cd /tmp/workspace && python3 << 'EOF' import pdfplumber import re from collections import defaultdict pdf_path = "/tmp/workspace/attachments/c48813da-810e-487d-9f95-1a6a9116258f/UGNEET_ALLOT_2025_R2_prov_2ND_PROV_DEN_10092025kannada.pdf" with pdfplumber.open(pdf_path) as pdf: print(f"Total pages: {len(pdf.pages)}") # Print first 2 pages to understand structure for i in range(min(3, len(pdf.pages))): print(f"\n=== PAGE {i+1} ===") text = pdf.pages[i].extract_text() if text: print(text[:3000]) EOF

python3 << 'EOF' import pdfplumber import re from collections import defaultdict pdf_path = "/tmp/workspace/attachments/c48813da-810e-487d-9f95-1a6a9116258f/UGNEET_ALLOT_2025_R2_prov_2ND_PROV_DEN_10092025kannada.pdf" # Data structure: {college_name: {course_type: max_rank}} college_data = defaultdict(lambda: {"BDS-GOVT.": 0, "BDS-PRIV.": 0}) with pdfplumber.open(pdf_path) as pdf: all_text = "" for page in pdf.pages: text = page.extract_text() if text: all_text += text + "\n" # Parse lines lines = all_text.split('\n') # We need to identify rows: SL.NO | RANK | COURSE_CODE | COLLEGE_NAME | COURSE_NAME | FEES | STATUS # Pattern: line starts with a number (SL), followed by rank, code, college, course # Let's try a regex approach to capture each entry # Typical line format (may span multiple lines due to long college names): # <sl_no> <rank> <code> <college_name> BDS-GOVT./BDS-PRIV. <category> <fees> <status> # Rebuild multi-line entries # Strategy: find blocks starting with a digit (sl no), ending before next sl no import re # Extract all entries using regex # The pattern: number, space, number (rank), space, code (D\w+), then college name, then BDS-GOVT. or BDS-PRIV. pattern = re.compile( r'(\d+)\s+(\d+)\s+(D\d+D[GP])\s+(.*?)\s+(BDS-(?:GOVT|PRIV)\.)\s+(\w+)\s+(\d+)\s+(\w+)', re.DOTALL ) # Actually let's parse line by line more carefully # Each entry has: SL, Rank, CourseCode, CollegeName (multiline), CourseName, Category, Fees, Status # Better approach: find all rank+course combinations # Look for patterns like: number TAB/spaces number TAB/spaces D-code entries = [] # Join all text and use a comprehensive regex full_text = all_text # Pattern to match each row # SL.NO, Rank, CourseCode are on one line usually # Then college name (possibly multi-line) # Then BDS-GOVT. or BDS-PRIV. on a line # Let's find all occurrences of BDS-GOVT. and BDS-PRIV. with context bds_pattern = re.compile(r'(\d+)\s+(D\d+D[GP])\s+(.*?)(BDS-(?:GOVT|PRIV)\.)', re.DOTALL) # Better: extract line by line and find the pattern # Each page has consistent format - let's extract tables # Re-approach: for each page extract tables all_rows = [] with pdfplumber.open(pdf_path) as pdf: for page_num, page in enumerate(pdf.pages): # Try table extraction tables = page.extract_tables() if tables: for table in tables: for row in table: if row: all_rows.append(row) else: # fallback to text text = page.extract_text() if text: pass print(f"Total rows from tables: {len(all_rows)}") if all_rows: print("First 5 rows:") for r in all_rows[:5]: print(r) EOF

python3 << 'EOF' import pdfplumber from collections import defaultdict pdf_path = "/tmp/workspace/attachments/c48813da-810e-487d-9f95-1a6a9116258f/UGNEET_ALLOT_2025_R2_prov_2ND_PROV_DEN_10092025kannada.pdf" # {college_name: {course_type: max_rank}} college_data = defaultdict(lambda: {"BDS-GOVT.": None, "BDS-PRIV.": None}) all_rows = [] with pdfplumber.open(pdf_path) as pdf: for page in pdf.pages: tables = page.extract_tables() if tables: for table in tables: for row in table: if row and len(row) >= 7: all_rows.append(row) print(f"Total rows: {len(all_rows)}") # Skip header rows data_rows = [] for row in all_rows: # Skip header rows if row[0] and row[0].strip().upper() in ('SL.NO', 'SL NO', 'SL', ''): continue if row[0] and 'SL' in str(row[0]).upper(): continue try: sl = int(str(row[0]).strip()) rank = int(str(row[1]).strip()) college = str(row[3]).replace('\n', ' ').strip() course = str(row[4]).strip() data_rows.append((sl, rank, college, course)) except (ValueError, TypeError): continue print(f"Data rows parsed: {len(data_rows)}") # For each college, find the MAXIMUM rank (last rank = highest rank number = hardest to get) for sl, rank, college, course in data_rows: if course in ("BDS-GOVT.", "BDS-PRIV."): current = college_data[college][course] if current is None or rank > current: college_data[college][course] = rank # Print results print("\n" + "="*120) print(f"{'College':<65} {'BDS-GOVT Last Rank':>20} {'BDS-PRIV Last Rank':>20}") print("="*120) colleges = sorted(college_data.keys()) for col in colleges: govt = college_data[col]["BDS-GOVT."] priv = college_data[col]["BDS-PRIV."] govt_str = str(govt) if govt else "-" priv_str = str(priv) if priv else "-" print(f"{col:<65} {govt_str:>20} {priv_str:>20}") EOF

python3 << 'EOF' import pdfplumber from collections import defaultdict import csv, os pdf_path = "/tmp/workspace/attachments/c48813da-810e-487d-9f95-1a6a9116258f/UGNEET_ALLOT_2025_R2_prov_2ND_PROV_DEN_10092025kannada.pdf" college_data = defaultdict(lambda: {"BDS-GOVT.": None, "BDS-PRIV.": None}) all_rows = [] with pdfplumber.open(pdf_path) as pdf: for page in pdf.pages: tables = page.extract_tables() if tables: for table in tables: for row in table: if row and len(row) >= 7: all_rows.append(row) for row in all_rows: if row[0] and ('SL' in str(row[0]).upper() or 'sl' in str(row[0]).lower()): continue try: sl = int(str(row[0]).strip()) rank = int(str(row[1]).strip()) college = str(row[3]).replace('\n', ' ').strip() course = str(row[4]).strip() if course in ("BDS-GOVT.", "BDS-PRIV."): current = college_data[college][course] if current is None or rank > current: college_data[college][course] = rank except (ValueError, TypeError): continue os.makedirs("/tmp/workspace/output", exist_ok=True) out_path = "/tmp/workspace/output/BDS_LastRank_ByCollege.csv" with open(out_path, "w", newline="") as f: writer = csv.writer(f) writer.writerow(["College Name", "BDS-GOVT Last Rank", "BDS-PRIV Last Rank"]) for col in sorted(college_data.keys()): govt = college_data[col]["BDS-GOVT."] or "-" priv = college_data[col]["BDS-PRIV."] or "-" writer.writerow([col, govt, priv]) print(f"CSV saved to {out_path}") EOF