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

Merge branch 'master' of https://github.com/unkn0w7n/calibre

Browse Source
This commit is contained in:
Kovid Goyal 2025-04-10 07:35:11 +05:30
commit a48e0e4157
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 39 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
recipes/scmp.recipe
View File

@ -24,7 +24,12 @@ def E(parent, name, text='', **attrs):
def process_node(node, html_parent):
ntype = node.get('type')
if ntype not in {'track-viewed-percentage', 'inline-ad-slot', 'inline-widget', 'text'}:
if ntype not in {
'track-viewed-percentage',
'inline-ad-slot',
'inline-widget',
'text',
}:
c = html_parent.makeelement(ntype)
if ntype != 'p':
c.attrib.update({k: v or '' for k, v in node.get('attribs', {}).items()})
@ -54,12 +59,23 @@ def load_article_from_json(raw, root):
for child in tuple(body):
body.remove(child)
article = E(body, 'article')
E(article, 'div', replace_entities(data['firstTopic']['name']), style='color: gray; font-size:small; font-weight:bold;')
E(
article,
'div',
replace_entities(data['firstTopic']['name']),
style='color: gray; font-size:small; font-weight:bold;',
)
E(article, 'h1', replace_entities(data['headline']))
# E(article, 'p', replace_entities(data['subHeadline']['text']), style='font-style: italic; color:#202020;')
for subh in data['subHeadline']['json']:
process_node(subh, article)
auth = ts_date(data['publishedDate']) + ' | ' + str(data.get('readingTime', '')) + ' min read | ' + ', '.join([a['name'] for a in data['authors']])
auth = (
ts_date(data['publishedDate'])
+ ' | '
+ str(data.get('readingTime', ''))
+ ' min read | '
+ ', '.join([a['name'] for a in data['authors']])
)
E(article, 'p', auth, style='color: #202020; font-size:small;')
main_image_url = sub_img = ''
for l in data['images']:
@ -102,24 +118,23 @@ class SCMP(BasicNewsRecipe):
def get_cover_url(self):
soup = self.index_to_soup('https://www.frontpages.com/south-china-morning-post/')
return 'https://www.frontpages.com' + soup.find('img', attrs={'id':'giornale-img'})['src']
return (
'https://www.frontpages.com'
+ soup.find('img', attrs={'id': 'giornale-img'})['src']
)
recipe_specific_options = {
'days': {
'short': 'Oldest article to download from this news source. In days ',
'long': 'For example, 0.5, gives you articles from the past 12 hours',
'default': str(oldest_article)
},
'comp': {
'short': 'Compress News Images?',
'long': 'enter yes',
'default': 'no'
'default': str(oldest_article),
},
'comp': {'short': 'Compress News Images?', 'long': 'enter yes', 'default': 'no'},
'rev': {
'short': 'Reverse the order of articles in each feed?',
'long': 'enter yes',
'default': 'no'
}
'default': 'no',
},
}
def __init__(self, *args, **kwargs):
@ -162,7 +177,7 @@ class SCMP(BasicNewsRecipe):
('Sport', 'https://www.scmp.com/rss/95/feed'),
('Post Mag', 'https://www.scmp.com/rss/71/feed'),
('Style', 'https://www.scmp.com/rss/72/feed'),
('News', 'https://www.scmp.com/rss/91/feed')
('News', 'https://www.scmp.com/rss/91/feed'),
]
def print_version(self, url):
@ -188,11 +203,17 @@ class SCMP(BasicNewsRecipe):
def preprocess_html(self, soup):
from urllib.parse import urlparse
for img in soup.findAll('img', attrs={'src': True}):
y = 'https://img.i-scmp.com/cdn-cgi/image/fit=contain,width=768,format=auto'
img['src'] = y + urlparse(img['src']).path
for img in soup.findAll('img', attrs={'title': True}):
div = soup.new_tag('div', attrs={'style':'text-align:center; font-size:small;'})
div = soup.new_tag(
'div', attrs={'style': 'text-align:center; font-size:small;'}
)
div.string = img.get('title', '')
if img.find_parent('div'):
img.find_parent('div').append(div)
else:
img.append(div)
return soup