def filesystem_op(self, op, *args):
"""
Filesystem interface
"""
dry_run = self._dry_run
if dry_run:
print("[{}] {}".format(op, args))
return
try:
if op == 'move':
(src, dst) = (args[0], args[1])
d = dirname(dst)
if not isdir(d):
makedirs(d)
if stat(src).st_dev == stat(d).st_dev:
rename(src, dst)
else:
shutil.copy2(src, dst)
if isdir(dst):
shutil.rmtree(src)
else:
unlink(src)
self.logger.info("[move] {} => {}".format(shortify(src), shortify(dst)))
return
if op == 'remove':
target = args[0]
if isdir(target):
rmdir(target)
else:
unlink(target)
self.logger.info("[remove] {}".format(shortify(target)))
return
except Exception as e:
self.logger.error("Error with operation '{}' ({}): {}".format(op, args, e))
return
raise Exception("Invalid operation {}".format(op))
def get_analisys(analizer, url):
buff_src = None
# Fetch buffer for url
buff = None
if self._cachebag:
buff = self._cachebag.get(url.encode('utf-8'))
buff_src = 'cache' if buff else buff_src
if not buff:
try:
buff = self._fetcher.fetch(url)
except FetchError as e:
self._logger.warning("Unable to fetch '{}': {}".format(url, e))
return []
buff_src = 'fetcher' if buff else buff_src
if not buff:
raise Exception('Cannot get url')
self._logger.info(_('Got {} from {}').format(shortify(url), buff_src))
# Try analizer
try:
analisys = analizer.process(buff)
except InvalidMarkup:
self._logger.warning(_('Invalid markup on {}').format(shortify(url)))
return []
except Exception as e:
self._logger.warning(_('Unknow error {} on {}').format(e.__class__.__name__, shortify(url)))
return []
# Save to cachebag
if self._cachebag:
if type(buff) != bytes:
buff = bytes(buff, encoding='utf-8')
self._cachebag.set(url.encode('utf-8'), buff)
return analisys
def run(self, analizer,
seed_url=None, iterations=1, forced_type=None, forced_language=None,
reset_db=False, dry_run=False):
def get_analisys(analizer, url):
buff_src = None
# Fetch buffer for url
buff = None
if self._cachebag:
buff = self._cachebag.get(url.encode('utf-8'))
buff_src = 'cache' if buff else buff_src
if not buff:
try:
buff = self._fetcher.fetch(url)
except FetchError as e:
self._logger.warning("Unable to fetch '{}': {}".format(url, e))
return []
buff_src = 'fetcher' if buff else buff_src
if not buff:
raise Exception('Cannot get url')
self._logger.info(_('Got {} from {}').format(shortify(url), buff_src))
# Try analizer
try:
analisys = analizer.process(buff)
except InvalidMarkup:
self._logger.warning(_('Invalid markup on {}').format(shortify(url)))
return []
except Exception as e:
self._logger.warning(_('Unknow error {} on {}').format(e.__class__.__name__, shortify(url)))
return []
# Save to cachebag
if self._cachebag:
if type(buff) != bytes:
buff = bytes(buff, encoding='utf-8')
self._cachebag.set(url.encode('utf-8'), buff)
return analisys
sess = create_session(dbpath=dbpath)
if reset_db:
if not dry_run:
for t in sess.query(Torrent):
t.state = Torrent.State.NONE
else:
self._logger.info('Reset db')
# Build analizer
self._analizers = AnalizersMng()
try:
analizer = self._analizers.get_addon(analizer)()
except KeyError as e:
raise InvalidAnalizer("Analizer {} not found: {}".format(analizer, e))
# Prepare loop
url = seed_url or analizer.get_default_url()
iter_ = 0
counters = {}
while iter_ < max(1, iterations):
self._logger.debug(_("Analizing {0}").format(url))
counters[url] = 0
torrents = get_analisys(analizer, url)
for torrent in torrents:
torrent.provider = analizer.PROVIDER
if forced_type:
torrent.type = forced_type
if forced_language:
torrent.language = forced_language
self._logger.info(_("{0} torrents from {1} added").format(len(torrents), shortify(url)))
if not dry_run:
for torrent in torrents:
prev_torrent = sess.query(Torrent).filter_by(uri=torrent.uri).first()
if not prev_torrent:
counters[url] += 1
sess.add(torrent)
else:
# This is… emmm
for k in 'name type language timestamp seeds leechers size provider'.split(' '):
setattr(torrent, k, getattr(prev_torrent, k))
sess.commit()
iter_ += 1
url = analizer.get_next_url(url)
total = sum(counters.values())
if total:
notify(msg=_('Found {} torrent(s) from {}').format(total, analizer.PROVIDER))
def process(path, classifier, settings=None):
"""
Computes the destination filename form path using provided info and suplied rename_patterns
Returns destination path or
UnknowFileType if path is not recognised
InvalidPattern if the aplied pattern is invalid (eg. contains invalid keys)
"""
def generate_tokens(info):
tokens = info.copy()
# Fix title
if 'title' not in tokens:
tokens['title'] = ''
# Generate uc/lc/cc variants
tmp = {}
for (k, v) in [(k, v) for (k, v) in tokens.items() if isinstance(v, str)]:
tmp[k+'_uc'] = v.capitalize()
tmp[k+'_lc'] = v.lower()
tmp[k+'_cc'] = string.capwords(v)
tokens.update(tmp)
# Generate white space variants
tmp = {}
variants = ((' {}', 'prefix'), ('{} ', 'suffix'), (' {} ', 'surround'))
for (variant, name) in variants:
for (token_name, token_value) in [(k, v) for (k, v) in tokens.items() if isinstance(v, str)]:
toktype = token_name.split('_')[0]
if toktype in ('series', 'title'):
tmp[token_name+'_ws_'+name] = variant.format(token_value) if token_value else ''
tokens.update(tmp)
# Some tokens must be overriden
replacements = settings.get_section_dict('pattern_renaming:replacements')
for (pattern, replacement) in replacements.items():
for (token_name, token_value) in [(k, v) for (k, v) in tokens.items() if isinstance(v, str)]:
tokens[token_name] = re.subn(pattern, replacement, token_value, flags=re.IGNORECASE)[0]
return tokens
if not isfile(path):
return [path]
info = guessit.guess_video_info(path)
ftype = info.get('type', 'unknown')
if ftype == 'unknown':
classifier.logger.warning('Unknow filetype for {}'.format(shortify(path)))
return [path]
pattern = None
if ftype == 'episode':
series_name = info.get('series', None)
if series_name:
pattern = settings.get('pattern_renaming', "{}[{}]".format(ftype, series_name.lower()), fallback=None)
if not pattern:
pattern = settings.get('pattern_renaming', ftype, fallback=None)
if not pattern:
return [path]
dst = None
try:
tokens = generate_tokens(info)
dst = expanduser(pattern.format(**tokens))
except KeyError as e:
classifier.logger.warning("Cannot use pattern for '{}' for '{}': Missing key {}'".format(pattern, path, e))
return [path]
classifier.filesystem_op('move', path, dst)
return [dst]