program cannot handle big file

from sqlite3 import dbapi2 as sqlite
 
#DEFINE  ########################################################
#Do not change these 
class URL_TITLE_OUTPUT_TYPE():
    URL_ONLY = 1
    TITLE_ONLY = 2
    BOTH = 3
 
class CSV_DELIMIT_TYPE():
    TAB = "\t"
    COMMA = "," 
# END DEFINE  ########################################################    
 
#USE the switch var below to config
 
SWITCH_URL_TITLE_OUTPUT = URL_TITLE_OUTPUT_TYPE.TITLE_ONLY  # or URL_TITLE_OUTPUT_TYPE.TITLE_ONLY or URL_TITLE_OUTPUT_TYPE.BOTH
SWITCH_CSV_DELIMIT = CSV_DELIMIT_TYPE.COMMA   # or CSV_DELIMIT_TYPE.COMMA 
 
########################################################        
 
CSV_FILE = "C:/his/testdata.csv"
DATABASE_FILE = "C:/his/test.db"
index_dict ={}
index_dict_for_title = {}
 
def write_to_csv(content_list):
 
   f = open(CSV_FILE,"a")
   f.write(SWITCH_CSV_DELIMIT.join(content_list) + "\n")
   f.flush()
   f.close()
 
def get_csv_output(matrix,words,urls):
 
   title = []
   judge_url_title_output(title,"WebAddress","Titles")
   title.extend(words)
   write_to_csv(title)
 
   for url in urls:
       line = []
       judge_url_title_output(line,url,get_title(matrix,url))
       for word in words:
           line.append(get_amount(matrix,word,url));
       print "finish make url : " + url
       write_to_csv(line)
 
   print "have done..."
 
def judge_url_title_output(line_list,url,title):
    if SWITCH_URL_TITLE_OUTPUT == URL_TITLE_OUTPUT_TYPE.URL_ONLY:
        line_list.append(url)
    elif SWITCH_URL_TITLE_OUTPUT == URL_TITLE_OUTPUT_TYPE.TITLE_ONLY:
        line_list.append(title)
    elif SWITCH_URL_TITLE_OUTPUT == URL_TITLE_OUTPUT_TYPE.BOTH:    
        line_list.append(url)
        line_list.append(title)
    else:
        print "SWITCH_URL_TITLE_OUTPUT var error,can not lookup value ,check it pls"    
        line_list.append(url)
 
 
def get_amount(matrix,word,url):
   key = word + "&" + url
   if index_dict.has_key(key):
       return index_dict[key]
   else:
       return "0"
 
def get_title(matrix,url):
   key =  url
   if index_dict_for_title.has_key(key):
       return index_dict_for_title[key]
   else:
       return ""
 
def make_index_dict(rows):
   key =""
   value = ""
   for row in rows:
       key = row[1]+"&"+row[2]
       index_dict[key] = str(row[0])
       index_dict_for_title[row[2]] = str(row[3])
   print "finish init index_dict..."
 
 
 
 
def start():
 
   conn = sqlite.connect(DATABASE_FILE)
   # I  add titleName column in the sql query
   sql = '''SELECT count( wordlocation.wordid ) AS amount ,
                                   wordlist.word ,urllist.url , titles.titleName
                                       FROM wordlocation , wordlist , urllist, titles
                                       WHERE wordlist.rowid = wordlocation.wordid
                                       AND urllist.rowid = wordlocation.urlid
                                       AND urllist.rowid = titles.urlid
                                       GROUP BY wordlocation.urlid , wordid'''
 
   cu = conn.cursor()
   cu.execute(sql)
   rs = cu.fetchall()
 
   if not rs  or len(rs)==0 :
       print "no data found..."
 
