mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-11-13 01:57:00 -05:00
108 lines
3.3 KiB
Python
108 lines
3.3 KiB
Python
#!/usr/bin/env python
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
|
|
'''
|
|
usatoday.com
|
|
'''
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from calibre.ptempfile import PersistentTemporaryFile
|
|
|
|
|
|
def classes(classes):
|
|
q = frozenset(classes.split(' '))
|
|
return dict(attrs={
|
|
'class': lambda x: x and frozenset(x.split()).intersection(q)})
|
|
|
|
|
|
class USAToday(BasicNewsRecipe):
|
|
|
|
title = 'USA Today'
|
|
__author__ = 'Kovid Goyal, unkn0wn'
|
|
description = 'newspaper'
|
|
encoding = 'utf-8'
|
|
language = 'en'
|
|
|
|
use_embedded_content = False
|
|
timefmt = ' [%d %b %Y]'
|
|
max_articles_per_feed = 25
|
|
no_stylesheets = True
|
|
remove_empty_feeds = True
|
|
|
|
keep_only_tags = [
|
|
classes('gnt_ar_hl gnt_ar_by gnt_ar_b topper__inner in-depth-content'),
|
|
]
|
|
|
|
remove_tags = [
|
|
classes('component--pullquote__icon gnt_ss gnt_em_vp__tp'),
|
|
dict(attrs={'aria-label': ['advertisement']}),
|
|
dict(name=['link', 'media-gallery', 'button']),
|
|
]
|
|
|
|
extra_css = '''
|
|
h1, h2 {
|
|
font-size:xx-large;
|
|
font-family:Arial,Helvetica,sans-serif;}
|
|
#post-attributes, .info,
|
|
.clear {
|
|
font-size:xx-small; color:#4D4D4D;
|
|
font-family:Arial,Helvetica,sans-serif;
|
|
}
|
|
#post-body,
|
|
#content {
|
|
font-size:medium;
|
|
font-family:Arial,Helvetica,sans-serif;
|
|
}
|
|
.gnt_em_img_ccw__cap {
|
|
font-size:small;
|
|
text-align:center;
|
|
}
|
|
'''
|
|
|
|
ignore_duplicate_articles = {'title'}
|
|
resolve_internal_links = True
|
|
remove_empty_feeds = True
|
|
|
|
articles_are_obfuscated = True
|
|
|
|
def get_obfuscated_article(self, url):
|
|
br = self.get_browser()
|
|
try:
|
|
br.open(url)
|
|
except Exception as e:
|
|
url = e.hdrs.get('location')
|
|
soup = self.index_to_soup(url)
|
|
link = soup.find('a', href=True)
|
|
skip_sections =[ # add sections you want to skip
|
|
'/video/', '/videos/', '/media/', 'podcast-'
|
|
]
|
|
if any(x in link['href'] for x in skip_sections):
|
|
self.log('Aborting Article ', link['href'])
|
|
self.abort_article('skipping video links')
|
|
|
|
self.log('Downloading ', link['href'])
|
|
html = br.open(link['href']).read()
|
|
pt = PersistentTemporaryFile('.html')
|
|
pt.write(html)
|
|
pt.close()
|
|
return pt.name
|
|
|
|
feeds = []
|
|
|
|
sections = [
|
|
'news', 'nation', 'politics', 'opinion', 'tech', 'entertainment', 'money', 'sports', 'travel', 'life', 'investigations',
|
|
]
|
|
|
|
for sec in sections:
|
|
a = 'https://news.google.com/rss/search?q=when:27h+allinurl:https%3A%2F%2Fwww.usatoday.com%2Fstory{}&hl=en-US&gl=US&ceid=US:en'
|
|
feeds.append((sec.capitalize(), a.format('%2F' + sec + '%2F')))
|
|
# feeds.append(('Others', a.format('')))
|
|
|
|
def preprocess_html(self, soup):
|
|
for img in soup.findAll('img', src=True):
|
|
img['src'] = 'https://www.usatoday.com' + img['src']
|
|
for div in soup.findAll(attrs={'data-c-caption':True}):
|
|
div.string = div['data-c-caption']
|
|
return soup
|