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

Update CNN recipe

Browse Source
This commit is contained in:
Kovid Goyal 2023-02-07 16:49:34 +05:30
parent 2053856864
commit 902941adcc
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 10 additions and 39 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
recipes/cnn.recipe
View File

@ -4,8 +4,7 @@ __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
Profile to download CNN
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.web.feeds.news import BasicNewsRecipe, classes
class CNN(BasicNewsRecipe):
@ -18,38 +17,14 @@ class CNN(BasicNewsRecipe):
no_stylesheets = True
use_embedded_content = False
oldest_article = 15
oldest_article = 2
ignore_duplicate_articles = {'url'}
# recursions = 1
# match_regexps = [r'http://sportsillustrated.cnn.com/.*/[1-9].html']
max_articles_per_feed = 25
compress_news_images = True
compress_news_images_auto_size = 12
extra_css = '''
h1 {font-size:xx-large; font-family:Arial,Helvetica,sans-serif;}
.cnn_story_author, .cnn_stryathrtmp {font-size:xx-small; color:#4D4D4D; font-family:Arial,Helvetica,sans-serif;}
.cnn_strycaptiontxt, .cnnArticleGalleryPhotoContainer {font-size:xx-small; color:#4D4D4D; font-family:Arial,Helvetica,sans-serif;}
.cnn_strycbftrtxt, .cnnEditorialNote {font-size:xx-small; color:#4D4D4D; font-family:Arial,Helvetica,sans-serif;}
.cnn_strycntntlft {font-size:medium; font-family:Arial,Helvetica,sans-serif;}
'''
preprocess_regexps = [
(re.compile(r'<!--\[if.*if\]-->', re.DOTALL), lambda m: ''),
(re.compile(r'<script.*?</script>', re.DOTALL), lambda m: ''),
(re.compile(r'<style.*?</style>', re.DOTALL), lambda m: ''),
]
remove_attributes = ['style', 'height', 'width']
keep_only_tags = [
dict(id=['body-text', 'storycontent']),
dict(attrs={'class': ['pg-headline', 'metadata']}),
]
remove_tags = [
dict(attrs={'class': lambda x: x and bool({
'video__end-slate', 'owl-filmstrip', 'el-embed-instagram',
}.intersection(set(x.split())))}),
classes('headline__wrapper headline__sub-container article__main'),
]
remove_tags = [classes('video-inline_carousel')]
feeds = [
('Top News', 'http://rss.cnn.com/rss/cnn_topstories.rss'),
@ -68,15 +43,6 @@ class CNN(BasicNewsRecipe):
('Most Popular', 'http://rss.cnn.com/rss/cnn_mostpopular.rss')
]
def preprocess_html(self, soup):
body = soup.find('body')
for h2 in soup.findAll(attrs={'class': 'pg-headline'}):
h2.extract()
body.insert(0, h2)
for img in soup.findAll('img', attrs={'data-src-medium': True}):
img['src'] = img['data-src-medium']
return soup
def get_article_url(self, article):
ans = BasicNewsRecipe.get_article_url(self, article)
ans = ans.partition('?')[0]
@ -93,3 +59,8 @@ class CNN(BasicNewsRecipe):
self.log("\nCover unavailable")
masthead = None
return masthead
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'src':lambda x: x and x.endswith('.svg')}):
img.extract()
return soup