init commit

.idea/.gitignore

@@ -0,0 +1,3 @@
+# Default ignored files
+/shelf/
+/workspace.xml

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/mail_loader.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="jdk" jdkName="Python 3.13" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/misc.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Black">
+    <option name="sdkName" value="Python 3.13" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.13" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/mail_loader.iml" filepath="$PROJECT_DIR$/.idea/mail_loader.iml" />
+    </modules>
+  </component>
+</project>

credentials.json

@@ -0,0 +1 @@
+{"installed":{"client_id":"725019411610-rkg50rru2dklsqdapvekdustsrfe0099.apps.googleusercontent.com","project_id":"phonic-entity-272321","auth_uri":"https://accounts.google.com/o/oauth2/auth","token_uri":"https://oauth2.googleapis.com/token","auth_provider_x509_cert_url":"https://www.googleapis.com/oauth2/v1/certs","client_secret":"aWJYZre_RE55kM64Kf1j_cZB","redirect_uris":["http://localhost"]}}

docker-compose.yml

@@ -0,0 +1,45 @@
+version: "3.8"
+services:
+  mail_czsk:
+    build: .
+    container_name: mail_czsk
+    environment:
+      - SUPPORT_ADDRESS=dalkove.ovladace@gmail.com
+      - TOKEN_PATH=/app/tokens/token_czsk.json
+      - OUTPUT_DIR=/data
+    volumes:
+      # Shared OAuth client credentials
+      - ./credentials.json:/app/credentials.json:ro
+      # Per-account token storage
+      - ./tokens:/app/tokens
+      # Where JSON outputs go
+      - ./data/czsk:/data
+
+  mail_rcw:
+    build: .
+    container_name: mail_rcw
+    environment:
+      - SUPPORT_ADDRESS=remote.control.world1@gmail.com
+      - TOKEN_PATH=/app/tokens/token_rcw.json
+      - OUTPUT_DIR=/data
+    volumes:
+      - ./credentials.json:/app/credentials.json:ro
+      - ./tokens:/app/tokens
+      - ./data/rcw:/data
+
+  mail_rcw_offers:
+    build: .
+    container_name: mail_rcw_offers
+    environment:
+      - SUPPORT_ADDRESS=rcw.offline@gmail.com
+      - TOKEN_PATH=/app/tokens/token_rcw_offers.json
+      - OUTPUT_DIR=/data
+    volumes:
+      - ./credentials.json:/app/credentials.json:ro
+      - ./tokens:/app/tokens
+      - ./data/rcw_offers:/data
+
+# Optional: put all three on the same network
+networks:
+  default:
+    driver: bridge

docker/Dockerfile

@@ -0,0 +1,24 @@
+# Use a slim Python base
+FROM python:3.11-slim
+
+# Set working directory
+WORKDIR /app
+
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends \
+      build-essential \
+      libmariadb-dev-compat \
+      libmariadb-dev \
+    && rm -rf /var/lib/apt/lists/*
+
+
+# Install dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy code & credentials template
+COPY main.py .
+COPY credentials.json .
+
+# Entrypoint: reads SUPPORT_ADDRESS, TOKEN_PATH, OUTPUT_DIR env vars
+ENTRYPOINT ["bash", "-lc", "python main.py"]

