-
-
Notifications
You must be signed in to change notification settings - Fork 2.3k
/
bbc_fast.recipe
189 lines (163 loc) · 6.84 KB
/
bbc_fast.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
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
#!/usr/bin/env python
# vim:fileencoding=utf-8
# License: GPLv3 Copyright: 2020, Kovid Goyal <kovid at kovidgoyal.net>
import json
from calibre import prepare_string_for_xml
from calibre.web.feeds.recipes import BasicNewsRecipe
# Article JSON parser {{{
def serialize_image(block):
yield '<div>'
block = block['model']
img = block['image']
alt = prepare_string_for_xml(img.get('alt') or '', True)
for q in ('originalSrc', 'src'):
if q in img:
src = prepare_string_for_xml(img[q])
break
else:
raise ValueError('No src found in img block: {}'.format(img))
yield '<img src="{}" alt="{}"/>'.format(src, alt)
caption = block.get('caption')
if caption and caption.get('type') == 'text':
yield '<div>'
yield from serialize_paragraph(caption)
yield '</div>'
yield '</div>'
def block_tag(name, generator):
yield '<' + name + '>'
yield from generator
yield '</' + name + '>'
def serialize_paragraph(block):
block = block['model']
for x in block['blocks']:
xt = x['type']
if xt == 'fragment':
styles = []
model = x['model']
for attr in model['attributes']:
if attr == 'bold':
styles.append('font-weight: bold')
elif attr in ('italic', 'italics'):
styles.append('font-style: italic')
if styles:
prefix = '<span style="{}">'.format('; '.join(styles))
suffix = '</span>'
else:
prefix = suffix = ''
yield prefix + prepare_string_for_xml(model['text']) + suffix
elif xt == 'urlLink':
model = x['model']
yield '<a href="{}">{}</a>'.format(prepare_string_for_xml(model['locator'], True), prepare_string_for_xml(model['text']))
def serialize_list(block):
for x in block['model']['blocks']:
if x['type'] == 'listItem':
yield from block_tag('li', serialize_paragraph(x))
def serialize_text(block):
block = block['model']
for x in block['blocks']:
xt = x['type']
if xt == 'paragraph':
yield from block_tag('p', serialize_paragraph(x))
elif xt == 'unorderedList':
yield from block_tag('ul', serialize_list(x))
elif xt == 'orderedList':
yield from block_tag('ol', serialize_list(x))
else:
raise KeyError('Unknown block type: ' + x['type'])
def serialize_contributor(contributor):
if 'title' in contributor:
yield '<h3>' + prepare_string_for_xml(contributor['title']) + '</h3>'
if 'subtitle' in contributor:
yield '<div>' + prepare_string_for_xml(contributor['subtitle']) + '</div>'
def parse_article_json(root, abort_article):
data = root['data']
has_media_experience = False
for key in data:
if key.startswith('article?'):
article = data[key]['data']
break
elif key.startswith('media-experience?'):
has_media_experience = True
else:
if has_media_experience:
abort_article('Skipping video article')
return
raise KeyError('No article found in data keys: {}'.format(data.keys()))
lines = []
if article.get('headline'):
lines.append('<h1>{}</h1>'.format(prepare_string_for_xml(article['headline'])))
if article.get('contributor'):
lines.extend(serialize_contributor(article['contributor']))
for block in article['content']['model']['blocks']:
bt = block.get('type')
if bt == 'image':
lines.extend(serialize_image(block))
elif bt == 'text':
lines.extend(serialize_text(block))
return '<html><body id="main-content">' + '\n'.join(lines) + '</body></html>'
def parse_raw_html(html, abort_article):
q = '>window.__INITIAL_DATA__="{'
idx = html.find(q)
if idx < 0:
raise ValueError('Failed to find JSON')
data = html[idx + len(q) - 2:]
idx = data.find('}";</script>')
data = data[:idx+2]
data = json.loads(data)
root = json.loads(data)
return parse_article_json(root, abort_article)
if __name__ == '__main__':
print(parse_raw_html(open('/t/raw.html').read(), print))
# }}}
class BBC(BasicNewsRecipe):
title = 'BBC News (fast)'
__author__ = 'Kovid Goyal'
description = 'Visit BBC News for up-to-the-minute news, breaking news, video, audio and feature stories. BBC News provides trusted World and UK news as well as local and regional perspectives. Also entertainment, business, science, technology and health news.' # noqa
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'utf8'
publisher = 'BBC'
category = 'news, UK, world'
language = 'en_GB'
conversion_options = {
'comments': description, 'tags': category, 'language': language, 'publisher': publisher,
}
# Removes empty feeds - why keep them!?
remove_empty_feeds = True
ignore_duplicate_articles = {'title', 'url'}
resolve_internal_links = True
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)
}
}
def __init__(self, *args, **kwargs):
BasicNewsRecipe.__init__(self, *args, **kwargs)
d = self.recipe_specific_options.get('days')
if d and isinstance(d, str):
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'),
('Entertainment/Arts',
'https://feeds.bbci.co.uk/news/entertainment_and_arts/rss.xml'),
('Magazine', 'https://feeds.bbci.co.uk/news/magazine/rss.xml'),
('Business', 'https://feeds.bbci.co.uk/news/business/rss.xml'),
('Politics', 'https://feeds.bbci.co.uk/news/politics/rss.xml'),
('Health', 'https://feeds.bbci.co.uk/news/health/rss.xml'),
('US&Canada', 'https://feeds.bbci.co.uk/news/world/us_and_canada/rss.xml'),
('Latin America', 'https://feeds.bbci.co.uk/news/world/latin_america/rss.xml'),
('Europe', 'https://feeds.bbci.co.uk/news/world/europe/rss.xml'),
('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')
]
def preprocess_raw_html(self, raw_html, url):
return parse_raw_html(raw_html, self.abort_article)