here i have posted my code...plz tell why am i getting the error "int
argument required" on the hash marked line(see below) although i am
giving an int value
#the code
import os
import string
import MySQLdb
import stopcheck
conn = MySQLdb.connect(host='localhost',user='root',db='urdb')
def file_extractor(dir_name):
url_count = 0
for file in os.listdir(dir_name):
if(file[-4:] == '.txt'):
file_path = os.path.join(dir_name,file)
curse = conn.cursor()
url_count += 1
curse.execute("INSERT INTO URL_TABLE VALUES(%d,%s)",
(url_count,file_path)) #error
word_extractor(url_count,file_path)
def word_extractor(url_count,file):
fhandle = open(file)
line = fhandle.readline()
k=stopcheck.checker()
k.create()
while line:
words = line.split()
cursor = conn.cursor()
for word1 in words:
if word1 not in string.punctuation:
if (k.check(word1) is 0) and (word1[0:4] != 'http') :
word_count+=1
try:
cursor.execute("INSERT INTO word_table(id,word)
VALUES(%d,%s)" , (word_count,word1))
cursor.execute("INSERT INTO wordmatch
(word_id,url_id) values(%d,%d)",(word_count,url_count))
except MySQLdb.Error, e:
print "Error %d: %s" % (e.args[0], e.args[1])
line=fhandle.readline()
if __name__ == '__main__':
#url_count=0
#word_count=0
dir = os.path.join('D://','acm')
file_extractor(dir)
