refactoring

.gitignore

@@ -14,3 +14,4 @@ src/captchaImage.jpeg
 src/HowBadIsMyBatch.nbconvert.ipynb
 src/HowBadIsMyBatch.nbconvert.html
 src/__pycache__/
+src/intensivstationen/__pycache__/

src/HowBadIsMyBatch.ipynb

@@ -138,7 +138,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.8"
+   "version": "3.10.8 (main, Nov 24 2022, 14:13:03) [GCC 11.2.0]"
   },
   "vscode": {
    "interpreter": {

src/intensivstationen/DateProvider.py

@@ -0,0 +1,55 @@
+from bs4 import BeautifulSoup
+import requests
+from datetime import datetime
+from time import sleep
+from selenium import webdriver
+from selenium.webdriver.firefox.options import Options
+import pandas as pd
+
+class DateProvider:
+    
+    INTENSIVSTATIONEN_DATE_FORMAT = "%d.%m.%Y, %H:%M Uhr"
+
+    def __init__(self):
+        self.lastUpdated = None
+        self.lastUpdatedDataSource = None
+
+    def needsUpdate(self):
+        return self.getLastUpdated() < self.getLastUpdatedDataSource()
+        
+    def getLastUpdated(self):
+        if self.lastUpdated is None:
+            htmlContent = requests.get("https://knollfrank.github.io/HowBadIsMyBatch/intensivstationen.html").text
+            soup = BeautifulSoup(htmlContent, "lxml")
+            dateStr = soup.find(id = "Datenstand").text
+            self.lastUpdated = datetime.strptime(dateStr, DateProvider.INTENSIVSTATIONEN_DATE_FORMAT)
+        
+        return self.lastUpdated
+
+    def getLastUpdatedDataSource(self):
+        if self.lastUpdatedDataSource is None:
+            html = self._getOriginalHtml()
+            lastUpdatedColumn = 'Letzte Änderung'
+            dataFrame = self._asDataFrame(html, lastUpdatedColumn)
+            self.lastUpdatedDataSource = dataFrame.loc['Landkreis-Daten', lastUpdatedColumn].to_pydatetime()
+
+        return self.lastUpdatedDataSource
+
+    def _getOriginalHtml(self):
+        options = Options()
+        options.headless = True
+        options.add_argument("-profile")
+        # put the root directory your default profile path here, you can check it by opening Firefox and then pasting 'about:profiles' into the url field 
+        options.add_argument("/home/frankknoll/snap/firefox/common/.mozilla/firefox/1j6r2yp6.default")
+        driver = webdriver.Firefox(options = options)
+        driver.get('https://www.intensivregister.de/#/aktuelle-lage/downloads')
+        sleep(10)
+        innerHTML = driver.execute_script("return document.body.innerHTML")
+        driver.quit()
+        return innerHTML
+
+    def _asDataFrame(self, html, lastUpdatedColumn):
+        dataFrame = pd.read_html(html, parse_dates = [lastUpdatedColumn])[0]
+        dataFrame[lastUpdatedColumn] = pd.to_datetime(dataFrame[lastUpdatedColumn], format = "%d.%m.%Y %H:%M Uhr")
+        dataFrame.set_index('Name', inplace = True)
+        return dataFrame

