init

app.py

@@ -0,0 +1,470 @@
+import streamlit as st
+import msal
+import requests
+import pandas as pd
+import re
+from bs4 import BeautifulSoup
+from io import BytesIO, StringIO
+from datetime import datetime, timedelta
+
+# ── Page config ────────────────────────────────────────────────────────────────
+st.set_page_config(
+    page_title="RJ Email Processor",
+    page_icon="📬",
+    layout="wide",
+)
+
+# ── Styling ────────────────────────────────────────────────────────────────────
+st.markdown("""
+<style>
+    @import url('https://fonts.googleapis.com/css2?family=DM+Serif+Display&family=DM+Sans:wght@400;500;600&display=swap');
+
+    html, body, [class*="css"] {
+        font-family: 'DM Sans', sans-serif;
+    }
+    h1, h2, h3 {
+        font-family: 'DM Serif Display', serif;
+    }
+    .main { background: #f7f5f0; }
+    .block-container { padding-top: 2rem; max-width: 960px; }
+
+    .status-card {
+        background: white;
+        border: 1px solid #e5e0d8;
+        border-radius: 12px;
+        padding: 1.5rem 2rem;
+        margin-bottom: 1.2rem;
+        box-shadow: 0 1px 4px rgba(0,0,0,0.05);
+    }
+    .step-label {
+        font-size: 0.72rem;
+        font-weight: 600;
+        letter-spacing: 0.1em;
+        text-transform: uppercase;
+        color: #9a8f82;
+        margin-bottom: 0.25rem;
+    }
+    .step-title {
+        font-size: 1.1rem;
+        font-weight: 600;
+        color: #1a1612;
+    }
+    .badge-success {
+        background: #d4edda; color: #155724;
+        padding: 2px 10px; border-radius: 20px;
+        font-size: 0.78rem; font-weight: 600;
+    }
+    .badge-pending {
+        background: #fff3cd; color: #856404;
+        padding: 2px 10px; border-radius: 20px;
+        font-size: 0.78rem; font-weight: 600;
+    }
+    .stButton > button {
+        background: #1a1612 !important;
+        color: white !important;
+        border: none !important;
+        border-radius: 8px !important;
+        font-family: 'DM Sans', sans-serif !important;
+        font-weight: 600 !important;
+        padding: 0.55rem 1.4rem !important;
+        font-size: 0.9rem !important;
+    }
+    .stButton > button:hover {
+        background: #3d3530 !important;
+        transform: translateY(-1px);
+        transition: all 0.15s ease;
+    }
+    div[data-testid="stNumberInput"] label,
+    div[data-testid="stTextInput"] label {
+        font-weight: 600;
+        font-size: 0.85rem;
+        color: #3d3530;
+    }
+    .result-header {
+        font-size: 1rem;
+        font-weight: 700;
+        color: #1a1612;
+        margin-bottom: 0.4rem;
+        padding-bottom: 0.4rem;
+        border-bottom: 2px solid #e5e0d8;
+    }
+</style>
+""", unsafe_allow_html=True)
+
+# ── Constants ──────────────────────────────────────────────────────────────────
+CLIENT_ID = "bfcbb298-4cc1-496e-9d9b-ff8c2d967a3a"
+TENANT_ID = "5dac2bf2-8842-4788-ae07-33fb103b55d6"
+AUTHORITY = f"https://login.microsoftonline.com/{TENANT_ID}"
+SCOPES = ["Mail.Read"]
+
+# ── Session state defaults ─────────────────────────────────────────────────────
+for key, default in {
+    "token": None,
+    "messages": [],
+    "rj_emails": [],
+    "cash_df": None,
+    "withdrawals_df": None,
+    "deposits_df": None,
+    "notice_df": None,
+}.items():
+    if key not in st.session_state:
+        st.session_state[key] = default
+
+# ── Helper functions ───────────────────────────────────────────────────────────
+
+def get_access_token():
+    app = msal.PublicClientApplication(CLIENT_ID, authority=AUTHORITY)
+    result = app.acquire_token_interactive(scopes=SCOPES)
+    if "access_token" not in result:
+        raise RuntimeError(result.get("error_description", str(result)))
+    return result["access_token"]
+
+
+def get_emails_from_sender(token, sender_email, top=50):
+    url = "https://graph.microsoft.com/v1.0/me/mailFolders/inbox/messages"
+    headers = {
+        "Authorization": f"Bearer {token}",
+        "Prefer": 'outlook.body-content-type="html"',
+    }
+    params = {
+        "$top": top,
+        "$filter": f"from/emailAddress/address eq '{sender_email}'",
+        "$select": "subject,from,toRecipients,ccRecipients,receivedDateTime,body,id",
+    }
+    resp = requests.get(url, headers=headers, params=params, timeout=60)
+    resp.raise_for_status()
+    return resp.json().get("value", [])
+
+
+def extract_email_info(msg):
+    def get_addresses(recipients):
+        return [
+            (r.get("emailAddress") or {}).get("address")
+            for r in (recipients or [])
+            if (r.get("emailAddress") or {}).get("address")
+        ]
+    body_html = (msg.get("body") or {}).get("content", "")
+    return {
+        "id": msg.get("id"),
+        "subject": msg.get("subject"),
