def __init__(self, destination, fileName, modelName='', ldaPasses='', topicNum=''):
'''
Constructor
'''
logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO)
self.__destination = destination
self.__fileName = fileName
self.__modelName = modelName
self.__ldaPasses = ldaPasses
self.__topicNum = topicNum
#=======================================================================
# STOP WORDS AND CAHRACTERS
#=======================================================================
self.__stopwords = stopwords.words('english')# + string.punctuation
self.__chars_to_remove = [u'[', u']', u'(', u')', u'*', u'%', u'{', u'}', u'\n', u'\n\n', u'\t', u';',u'/',u'^',u'--',u'\\',u'+',u'-',u'.',u'?',u'&',u'#',u'',u'']
self.__stopwords.extend(self.__chars_to_remove)
self.__stopwords.extend([item for item in string.punctuation])
#=======================================================================
# DATABASE
#=======================================================================
self.__db = connectMySQL(db='xpath', port=3366)
self.__queryResults = None
self.__cleanedCorpus = []
if modelName != '' and os.path.exists(self.__destination+modelName+'.lda'):
self.__ldaModel = LdaModel.load(self.__destination+modelName+'.lda', mmap='r')
if fileName != '' and os.path.exists(self.__destination+fileName+'.dict'):
self.__modelDict = corpora.Dictionary.load(self.__destination+fileName+'.dict')
class ContentExtractor(object):
'''
classdocs
'''
'''
steps:
get serialized json file
'''
@profile
def __init__(self,
domain,
htmlFileURL,
pwd,
CoreNLPner='',
spacyNER='',
dbConnection=''):
'''
Constructor
'''
self.__fileURL = htmlFileURL
self.__domainDBkey = domain
try:
self.__XpathList = pickle.load(
open(
pwd + '/xpathModels/' + str(self.__domainDBkey) +
'.pickle', 'rb'))
#===================================================================
# self.__XpathListID = pickle.load(open('/Users/jurica/Documents/workspace/eclipse/TechDashboard/xpathModels/'+str(self.__domainDBkey)+'_ID.pickle', 'rb'))
# self.__XpathListNoAttrib = pickle.load(open('/Users/jurica/Documents/workspace/eclipse/TechDashboard/xpathModels/'+str(self.__domainDBkey)+'_NoAttrib.pickle', 'rb'))
#===================================================================
except PicklingError, e:
print e
self.__htmlElements = [
'body', 'header', 'nav', 'footer', 'article', 'section', 'aside',
'div', 'span'
]
self.__htmlAttributes = ['id', 'class']
self.__documentIDKey = ''
self.__utilitiesFunctions = utilities()
#DB CONNECTIVITY AND FUNCTIONALITY
self.__db = connectMySQL(db='xpath', port=3366)
self.__topicModel = techDashTopicModel(destination=pwd + '/modelsLDA/',
fileName='fullModel',
modelName='fullModel_100P_20T')
#=======================================================================
# OPEN URL
#=======================================================================
url2Open, self.__htmlFile = self.__utilitiesFunctions.openULR(
self.__fileURL)
#=======================================================================
# NER
#=======================================================================
self.__extractNerStanford = CoreNLPner
self.__extractNerSpacy = spacyNER
def __init__(self,
html4Elements=__html4Elements,
html5Elements=__html5Elements,
doctype=__doctype,
url=__url,
fileName=__fileName,
domain=__domain,
domainDBkey=__domainDBkey):
#URL TO EXTRACT XPATH AND CONTENT FROM
self.__url = url
#BASED ON DOCTYPE, DIFFERENT SET OF STRUCTURE HTML ELEMENTS ARE USED
self.__doctype = doctype
self.__html4Elements = html4Elements
self.__html5Elements = html5Elements
self.__structureElements = None
#INITAL EMPTY DICTIONARY FOR INITAL STAGE OF PARSING/EXTRACTING
self.__domDict = {}
#DB CONNECTIVITY AND FUNCTIONALITY
self.__db = connectMySQL(db='xpath', port=3366)
#print dir(self.__db)
#domain information
self.__domain = domain
self.__domainDBkey = domainDBkey
self.__documentIDKey = None
#CSV file operations - DISCARDED FOR NOW, SWITHING TO MYSQL OPERATION
self.__fileName = fileName
try:
self.__f = open(self.__fileName, "a")
self.__spamwriter = csv.writer(self.__f,
delimiter=';',
quotechar='/',
quoting=csv.QUOTE_NONE)
except:
print("There is no file named", self.__filename)
#GET DB KEY FOR CURRENT DOMAIN OR INSERT IN TO DB IF CONTENT FROM TAHT DOMAIN NOT YET ANALYZED
self.getDomainKey()
#=======================================================================
