Debian Codegraph @

recipes/liberation.recipe

raw
1 #!/usr/bin/env python
2 # vim:fileencoding=utf-8
3 """
4 liberation.fr
5 """
6
7 import base64
8 import json
9 import time
10 from datetime import datetime, timedelta
11 from urllib.parse import quote, urlencode, urlparse
12
13 from mechanize import Request
14
15 from calibre import browser
16 from calibre.web.feeds.news import BasicNewsRecipe
17
18
19 def resize(x):
20 for k, v in x.items():
21 if '_750' in k:
22 return v
23
24
25 m_fr = {
26 1: 'Janvier',
27 2: 'Février',
28 3: 'Mars',
29 4: 'Avril',
30 5: 'Mai',
31 6: 'Juin',
32 7: 'Juillet',
33 8: 'Août',
34 9: 'Septembre',
35 10: 'Octobre',
36 11: 'Novembre',
37 12: 'Décembre',
38 }
39
40
41 def json_to_html(raw):
42 data = json.loads(raw)
43
44 title = '<h1>' + data['headlines']['basic'] + '</h1>\n'
45 sub = '<p class="desc">' + data['subheadlines']['basic'] + '</p>'
46
47 auth = '<p class="auth">{}</p>\n'
48 dt = datetime.fromisoformat(data['last_updated_date'][:-1]) + timedelta(seconds=time.timezone)
49 dt = dt.strftime(m_fr[dt.month] + ' %d, %Y')
50 a = [x['name'] for x in data['credits']['by']]
51 if a:
52 auth = auth.format(', '.join(a) + ' | ' + dt)
53 else:
54 auth = auth.format(dt)
55
56 lede = ''
57 if data['promo_items']['basic'].get('type', '') == 'image':
58 lede = '<br><img src="{}"><div class="figc">{}</div>\n'.format(
59 resize(data['promo_items']['basic']['resized_image_urls']), data['promo_items']['basic'].get('caption', '')
60 )
61
62 body = ''
63 for c in data['content_elements']:
64 if c.get('type', '') == 'text':
65 body += '\t<p>' + c['content'] + '</p>\n'
66 if c.get('type', '') == 'image':
67 body += '\t<br><img src="{}"><div class="figc">{}</div>\n'.format(resize(c['resized_image_urls']), c.get('caption', ''))
68 if c.get('type', '') == 'header':
69 body += '\t<h4>' + c['content'] + '</h4>\n'
70 if c.get('type', '') == 'list':
71 body += '\t<ul>'
72 if 'items' in c:
73 for l in c['items']:
74 if 'content' in l:
75 body += '<li>' + l['content'] + '</li>'
76 body += '\t</ul>'
77 if c.get('type', '') == 'oembed_response':
78 if 'raw_oembed' in c:
79 if 'html' in c['raw_oembed']:
80 body += c['raw_oembed']['html']
81
82 return '<html><body><div>\n' + title + sub + auth + lede + body + '\n</div></body></html>'
83
84
85 class Liberation(BasicNewsRecipe):
86 title = 'Libération'
87 __author__ = 'unkn0wn'
88 description = (
89 "Libération est un quotidien d'information libre, vigilant et engagé. L'objectif de Libération est de "
90 'fournir une information complète et vérifiée, dans tous les domaines. Sans préjugés, ni complaisance, '
91 "ses enquêtes reportages et analyses s'emploient à comprendre et à décrire l'actualité et à révéler "
92 'les mutations des sociétés et des cultures.'
