download link from url %s' % url)
return down_link.get('href')
def parse_download_page(self, page_url):
page = urlopener(page_url, log)
try:
soup = get_soup(page)
except Exception as e:
raise UrlRewritingError(e)
tag_a = soup.find("a", {"class": "dl_link"})
if not tag_a:
raise UrlRewritingError(
'FTDB Unable to locate download link from url %s and tag_a is : %s'
% (page_url, tag_a))
torrent_url = "http://www3.frenchtorrentdb.com" + tag_a.get(
'href') + "&js=1"
log.debug('TORRENT URL is : %s' % torrent_url)
return torrent_url
def parse_download_page(self, url):
page = urlopener(url, log)
log.debug('%s opened', url)
try:
soup = get_soup(page)
torrent_url = 'http://www.t411.me' + soup.find(
text='Télécharger').findParent().get('href')
except Exception as e:
raise UrlRewritingError(e)
if not torrent_url:
raise UrlRewritingError(
'Unable to locate download link from url %s' % url)
return torrent_url
def get_first_result(tmdb_function, value):
if isinstance(value, basestring):
value = quote(value.encode('utf-8'), safe='')
url = '%s/2.1/Movie.%s/%s/json/%s/%s' % (server, tmdb_function, lang,
api_key, value)
try:
data = urlopener(url, log)
except URLError:
log.warning('Request failed %s' % url)
return
try:
result = json.load(data)
except ValueError:
log.warning('TMDb returned invalid json.')
return
# Make sure there is a valid result to return
if isinstance(result, list) and len(result):
result = result[0]
if isinstance(result, dict) and result.get('id'):
return result
def parse_download_page(self, page_url):
page = urlopener(page_url, log)
try:
soup = get_soup(page)
except Exception as e:
raise UrlRewritingError(e)
tag_a = soup.find("a", {"class": "dl_link"})
if not tag_a:
if soup.findAll(text="Connexion ?"):
raise UrlRewritingError('You are not logged in,\
check if your cookie for\
authentication is up to date')
else:
raise UrlRewritingError('You have reached your download\
limit per 24hours, so I cannot\
get the torrent')
torrent_url = ("http://www.frenchtorrentdb.com" + tag_a.get('href') +
"&js=1")
log.debug('TORRENT URL is : %s' % torrent_url)
return torrent_url
def url_rewrite(self, task, entry):
try:
# need to fake user agent
txheaders = {'User-agent': 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'}
req = urllib2.Request(entry['url'], None, txheaders)
page = urlopener(req, log)
soup = get_soup(page)
results = soup.find_all('a', attrs={'class': 'l'})
if not results:
raise UrlRewritingError('No results')
for res in results:
url = res.get('href')
url = url.replace('/interstitial?url=', '')
# generate match regexp from google search result title
regexp = '.*'.join([x.contents[0] for x in res.find_all('em')])
if re.match(regexp, entry['title']):
log.debug('resolved, found with %s' % regexp)
entry['url'] = url
return
raise UrlRewritingError('Unable to resolve')
except Exception as e:
raise UrlRewritingError(e)
def search(self, query, comparator, config=None):
# TODO: Implement comparator matching
url = u'http://newzleech.com/?%s' % str(
urllib.urlencode({
'q': query.encode('latin1'),
'm': 'search',
'group': '',
'min': 'min',
'max': 'max',
'age': '',
'minage': '',
'adv': ''
}))
#log.debug('Search url: %s' % url)
txheaders = {
'User-Agent': 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)',
'Accept':
'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Language': 'en-us,en;q=0.5',
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
'Keep-Alive': '300',
'Connection': 'keep-alive',
}
req = urllib2.Request(url, headers=txheaders)
page = urlopener(req, log)
soup = get_soup(page)
nzbs = []
for item in soup.find_all('table', attrs={'class': 'contentt'}):
subject_tag = item.find('td', attrs={'class': 'subject'}).next
subject = ''.join(subject_tag.find_all(text=True))
complete = item.find('td', attrs={'class': 'complete'}).contents[0]
size = item.find('td', attrs={'class': 'size'}).contents[0]
nzb_url = 'http://newzleech.com/' + item.find('td',
attrs={
'class': 'get'
}).next.get('href')
#TODO: confidence match
# generate regexp from entry title and see if it matches subject
regexp = query
wildcardize = [' ', '-']
for wild in wildcardize:
regexp = regexp.replace(wild, '.')
