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 BBC

Browse Source
This commit is contained in:
unkn0w7n 2025-05-13 18:41:13 +05:30
parent 3ed06bcbac
commit 51f382c0d3
2 changed files with 25 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
recipes/bbc.recipe
View File

@ -136,7 +136,6 @@ class BBCNews(BasicNewsRecipe):
# Select / de-select the feeds you want in your ebook.
feeds = [
('News Home', 'https://feeds.bbci.co.uk/news/rss.xml'),
('UK', 'https://feeds.bbci.co.uk/news/uk/rss.xml'),
('World', 'https://feeds.bbci.co.uk/news/world/rss.xml'),
# ("England", "https://feeds.bbci.co.uk/news/england/rss.xml"),
@ -205,6 +204,7 @@ class BBCNews(BasicNewsRecipe):
# ("Canolbarth", "https://feeds.bbci.co.uk/newyddion/canolbarth/rss.xml"),
# ("De-Ddwyrain", "https://feeds.bbci.co.uk/newyddion/de-ddwyrain/rss.xml"),
# ("De-Orllewin", "https://feeds.bbci.co.uk/newyddion/de-orllewin/rss.xml"),
('News', 'https://feeds.bbci.co.uk/news/rss.xml'),
]
# **** SELECT YOUR USER PREFERENCES ****
@ -309,18 +309,27 @@ class BBCNews(BasicNewsRecipe):
remove_tags = [
dict(name=['button', 'svg', 'iframe']),
dict(attrs={'data-component': ['ad-slot', 'tags', 'links-block']})
dict(attrs={'data-component': ['ad-slot', 'tags', 'links-block', 'metadata-block', 'topic-list']})
]
remove_attributes = ['style', 'height', 'width']
no_stylesheets = True
extra_css = '''
figure, [data-component="byline-block"], [data-component="caption-block"], [data-component="image-block"] { font-size:small; }
figure,
[data-component="byline-block"],
[data-component="caption-block"],
[data-component="image-block"] {
font-size:small;
}
'''
cover_url = 'https://upload.wikimedia.org/wikipedia/commons/thumb/6/62/BBC_News_2019.svg/768px-BBC_News_2019.svg.png'
masthead_url = 'https://upload.wikimedia.org/wikipedia/commons/4/41/BBC_Logo_2021.svg'
def preprocess_html(self, soup):
for placeholder in soup.findAll('img', attrs={'src': lambda x: x and x.endswith('placeholder.png')}):
placeholder.decompose()
for img in soup.findAll('img'):
img.attrs = {'src': img.get('src', '')}
for h2 in soup.findAll(['h2', 'h3']):
h2.name = 'h4'
return soup

17
recipes/bbc_fast.recipe
View File

@ -158,20 +158,29 @@ class BBC(BasicNewsRecipe):
remove_tags = [
dict(name=['button', 'svg', 'iframe']),
dict(attrs={'data-component': ['ad-slot', 'tags', 'links-block']})
dict(attrs={'data-component': ['ad-slot', 'tags', 'links-block', 'metadata-block', 'topic-list']})
]
remove_attributes = ['style', 'height', 'width']
no_stylesheets = True
extra_css = '''
figure, [data-component="byline-block"], [data-component="caption-block"], [data-component="image-block"] { font-size:small; }
figure,
[data-component="byline-block"],
[data-component="caption-block"],
[data-component="image-block"] {
font-size:small;
}
'''
cover_url = 'https://upload.wikimedia.org/wikipedia/commons/thumb/6/62/BBC_News_2019.svg/768px-BBC_News_2019.svg.png'
masthead_url = 'https://upload.wikimedia.org/wikipedia/commons/4/41/BBC_Logo_2021.svg'
def preprocess_html(self, soup):
for placeholder in soup.findAll('img', attrs={'src': lambda x: x and x.endswith('placeholder.png')}):
placeholder.decompose()
for img in soup.findAll('img'):
img.attrs = {'src': img.get('src', '')}
for h2 in soup.findAll(['h2', 'h3']):
h2.name = 'h4'
return soup
recipe_specific_options = {
@ -189,7 +198,6 @@ class BBC(BasicNewsRecipe):
self.oldest_article = float(d)
feeds = [
('Top Stories', 'https://feeds.bbci.co.uk/news/rss.xml'),
('Science/Environment',
'https://feeds.bbci.co.uk/news/science_and_environment/rss.xml'),
('Technology', 'https://feeds.bbci.co.uk/news/technology/rss.xml'),
@ -205,7 +213,8 @@ class BBC(BasicNewsRecipe):
('South Asia', 'https://feeds.bbci.co.uk/news/world/south_asia/rss.xml'),
('England', 'https://feeds.bbci.co.uk/news/england/rss.xml'),
('Asia-Pacific', 'https://feeds.bbci.co.uk/news/world/asia_pacific/rss.xml'),
('Africa', 'https://feeds.bbci.co.uk/news/world/africa/rss.xml')
('Africa', 'https://feeds.bbci.co.uk/news/world/africa/rss.xml'),
('Top Stories', 'https://feeds.bbci.co.uk/news/rss.xml'),
]
def preprocess_raw_html(self, raw_html, url):