def __init__(self, db):
self.db = db
self.findex = Findex(db)
self.env = {}
self.files = None
class Searcher():
def __init__(self, cfg, db):
self.cfg = cfg
self.db = db
self.findex = Findex(self.db)
def _key_check(self, keyword):
if isinstance(keyword, dict):
if not 'key' in keyword or not keyword['key']:
raise SearchException('Search query must contain 4 characters or more')
keyword = keyword['key'][0]
block = ['-', ',', '+', '_', '%']
for b in block:
keyword = keyword.replace(b, ' ')
if len(keyword) < 4:
raise SearchException('Search query must contain 4 characters or more')
return keyword
def search(self, vars):
val = self._key_check(vars)
val = val.lower()
filtered = False
start_dbtime = datetime.now()
# to-do: move this to API (or make api.py use this class)
q = self.db.query(Files)
# if this is later set with Files.<column_name>, it will be sorted on this.
sort = ''
sdata = {
'protocols': [],
'hosts': [],
'exts': [],
'cats': [],
'fsize': 0
}
if 'protocols' in vars:
protocols = [z.lower() for z in vars['protocols']]
plookup = {'ftp': 0, 'http': 1, 'smb': 2}
protocols_ids = []
if isinstance(protocols, list):
protocols = [z.lower() for z in protocols]
for p in protocols:
if p in plookup and not plookup[p] in protocols_ids:
protocols_ids.append(plookup[p])
if protocols_ids:
sdata['protocols'] = protocols_ids
else:
sdata['protocols'] = [0, 1, 2]
if 'hosts' in vars:
dhosts = vars['hosts']
if isinstance(dhosts, list):
if not dhosts[0] == '*':
host_ids = []
for host in dhosts:
host_results = self.db.query(Hosts).filter(Hosts.address==host).filter(Hosts.protocol.in_(sdata['protocols'])).all()
for host_result in host_results:
host_ids.append(host_result.id)
if host_ids:
sdata['hosts'] = host_ids
else:
raise SearchException('Could not find any host entries for specified host(s)')
if sdata['hosts']:
q = q.filter(Files.host_id.in_(sdata['hosts']))
filtered = True
if 'cats' in vars:
clookup = {
'unknown': 0,
'documents': 1,
'movies': 2,
'music': 3,
'pictures': 4
}
dformats = []
for cat in [z.lower() for z in vars['cats']]:
if cat in clookup:
dformats.append(clookup[cat])
else:
dformats.append(int(cat))
if isinstance(dformats, list):
q = q.filter(Files.file_format.in_(dformats))
for dformat in dformats:
sdata['cats'].append(dformat)
else:
sdata['cats'] = [0, 1, 2, 3, 4]
for i in [0, 1, 2, 3, 4]:
if not i in sdata['cats']:
filtered = True
if 'exts' in vars:
exts = vars['exts']
if isinstance(exts, list):
exts = [z.replace('.', '') for z in exts if z]
q = q.filter(Files.file_ext.in_(exts))
filtered = True
for ext in exts:
sdata['exts'].append(ext)
elif '.' in val:
spl = val.split('.', 1)
ext = spl[1].replace(',', '').strip()
q = q.filter(Files.file_ext == ext)
sdata['exts'].append(ext)
val = self._key_check(spl[0])
filtered = True
if 'size' in vars:
fsize = vars['size']
if isinstance(fsize, list):
fsize = int(fsize[0])
sizes = {
0: '*',
1: (0, 8388600),
2: (8388600, 134220000),
3: (134220000, 536870912),
4: (536870912, 2147483648),
5: (2147483648, 8589934592),
6: (8589934592)
}
if fsize == 0:
pass
elif 1 <= fsize <= 5:
q = q.filter(Files.file_size > sizes[fsize][0], Files.file_size < sizes[fsize][1])
filtered = True
elif fsize == 6:
q = q.filter(Files.file_size > sizes[fsize])
filtered = True
sdata['fsize'] = fsize
sort = 'file_size'
if 'path' in vars:
path = vars['path']
if isinstance(path, list):
path = path[0]
if len(path) > 3:
path = quote_plus(path)
q = q.filter(Files.file_path.like(path+'%'))
filtered = True
if 'host' in vars:
host = vars['host']
if isinstance(host, list):
host = int(host[0])
q = q.filter(Files.host_id == host)
filtered = True
q = q.filter(Files.searchable.like('%'+val+'%')).limit(600)
results = {}
results['data'] = q.all()
