Upload 8 files

main.py

@@ -20,6 +20,7 @@ import csv
 import io
 import pptx
 from db import get_db, Chat, ChatMessage, User, Document, SessionLocal
+from pyqs import get_q_paper
 
 from fastapi.security import OAuth2PasswordBearer
 import requests
@@ -203,6 +204,53 @@ def extract_text_from_file(file: UploadFile):
     except Exception as e:
         raise HTTPException(status_code=400, detail=f"Error processing file: {str(e)}")
 
+
+@app.get("/searchBySubjectCode")
+async def search_by_subject_code(subject_code: str, user_data: dict = Depends(decode_token)):
+    codes = requests.get(f"https://cl.thapar.edu/search1.php?term={subject_code}",verify=False).json()
+    return codes
+
+
+@app.get("/chats/{chat_id}/importQPapers")
+async def import_q_papers(chat_id: str, subject_code: str, user_data: dict = Depends(decode_token), db: SessionLocal = Depends(get_db)):
+    user_id = user_data["id"]
+
+    chat = db.query(Chat).filter(Chat.chat_id == chat_id, Chat.user_id == user_id).first()
+    if not chat:
+        raise HTTPException(status_code=404, detail="Chat not found")
+
+    q_papers = get_q_paper(subject_code)
+    if not q_papers:
+        raise HTTPException(status_code=404, detail="No question papers found for the given subject code")
+    
+    for paper in q_papers:
+        download_link = paper["DownloadLink"]
+        response = requests.get(download_link, verify=False)
+        if response.status_code != 200:
+            raise HTTPException(status_code=500, detail=f"Failed to download the paper from {download_link}")
+
+        try:
+            pdf_reader = PyPDF2.PdfReader(io.BytesIO(response.content))
+            text = "\n".join([page.extract_text() for page in pdf_reader.pages])
+        except Exception as e:
+            raise HTTPException(status_code=500, detail=f"Failed to process PDF: {str(e)}")
+        
+        title = f"{paper['CourseName']}_{paper['Year']}_{paper['Semester']}_{paper['ExamType']}..pdf"
+        doc_id = str(uuid.uuid4())
+
+        document = Document(
+            id=doc_id,
+            chat_id=chat_id,
+            name=title,
+            content=text,
+            timestamp=datetime.now()
+        )
+        db.add(document)
+    
+    db.commit()
+    return {"message": "Question papers imported successfully"}
+
+
 @app.post("/chats/{chat_id}/upload")
 async def upload_document(chat_id: str, file: UploadFile = File(...), user_data: dict = Depends(decode_token), db: SessionLocal = Depends(get_db)):
     user_id = user_data["id"]

pyqs.py

@@ -0,0 +1,46 @@
+import requests
+from bs4 import BeautifulSoup
+
+def get_q_paper(ccode):
+    files = {
+        'ccode': (None, ccode),
+        'submit': (None, ''),
+    }
+
+    response = requests.post('https://cl.thapar.edu/view1.php', files=files,verify=False)
+    return extract_question_papers(response.text)
+
+
+
+def extract_question_papers(html_content):
+    soup = BeautifulSoup(html_content, 'html.parser')
+    table = soup.find('table', {'border': '1'})  # Find the table with question papers
+    rows = table.find_all('tr')[2:]  # Skip the header rows
+    
+    question_papers = []
+    for row in rows:
+        columns = row.find_all('td')
+        if len(columns) == 6:  # Ensure it's a valid row with 6 columns
+            course_code = columns[0].text.strip()
+            course_name = columns[1].text.strip()
+            year = columns[2].text.strip()
+            semester = columns[3].text.strip()
+            exam_type = columns[4].text.strip()
+            download_link = columns[5].find('a')['href'].strip()
+            
+            question_papers.append({
+                'CourseCode': course_code,
+                'CourseName': course_name,
+                'Year': year,
+                'Semester': semester,
+                'ExamType': exam_type,
+                'DownloadLink': "https://cl.thapar.edu/" +  download_link,
+            })
+    
+    return question_papers
+
+
+# Example usage
+if __name__ == "__main__":
+    result = get_q_paper("UCS414")
+    print(result)

requirements.txt

@@ -18,3 +18,4 @@ python-dotenv
 sqlalchemy-utils
 gunicorn
 python-pptx
+bs4