latest update

scratch/inspect_table_cells.py

@@ -0,0 +1,18 @@
+import re
+
+with open('real_timetable.html', 'r', encoding='utf-8') as f:
+    content = f.read()
+
+# Find rows in the timetable table
+rows = re.findall(r'<tr[^>]*>(.*?)</tr>', content, re.DOTALL)
+print(f"Total tr rows: {len(rows)}")
+
+for idx, r in enumerate(rows):
+    if 'tuesday' in r.lower() or 'tue' in r.lower():
+        print(f"\n--- ROW {idx} (TUESDAY) ---")
+        tds = re.findall(r'<td[^>]*>(.*?)</td>', r, re.DOTALL)
+        print(f"Total td cells in Tuesday row: {len(tds)}")
+        for col_i, td in enumerate(tds):
+            clean_td = ' '.join(re.sub(r'<[^>]+>', ' ', td).split())
+            forms_in_td = re.findall(r'<form[^>]*>(.*?)</form>', td, re.DOTALL)
+            print(f"  Col {col_i}: forms_count={len(forms_in_td)} | text={clean_td[:80]}")

scratch/inspect_tt_periods.py

@@ -0,0 +1,24 @@
+import re
+
+with open('real_timetable.html', 'r', encoding='utf-8') as f:
+    content = f.read()
+
+forms = re.findall(r'<form[^>]*class="[^"]*period_form[^"]*"[^>]*>(.*?)</form>', content, re.DOTALL)
+print(f"Total forms found: {len(forms)}")
+
+by_day = {}
+for form in forms:
+    day_m = re.search(r'name="day"\s+value="([^"]+)"', form)
+    per_m = re.search(r'name="period"\s+value="([^"]+)"', form)
+    day = day_m.group(1).lower() if day_m else 'unknown'
+    per = per_m.group(1) if per_m else '0'
+    by_day.setdefault(day, []).append((per, form))
+
+for day in sorted(by_day.keys()):
+    print(f"\n=== DAY: {day.upper()} (Count: {len(by_day[day])}) ===")
+    for per, form in by_day[day]:
+        primaries = re.findall(r'class="[^"]*text-primary[^"]*"[^>]*>(.*?)</span>', form, re.DOTALL)
+        clean_p = [re.sub(r'<[^>]+>', '', p).strip() for p in primaries]
+        full_txt = re.sub(r'<[^>]+>', ' ', form).strip()
+        full_txt = ' '.join(full_txt.split())
+        print(f"  Period {per}: primaries={clean_p} | full_txt={full_txt[:100]}")

scratch/inspect_tue_context.py

@@ -0,0 +1,13 @@
+import re
+
+with open('real_timetable.html', 'r', encoding='utf-8') as f:
+    content = f.read()
+
+print("File length:", len(content))
+# Search for Tuesday in content
+tue_matches = [m.start() for m in re.finditer(r'tuesday', content, re.IGNORECASE)]
+print("Tuesday matches at indices:", tue_matches)
+
+for pos in tue_matches[:3]:
+    print("\n--- Context around Tuesday ---")
+    print(content[max(0, pos-200):min(len(content), pos+400)])

scratch/test_lab_assignment_marks.py

@@ -0,0 +1,53 @@
+import urllib.request
+import urllib.parse
+import http.cookiejar
+import re
+
+cj = http.cookiejar.CookieJar()
+opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cj))
+
+login_url = "https://ims.rajalakshmi.edu.in/ims/login"
+
+headers = {
+    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
+    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+}
+
+# Step 1: GET login page
+req = urllib.request.Request(login_url, headers=headers)
+with opener.open(req) as resp:
+    html = resp.read().decode('utf-8')
+
+csrf_m = re.search(r'name="_token"\s+value="([^"]+)"', html)
+csrf_token = csrf_m.group(1) if csrf_m else ''
+print(f"CSRF Token: {csrf_token}")
+
+# Step 2: POST login
+post_data = urllib.parse.urlencode({
+    '_token': csrf_token,
+    'username': '2117240070293',
+    'password': '7010406809'
+}).encode('utf-8')
+
+req_post = urllib.request.Request(login_url, data=post_data, headers=headers)
+with opener.open(req_post) as resp_post:
+    dash_html = resp_post.read().decode('utf-8')
+
+print(f"Login success! Dash HTML length: {len(dash_html)}")
+
+# Step 3: Find all <a> hrefs containing lab or assignment or mark or report
+all_links = re.findall(r'<a[^>]+href="([^"]+)"[^>]*>(.*?)</a>', dash_html, re.DOTALL)
+print(f"Total links found: {len(all_links)}")
+
+for href, label in all_links:
+    clean_label = re.sub(r'<[^>]+>', '', label).strip()
+    clean_label_lower = clean_label.lower()
+    if 'lab' in clean_label_lower or 'assignment' in clean_label_lower or 'mark' in clean_label_lower or 'grade' in clean_label_lower or 'cat' in clean_label_lower:
+        print(f"Link: '{clean_label}' -> Href: '{href}'")
+
+# Also search for all hrefs in the full HTML to be sure
+all_hrefs = re.findall(r'href="([^"]+)"', dash_html)
+print("\n--- ALL UNIQUE HREFS IN DASHBOARD ---")
+for h in set(all_hrefs):
+    if 'admin' in h or 'student' in h or 'mark' in h or 'report' in h:
+        print(" ", h)