results['load_dbtime'] = (datetime.now() - start_dbtime).total_seconds()
if sort:
results['data'] = sorted(results['data'], key=lambda k: k.file_size, reverse=True)
# to-do: dont do this here
for r in results['data']:
host = self.findex.get_host_objects(r.host_id)
setattr(r, 'host', host)
results['data'] = self.findex.set_humanize(results['data'])
results['data'] = self.findex.set_icons(results['data'])
sdata['filtered'] = filtered
return {'sdata': sdata, 'results': results, 'key': jinja2.escape(vars['key'][0])}
class Browser:
def __init__(self, db):
self.db = db
self.findex = Findex(db)
self.env = {}
self.files = None
def parse_incoming_path(self, path):
self.env["isdir"] = path.endswith("/")
spl = path.split("/")
self.env["host"] = spl[0]
self.env["file_path"] = "/" + "/".join(spl[1:-1])
if not self.env["isdir"]:
self.env["file_name"] = path.split("/")[-1]
if self.env["file_path"] != "/":
self.env["file_path"] += "/"
self.env["file_path_quoted"] = quote_plus(self.env["file_path"])
def fetch_files(self):
host = self.db.query(Hosts).filter_by(address=self.env["host"]).first()
if not host:
raise BrowseException("No host found")
self.env["host_id"] = host.id
files = self.findex.get_files_objects(host_id=host.id, file_path=self.env["file_path_quoted"])
if not files:
raise BrowseException("No files found")
self.files = files
def prepare_files(self, sort=None):
# sort files
self.files = sorted(self.files, key=lambda k: k.file_name) # alphabetically
self.files = sorted(self.files, key=lambda k: k.file_isdir, reverse=True) # folders always on top
if not self.env["file_path"] == "/": # add CDUP dirs
x = Files(
file_name="..",
file_path="../",
file_ext="",
file_format=-1,
file_isdir=True,
file_modified=datetime.now(),
file_perm=None,
searchable=None,
file_size=0,
host=self.env["host"],
)
setattr(x, "file_name_human", "..")
self.files.insert(0, x)
self.files = self.findex.set_icons(self.files)
def sort(self):
# calculate total folder file size (non-recursive)
total_size = 0
for f in self.files:
total_size += f.file_size
def generate_action_fetches(self):
url = "ftp://%s" % self.env["host"]
if self.env["file_path"] == "/":
path = ""
elif self.env["file_path"].startswith("/") and url.endswith("/"):
path = self.env["file_path"][1:]
wget_extras = ""
lftp_extras = ""
# if self.source.crawl_authtype:
# wget_extras = 'user=%s password=%s ' % (self.source.crawl_username, self.source.crawl_password)
#
# if self.source.crawl_authtype == 'HTTP_DIGEST':
# lftp_extras = Debug('Authentication using DIGEST is not supported by lftp')
# else:
# lftp_extras = '-u %s,%s ' % (self.source.crawl_username, self.source.crawl_password)
wget = "wget %s-r -nH --no-parent '%s'" % (wget_extras, url + self.env["file_path"])
# if not isinstance(lftp_extras, Debug):
lftp = "lftp %s-e 'mirror' '%s'" % (lftp_extras, url + self.env["file_path"])
# else:
# lftp = lftp_extras.message
return dict(wget=wget, lftp=lftp)
def breadcrumbs(self):
data = [self.env["host"]]
data += [z for z in self.env["file_path"].split("/")[1:] if z]
return data
def output_json(self):
data = []
for source_file in self.files:
if source_file.filename_human == "..":
continue
data.append(
"[%s] %s%s%s"
% (
"D" if source_file.is_directory else "F",
self.folder.source.crawl_url,
source_file.filepath_human,
source_file.filename_human,
)
)
return "\n".join(data)
def __init__(self, cfg, db):
self.cfg = cfg
self.db = db
self.findex = Findex(db=self.db)
def __init__(self, cfg, db):
self.cfg = cfg
self.db = db
self.findex = Findex(self.db)
class Browse():
def __init__(self, cfg, db):
self.cfg = cfg
self.db = db
self.findex = Findex(db=self.db)
@data_strap
def hosts(self, env):
data = {}
data['hosts'] = self.db.query(Hosts).all()
