Created
June 2, 2014 14:34
-
-
Save alangampel/7a46df8cb92dfe821b8e to your computer and use it in GitHub Desktop.
Third program: tokenizes text from a URL and then searches Google in groups of X number of words.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import urllib | |
import urllib.request | |
import urllib.parse | |
import json | |
print('\n') | |
print('----------------------------------') | |
print('Searching for internet matches') | |
print('----------------------------------') | |
# open file with greek content | |
print('\n') | |
url_str = input('File URL? ') | |
response = urllib.request.urlopen(url_str).read() | |
response_str = response.decode("utf-8") | |
# buffer all text in the file | |
text_buf = '' | |
for line in response_str: | |
text_buf += line | |
# tokenize | |
tokens = text_buf.split(); | |
print('\n') | |
print('There are ' + str(len(tokens)) + ' tokens in the file') | |
print('All tokens from file:\n') | |
print(tokens) | |
print('\n') | |
# create string of x tokens | |
token_count_str = input('How many words in search phrase? ') | |
token_count = int(token_count_str) | |
print('\n') | |
# create index into text tokens | |
token_idx = 0 | |
num_tokens = len(tokens) | |
loop_termination_value = num_tokens - token_count | |
while token_idx < loop_termination_value: | |
#delineate new query | |
print ('-----------------------------------------------------------') | |
print("Search number " + str (token_idx + 1)) | |
# concatenate the search string contents, i.e. the token_count words fromt the file | |
i = 0 | |
content_str = '' | |
while i < token_count: | |
content_str += tokens[i + token_idx] + ' ' | |
i += 1 | |
print("Content string is:") | |
print(content_str) | |
print('') | |
# build the URL | |
url = "http://ajax.googleapis.com/ajax/services/search/web?v=1.0&" | |
query = url+content_str | |
query = urllib.parse.urlencode({'q':content_str}) | |
print("URL query is: ") | |
print('') | |
print(url + query) | |
print('') | |
# get the response from google | |
response = urllib.request.urlopen(url+query).read() | |
json_data = json.loads(response.decode("utf-8")) | |
print ("JSON data: ") | |
print (json_data) | |
data_present_test = json_data['responseData'] | |
if str(data_present_test) == 'None': | |
print("No data for this query") | |
token_idx += 1 | |
continue | |
results = json_data['responseData']['results'] | |
# format the response and print it | |
indx = 0 | |
for result in results: | |
title = result['title'] | |
url = result['url'] | |
print("JSON result " , indx + 1, ':') | |
print ( title + '; ' + url ) | |
print('') | |
indx += 1 | |
print('\n') | |
# increment token_idx so as to move to the next chunk of text in the file | |
token_idx += 1 | |
# end of while token_idx < loop_termination_value |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment