| 1 |
#!/usr/bin/env python |
| 2 |
# vim:fileencoding=utf-8 |
| 3 |
""" |
| 4 |
Recipe for Die Tagespost |
| 5 |
""" |
| 6 |
|
| 7 |
from calibre.web.feeds.news import BasicNewsRecipe, classes |
| 8 |
|
| 9 |
|
| 10 |
class Tagespost(BasicNewsRecipe): |
| 11 |
title = 'Tagespost' |
| 12 |
language = 'de' |
| 13 |
__author__ = 'unkn0wn' |
| 14 |
description = ( |
| 15 |
'Die Tagespost trägt den Untertitel Katholische Wochenzeitung für Politik, Gesellschaft' |
| 16 |
' und Kultur und ist eine überregionale, wöchentlich im Johann Wilhelm Naumann Verlag ' |
| 17 |
'in Würzburg erscheinende Zeitung.' |
| 18 |
) |
| 19 |
oldest_article = 2 |
| 20 |
encoding = 'utf-8' |
| 21 |
ignore_duplicate_articles = {'url'} |
| 22 |
masthead_url = 'https://www.die-tagespost.de/design2020/images/tp_logo_small.webp' |
| 23 |
remove_javascript = True |
| 24 |
keep_only_tags = [classes('topline headline description datetime autor-name article_main')] |
| 25 |
remove_tags = [ |
| 26 |
dict(name=['source', 'svg', 'aside', 'clearfix', 'footer']), |
| 27 |
classes('content-box extras jwnIconTeaser behindWall'), |
| 28 |
] |
| 29 |
remove_tags_after = [classes('abbinder-text')] |
| 30 |
no_stylesheets = True |
| 31 |
use_embedded_content = False |
| 32 |
remove_attributes = ['style', 'height', 'width'] |
| 33 |
recipe_specific_options = { |
| 34 |
'days': { |
| 35 |
'short': 'Oldest article to download from this news source. In days ', |
| 36 |
'long': 'For example, 0.5, gives you articles from the past 12 hours', |
| 37 |
'default': str(oldest_article), |
| 38 |
}, |
| 39 |
} |
| 40 |
|
| 41 |
def __init__(self, *args, **kwargs): |
| 42 |
BasicNewsRecipe.__init__(self, *args, **kwargs) |
| 43 |
d = self.recipe_specific_options.get('days') |
| 44 |
if d and isinstance(d, str): |
| 45 |
self.oldest_article = float(d) |
| 46 |
|
| 47 |
def get_cover_url(self): |
| 48 |
soup = self.index_to_soup('https://www.ikiosk.de/shop/epaper/die-tagespost.html') |
| 49 |
return soup.find('a', attrs={'class': 'preview-cover'})['href'] |
| 50 |
|
| 51 |
feeds = [ |
| 52 |
( |
| 53 |
'Tagespost', |
| 54 |
'https://www.die-tagespost.de/storage/rss/rss/die-tagespost-komplett.xml', |
| 55 |
), |
| 56 |
] |
| 57 |
extra_css = ''' |
| 58 |
.abbinder-text, |
| 59 |
.calibre-nuked-tag-figcaption, |
| 60 |
.datetime, |
| 61 |
.autor-name, |
| 62 |
.topline { |
| 63 |
font-size:small; |
| 64 |
} |
| 65 |
.description { font-style: italic; } |
| 66 |
''' |
| 67 |
|
| 68 |
def preprocess_html(self, soup): |
| 69 |
desc = soup.find(**classes('description')) |
| 70 |
if desc: |
| 71 |
desc.name = 'p' |
| 72 |
for h2 in soup.findAll(['h2', 'h3']): |
| 73 |
h2.name = 'h4' |
| 74 |
return soup |