# START CREATING DOM TREE
#=======================================================================
self.readDOMrecursive()
def __init__(self,
destination,
fileName,
modelName='',
ldaPasses='',
topicNum=''):
'''
Constructor
'''
logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s',
level=logging.INFO)
self.__destination = destination
self.__fileName = fileName
self.__modelName = modelName
self.__ldaPasses = ldaPasses
self.__topicNum = topicNum
#=======================================================================
# STOP WORDS AND CAHRACTERS
#=======================================================================
self.__stopwords = stopwords.words('english') # + string.punctuation
self.__chars_to_remove = [
u'[', u']', u'(', u')', u'*', u'%', u'{', u'}', u'\n', u'\n\n',
u'\t', u';', u'/', u'^', u'--', u'\\', u'+', u'-', u'.', u'?',
u'&', u'#', u'', u''
]
self.__stopwords.extend(self.__chars_to_remove)
self.__stopwords.extend([item for item in string.punctuation])
#=======================================================================
# DATABASE
#=======================================================================
self.__db = connectMySQL(db='xpath', port=3366)
self.__queryResults = None
self.__cleanedCorpus = []
if modelName != '' and os.path.exists(self.__destination + modelName +
'.lda'):
self.__ldaModel = LdaModel.load(self.__destination + modelName +
'.lda',
mmap='r')
if fileName != '' and os.path.exists(self.__destination + fileName +
'.dict'):
self.__modelDict = corpora.Dictionary.load(self.__destination +
fileName + '.dict')
def __init__(
self,
html4Elements=__html4Elements,
html5Elements=__html5Elements,
doctype=__doctype,
url=__url,
fileName=__fileName,
domain=__domain,
domainDBkey=__domainDBkey,
):
# URL TO EXTRACT XPATH AND CONTENT FROM
self.__url = url
# BASED ON DOCTYPE, DIFFERENT SET OF STRUCTURE HTML ELEMENTS ARE USED
self.__doctype = doctype
self.__html4Elements = html4Elements
self.__html5Elements = html5Elements
self.__structureElements = None
# INITAL EMPTY DICTIONARY FOR INITAL STAGE OF PARSING/EXTRACTING
self.__domDict = {}
# DB CONNECTIVITY AND FUNCTIONALITY
self.__db = connectMySQL(db="xpath", port=3366)
# print dir(self.__db)
# domain information
self.__domain = domain
self.__domainDBkey = domainDBkey
self.__documentIDKey = None
# CSV file operations - DISCARDED FOR NOW, SWITHING TO MYSQL OPERATION
self.__fileName = fileName
try:
self.__f = open(self.__fileName, "a")
self.__spamwriter = csv.writer(self.__f, delimiter=";", quotechar="/", quoting=csv.QUOTE_NONE)
except:
print ("There is no file named", self.__filename)
# GET DB KEY FOR CURRENT DOMAIN OR INSERT IN TO DB IF CONTENT FROM TAHT DOMAIN NOT YET ANALYZED
self.getDomainKey()
# =======================================================================
# START CREATING DOM TREE
# =======================================================================
self.readDOMrecursive()
'''
Created on 27 Nov 2015
@author: jurica
'''
from mysqlUtilities import connectMySQL
from spacy.en import English, LOCAL_DATA_DIR
db = connectMySQL(db='xpath', port=3366)
sqlQuery = "SELECT xpathValuesID, xpathValuesXPathNER FROM xpath.xpathValuesXPath where xpathValuesXPathNER like '%[%]' order by xpathValuesXPathDateTime desc"
db.executeQuery(sqlQuery)
for item in db._connectMySQL__results:
#===========================================================================
# print item[1], type(item[1])
#===========================================================================
#===========================================================================
# print len(item[1]), item[1]
#===========================================================================
print '========'
if len(item[1])>2:
tempList = []
for tem in item[1].split(','):
stripped = tem.strip('"').strip("'").strip('[').strip("]")
stripped = stripped.replace("'","")
stripped = stripped.replace('"','')
tempList.append(stripped)
nerEntities = ",".join(list(set(tempList)))
print nerEntities
else:
nerEntities = 'No NERs Recognized'
from tweepy import Stream
from tweepy import OAuthHandler
from tweepy.streaming import StreamListener
import json
from mysqlUtilities import connectMySQL
from pprint import pprint
import time
import traceback
# tags = ['izboriRH','izboriHR','izbori2015','izbori']
tags = ["izboriRH"]
from mysqlUtilities import connectMySQL
db = connectMySQL(db="crolections", port=3366)
