Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 10:14:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Handelsblatt

Browse Source
This commit is contained in:
Aimylios 2018-06-17 11:48:31 +02:00
parent 472fc44c70
commit 4d1ecd0986
1 changed files with 9 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
recipes/handelsblatt.recipe
View File

@ -22,7 +22,7 @@ class Handelsblatt(BasicNewsRecipe):
language = 'de'
oldest_article = 2
max_articles_per_feed = 30
max_articles_per_feed = 15
simultaneous_downloads = 10
no_stylesheets = True
remove_javascript = True
@ -58,11 +58,15 @@ class Handelsblatt(BasicNewsRecipe):
dict(name='aside', attrs={'class': ['vhb-article-element vhb-left',
'vhb-article-element vhb-left vhb-teasergallery',
'vhb-article-element vhb-left vhb-shorttexts']}),
dict(name='aside', attrs={'class': re.compile('vhb-club-events')}),
dict(name='article', attrs={'class': ['vhb-imagegallery vhb-teaser',
'vhb-teaser vhb-type-video']}),
dict(name='small', attrs={'class': ['vhb-credit']}),
dict(name='div', attrs={'class': ['white_content', 'fb-post',
'opinary-widget-wrapper']}),
'opinary-widget-wrapper',
'vhb-hollow-area vhb-hollow-area--col-1']}),
dict(name='div', attrs={'class': re.compile('vhb-imagegallery')}),
dict(name='div', attrs={'id': ['highcharts_infografik']}),
dict(name='div', attrs={'id': re.compile('dax-sentiment')}),
dict(name=['div', 'section'], attrs={'class': re.compile('slider')}),
dict(name='a', attrs={'class': ['twitter-follow-button']}),
@ -141,9 +145,9 @@ class Handelsblatt(BasicNewsRecipe):
# make sure that all figure captions (including the source) are shown
# without linebreaks by using the alternative text given within <img/>
# instead of the original text (which is oddly formatted)
for fig in soup.findAll('figure', {'class': 'vhb-image'}):
fig.find('div', {'class': 'vhb-caption'}
).replaceWith(fig.find('img')['alt'])
for fig in soup.findAll('figcaption', {'class': 'vhb-inline-picture'}):
cap = fig.find('img')['alt']
fig.find('div', {'class': 'vhb-caption'}).replaceWith(cap)
# clean up remainders of embedded content
for div in soup.findAll('div', {'style': True}):
if len(div.attrs) == 1: