def __init__(self, params=None):
"""
Initialize RRSDatabase, lookup rules, handle_rules, queue and object
topology map.
"""
# param initialization
self.lookup_level = LOOKUP_PRECISE
self.update_rule = RRSDB_MISSING
self.logfile = 'xmlimport'
self.logs = SELE_LOG
self.module = 'unknown_module'
self.schema = 'data'
for arg in ('update_rule', 'logfile', 'lookup_level', 'module', 'schema', 'logs'):
if arg in params and params[arg] is not None:
self.__dict__[arg] = params[arg]
# working space
self._queue = IMWaitingQueue()
self._mime = MIMEHandler()
self._rrsdb = RRSDatabase(self.logfile, self.schema, self.logs)
self._db = self._rrsdb._db
self._table_to_class_map = self._rrsdb._table_to_class_map
self._lookup_rules = _LookupRules()
# set logging
self.manager = RRSLogManager()
logfilename = "%s.importer.log" % self.logfile
self.logger = self.manager.new_logger("xml_import_manager", logfilename)
self.logger.info("RRSImportManager initialized.")
def __init__(self):
self.crawler = GetHTMLPage()
self.crawler.set_headers((
('User-Agent', 'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.19) Gecko/2010040116 Ubuntu/9.04 (jaunty) Firefox/3.0.19'), \
('Accept', 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8')
))
self.mime_handler = MIMEHandler()
# define wanted/unwanted file types
self.wanted_mimes = [
'application/pdf', 'application/msword', 'text/rtf'
'application/postscript', 'octet/stream',
'application/vnd.oasis.opendocument.text'
]
self.unwanted_mimes = [
'application/zip', 'application/x-tar', 'application/x-gtar'
]