|
Enthusiast
Posts: 32
Karma: 10
Join Date: Sep 2013
Location: DE
Device: Linux PC's, Android devices, Amazon Fire HD10
|
PressePortal_DE Recipe - latest News and local Police News!
Hi, folks,
here is another nice little recipe for 'our' calibre.
It will give you a daily news.
Most of the tag, in the recipe are commended or self-explanatory.
Feel free to test, modify and use.
May, kovidgoyal or someone else put it into the recipe-list of the calibre program, so that everybody can use that after next update.
kindly regards
VoHegg
________________ Recipe file as Text _____________________
Code:
#!/usr/bin/env python2
# vim:fileencoding=utf-8
from __future__ import unicode_literals, division, absolute_import, print_function
from calibre.web.feeds.news import BasicNewsRecipe
from datetime import datetime
class PressePortalDE(BasicNewsRecipe):
# Titel of the Recipe
title = 'Presseportal DE'
# Author
__author__ = 'Volker Heggemann, VoHe'
# oldes article to download (in days) ---- can be edit by user
oldest_article = 1
# describes itself, ---- can be edit by user
max_articles_per_feed = 100
# speed up the download on fast computers be carefull (I test max.20) ---- can be edit by user
simultaneous_downloads = 10
#description, some Reader show this in titlepage
description = u'Presseportal News Feed DE'
#add date to description so for dayly downloads you can find them easier ---- can be edit by user
description = description +' fetched: ' + datetime.now().strftime("%Y-%m-%d") # %H:%M:%S")
#Who published the content?
publisher = u'Presseportal.de'
#What is the content of?
category = u'latest news, national Police, Germany'
# describes itself, ---- can be edit by user
use_embedded_content = False
# describes itself, ---- can be edit by user
language = 'de'
#encoding of content. e.g. utf-8, None, ... ---- can be edit by user
encoding = None # 'utf-8' doesn't work here
# Removes javascript- why keep this, we only want static content
remove_javascript = True
# Removes empty feeds - why keep them!?
remove_empty_feeds = True
#some formatations for lrf and epub files
html2lrf_options = [
'--comment', description
, '--category', category
, '--publisher', publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
#The cover Picture of the book. Here I use a local picture, but it's possible to use a link, too
cover_url = '/home/user/.config/calibre/eigene_icons/presseportal.png'
#cover_url = 'http://www.cleantechrelations.com/images/Presseportal.jpg'
#remove the rubbish (in ebook)
auto_cleanup = True
#now the content description and URL follows
# feel free to add, wipe out what you need ---- can be edit by user
#
# some of this are double
# so if you load "Alle Ressort" you don't need "Wirtschaft, Finanzen, Politik, Vermischtes..." at all.
#
#
# Make some tests, may you first comment all of them out, and step by step you add what you'll need?
#
feeds = [ #Ressorts
# Add or Remove the '#' symbol in front of line, to get or discard this rss-feed
#
# ---- each line can be edit by user
#
# (u'Alle Ressort',u'http://www.presseportal.de/rss/presseportal.rss2'),
(u'Wirtschaft',u'http://www.presseportal.de/rss/wirtschaft.rss2'),
(u'Finanzen',u'http://www.presseportal.de/rss/finanzen.rss2'),
(u'Politik',u'http://www.presseportal.de/rss/politik.rss2'),
(u'Vermischtes',u'http://www.presseportal.de/rss/vermischtes.rss2'),
(u'Sport',u'http://www.presseportal.de/rss/sport.rss2'),
(u'Kultur',u'http://www.presseportal.de/rss/kultur.rss2'),
#Branchen
(u'Arbeit',u'http://www.presseportal.de/rss/arbeit.rss2'),
(u'Auto',u'http://www.presseportal.de/rss/auto.rss2'),
(u'Banken',u'http://www.presseportal.de/rss/banken.rss2'),
(u'Bildung',u'http://www.presseportal.de/rss/bildung.rss2'),
(u'Bauwesen',u'http://www.presseportal.de/rss/bauwesen.rss2'),
(u'Celebrities',u'http://www.presseportal.de/rss/celebrities.rss2'),
(u'Chemie',u'http://www.presseportal.de/rss/chemie.rss2'),