main.py

@@ -0,0 +1,215 @@
+#!/usr/bin/env python3
+"""
+download_emails.py
+
+- Uses Gmail API to fetch all messages delivered to a single support address.
+- Pulls configured Gmail signatures (in any language) via Settings API.
+- Parses out headers, body, and matches against signatures or falls back to regex or manual name mapping.
+- Tally per-day sent vs. received counts and per-author sent email counts.
+- Writes each month's emails into JSON files under OUTPUT_DIR/YYYY/MM/emails.json.
+- Writes overall stats into OUTPUT_DIR as JSON files.
+- Outputs progress logs to stdout for Docker visibility.
+- (Commented-out) Stubs for loading the daily/author stats into MariaDB.
+"""
+
+import os
+import json
+import base64
+import re
+from datetime import datetime
+from collections import defaultdict
+import logging
+
+from google.oauth2.credentials import Credentials
+from google_auth_oauthlib.flow import InstalledAppFlow
+from googleapiclient.discovery import build
+
+# Configure logging for progress
+logging.basicConfig(level=logging.INFO, format='%(asctime)s [%(levelname)s] %(message)s')
+logger = logging.getLogger(__name__)
+
+# Gmail API scope
+SCOPES = ['https://www.googleapis.com/auth/gmail.readonly']
+
+# Configuration from environment
+SUPPORT_ADDRESS = os.environ.get('SUPPORT_ADDRESS', 'remote.control.world1@gmail.com')
+TOKEN_PATH      = os.environ.get('TOKEN_PATH', 'tokens/test.json')
+OUTPUT_DIR      = os.environ.get('OUTPUT_DIR', 'data')
+
+# Aliases considered as sent
+SENDER_ALIASES = [SUPPORT_ADDRESS.lower(), 'orders@remote-control-world.eu']
+
+# Manual name mapping if signatures not found
+NAME_PATTERNS = {
+    'Josefina': ['Josefína Bartková'],
+    'Ondra': ['Kateřina Kulhánková', 'Kateřina Kulhánkova', 'Ondrej', 'Ondřej'],
+    'Honza': ['Jan Klus'],
+    'Halina': ['Halina Kutláková'],
+    'Helena': ['Helena Urbášková'],
+    'AdamH': ['Adam Holuša'],
+    'AdamK': ['Adam Kulhánek'],
+    'KubaS': ['Jakub Sopuch'],
+    'LukasZ': ['Lukáš Zdražila'],
+    'Breta': ['Břetislav Střaslička'],
+    'TerkaP': ['Tereza Pěchulová'],
+    'Marketa': ['Marketa', 'Markéta'],
+}
+
+
+def get_gmail_service(token_path: str):
+    """
+    Load OAuth client credentials and per-account token.
+    """
+    creds = None
+    if os.path.exists(token_path):
+        creds = Credentials.from_authorized_user_file(token_path, SCOPES)
+    if not creds or not creds.valid:
+        flow = InstalledAppFlow.from_client_secrets_file('credentials.json', SCOPES)
+        creds = flow.run_local_server(port=0)
+        with open(token_path, 'w') as f:
+            f.write(creds.to_json())
+    return build('gmail', 'v1', credentials=creds)
+
+
+def extract_body(payload) -> str:
+    """
+    Recursively find text/plain payload.
+    """
+    if payload.get('mimeType') == 'text/plain' and payload.get('body', {}).get('data'):
+        data = payload['body']['data']
+        return base64.urlsafe_b64decode(data).decode('utf-8', errors='ignore')
+    for part in payload.get('parts', []):
+        text = extract_body(part)
+        if text:
+            return text
+    return ''
+
+
+def load_signatures(service):
+    """
+    Fetch configured Gmail signatures.
+    """
+    sigs = []
+    resp = service.users().settings().sendAs().list(userId='me').execute()
+    for entry in resp.get('sendAs', []):
+        html = entry.get('signature') or ''
+        text = re.sub(r'<[^>]+>', '', html).strip()
+        if text:
+            sigs.append({
+                'email': entry['sendAsEmail'],
+                'name': entry.get('displayName') or entry['sendAsEmail'],
+                'signature': text
+            })
+    logger.info(f"Loaded {len(sigs)} configured signatures from Gmail settings")
+    return sigs
+
+
+def extract_author(body: str, signatures: list) -> str:
+    """
+    Identify author by:
+    1) Matching configured signature blocks