+        "from": ((msg.get("from") or {}).get("emailAddress") or {}).get("address"),
+        "to": get_addresses(msg.get("toRecipients")),
+        "cc": get_addresses(msg.get("ccRecipients")),
+        "received_time": msg.get("receivedDateTime"),
+        "body_html": body_html,
+    }
+
+
+def html_to_text(html):
+    if not html:
+        return ""
+    return BeautifulSoup(html, "html.parser").get_text("\n", strip=True)
+
+
+def reply_marker_html(body_html):
+    if not body_html:
+        return ""
+    soup = BeautifulSoup(body_html, "html.parser")
+    marker = soup.find(id="divRplyFwdMsg")
+    if not marker:
+        return ""
+    return "".join(str(n) for n in marker.next_siblings).strip()
+
+
+def extract_forwarded_headers(body_html):
+    text = html_to_text(body_html)
+    def grab(label):
+        m = re.search(rf"{label}:\s*(.*)", text)
+        return m.group(1).strip() if m else ""
+    return {
+        "forwarded_from": grab("From"),
+        "forwarded_sent_time": grab("Sent"),
+        "forwarded_to": grab("To"),
+        "forwarded_cc": grab("Cc"),
+        "forwarded_subject": grab("Subject"),
+    }
+
+
+def is_rj_forward(info):
+    subject = (info.get("subject") or "").lower()
+    body_html = info.get("body_html") or ""
+    body_text = html_to_text(body_html).lower()
+    if "rj emails--overview" in subject:
+        return False
+    has_forward = 'id="divRplyFwdMsg"' in body_html or ("from:" in body_text and "sent:" in body_text)
+    if not has_forward:
+        return False
+    return any([
+        "raymond james" in subject,
+        "raymond james" in body_text,
+        "amstradingadmin@raymondjames.com" in body_text,
+        "ams managed operations" in subject,
+        "ams managed operations" in body_text,
+        "direct asset transfers" in subject,
+        "distribution & cash balance check" in subject,
+    ])
+
+
+def build_rj_emails(messages, target_filter):
+    rows = []
+    for idx, msg in enumerate(messages, 1):
+        info = extract_email_info(msg)
+        recipients = [a.lower() for a in info.get("to", []) + info.get("cc", [])]
+        if target_filter.lower() not in recipients:
+            continue
+        if not is_rj_forward(info):
+            continue
+        fwd = extract_forwarded_headers(info.get("body_html", ""))
+        rows.append({
+            "email_id": info.get("id") or f"msg_{idx}",
+            "fw_subject": info.get("subject"),
+            "fw_from": info.get("from"),
+            "fw_to": ", ".join(info.get("to", [])),
+            "fw_cc": ", ".join(info.get("cc", [])),
+            "fw_received_time": info.get("received_time"),
+            "fw_body_html": info.get("body_html", ""),
+            "original_from": fwd.get("forwarded_from", ""),
+            "original_sent_time": fwd.get("forwarded_sent_time", ""),
+            "original_to": fwd.get("forwarded_to", ""),
+            "original_cc": fwd.get("forwarded_cc", ""),
+            "original_subject": fwd.get("forwarded_subject", ""),
+            "original_body_html": reply_marker_html(info.get("body_html", "")),
+        })
+    return rows
+
+
+def extract_tables(body_html):
+    if not body_html:
+        return []
+    soup = BeautifulSoup(body_html, "html.parser")
+    out = []
+    for node in soup.find_all(string=True):
+        label = node.strip()
+        if label not in {"Cash Only Transactions", "Withdrawals", "Deposits"}:
+            continue
+        table = node.find_next("table")
+        if not table:
+            continue
+        try:
+            dfs = pd.read_html(StringIO(str(table)))
+        except ValueError:
+            continue
+        for df in dfs:
+            df.columns = [str(c).strip() for c in df.columns]
+            df = df.dropna(how="all").reset_index(drop=True)
+            out.append((label, df))
+    return out
+
+
+def parse_date(value):
+    if not value:
+        return None
+    for fmt in ("%m/%d/%Y", "%m/%d/%y", "%A, %B %d, %Y %I:%M %p"):
+        try:
+            return datetime.strptime(value.strip(), fmt)
+        except ValueError:
+            pass
+    return None
+
+
+def build_notice(row):
+    section = row.get("source_section")
+    account = row.get("Account") or row.get("customer_account")
+    amount = row.get("Cash Amount") or row.get("Amount")
+    row_type = (row.get("Type") or "").strip()
+
+    if section == "Withdrawals":
+        input_date = row.get("Input date")
+        deadline = parse_date(input_date)
+        response_time = (
+            (deadline + timedelta(days=8)).strftime("%Y-%m-%d") if deadline
+            else f"8 calendar days after {input_date}"
+        )
+        action = (
+            f"Enter withdrawal in portal for account {account} for {amount}. "
+            f"Schedule 8 calendar days after input date {input_date}."
