def main(query_file, document_list, stopwordfile):
# Load the document list - one file per line
with open(document_list, 'r') as f:
print(f"Loading document list from {document_list}")
doclist = f.read().split()
# Construct the vocabulary
vocabulary, document_tokens = build_vocabulary(doclist, stopwordfile)
# Build the inverse index
inverse_index = build_inverse_index(document_tokens, vocabulary)
# Computer the inverse doc frequencies
idf = calc_idf(inverse_index, len(doclist))
# Load the query
with open(query_file, 'r') as f:
query = f.read()
# stop and stem the query
query_text = stop_remover(query, stopwordfile)
query_tokens = stemmer(query_text)
# compute the word frequencies in the query
query_wf = dict()
for term in set(query_tokens):
query_wf[term] = query_tokens.count(term)
print(f"\nQuery word frequencies")
print(query_wf)
# Now we compute the similarity with each document
print("\nComputing similarity of query with documents")
for doc_number in range(len(doclist)):
similarity = sim(query_wf, doc_number, inverse_index, idf)
print(f"sim(q,d{doc_number}) = {similarity:.2f}")
return None
def searchPage( url, searchTags):
try:
tokens = stemmer.stemmer(tokenizer.contentTokenizer(url))
print "Calculating priority for : " + url
token_set = set(tokens)
tf = {}
queryTf = {}
for word in token_set:
tf[word] = float(tokens.count(word)) / len(tokens)
#searchTags = stemmer.stemmer(tokenizer.stringTokenizer(string))
for tag in searchTags:
if tf.has_key(tag):
queryTf[tag] = tf.get(tag)
else:
queryTf[tag] = 0
priority = calcPriority(queryTf)
except:
print "Priority calculation error"
#print "Priority for " + url + " - " + priority
return priority
#print queryCount
#print searchPage(url, "Big Bang theory cast sheldon")
#print searchPage(url, "Big armadillo hello lol this")
#print searchPage(url, "hello")
def search(path_to_index, queries):
a = os.path.join(path_to_index, 'inverted_index')
from stemmer import stemmer
from stopwords import stopwords
from search_handler import search
stemmer = stemmer()
stopwords = stopwords()
search = search(a, stemmer, stopwords)
outputs = []
for query in queries:
the_result = search.search(query)
if the_result is None:
outputs.append(['.'] * 10)
else:
outputs.append(the_result)
return outputs
def searchPage(url, searchTags):
try:
tokens = stemmer.stemmer(tokenizer.contentTokenizer(url))
print "Calculating priority for : " + url
token_set = set(tokens)
tf = {}
queryTf = {}
for word in token_set:
tf[word] = float(tokens.count(word)) / len(tokens)
#searchTags = stemmer.stemmer(tokenizer.stringTokenizer(string))
for tag in searchTags:
if tf.has_key(tag):
queryTf[tag] = tf.get(tag)
else:
queryTf[tag] = 0
priority = calcPriority(queryTf)
except:
print "Priority calculation error"
#print "Priority for " + url + " - " + priority
return priority
def build_vocabulary(doclist, stopwordfile):
# Create an empty set for the vocabulary
print("Building the vocabulary")
vocabulary = set()
document_tokens = []
for doc in doclist:
print(f"Loading document {doc}")
with open(doc, 'r') as f:
text = f.read()
# Remove stop words
text = stop_remover(text, stopwordfile)
# stem
tokens = stemmer(text)
document_tokens.append(tokens)
unique_tokens = set(tokens)
print(f"{len(unique_tokens)} unique tokens")
# Add the tokens to the vocab if they are not already there.
vocabulary = vocabulary.union(unique_tokens)
print(f"There are now {len(vocabulary)} words in the vocabulary\n")
return vocabulary, document_tokens
def loginFormHandling():
from stemmer import stemmer
from stopwords import stopwords
from search_handler import search
stemmer = stemmer()
stopwords = stopwords()
search = search("path", stemmer, stopwords)
data = request.form
query = request.form['query']
flag = 0
if data['title'] != '':
flag = 1
query += " title:"
query += data['title']
if data['infobox'] != '':
flag = 1
query += " infobox:"
query += data['infobox']
if data['references'] != '':
flag = 1
query += " ref:"
query += data['references']
if data['category'] != '':
flag = 1
query += " category:"
query += data['category']
if data['links'] != '':
flag = 1
query += " links:"
query += data['links']
if data['body'] != '':
flag = 1
query += " body:"
query += data['body']
# if (flag == 1):
# r = len(request.form ['query'])
# query = query[r:]
print(query)
the_result = search.search(query)
return render_template('results.html', query=query, results=the_result)
return count
# Extensions to be avoided
excludedExtentions = [
'.png', '.gif', '.jpg', '.jpeg', '.pdf', '.mp3', '.wmv', '.svg', '.ogg',
'.jsp', '.ogv', '.py', '.tar.gz', '.css', '.ico', '.gz', '.ppt', '.zip',
'.rar', '.ps', '.ppsx'
]
excludedExtensions = set(
excludedExtentions) # Making set for easy membership test
errorcount = 0
query = sys.argv[1] # Initial query for focused crawler
urlcount = int(sys.argv[2])
searchTags = stemmer.stemmer(tokenizer.stringTokenizer(
query)) # Stemming and tokenizing search query to avoid duplicate effort
print "Search tokens : "
print searchTags
top10urls = gQuery.googleSearch(query)
urls = MyPriorityQueue() # Queue for storing URLs yet to be visisted
results = {} # Dictionary structure for storing results URLs
visited = set()
for i in range(len(top10urls)): # Adding top 10 results to Queue
urls.put(top10urls[i], 1)
br = mechanize.Browser()
f = open('results.txt', 'w+')
import pickle, os, sys
import time
start = time.time()
from stemmer import stemmer
from stopwords import stopwords
from parser import parser
stemmer = stemmer()
stopwords = stopwords()
path_to_dump = sys.argv[1]
path_to_index_folder = sys.argv[2]
print (path_to_index_folder)
wikipedia_parser = parser (path_to_index_folder, stemmer, stopwords)
wikipedia_parser.parse (path_to_dump)
wikipedia_parser.make_alphabet_pairs ()
# wikipedia_parser.merge_files ()
# wikipedia_parser.divide_files ()
end = time.time()
print ("It took", end-start, "seconds")
def urlContains(url, searchTags):
count = 0
for tag in searchTags:
if tag in url:
count +=1
return count
# Extensions to be avoided
excludedExtentions = ['.png', '.gif', '.jpg', '.jpeg', '.pdf', '.mp3', '.wmv', '.svg', '.ogg','.jsp', '.ogv', '.py', '.tar.gz', '.css', '.ico', '.gz', '.ppt', '.zip', '.rar', '.ps', '.ppsx']
excludedExtensions = set(excludedExtentions) # Making set for easy membership test
errorcount = 0
query = sys.argv[1] # Initial query for focused crawler
urlcount = int(sys.argv[2])
searchTags = stemmer.stemmer(tokenizer.stringTokenizer(query)) # Stemming and tokenizing search query to avoid duplicate effort
print "Search tokens : "
print searchTags
top10urls = gQuery.googleSearch(query)
urls = MyPriorityQueue() # Queue for storing URLs yet to be visisted
results = {} # Dictionary structure for storing results URLs
visited = set()
for i in range(len(top10urls)): # Adding top 10 results to Queue
urls.put(top10urls[i],1)
br = mechanize.Browser()
f = open('results.txt','w+')