   urls = []
   words = []
   moreIgnoreWords = ['googl', 'blog', 'search', 't', 'link', 'activ',  'background', 'k', 'h', 'font', 'i', 'z', 'displai', 'none', 'div', 'n', 'margin', 'top',  'bold', 'q', 'b', 'ch', 'cursor', 'pointer', 'e', 'p', 'pr', 'ul',   'li', 'list', 'style',  'j', 'line', 'height', 'br', 'sbb', 'td', 'lrr', 'sop', 'gbar', 'float', 'gbh', 'border', 'solid', 'posit', 'absolut', 'gbi', 'fff', 'index', 'guser', 'import', 'media', 'all', 'right', 'vertic', 'align', 'block', 'text', 'decor', 'hover', 'bodi', 'famili', 'arial', 'san', 'serif', 'm', 'tpb', 'ttb', 'white', 'space', 'nowrap', 'rsb', 'btb', 'bt', 'ln', 'ccc', 'hd', 'eee', 's', 'f', 'fl', 'w', 'green', 'img', 'l', 'g', 'tr', 'asb', 'as', 'window', 'function', 'd', 'c', 'var', 'on', 'if', 'addeventlisten', 'fals', 'els', 'attachev', 'appli', 'thi', 'argument', 'return', 'undefin', 'o', 'firstchild', 'tagnam', 'px', 'tg', 'navextra', 'document', 'getelementbyid', 'getelementsbytagnam', 'span', 'event', 'cancelbubbl', 'createel', 'arrai', 'everi', 'createpopup', 'ifram', 'framebord', 'scroll', 'no', 'src', 'javascript', 'parentnod', 'appendchild', 'id', 'for', 'insertbefor', 'classnam', 'click', 'close', 'while', 'do', 'offsetleft', 'offsetpar', 'ss', 'statu', 'TRUE', 'cs', 'ga', 'substr', 'r', 'target', 'srcelement', 'locat', 'href', 'clk', 'url', 'ct', 'cd', 'cad', 'sg', 'rwurl', 'escap', 'replac', 'rdh', 'rdp', 'length', 'host', 'hostnam', 'pathnam', 'field', 'split', 'break', 'new', 'imag', 'blogsearch', 'sa', 'ei', 'rl', 'nln', 'continu', 'sig', 'colonpo', 'indexof', 'posidarrai', 'pb', 'number', 'nan', 'onmousedown', 're', 'web', 'map', 'shop', 'gmail', 'more', 'video', 'group', 'book', 'scholar', 'financ', 'youtub', 'calendar', 'photo', 'reader', 'even', 'raquo', 'sign', 'nbsp', 'advanc', 'prefer', 'result', 'about', 'second', 'toggletoadvanc', 'noadvanc', 'togglefromadvanc', 'publish', 'last', 'hour', 'dai', 'past', 'week', 'month', 'anytim', 'write', 'choos', 'date', 'hide', 'form', 'action', 'http', 'com', 'daterang', 'name', 'onsubmit', 'formatdateinput', 'input', 'as_q', 'type', 'hidden', 'valu', 'num', 'hl', 'en', 'as_epq', 'as_eq', 'lr', 'safe', 'ie', 'iso', 'as_mind', 'as_minm', 'as_mini', 'as_maxd', 'as_maxm', 'as_maxi', 'as_drrb', 'ctz', 'start', 'autocomplet', 'off', 'maxlength', 'onblur', 'checkandclos', 'onfocu', 'open', 'end', 'option', 'btnd', 'submit', 'go', 'gettimezoneoffset', 'montharrai', 'jan', 'feb', 'mar', 'apr', 'mai', 'jun', 'jul', 'aug', 'sep', 'oct', 'nov', 'dec', 'dowarrai', 'su', 'tu', 'th', 'datedelim', 'ymdpermut', 'mdy', '_calendarpopup', 'setinitialcalendarset', 'class', 'ddcalp_dai', 'curr_dai', 'subscrib', 'alert', 'atom', 'rss', 'sort', 'by', 'relev', 'relat', 'care', 'center', 'inform', 'you', 'can', 'us']
   #moreIgnoreWords = ['flibberish']
   
 
   rows = rs
   print "finish load data..."
 
   filtered_rows = []
   for row in rows:
        if row[1] not in moreIgnoreWords:        
            filtered_rows.append(row)
   rows =  filtered_rows
 
   for row in rows:
        if row[2] not in urls:
            urls.append(row[2])
        if row[1] not in words:
            words.append(row[1])
 
   make_index_dict(rows)
   
   get_csv_output(rows,words,urls)
 
if __name__ =="__main__":
    start()