+        )
+    elif section == "Deposits" or row_type.lower() == "deposit":
+        response_time = "As soon as practical after email receipt"
+        action = (
+            f"Message dutytrader in Teams: contribution/deposit for account {account} "
+            f"({amount}) approved to invest in model."
+        )
+    else:
+        response_time = "ASAP"
+        action = (
+            f"Halt account and advise of pending trades on {account}. "
+            f"Immediate cash movement noted: {amount}."
+        )
+    return {
+        "email_id": row.get("email_id"),
+        "sent_time": row.get("fw_received_time"),
+        "response_time_needed": response_time,
+        "account": account,
+        "action": action,
+        "source_section": section,
+    }
+
+
+def to_excel(dfs_dict):
+    buf = BytesIO()
+    with pd.ExcelWriter(buf, engine="openpyxl") as writer:
+        for sheet_name, df in dfs_dict.items():
+            if df is not None and not df.empty:
+                df.to_excel(writer, sheet_name=sheet_name, index=False)
+    return buf.getvalue()
+
+
+# ── UI ─────────────────────────────────────────────────────────────────────────
+
+st.markdown("## 📬 Raymond James Email Processor")
+st.markdown("Pulls forwarded RJ emails from your inbox, extracts cash movement tables, and generates action notices.")
+st.divider()
+
+# Step 1 — Login
+st.markdown('<div class="step-label">Step 1</div>', unsafe_allow_html=True)
+col1, col2 = st.columns([4, 1])
+with col1:
+    st.markdown('<div class="step-title">Sign in to Microsoft</div>', unsafe_allow_html=True)
+with col2:
+    if st.session_state.token:
+        st.markdown('<span class="badge-success">✓ Signed in</span>', unsafe_allow_html=True)
+    else:
+        st.markdown('<span class="badge-pending">Not signed in</span>', unsafe_allow_html=True)
+
+if not st.session_state.token:
+    st.markdown("Click the button below. A Microsoft login window will open in your browser.")
+    if st.button("🔐 Sign in with Microsoft"):
+        with st.spinner("Opening Microsoft login window..."):
+            try:
+                st.session_state.token = get_access_token()
+                st.success("Signed in successfully!")
+                st.rerun()
+            except Exception as e:
+                st.error(f"Login failed: {e}")
+else:
+    st.markdown("You are signed in. ✓")
+
+# Step 2 — Configuration
+st.markdown('<div class="step-label">Step 2</div>', unsafe_allow_html=True)
+st.markdown('<div class="step-title">Configure</div>', unsafe_allow_html=True)
+
+col_a, col_b, col_c = st.columns(3)
+with col_a:
+    sender_email = st.text_input(
+        "Sender email (who forwards the RJ emails)",
+        value="agabrielse@newfrontieradvisors.com",
+    )
+with col_b:
+    target_email = st.text_input(
+        "Filter: recipient email to look for",
+        value="cfeng@newfrontieradvisors.com",
+    )
+with col_c:
+    top_n = st.number_input("Max emails to fetch", min_value=5, max_value=200, value=50, step=5)
+
+# Step 3 — Run
+st.markdown('<div class="step-label">Step 3</div>', unsafe_allow_html=True)
+st.markdown('<div class="step-title">Fetch & Process Emails</div>', unsafe_allow_html=True)
+
+if st.button("▶ Run", disabled=not st.session_state.token):
+    with st.spinner("Fetching emails from Outlook..."):
+        try:
+            raw = get_emails_from_sender(st.session_state.token, sender_email, top=int(top_n))
+            st.session_state.messages = raw
+        except Exception as e:
+            st.error(f"Failed to fetch emails: {e}")
+            st.stop()
+
+    with st.spinner("Filtering Raymond James forwarded emails..."):
+        st.session_state.rj_emails = build_rj_emails(raw, target_email)
+
+    with st.spinner("Extracting tables from email bodies..."):
+        cash_rows, wd_rows, dep_rows = [], [], []
+        for email in st.session_state.rj_emails:
+            for section, df in extract_tables(email.get("original_body_html", "")):
+                rows = df.to_dict("records")
+                for row in rows:
+                    row.update({
+                        "email_id": email.get("email_id"),
+                        "fw_subject": email.get("fw_subject"),
+                        "fw_received_time": email.get("fw_received_time"),
+                        "original_subject": email.get("original_subject"),
+                        "original_from": email.get("original_from"),
+                        "original_sent_time": email.get("original_sent_time"),
+                        "source_section": section,
+                    })
+                if section == "Cash Only Transactions":
+                    cash_rows.extend(rows)
+                elif section == "Withdrawals":
+                    wd_rows.extend(rows)
+                elif section == "Deposits":
+                    dep_rows.extend(rows)
+
+        st.session_state.cash_df = pd.DataFrame(cash_rows) if cash_rows else pd.DataFrame()
+        st.session_state.withdrawals_df = pd.DataFrame(wd_rows) if wd_rows else pd.DataFrame()
+        st.session_state.deposits_df = pd.DataFrame(dep_rows) if dep_rows else pd.DataFrame()
+
+    with st.spinner("Building action notices..."):
+        all_rows = cash_rows + wd_rows + dep_rows
+        st.session_state.notice_df = (
+            pd.DataFrame([build_notice(r) for r in all_rows])
+            if all_rows else pd.DataFrame()
+        )
+
+    st.success(f"Done! Found {len(st.session_state.rj_emails)} RJ forwarded emails.")
+
+# ── Results ────────────────────────────────────────────────────────────────────
+if st.session_state.rj_emails:
+    st.divider()
+    st.markdown("### Results")
+
+    tab1, tab2, tab3, tab4 = st.tabs([
+        "📋 Action Notices",
+        "💵 Cash Transactions",
+        "⬆ Withdrawals",
+        "⬇ Deposits",
+    ])
+
+    with tab1:
+        df = st.session_state.notice_df
+        if df is not None and not df.empty:
+            st.dataframe(df, width="stretch", hide_index=True)
+        else:
+            st.info("No action notices generated.")
+
+    with tab2:
+        df = st.session_state.cash_df
+        if df is not None and not df.empty:
+            st.dataframe(df, width="stretch", hide_index=True)
+        else:
+            st.info("No cash transactions found.")
+
+    with tab3:
+        df = st.session_state.withdrawals_df
+        if df is not None and not df.empty:
+            st.dataframe(df, width="stretch", hide_index=True)
+        else:
+            st.info("No withdrawals found.")
+
+    with tab4:
+        df = st.session_state.deposits_df
+        if df is not None and not df.empty:
+            st.dataframe(df, width="stretch", hide_index=True)
+        else:
+            st.info("No deposits found.")
+
+    # Download
+    st.divider()
+    excel_bytes = to_excel({
+        "Action Notices": st.session_state.notice_df,
+        "Cash Transactions": st.session_state.cash_df,
+        "Withdrawals": st.session_state.withdrawals_df,
+        "Deposits": st.session_state.deposits_df,
+    })
+    st.download_button(
+        label="⬇ Download Excel Report",
+        data=excel_bytes,
+        file_name=f"rj_emails_{datetime.now().strftime('%Y%m%d_%H%M')}.xlsx",
+        mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
+    )

requirements.txt

@@ -1,3 +1,7 @@
-altair
-pandas
-streamlit
+streamlit>=1.35.0
+msal>=1.28.0
+requests>=2.31.0
+beautifulsoup4>=4.12.0
+pandas>=2.0.0
+openpyxl>=3.1.0
+lxml>=5.0.0