(u'Comuter',u'http://www.presseportal.de/rss/computer.rss2'),
(u'Energie',u'http://www.presseportal.de/rss/energie.rss2'),
(u'Fernsehn',u'http://www.presseportal.de/rss/fernsehn.rss2'),
(u'Fussball',u'http://www.presseportal.de/rss/fussball.rss2'),
(u'Gesundheit',u'http://www.presseportal.de/rss/gesundheit.rss2'),
(u'Handel',u'http://www.presseportal.de/rss/handel.rss2'),
(u'Immobilien',u'http://www.presseportal.de/rss/immobilien.rss2'),
(u'Kinder',u'http://www.presseportal.de/rss/kinder.rss2'),
(u'Lebensmittel',u'http://www.presseportal.de/rss/lebensmittel.rss2'),
(u'Livestyle',u'http://www.presseportal.de/rss/livestyle.rss2'),
(u'Logistik',u'http://www.presseportal.de/rss/logistik.rss2'),
(u'Maschinenbau',u'http://www.presseportal.de/rss/maschinenbau.rss2'),
(u'Medien',u'http://www.presseportal.de/rss/medien.rss2'),
(u'Motorsport',u'http://www.presseportal.de/rss/motorsport.rss2'),
(u'Ratgeber',u'http://www.presseportal.de/rss/ratgeber.rss2'),
(u'Recht',u'http://www.presseportal.de/rss/recht.rss2'),
(u'Soziales',u'http://www.presseportal.de/rss/soziales.rss2'),
(u'Telekommunikation',u'http://www.presseportal.de/rss/telekommunikation.rss2'),
(u'Touristik',u'http://www.presseportal.de/rss/touristik.rss2'),
(u'Umwelt',u'http://www.presseportal.de/rss/umwelt.rss2'),
(u'Unterhaltung',u'http://www.presseportal.de/rss/unterhaltung.rss2'),
(u'Versicherung',u'http://www.presseportal.de/rss/versicherung.rss2'),
(u'Wissenschaft',u'http://www.presseportal.de/rss/wissenschaft.rss2'),
#Themen
(u'Polizei (gesamt)',u'http://www.presseportal.de/rss/polizei.rss2'),
(u'Bilder',u'http://www.presseportal.de/rss/98,306.rss2'),
(u'Video',u'http://www.presseportal.de/rss/videocast.rss2'),
(u'Audio',u'http://www.presseportal.de/rss/podcast.rss2'),
(u'Investor Relations',u'http://www.presseportal.de/rss/ir.rss2'),
(u'Presseschau',u'http://www.presseportal.de/rss/1043.rss2'),
#Polizeipresse - Kommunal!
(u'Polizei BW',u'http://www.presseportal.de/rss/polizei/laender/1.rss2'),
(u'Polizei BY',u'http://www.presseportal.de/rss/polizei/laender/2.rss2'),
(u'Polizei BE',u'http://www.presseportal.de/rss/polizei/laender/3.rss2'),
(u'Polizei HB',u'http://www.presseportal.de/rss/polizei/laender/4.rss2'),
(u'Polizei HH',u'http://www.presseportal.de/rss/polizei/laender/5.rss2'),
(u'Polizei HE',u'http://www.presseportal.de/rss/polizei/laender/6.rss2'),
(u'Polizei MV',u'http://www.presseportal.de/rss/polizei/laender/7.rss2'),
(u'Polizei NI',u'http://www.presseportal.de/rss/polizei/laender/8.rss2'),
(u'Polizei NW',u'http://www.presseportal.de/rss/polizei/laender/9.rss2'),
(u'Polizei RP',u'http://www.presseportal.de/rss/polizei/laender/10.rss2'),
(u'Polizei SH',u'http://www.presseportal.de/rss/polizei/laender/11.rss2'),
(u'Polizei BUND',u'http://www.presseportal.de/rss/polizei/laender/12.rss2'),
(u'Polizei SL',u'http://www.presseportal.de/rss/polizei/laender/13.rss2'),
(u'Polizei SA',u'http://www.presseportal.de/rss/polizei/laender/14.rss2'),
(u'Polizei TH',u'http://www.presseportal.de/rss/polizei/laender/15.rss2'),
(u'Polizei ST',u'http://www.presseportal.de/rss/polizei/laender/16.rss2'),
]
def print_version(self, url):
# Separate the last part of the Url : http://www.presseportal.de/pm/70776/3120111
# tuple it in partitions (from the right) at the edges of
# the '/' symbol : ('http://www.presseportal.de/pm/70776','/','3120111')
# take the last of this tuples : '3120111'
# and split this at the symbol '.' (if there) : ('3120111',)
# from this take the first tuple. '3120111'
side = (url.rpartition('/')[-1]).rsplit('.',1)[0]
# print 'ConvertPrintURL from : ' + url + '/n to ' + side
printurl='http://www.presseportal.de/print/' + side + '-print.html'
return printurl
________________ end of Recipe _________________________
it also attached as .zip file
Last edited by VoHegg; 09-12-2015 at 11:43 AM.
Reason: put in the source
|