def _extractFromDocument(extractorSelector,
filepath,
documentClass,
index=None):
documentString = readFromFile(filepath)
print "\n---------\nDocument:\n---------\n", documentString, "\n---------"
processedDocument = PreProcessor.removeEscapeChars(documentString)
if index is not None:
parser = TextParser(os.getcwd() + "/Parsers")
email, isMultipart = parser.getEmailFromString(documentString)
payload = email.get_payload()
print "Email no. " + str(index) + ": "
print "---------"
for header in email.keys():
print "\n" + header + ": " + email.get(header)
print "\nPayload: " + payload
print "---------"
processedPayload = PreProcessor.removeEscapeChars(payload)
return _selectExtractorAndProcess(extractorSelector,\
processedDocument,\
documentClass,\
email.get("Message-Id"),\
processedPayload)
else:
return _selectExtractorAndProcess(extractorSelector,\
processedDocument,\
documentClass)
def __init__(self,
documentName,
indicators=None,
functionToCall=None,
paramList=None):
self.featureSet = None
self.documentName = documentName
self.tagged = False
pathToParser = os.getcwd() + "/Parsers"
self.textParser = TextParser(pathToParser)
self.htmlParser = HTMLParser()
self.functionToCall = functionToCall
self.paramList = paramList
if isinstance(indicators,
(list, tuple)): #If 'indicators' is a list or tuple
self.indicators = indicators
else:
self.indicators = []