Initial version of blog Gen

2023-10-07 10:51:22 +05:30
commit 12010c0478
27 changed files with 1295 additions and 0 deletions
--- a/lib/plagiarism_checker/main.py
+++ b/lib/plagiarism_checker/main.py
@@ -0,0 +1,20 @@
+## main.py
+from plagiarism_checker import PlagiarismChecker
+
+
+def main():
+    # Create an instance of the PlagiarismChecker class
+    checker = PlagiarismChecker()
+
+    # Get the input string from the user
+    input_string = input("Enter the input string: ")
+
+    # Check plagiarism in the input string
+    percentage = checker.check_plagiarism(input_string)
+
+    # Print the percentage of original content
+    print(f"The percentage of original content is: {percentage}%")
+
+
+if __name__ == "__main__":
+    main()
--- a/lib/plagiarism_checker/plagiarism_checker_from_known_sources.py
+++ b/lib/plagiarism_checker/plagiarism_checker_from_known_sources.py
@@ -0,0 +1,71 @@
+import re
+
+class PlagiarismChecker:
+    def __init__(self, known_sources):
+        self.known_sources = known_sources
+
+    def check_plagiarism(self, html_content):
+        try:
+            # Preprocess the HTML content by removing HTML tags and extra spaces
+            text = re.sub(r'<[^>]+>', ' ', html_content)
+            text = re.sub(r'\s+', ' ', text).strip().lower()
+
+            # Check for exact matches with known sources
+            for source in self.known_sources:
+                source_text = re.sub(r'<[^>]+>', ' ', source)
+                source_text = re.sub(r'\s+', ' ', source_text).strip().lower()
+                if text == source_text:
+                    return f"Plagiarism detected: Matches known source - {source}"
+
+            # If no exact matches are found
+            return "No plagiarism detected. Content is original."
+
+        except Exception as e:
+            return str(e)
+
+# Example usage:
+if __name__ == "__main__":
+    # List of known sources
+    known_sources = [
+        """
+        <html>
+        <head>
+            <title>Sample Page 1</title>
+        </head>
+        <body>
+            <h1>Hello, World!</h1>
+            <p>This is sample content from known source 1.</p>
+        </body>
+        </html>
+        """,
+        """
+        <html>
+        <head>
+            <title>Sample Page 2</title>
+        </head>
+        <body>
+            <h1>Welcome to Known Source 2</h1>
+            <p>This is some content from another known source.</p>
+        </body>
+        </html>
+        """
+    ]
+
+    # HTML content to check for plagiarism
+    html_content = """
+    <html>
+    <head>
+        <title>Sample Page</title>
+    </head>
+    <body>
+        <h1>Hello, World!</h1>
+        <p>This is sample content.</p>
+    </body>
+    </html>
+    """
+
+    plagiarism_checker = PlagiarismChecker(known_sources)
+    result = plagiarism_checker.check_plagiarism(html_content)
+
+    print(result)
+