Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-06-23 15:30:45 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Wirtschaft Woche

Browse Source
This commit is contained in:
Kovid Goyal 2022-08-08 07:37:11 +05:30
parent 718d5fb94b
commit a398c0ece2
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 25 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
recipes/wirtscafts_woche.recipe
View File

@ -3,8 +3,8 @@ __copyright__ = '2013, Armin Geller'
##
# Written: May 2013 (new coding)
# Version: 5.0
# Last update: 2022-08-05
# Version: 5.1
# Last update: 2022-08-07
##
##
'''
@ -53,16 +53,26 @@ class WirtschaftsWocheOnline(BasicNewsRecipe):
]}),
dict(
name='div',
attrs={'class': ['o-article__element', 'o-article__content c-richText']}
)
attrs={
'class': [
'o-article__element',
'o-article__content c-richText',
]
}
),
dict(name='div', attrs={'id': [
'biga_wrapper',
]})
]
remove_tags = [
dict(name='source'),
dict(
name='div',
attrs={
'class': [
'c-list', 'o-article__element u-margin-xxl u-font-s-md',
'c-list',
'o-article__element u-margin-xxl u-font-s-md',
'c-advertisment__fullWidth c-advertisment--P4_desktop',
'c-advertisment__fullWidth c-advertisment--P3_mobile',
'c-advertisment__fullWidth c-advertisment--P2_mobile',
@ -71,9 +81,10 @@ class WirtschaftsWocheOnline(BasicNewsRecipe):
'c-teaser c-teaser-inline isPremiumTeaser',
'c-teaser c-teaser-inline c-teaser-inline--column',
'c-teaser c-teaser-inline c-teaser-inline--xl isPremiumTeaser',
'u-flex', 'o-article__content-element u-margin-xxl',
'o-teaser-list js-tt o-artbox o-artbox--articleboxplus',
'o-article__content-element u-margin-xxl',
'o-article__content-element u-margin-xxl ajaxify',
'o-article__element o-article__element-block'
'o-article__element o-article__element-block',
]
}
)
@ -91,13 +102,17 @@ class WirtschaftsWocheOnline(BasicNewsRecipe):
]
def image_url_processor(self, baseurl, url):
# print('****** AGE Baseurl *****',baseurl)
# print('****** AGE url *****',url)
if url.startswith('/images/'):
# print('****** AGE url /images/ *****','https://www.wiwo.de' + url)
return 'https://www.wiwo.de' + url
return url
def preprocess_raw_html(self, raw, url):
# Slideshow image source need some help to find all images
soup = self.index_to_soup(raw)
for img in soup.findAll('img', attrs={'data-lazy': True}):
img['src'] = 'https://www.wiwo.de' + img['data-lazy']
return str(soup)
def print_version(self, url):
main, sep, rest = url.rpartition('.')
return main + '-all' + sep + rest