+    2) Manual name mapping
+    3) Regex fallback for common sign-offs
+    """
+    # 1) Signature blocks
+    for s in signatures:
+        sig = s.get('signature')
+        if sig and sig in body:
+            return s['name']
+
+    # 2) Manual name patterns
+    for name, patterns in NAME_PATTERNS.items():
+        for pat in patterns:
+            if pat in body:
+                return name
+
+    # 3) Regex fallback
+    match = re.search(
+        r'(?im)(?:Podpis|S pozdravem|Díky|Thanks|Regards|Best regards|Sincerely)[\s,]*\r?\n([^\r\n]{2,})',
+        body
+    )
+    if match:
+        return match.group(1).strip()
+    return None
+
+
+def main():
+    os.makedirs(OUTPUT_DIR, exist_ok=True)
+    service = get_gmail_service(TOKEN_PATH)
+    signatures = load_signatures(service)
+
+    monthly_emails = defaultdict(list)
+    daily_counts = defaultdict(lambda: {'sent': 0, 'received': 0})
+    author_counts = defaultdict(int)
+
+    logger.info(f"Starting fetch for mailbox: {SUPPORT_ADDRESS}")
+    next_page_token = None
+    page_count = 0
+    total_msgs = 0
+
+    while True:
+        page_count += 1
+        resp = service.users().messages().list(
+            userId='me', q='after:2025-03-01', pageToken=next_page_token, maxResults=500
+        ).execute()
+        messages = resp.get('messages', [])
+        count = len(messages)
+        total_msgs += count
+        logger.info(f"Page {page_count}: fetched {count} messages (total so far: {total_msgs})")
+
+        if not messages:
+            break
+
+        for meta in messages:
+            msg = service.users().messages().get(
+                userId='me', id=meta['id'], format='full'
+            ).execute()
+            headers = {h['name']: h['value'] for h in msg['payload'].get('headers', [])}
+            body = extract_body(msg['payload'])
+            author = extract_author(body, signatures)
+
+            dt = datetime.fromtimestamp(int(msg['internalDate']) / 1000)
+            year, month, day = dt.strftime('%Y'), dt.strftime('%m'), dt.strftime('%Y-%m-%d')
+            from_hdr = headers.get('From', '').lower()
+            is_sent = any(alias in from_hdr for alias in SENDER_ALIASES)
+
+            if is_sent:
+                daily_counts[day]['sent'] += 1
+                if author:
+                    author_counts[author] += 1
+            else:
+                daily_counts[day]['received'] += 1
+
+            monthly_emails[(year, month)].append({
+                'id': msg['id'], 'threadId': msg.get('threadId'), 'source': SUPPORT_ADDRESS,
+                'from': headers.get('From'), 'to': headers.get('To'), 'date': headers.get('Date'),
+                'subject': headers.get('Subject'), 'internalDate': msg.get('internalDate'),
+                'body': body, 'author': author, 'sent': is_sent
+            })
+
+        next_page_token = resp.get('nextPageToken')
+        if not next_page_token:
+            break
+
+    logger.info(f"Fetch complete: total messages retrieved: {total_msgs}")
+
+    # Write monthly files
+    for (yr, mo), emails in monthly_emails.items():
+        path = os.path.join(OUTPUT_DIR, yr, mo)
+        os.makedirs(path, exist_ok=True)
+        with open(os.path.join(path, 'emails.json'), 'w', encoding='utf-8') as f:
+            json.dump(emails, f, ensure_ascii=False, indent=2)
+        logger.info(f"Wrote {len(emails)} emails to {yr}/{mo}/emails.json")
+
+    # Write stats
+    with open(os.path.join(OUTPUT_DIR, 'daily_counts.json'), 'w') as f:
+        json.dump(daily_counts, f, indent=2)
+    with open(os.path.join(OUTPUT_DIR, 'author_counts.json'), 'w') as f:
+        json.dump(author_counts, f, indent=2)
+
+    logger.info(f"Processed {total_msgs} messages into {len(monthly_emails)} month folders under {OUTPUT_DIR}")
+
+    # MariaDB stubs commented out
+
+if __name__ == '__main__':
+    main()

