feuerwehr-nea/einsaetze-rss-feed
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

2025-03-11

Browse Source
This commit is contained in:
Christian Jeworrek
2025-03-11 19:40:04 +01:00
parent 8872db6767
commit 9792af0ad9
1 changed files with 27 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

43
scripts/einsaetze_rss_feed.py
View File

@@ -11,7 +11,13 @@ locale.setlocale(locale.LC_TIME, 'de_DE.UTF-8')
BASEURL = os.getenv("BASEURL", default="https://www.feuerwehr-nea.de")
FWNAME = os.getenv("FWNAME", default="Feuerwehr Nea")
soup = BeautifulSoup(requests.get(BASEURL + "/einsaetze",timeout=20).content, 'html.parser')
session = requests.Session()
soup = BeautifulSoup(session.get(BASEURL + "/einsaetze",timeout=20).content, 'html.parser')
csrfmiddlewaretoken = soup.find('input', attrs={ "name": "csrfmiddlewaretoken" })['value']
soup = BeautifulSoup(session.post(BASEURL + "/einsaetze/load_reports/0/no_group/", data={ "csrfmiddlewaretoken": csrfmiddlewaretoken }, headers={'referer': BASEURL + "/einsaetze"}).content, 'html.parser')
print('<?xml version="1.0" encoding="UTF-8" ?>\n'
'<rss version="2.0">'
@@ -20,29 +26,34 @@ print('<?xml version="1.0" encoding="UTF-8" ?>\n'
'<link>' + BASEURL + '</link>'
'<description>' + FWNAME + ' Einsätze</description>')
for mysoup in soup.find_all('article', class_='teaser-element'):
mydatetime_str = mysoup.find('span', class_="date").string
for mysoup in soup.find_all('a', class_='einsatz-link text-nowrap'):
mylink = BASEURL + mysoup['href']
soup2 = BeautifulSoup(session.get( mylink ,timeout=10).content, 'html.parser')
mydatetime_str = soup2.find("th",string='Einsatzstart').find_next("td").string
mydatetime = datetime.strptime(mydatetime_str, '%d. %B %Y %H:%M')
mydatetime = timezone("CET").localize(mydatetime)
mylink = BASEURL + (mysoup.find('a', class_="einsatz-link"))['href']
soup2 = BeautifulSoup(requests.get(mylink,timeout=10).content, 'html.parser')
mylist = []
mykeywords = myunits = ""
for itemsoup in (soup2.find('tbody').find_all('td')):
if itemsoup.string is not None:
mylist.append(re.sub(r"\n\ *", " ", itemsoup.string.strip()))
if len(mylist) >= 4:
mykeywords = mylist[3]
if len(mylist) >= 3:
myunits = mylist[2]
mykeywords = soup2.find("th",string='Alarmierungsart')
if mykeywords is None:
mykeywords = soup2.find("th",string='Einsatzart')
if mykeywords is not None:
mykeywords = mykeywords.find_next("td").string.strip()
else:
mykeywords = ""
myunits = soup2.find("th",string='Alarmierte Einheiten')
if myunits is None:
myunits = soup2.find("th",string='Alarmierung')
if myunits is not None:
myunits = myunits.find_next("td").string.strip()
else:
myunits = ""
print("<item>")
locale.setlocale(locale.LC_TIME, 'en_US.UTF-8')
print("<pubDate>" + mydatetime.strftime('%a, %d %b %Y %H:%M:%S %z') + "</pubDate>")
locale.setlocale(locale.LC_TIME, 'de_DE.UTF-8')
print("<title>" + mykeywords + " - " + (mysoup.find('h3', class_="heading")).string.strip() + " - " + myunits + "</title>")
print("<title>" + mykeywords + " - " + (soup2.find('meta', attrs={ "property": "og:title" }))['content'] + " - " + myunits + "</title>")
print("<link>" + mylink + "</link>")
try:
print("<description>" + (mysoup.find('div', class_="teaser-element-text")).string.strip() + "</description>")
print("<description>" + (soup2.find('div', class_="description")).string.strip() + '&lt;br&gt;' + (soup2.find('div', class_="description").find_next("p").string.strip()) + '&lt;hr&gt;' + myunits + "</description>")
except:
print("<description></description>")
print("</item>")