Spaces:
Sleeping
Sleeping
Update Deliverable2.py
Browse files- Deliverable2.py +17 -34
Deliverable2.py
CHANGED
@@ -2,11 +2,14 @@ import requests
|
|
2 |
from bs4 import BeautifulSoup
|
3 |
from sentence_transformers import SentenceTransformer, util
|
4 |
from transformers import pipeline
|
|
|
|
|
5 |
from deliverable2 import URLValidator
|
|
|
|
|
6 |
validator = URLValidator()
|
7 |
print("Validator loaded successfully!")
|
8 |
|
9 |
-
|
10 |
class URLValidator:
|
11 |
def __init__(self):
|
12 |
self.similarity_model = SentenceTransformer('sentence-transformers/all-mpnet-base-v2')
|
@@ -33,23 +36,21 @@ class URLValidator:
|
|
33 |
sentiment_result = self.sentiment_analyzer(content[:512])[0]
|
34 |
return 100 if sentiment_result["label"] == "POSITIVE" else 50 if sentiment_result["label"] == "NEUTRAL" else 30
|
35 |
|
36 |
-
def validate_url(user_query, url_to_check):
|
37 |
-
|
38 |
-
|
39 |
-
|
40 |
-
|
41 |
-
if "Validation Error" in result:
|
42 |
-
return {"Error": result["Validation Error"]}
|
43 |
|
44 |
-
|
45 |
-
|
46 |
-
"Bias Score": f"{result['raw_score']['Bias Score']} / 100",
|
47 |
-
"Final Validity Score": f"{result['raw_score']['Final Validity Score']} / 100"
|
48 |
-
}
|
49 |
-
except Exception as e:
|
50 |
-
return {"Error": str(e)}
|
51 |
|
52 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
53 |
|
54 |
queries_urls = [
|
55 |
("Climate change effects", "https://www.nationalgeographic.com/environment/article/climate-change-overview"),
|
@@ -64,29 +65,12 @@ queries_urls = [
|
|
64 |
("Mental health awareness", "https://www.who.int/news-room/fact-sheets/detail/mental-health-strengthening-our-response")
|
65 |
]
|
66 |
|
67 |
-
validator = URLValidator()
|
68 |
results = [validator.rate_url_validity(query, url) for query, url in queries_urls]
|
69 |
|
70 |
for result in results:
|
71 |
print(result)
|
72 |
|
73 |
# Generate formatted output for the 10 predefined queries and URLs
|
74 |
-
queries_urls = [
|
75 |
-
("Climate change effects", "https://www.nationalgeographic.com/environment/article/climate-change-overview"),
|
76 |
-
("COVID-19 vaccine effectiveness", "https://www.cdc.gov/coronavirus/2019-ncov/vaccines/effectiveness.html"),
|
77 |
-
("Latest AI advancements", "https://www.technologyreview.com/topic/artificial-intelligence"),
|
78 |
-
("Stock market trends", "https://www.bloomberg.com/markets"),
|
79 |
-
("Healthy diet tips", "https://www.healthline.com/nutrition/healthy-eating-tips"),
|
80 |
-
("Space exploration missions", "https://www.nasa.gov/missions"),
|
81 |
-
("Electric vehicle benefits", "https://www.tesla.com/benefits"),
|
82 |
-
("History of the internet", "https://www.history.com/topics/inventions/history-of-the-internet"),
|
83 |
-
("Python programming tutorials", "https://realpython.com"),
|
84 |
-
("Mental health awareness", "https://www.who.int/news-room/fact-sheets/detail/mental-health-strengthening-our-response")
|
85 |
-
]
|
86 |
-
|
87 |
-
# Placeholder function ratings for demonstration
|
88 |
-
import random
|
89 |
-
|
90 |
formatted_output = []
|
91 |
|
92 |
for query, url in queries_urls:
|
@@ -100,4 +84,3 @@ for query, url in queries_urls:
|
|
100 |
|
101 |
# Display the formatted output
|
102 |
formatted_output
|
103 |
-
|
|
|
2 |
from bs4 import BeautifulSoup
|
3 |
from sentence_transformers import SentenceTransformer, util
|
4 |
from transformers import pipeline
|
5 |
+
import random
|
6 |
+
|
7 |
from deliverable2 import URLValidator
|
8 |
+
|
9 |
+
# Instantiate the validator
|
10 |
validator = URLValidator()
|
11 |
print("Validator loaded successfully!")
|
12 |
|
|
|
13 |
class URLValidator:
|
14 |
def __init__(self):
|
15 |
self.similarity_model = SentenceTransformer('sentence-transformers/all-mpnet-base-v2')
|
|
|
36 |
sentiment_result = self.sentiment_analyzer(content[:512])[0]
|
37 |
return 100 if sentiment_result["label"] == "POSITIVE" else 50 if sentiment_result["label"] == "NEUTRAL" else 30
|
38 |
|
39 |
+
def validate_url(self, user_query, url_to_check):
|
40 |
+
try:
|
41 |
+
result = self.rate_url_validity(user_query, url_to_check)
|
42 |
+
print("Validation Result:", result) # Debugging line
|
|
|
|
|
|
|
43 |
|
44 |
+
if "Validation Error" in result:
|
45 |
+
return {"Error": result["Validation Error"]}
|
|
|
|
|
|
|
|
|
|
|
46 |
|
47 |
+
return {
|
48 |
+
"Content Relevance Score": f"{result['raw_score']['Content Relevance']} / 100",
|
49 |
+
"Bias Score": f"{result['raw_score']['Bias Score']} / 100",
|
50 |
+
"Final Validity Score": f"{result['raw_score']['Final Validity Score']} / 100"
|
51 |
+
}
|
52 |
+
except Exception as e:
|
53 |
+
return {"Error": str(e)}
|
54 |
|
55 |
queries_urls = [
|
56 |
("Climate change effects", "https://www.nationalgeographic.com/environment/article/climate-change-overview"),
|
|
|
65 |
("Mental health awareness", "https://www.who.int/news-room/fact-sheets/detail/mental-health-strengthening-our-response")
|
66 |
]
|
67 |
|
|
|
68 |
results = [validator.rate_url_validity(query, url) for query, url in queries_urls]
|
69 |
|
70 |
for result in results:
|
71 |
print(result)
|
72 |
|
73 |
# Generate formatted output for the 10 predefined queries and URLs
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
74 |
formatted_output = []
|
75 |
|
76 |
for query, url in queries_urls:
|
|
|
84 |
|
85 |
# Display the formatted output
|
86 |
formatted_output
|
|