return jinja2_template('main/browse_hosts', env=env, data=data)
@data_strap
def browse(self, path, env):
env['load_dbtime'] = 0
browser = Browser(db=self.db)
try:
browser.parse_incoming_path(path)
start_dbtime = datetime.now()
browser.fetch_files()
env['load_dbtime'] = (datetime.now() -
start_dbtime).total_seconds()
browser.prepare_files()
data = {
'files': browser.files,
'breadcrumbs': browser.breadcrumbs(),
'action_fetches': browser.generate_action_fetches(),
'env': browser.env
}
return jinja2_template('main/browse_dir', env=env, data=data)
except Exception as ex:
return jinja2_template('main/error',
env=env,
data={'error': 'no files were found'})
return ''
@data_strap
def goto(self, path, env):
try:
uid = int(path)
f = self.findex.get_files_objects(id=uid)
if not f:
raise Exception()
f = f[0]
h = self.db.query(Hosts).filter_by(id=f.host_id).first()
if f and h:
data = {'file': f, 'host': h}
else:
raise Exception()
return jinja2_template('main/browse_goto', env=env, data=data)
except Exception as ex:
return 'error :( we could always stay here'
class Browse():
def __init__(self, cfg, db):
self.cfg = cfg
self.db = db
self.findex = Findex(db=self.db)
@data_strap
def hosts(self, env):
data = {}
data['hosts'] = self.db.query(Hosts).all()
return jinja2_template('main/browse_hosts', env=env, data=data)
@data_strap
def browse(self, path, env):
env['load_dbtime'] = 0
browser = Browser(db=self.db)
try:
browser.parse_incoming_path(path)
start_dbtime = datetime.now()
browser.fetch_files()
env['load_dbtime'] = (datetime.now() - start_dbtime).total_seconds()
browser.prepare_files()
data = {
'files': browser.files,
'breadcrumbs': browser.breadcrumbs(),
'action_fetches': browser.generate_action_fetches(),
'env': browser.env
}
return jinja2_template('main/browse_dir', env=env, data=data)
except Exception as ex:
return jinja2_template('main/error', env=env, data={
'error': 'no files were found'
})
return ''
@data_strap
def goto(self, path, env):
try:
uid = int(path)
f = self.findex.get_files_objects(id=uid)
if not f:
raise Exception()
f = f[0]
h = self.db.query(Hosts).filter_by(
id=f.host_id
).first()
if f and h:
data = {
'file': f,
'host': h
}
else:
raise Exception()
return jinja2_template('main/browse_goto', env=env, data=data)
except Exception as ex:
return 'error :( we could always stay here'
def __init__(self, db):
self.db = db
self.findex = Findex(db)
self.env = {}
self.files = None
class Browser():
def __init__(self, db):
self.db = db
self.findex = Findex(db)
self.env = {}
self.files = None
def parse_incoming_path(self, path):
self.env['isdir'] = path.endswith('/')
spl = path.split('/')
self.env['host'] = spl[0]
self.env['file_path'] = '/' + '/'.join(spl[1:-1])
if not self.env['isdir']: self.env['file_name'] = path.split('/')[-1]
if self.env['file_path'] != '/': self.env['file_path'] += '/'
self.env['file_path_quoted'] = quote_plus(self.env['file_path'])
def fetch_files(self):
host = self.db.query(Hosts).filter_by(
address=self.env['host']
).first()
if not host:
raise BrowseException('No host found')
self.env['host_id'] = host.id
files = self.findex.get_files_objects(host_id=host.id, file_path=self.env['file_path_quoted'])
if not files:
raise BrowseException('No files found')
self.files = files
def prepare_files(self, sort=None):
# sort files
self.files = sorted(self.files, key=lambda k: k.file_name) # alphabetically
self.files = sorted(self.files, key=lambda k: k.file_isdir, reverse=True) # folders always on top
if not self.env['file_path'] == '/': # add CDUP dirs
x = Files(
file_name='..', file_path='../', file_ext='', file_format=-1,
file_isdir=True, file_modified=datetime.now(), file_perm=None, searchable=None,
file_size=0, host=self.env['host']
)
setattr(x, 'file_name_human', '..')
