Добавил дату в базу данных для отправки одинаковых сообщений

close issue #1

.github/workflows/github-push-docker.yml

@@ -0,0 +1,41 @@
+name: Create and publish a Docker image
+
+on:
+  push:
+    branches: ['main']
+
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}
+
+jobs:
+  build-and-push-image:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+
+      - name: Log in to the Container registry
+        uses: docker/login-action@f054a8b539a109f9f41c372932f1ae047eff08c9
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@98669ae865ea3cffbcbaa878cf57c20bbf1c6c38
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+
+      - name: Build and push Docker image
+        uses: docker/build-push-action@ad44023a93711e3deb337508980b4b5e9bcdc5dc
+        with:
+          context: .
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}

Dockerfile

@@ -0,0 +1,17 @@
+FROM python:3.11.2-alpine3.17
+
+LABEL Maintainer="serega404"
+
+WORKDIR /app
+
+COPY requirements.txt requirements.txt
+RUN pip3 install -r requirements.txt
+
+# Setting up crontab
+COPY crontab /tmp/crontab
+RUN cat /tmp/crontab > /etc/crontabs/root
+
+COPY main.py main.py
+
+# run crond as main process of container
+CMD ["crond", "-f", "-l", "2"]

README.md

@@ -1 +1,25 @@
 # VodokanalParser
+
+[![MIT License](https://img.shields.io/github/license/serega404/VodokanalBot)](https://github.com/serega404/VodokanalBot)
+
+### Запуск в Docker
+
+``` Docker
+docker volume create vodokanal_bot_data
+docker run -d --name VodokanalBot \
+    --restart=always \
+    -v vodokanal_bot_data:/app/data \
+    -e TZ='Europe/Moscow' \
+    -e TELEGRAM_TOKEN='TOKEN' \
+    -e TELEGRAM_CHANNEL='CHAT_ID' \
+    ghcr.io/serega404/vodokanalbot:main
+```
+
+### Библиотеки
+
+* [Requests](https://requests.readthedocs.io/en/latest/)
+* [BeautifulSoup](https://www.crummy.com/software/BeautifulSoup/)
+
+### Лицензия
+
+Распространяется под MIT License. Смотри файл [`LICENSE`](./LICENSE) для того что бы узнать подробности.

crontab

@@ -0,0 +1,2 @@
+@reboot cd /app && python3 /app/main.py 
+*/10 * * * *  cd /app && python3 /app/main.py 

main.py

@@ -0,0 +1,83 @@
+import requests, json, os
+from bs4 import BeautifulSoup
+from datetime import datetime
+
+# Config
+
+URL = os.environ.get('VODOKANAL_URL', 'http://www.tgnvoda.ru/avarii.php')
+SEND_SILENT = os.environ.get('SEND_SILENT', False)
+TELEGRAM_TOKEN = os.environ.get('TELEGRAM_TOKEN', '')
+TELEGRAM_CHANNEL = os.environ.get('TELEGRAM_CHANNEL', '')
+
+if TELEGRAM_TOKEN == '':
+    print("Telegram token is not set")
+    exit()
+
+if TELEGRAM_CHANNEL == '':
+    print("Telegram channel is not set")
+    exit()
+
+# Load database
+
+db = None
+if (os.path.isfile('data/db.json')):
+    with open('data/db.json', 'r', encoding='utf-8') as f:
+        db = json.load(f)
+else:
+    print("Database not loaded")
+
+# Get data
+
+req = requests.get(URL)
+
+if (req.status_code != 200):
+    print("Request error: " + str(req.status_code))
+    exit()
+
+soup = BeautifulSoup(req.content, "html.parser")
+
+elements = []
+for tag in soup.find_all('font', size='2', face='VERDANA'):
+    date = tag.select_one('font:nth-of-type(1)').b.text
+    if not(date.split('.')[0] == str(datetime.today().day).zfill(2) and date.split('.')[1] == str(datetime.today().month).zfill(2)):
+        continue
+    elements.append(date + "$" + tag.select_one('font:nth-of-type(2)').text.replace('\n', ''))
+
+if elements == []:
+    print("No posts")
+    exit()
+
+print("The number of posts for this day:", len(elements))
+
+# Send telegram message
+
+def send_message(message):
+    req = requests.get("https://api.telegram.org/bot" + TELEGRAM_TOKEN + "/sendMessage?chat_id=" + TELEGRAM_CHANNEL + "&disable_notification=" + str(SEND_SILENT) + "&text=" + message)
+    if (req.status_code != 200):
+        print("Telegram request error: " + str(req.status_code))
+        exit()
+    else:
+        print("Telegram message sent, mess id: " + str(req.json()['result']['message_id']))
+
+# Compare db and elements
+
+if db is not None:
+    diff = set(elements) - set(db)
+    if diff == []:  
+        print("No new posts")
+        exit()
+
+    for i in diff:
+        send_message(i.split("$",1)[1])
+else:
+    for element in elements:
+        send_message(element.split("$",1)[1])
+
+# Save database
+
+if not os.path.exists("data"):
+   os.makedirs("data")
+
+with open('data/db.json', 'w', encoding='utf-8') as f:
+    json.dump(elements, f, ensure_ascii=False)
+    print("Database updated")

requirements.txt

@@ -0,0 +1,2 @@
+requests
+beautifulsoup4

src_php_deprecated/vodokanal.php

@@ -24,7 +24,7 @@ echo "Date now: " . $dateNow . "\n";
 
 foreach ($html->find('td[bgcolor="#ffffff"]') as $e) {
   $date = "";
-  preg_match("/\\d{2}\\.\\d{2}\\.\\d{4}/", $e->plaintext, $date);
+  preg_match("/(0[1-9]|1[0-9]|2[0-9]|3[01])[.](0[1-9]|1[0-2])[.](20[0-9][0-9]|[0-9][0-9])/", $e->plaintext, $date);
 
   if (strcasecmp(reset($date), $dateNow) == 0) { // get current date posts
     // remove date from content
@@ -39,7 +39,7 @@ foreach ($html->find('td[bgcolor="#ffffff"]') as $e) {
 }
 
 if ($all_elements == null) {
-  echo "Posts not dound\n";
+  echo "Posts not found\n";
   exit;
 }