# consumer key, consumer secret, access token, access secret.
ckey = "YaV9e065RrS7GDG7ZPOeCHl3c"
csecret = "ttfJ3oaGuViY2QnrB4AjtY259ow5uDef5CiK0GMOTVQW1kNDyF"
atoken = "2926971581-qhxdUJThotm8Jpmy9Ks5P2XWivDcYSeCtvaDCpj"
asecret = "eLd0UWqoFt5riom4hzKukk1jVrpK6zFdm5dPLVSJnfnz9"
class listener(StreamListener):
def on_data(self, data):
try:
all_data = json.loads(data)
# ===================================================================
# pprint(all_data)
#===============================================================================
# http://stackoverflow.com/questions/28267640/tweepy-get-old-tweets-now-possible-with-twitter-search-api
# how to get old tweets
#===============================================================================
from tweepy.models import Status
import tweepy
from pprint import pprint
import json
import time
from mysqlUtilities import connectMySQL
db = connectMySQL(db='crolections', port=3366)
ckey = "YaV9e065RrS7GDG7ZPOeCHl3c"
csecret = "ttfJ3oaGuViY2QnrB4AjtY259ow5uDef5CiK0GMOTVQW1kNDyF"
atoken = "2926971581-qhxdUJThotm8Jpmy9Ks5P2XWivDcYSeCtvaDCpj"
asecret = "eLd0UWqoFt5riom4hzKukk1jVrpK6zFdm5dPLVSJnfnz9"
auth = tweepy.OAuthHandler(ckey, csecret)
auth.set_access_token(atoken, asecret)
api = tweepy.API(auth)
query = '#izboriRH OR #izborirh OR #izbori2015 OR #izbori15 OR #politikahr'
for all_data in tweepy.Cursor(api.search, q=query).items():
sqlExists = 'select count(*) from izbori2015 where izbori2015_tweet_id = %d'%(all_data.id)
db.executeQuery(sqlExists)
#===========================================================================
# print sqlExists
'''
Created on 27 Nov 2015
@author: jurica
'''
from mysqlUtilities import connectMySQL
from spacy.en import English, LOCAL_DATA_DIR
db = connectMySQL(db='xpath', port=3366)
sqlQuery = "SELECT xpathValuesID, xpathValuesXPathNER FROM xpath.xpathValuesXPath where xpathValuesXPathNER like '%[%]' order by xpathValuesXPathDateTime desc"
db.executeQuery(sqlQuery)
for item in db._connectMySQL__results:
#===========================================================================
# print item[1], type(item[1])
#===========================================================================
#===========================================================================
# print len(item[1]), item[1]
#===========================================================================
print '========'
if len(item[1]) > 2:
tempList = []
for tem in item[1].split(','):
stripped = tem.strip('"').strip("'").strip('[').strip("]")
stripped = stripped.replace("'", "")
stripped = stripped.replace('"', '')
tempList.append(stripped)
nerEntities = ",".join(list(set(tempList)))
print nerEntities
else:
nerEntities = 'No NERs Recognized'
from tweepy import Stream
from tweepy import OAuthHandler
from tweepy.streaming import StreamListener
import json
from mysqlUtilities import connectMySQL
from pprint import pprint
import time
import traceback
#tags = ['izboriRH','izboriHR','izbori2015','izbori']
tags = ['izboriRH']
from mysqlUtilities import connectMySQL
db = connectMySQL(db='crolections', port=3366)
#consumer key, consumer secret, access token, access secret.
ckey = "YaV9e065RrS7GDG7ZPOeCHl3c"
csecret = "ttfJ3oaGuViY2QnrB4AjtY259ow5uDef5CiK0GMOTVQW1kNDyF"
atoken = "2926971581-qhxdUJThotm8Jpmy9Ks5P2XWivDcYSeCtvaDCpj"
asecret = "eLd0UWqoFt5riom4hzKukk1jVrpK6zFdm5dPLVSJnfnz9"
class listener(StreamListener):
def on_data(self, data):
try:
all_data = json.loads(data)
#===================================================================
# pprint(all_data)