self.files.insert(0, x)
self.files = self.findex.set_icons(self.files)
def sort(self):
# calculate total folder file size (non-recursive)
total_size = 0
for f in self.files:
total_size += f.file_size
def generate_action_fetches(self):
url = 'ftp://%s' % self.env['host']
if self.env['file_path'] == '/':
path = ''
elif self.env['file_path'].startswith('/') and url.endswith('/'):
path = self.env['file_path'][1:]
wget_extras = ''
lftp_extras = ''
# if self.source.crawl_authtype:
# wget_extras = 'user=%s password=%s ' % (self.source.crawl_username, self.source.crawl_password)
#
# if self.source.crawl_authtype == 'HTTP_DIGEST':
# lftp_extras = Debug('Authentication using DIGEST is not supported by lftp')
# else:
# lftp_extras = '-u %s,%s ' % (self.source.crawl_username, self.source.crawl_password)
wget = 'wget %s-r -nH --no-parent \'%s\'' % (wget_extras, url + self.env['file_path'])
#if not isinstance(lftp_extras, Debug):
lftp = 'lftp %s-e \'mirror\' \'%s\'' % (lftp_extras, url + self.env['file_path'])
#else:
# lftp = lftp_extras.message
return dict(wget=wget, lftp=lftp)
def breadcrumbs(self):
data = [self.env['host']]
data += [z for z in self.env['file_path'].split('/')[1:] if z]
return data
def output_json(self):
data = []
for source_file in self.files:
if source_file.filename_human == '..':
continue
data.append('[%s] %s%s%s' % (
'D' if source_file.is_directory else 'F',
self.folder.source.crawl_url,
source_file.filepath_human,
source_file.filename_human))
return '\n'.join(data)
class Searcher():
def __init__(self, cfg, db):
self.cfg = cfg
self.db = db
self.findex = Findex(self.db)
def _key_check(self, keyword):
if isinstance(keyword, dict):
if not 'key' in keyword or not keyword['key']:
raise SearchException(
'Search query must contain 4 characters or more')
keyword = keyword['key'][0]
block = ['-', ',', '+', '_', '%']
for b in block:
keyword = keyword.replace(b, ' ')
if len(keyword) < 4:
raise SearchException(
'Search query must contain 4 characters or more')
return keyword
def search(self, vars):
val = self._key_check(vars)
val = val.lower()
filtered = False
start_dbtime = datetime.now()
# to-do: move this to API (or make api.py use this class)
q = self.db.query(Files)