requirements.txt

@@ -0,0 +1,5 @@
+google-api-python-client>=2.70.0
+google-auth>=2.20.0
+google-auth-oauthlib>=0.8.0
+google-auth-httplib2>=0.1.0
+mariadb

tokens/token_czsk.json

@@ -0,0 +1 @@
+{"token": "ya29.A0AS3H6NxX5_wFQ28hw5Wvy34_Kr2dJ_qpGSpMB86BQSUHMMzPeFaZFP8DhwcDwJUuej8jxt1Z6sPFmpnFNyJTqXy40h8PFfrAj0N6GKLXbkswHCCDuH2FNT7zgTU-q1wVZfheDqlomIXt6ukLNVwFWdn9xhlrFhbqMdgPd7aZFH9GPR8IQ61knft3AWHECfcYytcpODgaCgYKAfkSARESFQHGX2MiOVdSBUIU6OxpKQ-ewhvXHQ0206", "refresh_token": "1//09WgPH6MscuSGCgYIARAAGAkSNwF-L9IrtR_J0YXxSAE-7quKW77B2QzGTzvIpdnrVy2I2w-_Ug42SDRFbzb3FvhN4RpLgVrFDyw", "token_uri": "https://oauth2.googleapis.com/token", "client_id": "725019411610-rkg50rru2dklsqdapvekdustsrfe0099.apps.googleusercontent.com", "client_secret": "aWJYZre_RE55kM64Kf1j_cZB", "scopes": ["https://www.googleapis.com/auth/gmail.readonly"], "universe_domain": "googleapis.com", "account": "", "expiry": "2025-07-18T13:40:45.787490Z"}

tokens/token_rcw.json

@@ -0,0 +1 @@
+{"token": "ya29.a0AS3H6NzeWcZMQcPsi1jy_NjB7zmmAJBlqvi0ua6m5RDob-TDnKLMqxWtIch1IlKZUPBqopiqsBTk60D88mbWci1l1gpfg6a4BZPYfjRilRizauvGwhmdBprCBTD8roR51AtsOjbJDyu6mV-6tyO7Sw4p7T1TZOFnD7pusaIzaCgYKAd8SARMSFQHGX2MiotN4orz1RRESdeSjksyeoA0175", "refresh_token": "1//09dd8-QNFUgKBCgYIARAAGAkSNwF-L9Iro08y7q9PmEZXCWIjykiIINgsK0wE-tcZvmQvaPOV3XZ5EjJuSdfxHuVte-yA2UEP4T4", "token_uri": "https://oauth2.googleapis.com/token", "client_id": "725019411610-rkg50rru2dklsqdapvekdustsrfe0099.apps.googleusercontent.com", "client_secret": "aWJYZre_RE55kM64Kf1j_cZB", "scopes": ["https://www.googleapis.com/auth/gmail.readonly"], "universe_domain": "googleapis.com", "account": "", "expiry": "2025-07-18T13:09:32.987158Z"}

tokens/token_rcw_offers.json

@@ -0,0 +1 @@
+{"token": "ya29.a0AS3H6NxUCppUuFN_LhoZnpuuD6IZTl-u8DgCKop7SwRd6kh7ENotgfOMzrB5nDtXB12vVA0Ko19MErZWCjAo3oL5EFcJt6-MgZyfHtx0nAfolICT4xTqzHbGnCwVRHoHaCRHNw_z7ZluK-a8QWCv1RVjEC7mJ9eaU-cDTqnJaCgYKASYSARYSFQHGX2MiKy4I0lPP4dsMNSdDdHAqww0175", "refresh_token": "1//09tZ1D9cViQReCgYIARAAGAkSNwF-L9IrpGT7p2Wkd3dlLINt5SwkkUEbjvlx3yDqXlohoi0z_evodLpu8M3Jv7EXbYAF1toQDNc", "token_uri": "https://oauth2.googleapis.com/token", "client_id": "725019411610-rkg50rru2dklsqdapvekdustsrfe0099.apps.googleusercontent.com", "client_secret": "aWJYZre_RE55kM64Kf1j_cZB", "scopes": ["https://www.googleapis.com/auth/gmail.readonly"], "universe_domain": "googleapis.com", "account": "", "expiry": "2025-07-18T13:40:22.079227Z"}