├── .gitattributes
├── README.md
└── MainModule.py


/.gitattributes:
--------------------------------------------------------------------------------
1 | # Auto detect text files and perform LF normalization
2 | * text=auto
3 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # Falsify - Fact Engine
 2 | 
 3 | Have you ever received a shocker message and didn't know if it was true?
 4 | Have you ever stood perplexed about a viral news that just came up?
 5 | Did you ever want to know, if the facts were true?
 6 | 
 7 | Presenting you, the one stop solution to all of that, Falsify.
 8 | 
 9 | Falsify, is a fact engine that looks up a given fact all over the internet, reads stories, news articles and recognizes if the given fact is a statement of truth or not, later it analyses the statement's genuinity and tells you if it's a Truth/Lie.
10 | 


--------------------------------------------------------------------------------
/MainModule.py:
--------------------------------------------------------------------------------
 1 | import numpy as np
 2 | from urllib.parse import urlencode, urlparse, parse_qs
 3 | from lxml.html import fromstring
 4 | from requests import get
 5 | from bs4 import BeautifulSoup
 6 | import nltk
 7 | import requests
 8 | import re
 9 | import heapq
10 | 
11 | def FactEngine(input_msg):
12 |     target_text=str(input_msg)
13 |     #Scrapes and Writes into File
14 |     fo = open("news.txt", "w",encoding = 'UTF-8')
15 |     fo.seek(0, 0)
16 |     for n in range(0,10,10):
17 |         num=int((n/10)+1)
18 |         fo.write("From Page "+str(num)+"\n\n")
19 |         target_url="https://www.google.com/search?q="+str(target_text)+"&tbm=nws&start="+str(n)
20 |         raw = get(target_url).text
21 |         page = fromstring(raw)
22 |         for result in page.cssselect(".r a"):
23 |             url = result.get("href")
24 |             if url.startswith("/url?"):
25 |                 url = parse_qs(urlparse(url).query)['q']
26 |                 fo.write("\n\n"+url[0])
27 |                 response = requests.get(url[0])
28 |                 soup = BeautifulSoup(response.content, "html.parser")
29 |                 links = soup.findAll("p")
30 |                 fo.write("\n\n"+re.sub('<[^>]+>', '',str(links))) 
31 |     
32 |     #NE Tagging Target Text, Important Words Shortlisted          
33 |     namedEnt = nltk.pos_tag(nltk.word_tokenize(target_text))
34 |     named_entities = []
35 |     search_query = []
36 |     for x in namedEnt:
37 |         if x[1] == 'NNP':
38 |             named_entities.append(x[0])
39 |     i=0
40 |     
41 |     while(True):
42 |         try:
43 |                 search_query.append(str(named_entities[i][0][0]))
44 |         except Exception as e:
45 |             break
46 |         i+=1
47 |     
48 |     #Reading back from File
49 |     k=g=0
50 |     count=[0]*len(search_query)
51 |     while(k<len(search_query)):
52 |         search_text=search_query[k]
53 |         with open('news.txt', 'r',encoding = 'UTF-8') as myfile:
54 |             data=myfile.read().replace('\n', '')
55 |             for i in data:
56 |                 if(i==search_text):
57 |                     count[k]+=1
58 |         k+=1
59 |     
60 |     min2=heapq.nsmallest(2,count)[-1]
61 |     rel=(min(count)/min2)*100
62 |     
63 |     if(rel>60):
64 |         print("Trust Me. It's True.")
65 |     else:
66 |         print("Oh Snap. It's a Lie!")
67 |     return 0


--------------------------------------------------------------------------------