forked from kovidgoyal/calibre
-
Notifications
You must be signed in to change notification settings - Fork 0
/
atlantic.recipe
168 lines (152 loc) · 6.95 KB
/
atlantic.recipe
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
#!/usr/bin/env python2
from __future__ import unicode_literals
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
'''
Recipe for web and magazine versions of the The Atlantic
'''
from calibre.web.feeds.news import BasicNewsRecipe
web_version = False
def classes(classes):
q = frozenset(classes.split(' '))
return dict(
attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)}
)
class TheAtlantic(BasicNewsRecipe):
if web_version:
title = 'TheAtlantic.com'
description = 'News and editorial about politics, culture, entertainment, tech, etc. Contains many articles not seen in The Atlantic magazine'
else:
title = 'The Atlantic'
description = 'Current affairs and politics focussed on the US'
INDEX = 'http://www.theatlantic.com/magazine/'
__author__ = 'Kovid Goyal'
language = 'en'
encoding = 'utf-8'
keep_only_tags = [
dict(id='rubric'),
dict(itemprop=['headline', 'image']),
classes(
'article-header c-article-meta lead-img article-cover-extra article-body article-magazine article-cover-content'
),
dict(itemprop='articleBody'),
]
remove_tags = [
classes(
'c-ad social-kit-top letter-writer-info callout secondary-byline embed-wrapper offset-wrapper boxtop-most-popular'
),
{
'name': ['meta', 'link', 'noscript', 'aside', 'h3']
},
{
'attrs': {
'class': ['offset-wrapper', 'boxtop-most-popular']
}
},
{
'attrs': {
'class': lambda x: x and 'article-tools' in x
}
},
{
'src': lambda x: x and 'spotxchange.com' in x
},
]
remove_tags_after = classes('article-body')
no_stylesheets = True
remove_attributes = ['style']
extra_css = '''
.credit { text-align: right; font-size: 75%; display: block }
.figcaption { font-size: 75% }
.caption { font-size: 75% }
.lead-img { display: block }
p.dropcap:first-letter {
float: left; text-transform: uppercase; font-weight: bold; font-size: 5.55em; line-height: 0.83;
margin: 0; padding-right: 7px; margin-bottom: -2px; text-align: center;
}
'''
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
br.set_cookie('inEuropeanUnion', '0', '.theatlantic.com')
return br
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-srcset': True}):
img['src'] = img['data-srcset'].split()[0]
return soup
def print_version(self, url):
ans = url.partition('?')[0] + '?single_page=true'
if '/video/' in ans:
ans = None
return ans
if web_version:
use_embedded_content = False
feeds = [
('The Atlantic', 'http://www.theatlantic.com/feed/all/'),
('Best of The Atlantic', 'http://www.theatlantic.com/feed/best-of/'),
('Politics | The Atlantic', 'http://www.theatlantic.com/feed/channel/politics/'),
('Business | The Atlantic', 'http://www.theatlantic.com/feed/channel/business/'),
('Culture | The Atlantic', 'http://www.theatlantic.com/feed/channel/entertainment/'),
('Global | The Atlantic', 'http://www.theatlantic.com/feed/channel/international/'),
('Technology | The Atlantic', 'http://www.theatlantic.com/feed/channel/technology/'),
('U.S. | The Atlantic', 'http://www.theatlantic.com/feed/channel/national/'),
('Health | The Atlantic', 'http://www.theatlantic.com/feed/channel/health/'),
('Video | The Atlantic', 'http://www.theatlantic.com/feed/channel/video/'),
('Sexes | The Atlantic', 'http://www.theatlantic.com/feed/channel/sexes/'),
('Education | The Atlantic', 'http://www.theatlantic.com/feed/channel/education/'),
('Science | The Atlantic', 'http://www.theatlantic.com/feed/channel/science/'),
('News | The Atlantic', 'http://www.theatlantic.com/feed/channel/news/'),
('Press Releases | The Atlantic', 'http://www.theatlantic.com/feed/channel/press-releases/'),
('Newsletters | The Atlantic', 'http://www.theatlantic.com/feed/channel/newsletters/'),
('The Atlantic Photo', 'http://feeds.feedburner.com/theatlantic/infocus'),
('Notes | The Atlantic', 'http://feeds.feedburner.com/TheAtlanticNotes'),
]
else:
def parse_index(self):
soup = self.index_to_soup(self.INDEX)
figure = soup.find('figure', id='cover-image')
if figure is not None:
img = figure.find('img', src=True)
if img:
self.cover_url = img['src']
current_section, current_articles = 'Cover Story', []
feeds = []
for div in soup.findAll('div', attrs={'class': lambda x: x and set(x.split()).intersection({'top-sections', 'bottom-sections'})}):
for h2 in div.findAll('h2', attrs={'class': True}):
if 'section-name' in h2['class'].split():
if current_articles:
feeds.append((current_section, current_articles))
current_articles = []
current_section = self.tag_to_string(h2)
self.log('\nFound section:', current_section)
elif 'hed' in h2['class'].split():
title = self.tag_to_string(h2)
a = h2.findParent('a', href=True)
url = a['href']
if url.startswith('/'):
url = 'http://www.theatlantic.com' + url
li = a.findParent(
'li',
attrs={'class': lambda x: x and 'article' in x.split()}
)
desc = ''
dek = li.find(
attrs={'class': lambda x: x and 'dek' in x.split()}
)
if dek is not None:
desc += self.tag_to_string(dek)
byline = li.find(
attrs={'class': lambda x: x and 'byline' in x.split()}
)
if byline is not None:
desc += ' -- ' + self.tag_to_string(byline)
self.log('\t', title, 'at', url)
if desc:
self.log('\t\t', desc)
current_articles.append({
'title': title,
'url': url,
'description': desc
})
if current_articles:
feeds.append((current_section, current_articles))
return feeds