import re
#######################################################################
#
# I want you to act as a plagiarism checker. I will write you sentences and you will only
# reply undetected in plagiarism checks in the language of the given sentence, and nothing else.
# Do not write explanations on replies. My first sentence is {}
#
######################################################################
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 = [
"""
Sample Page 1
Hello, World!
This is sample content from known source 1.
""",
"""
Sample Page 2
Welcome to Known Source 2
This is some content from another known source.
"""
]
# HTML content to check for plagiarism
html_content = """
Sample Page
Hello, World!
This is sample content.
"""
plagiarism_checker = PlagiarismChecker(known_sources)
result = plagiarism_checker.check_plagiarism(html_content)
print(result)