From 33d3e2b7201b70699f0fd3febf0f808993ad4358 Mon Sep 17 00:00:00 2001 From: frankknoll Date: Sun, 6 Mar 2022 22:50:37 +0100 Subject: [PATCH] checking needsUpdate() --- docs/batchCodeTable.html | 2 +- docs/intensivstationen.html | 2 +- src/HowBadIsMyBatch.ipynb | 36 ++++++++++++++++++++++++++++++++++++ 3 files changed, 38 insertions(+), 2 deletions(-) diff --git a/docs/batchCodeTable.html b/docs/batchCodeTable.html index 5c353b74f5f..24856a00f35 100644 --- a/docs/batchCodeTable.html +++ b/docs/batchCodeTable.html @@ -162,7 +162,7 @@

- Check out your batch code (Last updated: March 4, 2022) + Check out your batch code (Last updated: March 4, 2022)

diff --git a/docs/intensivstationen.html b/docs/intensivstationen.html index 339c70fbb1a..074e8ab19f2 100644 --- a/docs/intensivstationen.html +++ b/docs/intensivstationen.html @@ -452,7 +452,7 @@
Datensatz:
Landkreis-Daten
Datenstand:
-
05.03.2022, 12:38 Uhr
+
05.03.2022, 12:38 Uhr
diff --git a/src/HowBadIsMyBatch.ipynb b/src/HowBadIsMyBatch.ipynb index 671b1deeff7..5ecd236e50e 100644 --- a/src/HowBadIsMyBatch.ipynb +++ b/src/HowBadIsMyBatch.ipynb @@ -14,6 +14,42 @@ "pd.set_option('display.max_columns', None)" ] }, + { + "cell_type": "code", + "execution_count": null, + "id": "1dbf9321", + "metadata": {}, + "outputs": [], + "source": [ + "from bs4 import BeautifulSoup\n", + "import requests\n", + "import re\n", + "from dateutil.parser import parse\n", + "\n", + "def needsUpdate():\n", + " return _getLastUpdatedHowbadismybatch() < _getLastUpdatedOriginal()\n", + " \n", + "def _getLastUpdatedHowbadismybatch():\n", + " return _getLastUpdated(\n", + " url = \"https://knollfrank.github.io/HowBadIsMyBatch/batchCodeTable.html\",\n", + " getDateStr = lambda soup: soup.find(id = \"last_updated\").text)\n", + "\n", + "def _getLastUpdatedOriginal():\n", + " def getDateStr(soup):\n", + " lastUpdated = soup.find(string = re.compile(\"Last updated\"))\n", + " return re.search('Last updated: (.+).', lastUpdated).group(1)\n", + "\n", + " return _getLastUpdated(url = \"https://vaers.hhs.gov/data/datasets.html\", getDateStr = getDateStr)\n", + "\n", + "def _getLastUpdated(url, getDateStr):\n", + " htmlContent = requests.get(url).text\n", + " soup = BeautifulSoup(htmlContent, \"lxml\")\n", + " dateStr = getDateStr(soup)\n", + " return parse(dateStr).date()\n", + "\n", + "print('needsUpdate: ', needsUpdate())" + ] + }, { "cell_type": "code", "execution_count": null,