src/intensivstationen/Intensivstationen.ipynb

@@ -9,10 +9,13 @@
    "source": [
     "import pandas as pd\n",
     "from urllib import request\n",
+    "import os\n",
+    "from DateProvider import DateProvider\n",
+    "from datetime import datetime\n",
     "\n",
     "pd.set_option('display.max_rows', 100)\n",
     "pd.set_option('display.max_columns', None)\n",
-    "pd.set_option('mode.chained_assignment', 'raise')"
+    "pd.set_option('mode.chained_assignment', 'raise')\n"
    ]
   },
   {
@@ -22,92 +25,17 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from datetime import datetime\n",
-    "\n",
     "print(datetime.now().strftime(\"%d.%m.%Y, %H:%M:%S Uhr\"))"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "579c0911",
+   "id": "98981ab9",
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pwd"
+    "os.getcwd()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "dfa836ec",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "needsUpdate = False"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "79de4057",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from bs4 import BeautifulSoup\n",
-    "import requests\n",
-    "from datetime import datetime\n",
-    "from time import sleep\n",
-    "from selenium import webdriver\n",
-    "from selenium.webdriver.firefox.options import Options\n",
-    "\n",
-    "class DateProvider:\n",
-    "    \n",
-    "    INTENSIVSTATIONEN_DATE_FORMAT = \"%d.%m.%Y, %H:%M Uhr\"\n",
-    "\n",
-    "    def __init__(self):\n",
-    "        self.lastUpdated = None\n",
-    "        self.lastUpdatedDataSource = None\n",
-    "\n",
-    "    def needsUpdate(self):\n",
-    "        return self.getLastUpdated() < self.getLastUpdatedDataSource()\n",
-    "        \n",
-    "    def getLastUpdated(self):\n",
-    "        if self.lastUpdated is None:\n",
-    "            htmlContent = requests.get(\"https://knollfrank.github.io/HowBadIsMyBatch/intensivstationen.html\").text\n",
-    "            soup = BeautifulSoup(htmlContent, \"lxml\")\n",
-    "            dateStr = soup.find(id = \"Datenstand\").text\n",
-    "            self.lastUpdated = datetime.strptime(dateStr, DateProvider.INTENSIVSTATIONEN_DATE_FORMAT)\n",
-    "        \n",
-    "        return self.lastUpdated\n",
-    "\n",
-    "    def getLastUpdatedDataSource(self):\n",
-    "        if self.lastUpdatedDataSource is None:\n",
-    "            html = self._getOriginalHtml()\n",
-    "            lastUpdatedColumn = 'Letzte Änderung'\n",
-    "            dataFrame = self._asDataFrame(html, lastUpdatedColumn)\n",
-    "            self.lastUpdatedDataSource = dataFrame.loc['Landkreis-Daten', lastUpdatedColumn].to_pydatetime()\n",
-    "\n",
-    "        return self.lastUpdatedDataSource\n",
-    "\n",
-    "    def _getOriginalHtml(self):\n",
-    "        options = Options()\n",
-    "        options.headless = True\n",
-    "        options.add_argument(\"-profile\")\n",
-    "        # put the root directory your default profile path here, you can check it by opening Firefox and then pasting 'about:profiles' into the url field \n",
-    "        options.add_argument(\"/home/frankknoll/snap/firefox/common/.mozilla/firefox/1j6r2yp6.default\")\n",
-    "        driver = webdriver.Firefox(options = options)\n",
-    "        driver.get('https://www.intensivregister.de/#/aktuelle-lage/downloads')\n",
-    "        sleep(10)\n",
-    "        innerHTML = driver.execute_script(\"return document.body.innerHTML\")\n",
-    "        driver.quit()\n",
-    "        return innerHTML\n",
-    "\n",
-    "    def _asDataFrame(self, html, lastUpdatedColumn):\n",
-    "        dataFrame = pd.read_html(html, parse_dates = [lastUpdatedColumn])[0]\n",
-    "        dataFrame[lastUpdatedColumn] = pd.to_datetime(dataFrame[lastUpdatedColumn], format = \"%d.%m.%Y %H:%M Uhr\")\n",
-    "        dataFrame.set_index('Name', inplace = True)\n",
-    "        return dataFrame\n"
    ]
   },
   {
@@ -831,9 +759,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3.10.8 ('howbadismybatch-venv')",
+   "display_name": "howbadismybatch-venv-kernel",
    "language": "python",
-   "name": "python3"
+   "name": "howbadismybatch-venv-kernel"
   },
   "language_info": {
    "codemirror_mode": {