Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

improvements to atlantic recipe

Browse Source 
removed some things that were uglifying it. added imgs in addition to lead. smaller captions to distinguish from body. right-aligned credits
This commit is contained in:
jfhutson 2017-02-17 22:08:44 -06:00 committed by GitHub
parent 7cfda558ed
commit a896d661f1
1 changed files with 14 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
recipes/atlantic.recipe
View File

@ -26,19 +26,25 @@ class TheAtlantic(BasicNewsRecipe):
keep_only_tags = [
classes(
'article-header article-body article-magazine article-cover-content lead-img'),
]
'article-header article-body article-magazine article-cover-content article-cover-extra lead-img '),
{'name': ['img']},
]
remove_tags = [
{'name': ['meta', 'link', 'noscript']},
{'attrs': {'class': ['offset-wrapper', 'ad-boxfeatures-wrapper']}},
classes( 'social-kit-top letter-writer-info callout secondary-byline embed-wrapper offset-wrapper boxtop-most-popular'),
{'name': ['meta', 'link', 'noscript', 'aside', 'h3']},
{'attrs': {'class': ['offset-wrapper', 'boxtop-most-popular']}},
{'attrs': {'class': lambda x: x and 'article-tools' in x}},
{'src': lambda x: x and 'spotxchange.com' in x},
]
remove_tags_after = classes('article-body')
no_stylesheets = True
remove_attributes = ['style']
extra_css = '''
.credit { text-align: right; font-size: 75%; display: block }
.figcaption { font-size: 75% }
.caption { font-size: 75% }
.lead-img { display: block }'''
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
br.set_cookie('inEuropeanUnion', '0', '.theatlantic.com')
@ -51,8 +57,8 @@ class TheAtlantic(BasicNewsRecipe):
return url + '?single_page=true'
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-src': True}):
img['src'] = img['data-src']
for img in soup.findAll('img', attrs={'data-srcset': True}):
img['src'] = img['data-srcset']
return soup
def parse_index(self):