regexp = '.*' + regexp + '.*'
#log.debug('Title regexp: %s' % regexp)
if re.match(regexp, subject):
log.debug('%s matches to regexp' % subject)
if complete != u'100':
log.debug(
'Match is incomplete %s from newzleech, skipping ..' %
query)
continue
log.info('Found \'%s\'' % query)
def parse_size(value):
try:
num = float(value[:-3])
except:
log.error('Failed to parse_size %s' % value)
return 0
# convert into megabytes
if 'GB' in value:
num *= 1024
if 'KB' in value:
num /= 1024
return num
nzb = Entry(title=subject,
url=nzb_url,
content_size=parse_size(size))
nzb['url'] = nzb_url
nzb['size'] = parse_size(size)
nzbs.append(nzb)
if not nzbs:
log.debug('Unable to find %s' % query)
return
# choose largest file
nzbs.sort(reverse=True, key=lambda x: x.get('content_size', 0))
return nzbs
def on_task_download(self, task):
# filter all entries that have IMDB ID set
try:
entries = filter(lambda x: x['imdb_url'] is not None,
task.accepted)
except KeyError:
# No imdb urls on this task, skip it
# TODO: should do lookup via imdb_lookup plugin?
return
try:
s = ServerProxy("http://api.opensubtitles.org/xml-rpc")
res = s.LogIn("", "", "en", "FlexGet")
except:
log.warning('Error connecting to opensubtitles.org')
return
if res['status'] != '200 OK':
raise Exception(
"Login to opensubtitles.org XML-RPC interface failed")
config = self.get_config(task)
token = res['token']
# configuration
languages = config['languages']
min_sub_rating = config['min_sub_rating']
match_limit = config[
'match_limit'] # no need to change this, but it should be configurable
# loop through the entries
for entry in entries:
# dig out the raw imdb id
m = re.search("tt(\d+)/$", entry['imdb_url'])
if not m:
log.debug("no match for %s" % entry['imdb_url'])
continue
imdbid = m.group(1)
query = []
for language in languages:
query.append({'sublanguageid': language, 'imdbid': imdbid})
subtitles = s.SearchSubtitles(token, query)
subtitles = subtitles['data']
# nothing found -> continue
if not subtitles:
continue
# filter bad subs
subtitles = filter(lambda x: x['SubBad'] == '0', subtitles)
# some quality required (0.0 == not reviewed)
subtitles = filter(
lambda x: float(x['SubRating']) >= min_sub_rating or float(x[
'SubRating']) == 0.0, subtitles)
filtered_subs = []
# find the best rated subs for each language
for language in languages:
langsubs = filter(lambda x: x['SubLanguageID'] == language,
subtitles)
# did we find any subs for this language?
if langsubs:
def seqmatch(subfile):
s = difflib.SequenceMatcher(lambda x: x in " ._",
entry['title'], subfile)
#print "matching: ", entry['title'], subfile, s.ratio()
return s.ratio() > match_limit
# filter only those that have matching release names
langsubs = filter(
lambda x: seqmatch(x['MovieReleaseName']), subtitles)
if langsubs:
# find the best one by SubRating
langsubs.sort(key=lambda x: float(x['SubRating']))
langsubs.reverse()
filtered_subs.append(langsubs[0])
# download
for sub in filtered_subs:
log.debug('SUBS FOUND: ', sub['MovieReleaseName'],
sub['SubRating'], sub['SubLanguageID'])
f = urlopener(sub['ZipDownloadLink'], log)
subfilename = re.match(
'^attachment; filename="(.*)"$',
f.info()['content-disposition']).group(1)
outfile = os.path.join(config['output'], subfilename)
fp = file(outfile, 'w')
fp.write(f.read())
fp.close()
f.close()
s.LogOut(token)
def post_json_to_trakt(self, url, data):
"""Dumps data as json and POSTs it to the specified url."""
req = urllib2.Request(url, json.dumps(data),
{'content-type': 'application/json'})
return urlopener(req, log)