# if this is later set with Files.<column_name>, it will be sorted on this.
sort = ''
sdata = {
'protocols': [],
'hosts': [],
'exts': [],
'cats': [],
'fsize': 0
}
if 'protocols' in vars:
protocols = [z.lower() for z in vars['protocols']]
plookup = {'ftp': 0, 'http': 1, 'smb': 2}
protocols_ids = []
if isinstance(protocols, list):
protocols = [z.lower() for z in protocols]
for p in protocols:
if p in plookup and not plookup[p] in protocols_ids:
protocols_ids.append(plookup[p])
if protocols_ids:
sdata['protocols'] = protocols_ids
else:
sdata['protocols'] = [0, 1, 2]
if 'hosts' in vars:
dhosts = vars['hosts']
if isinstance(dhosts, list):
if not dhosts[0] == '*':
host_ids = []
for host in dhosts:
host_results = self.db.query(Hosts).filter(
Hosts.address == host).filter(
Hosts.protocol.in_(sdata['protocols'])).all()
for host_result in host_results:
host_ids.append(host_result.id)
if host_ids:
sdata['hosts'] = host_ids
else:
raise SearchException(
'Could not find any host entries for specified host(s)'
)
if sdata['hosts']:
q = q.filter(Files.host_id.in_(sdata['hosts']))
filtered = True
if 'cats' in vars:
clookup = {
'unknown': 0,
'documents': 1,
'movies': 2,
'music': 3,
'pictures': 4
}
dformats = []
for cat in [z.lower() for z in vars['cats']]:
if cat in clookup:
dformats.append(clookup[cat])
else:
dformats.append(int(cat))
if isinstance(dformats, list):
q = q.filter(Files.file_format.in_(dformats))
for dformat in dformats:
sdata['cats'].append(dformat)
else:
sdata['cats'] = [0, 1, 2, 3, 4]
for i in [0, 1, 2, 3, 4]:
if not i in sdata['cats']:
filtered = True
if 'exts' in vars:
exts = vars['exts']
if isinstance(exts, list):
exts = [z.replace('.', '') for z in exts if z]
q = q.filter(Files.file_ext.in_(exts))
filtered = True
for ext in exts:
sdata['exts'].append(ext)
elif '.' in val:
spl = val.split('.', 1)
ext = spl[1].replace(',', '').strip()
q = q.filter(Files.file_ext == ext)
sdata['exts'].append(ext)
val = self._key_check(spl[0])
filtered = True
if 'size' in vars:
fsize = vars['size']
if isinstance(fsize, list):
fsize = int(fsize[0])
sizes = {
0: '*',
1: (0, 8388600),
2: (8388600, 134220000),
3: (134220000, 536870912),
4: (536870912, 2147483648),
5: (2147483648, 8589934592),
6: (8589934592)
}
if fsize == 0:
pass
elif 1 <= fsize <= 5:
q = q.filter(Files.file_size > sizes[fsize][0],
Files.file_size < sizes[fsize][1])
filtered = True
elif fsize == 6:
q = q.filter(Files.file_size > sizes[fsize])
filtered = True
sdata['fsize'] = fsize
sort = 'file_size'
if 'path' in vars:
path = vars['path']
if isinstance(path, list):
path = path[0]
if len(path) > 3:
path = quote_plus(path)
q = q.filter(Files.file_path.like(path + '%'))
filtered = True
if 'host' in vars:
host = vars['host']
if isinstance(host, list):
host = int(host[0])
q = q.filter(Files.host_id == host)
filtered = True
q = q.filter(Files.searchable.like('%' + val + '%')).limit(600)
results = {}
results['data'] = q.all()
results['load_dbtime'] = (datetime.now() -
start_dbtime).total_seconds()
if sort:
results['data'] = sorted(results['data'],
key=lambda k: k.file_size,
reverse=True)
# to-do: dont do this here
for r in results['data']:
host = self.findex.get_host_objects(r.host_id)
setattr(r, 'host', host)
results['data'] = self.findex.set_humanize(results['data'])
results['data'] = self.findex.set_icons(results['data'])
sdata['filtered'] = filtered
return {
'sdata': sdata,
'results': results,
'key': jinja2.escape(vars['key'][0])
}
