| 1 |
#!/usr/bin/env python |
| 2 |
|
| 3 |
__license__ = 'GPL v3' |
| 4 |
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>' |
| 5 |
''' |
| 6 |
usatoday.com |
| 7 |
''' |
| 8 |
|
| 9 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 10 |
|
| 11 |
|
| 12 |
def classes(classes): |
| 13 |
q = frozenset(classes.split(' ')) |
| 14 |
return dict(attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)}) |
| 15 |
|
| 16 |
|
| 17 |
def absurl(url): |
| 18 |
if url.startswith('/'): |
| 19 |
return 'https://www.usatoday.com' + url |
| 20 |
|
| 21 |
|
| 22 |
class USAToday(BasicNewsRecipe): |
| 23 |
title = 'USA Today' |
| 24 |
__author__ = 'Kovid Goyal, unkn0wn' |
| 25 |
description = 'newspaper' |
| 26 |
encoding = 'utf-8' |
| 27 |
language = 'en_US' |
| 28 |
|
| 29 |
use_embedded_content = False |
| 30 |
timefmt = ' [%d %b %Y]' |
| 31 |
max_articles_per_feed = 25 |
| 32 |
no_stylesheets = True |
| 33 |
|
| 34 |
keep_only_tags = [ |
| 35 |
classes('gnt_ar_hl gnt_ar_by gnt_ar_b topper__inner in-depth-content'), |
| 36 |
] |
| 37 |
|
| 38 |
remove_tags = [ |
| 39 |
classes('component--pullquote__icon gnt_ss gnt_em_vp__tp'), |
| 40 |
dict(attrs={'aria-label': ['advertisement']}), |
| 41 |
dict(name=['link', 'media-gallery', 'button']), |
| 42 |
] |
| 43 |
|
| 44 |
extra_css = ''' |
| 45 |
h1, h2 { |
| 46 |
font-size:xx-large; |
| 47 |
font-family:Arial,Helvetica,sans-serif;} |
| 48 |
#post-attributes, .info, |
| 49 |
.clear { |
| 50 |
font-size:xx-small; color:#4D4D4D; |
| 51 |
font-family:Arial,Helvetica,sans-serif; |
| 52 |
} |
| 53 |
#post-body, |
| 54 |
#content { |
| 55 |
font-size:medium; |
| 56 |
font-family:Arial,Helvetica,sans-serif; |
| 57 |
} |
| 58 |
.gnt_em_img_ccw__cap { |
| 59 |
font-size:small; |
| 60 |
text-align:center; |
| 61 |
} |
| 62 |
''' |
| 63 |
|
| 64 |
ignore_duplicate_articles = {'title', 'url'} |
| 65 |
resolve_internal_links = True |
| 66 |
remove_empty_feeds = True |
| 67 |
|
| 68 |
def parse_index(self): |
| 69 |
index = 'https://www.usatoday.com/' |
| 70 |
sections = [ |
| 71 |
'news', |
| 72 |
'opinion', |
| 73 |
'tech', |
| 74 |
'entertainment', |
| 75 |
'money', |
| 76 |
'sports', |
| 77 |
'travel', |
| 78 |
'life', |
| 79 |
'investigations', |
| 80 |
] |
| 81 |
feeds = [] |
| 82 |
soup = self.index_to_soup(index) |
| 83 |
for sec in sections: |
| 84 |
section = sec.capitalize() |
| 85 |
self.log(section) |
| 86 |
articles = [] |
| 87 |
for a in soup.findAll('a', attrs={'href': lambda x: x and x.startswith('/story/' + sec + '/')}): |
| 88 |
url = absurl(a['href'].split('?')[0]) |
| 89 |
if url == index + '/story/' + sec + '/': |
| 90 |
continue |
| 91 |
title = self.tag_to_string(a) |
| 92 |
self.log('\t', title, '\n\t\t', url) |
| 93 |
articles.append({'title': title, 'url': url}) |
| 94 |
if articles: |
| 95 |
feeds.append((section, articles)) |
| 96 |
return feeds |
| 97 |
|
| 98 |
def preprocess_html(self, soup): |
| 99 |
for img in soup.findAll('img', src=True): |
| 100 |
img['src'] = 'https://www.usatoday.com' + img['src'] |
| 101 |
for div in soup.findAll(attrs={'data-c-caption': True}): |
| 102 |
div.string = div['data-c-caption'] |
| 103 |
return soup |