Parse the news site https://noc.rub.de and serve the headlines as RSS feeds. Using Flask

rss_noc.py

#!/usr/bin/env python

from flask import Flask, request, url_for
from werkzeug.contrib.atom import AtomFeed
from html.parser import HTMLParser
import urllib.request
from datetime import datetime

app = Flask(__name__)
url_noc = 'https://noc.rub.de/cgi-bin/status/'

@app.route('/noc/')
def noc():
    i = 0
    feed = AtomFeed('Noc News', feed_url=url_for('noc'))
    class TagParser(HTMLParser):
        def handle_starttag(self, tag, attrs):
            self.tag = tag

        def handle_data(self, data):
            try:
                if self.tag == 'h3':
                    # Set a random date, so it doesn't raise an error. Attempt to Parse the timestamp is in the other file
                    feed.add(title=data, content=data, updated=datetime(2016, 9, 1, minute=i), content_type='text', author='NOC', url=url_noc)
            except:
                pass

    response = urllib.request.urlopen(url_noc)
    html = response.read().decode('utf-8')
    parser = TagParser()
    parser.feed(html)
    return feed.get_response()

rss_noc_datefix.py

#!/usr/bin/env python

''' NOT WORKING
parsing the timestamp is ugly.
Maybe you have an idea?'''

from flask import Flask, request, url_for
from werkzeug.contrib.atom import AtomFeed
from html.parser import HTMLParser
import urllib.request
from datetime import datetime

app = Flask(__name__)
url_noc = 'https://noc.rub.de/cgi-bin/status/'

@app.route('/noc/')
def noc():
    last_tag = 'span'
    feed = AtomFeed('NOC News', feed_url=url_for('noc'))
    class TagParser(HTMLParser):
        def handle_starttag(self, tag, attrs):
            self.tag = tag
            try:
                for attr in attrs:
                    if attr[0] == 'id':
                        self.attr = attr[1]
            except:
                pass

        def handle_data(self, data):
            try:
                print(self.attr)
                #if last_tag == 'span' and self.tag == 'div':
                if self.tag == 'div' and last_tag == 'span' and 'headline' in self.attr:
                    print(self.tag)
                    last_tag = self.tag
                    url = '%s#%s' % (url_noc, self.attr)
                    print(url)
                elif last_tag == 'div' and self.tag == 'h3':
                    last_tag = self.tag
                    title = data
                    print(title)
                elif last_tag == 'h3':
                    if self.tag == 'span' and 'Uhr' in data:
                        last_tag = self.tag
                        print(datetime.strptime(data, "%d.%m.%Y %H:%M Uhr"))
                        feed.add(title=title, content=title, updated=datetime(2016, 9, 1, minute=i), content_type='text', author='NOC', url=url_noc)
            except:
                pass

    response = urllib.request.urlopen(url_noc)
    html = response.read().decode('utf-8')
    parser = TagParser()
    parser.feed(html)
    return feed.get_response()