93 )
94 language = 'fr'
95 oldest_article = 1.15
96 remove_empty_feeds = True
97 articles_are_obfuscated = True
98 timefmt = ' [%s]' % datetime.now().strftime(m_fr[datetime.now().month] + ' %d, %Y')
99 ignore_duplicate_articles = {'title', 'url'}
100 key = 'YTdYMjltQnZRZVAxTGQ5OENnRjJySzV1VHpXWTRo'
101 masthead_url = 'https://journal.liberation.fr/img/logo.svg'
102 extra_css = '''
103 .desc { font-style:italic; color:#202020; }
104 .auth { font-size:small; }
105 .figc { font-size:small; text-align:center; }
106 blockquote { color:#202020; }
107 '''
108
109 recipe_specific_options = {
110 'days': {
111 'short': 'Oldest article to download from this news source. In days ',
112 'long': 'For example, 0.5, gives you articles from the past 12 hours',
113 'default': str(oldest_article),
114 }
115 }
116
117 def __init__(self, *args, **kwargs):
118 BasicNewsRecipe.__init__(self, *args, **kwargs)
119 d = self.recipe_specific_options.get('days')
120 if d and isinstance(d, str):
121 self.oldest_article = float(d)
122
123 feeds = [
124 ('A la une', 'https://www.liberation.fr/arc/outboundfeeds/rss-all/collection/accueil-une/?outputType=xml'),
125 ('Politique', 'https://www.liberation.fr/arc/outboundfeeds/rss-all/category/politique/?outputType=xml'),
126 ('International', 'https://www.liberation.fr/arc/outboundfeeds/rss-all/category/international/?outputType=xml'),
127 ('CheckNews', 'https://www.liberation.fr/arc/outboundfeeds/rss-all/category/checknews/?outputType=xml'),
128 ('Culture', 'https://www.liberation.fr/arc/outboundfeeds/rss-all/category/culture/?outputType=xml'),
129 ('Idées et Débats', 'https://www.liberation.fr/arc/outboundfeeds/rss-all/category/idees-et-debats/?outputType=xml'),
130 ('Société', 'https://www.liberation.fr/arc/outboundfeeds/rss-all/category/societe/?outputType=xml'),
131 ('Environnement', 'https://www.liberation.fr/arc/outboundfeeds/rss-all/category/environnement/?outputType=xml'),
132 ('Economie', 'https://www.liberation.fr/arc/outboundfeeds/rss-all/category/economie/?outputType=xml'),
133 ('Lifestyle', 'https://www.liberation.fr/arc/outboundfeeds/rss-all/category/lifestyle/?outputType=xml'),
134 ('Portraits', 'https://www.liberation.fr/arc/outboundfeeds/rss-all/category/portraits/?outputType=xml'),
135 ('Sports', 'https://www.liberation.fr/arc/outboundfeeds/rss-all/category/sports/?outputType=xml'),
136 ('Sciences', 'https://www.liberation.fr/arc/outboundfeeds/rss-all/category/sciences/?outputType=xml'),
137 ('Forums & événements', 'https://www.liberation.fr/arc/outboundfeeds/rss-all/category/forums/?outputType=xml'),
138 ('Libération', 'https://www.liberation.fr/arc/outboundfeeds/rss/?outputType=xml'),
139 ]
140
141 def get_obfuscated_article(self, url):
142 slug = urlparse(url).path
143 br = browser()
144 b64 = base64.b64decode(self.key)
145 query = {
146 'website': 'liberation',
147 'website_url': str(slug),
148 'published': 'true',
149 '_sourceInclude': '_id,content_restrictions.content_code,credits,promo_items.basic.caption,promo_items.basic.credits,promo_items.basic.url,promo_items.basic.height,promo_items.basic.width,promo_items.basic.resized_image_urls,promo_items.basic.last_updated_date,promo_items.lead_art.caption,promo_items.lead_art.credits,promo_items.lead_art.url,promo_items.lead_art.height,promo_items.lead_art.width,promo_items.lead_art.resized_image_urls,promo_items.lead_art.last_updated_date,source.additional_properties.legacy_url,content_elements,source.source_id,taxonomy.primary_section.additional_properties.original._admin.alias_ids,taxonomy.primary_section.additional_properties.original.navigation.nav_title,taxonomy.primary_section._id,taxonomy.primary_section.name,taxonomy.primary_section.path,taxonomy.tags,label,subheadlines.basic,headlines.basic,source.additional_properties.legacy_url,source.source_type,first_publish_date,display_date,canonical_url', # noqa: E501
150 }
151 headers = {'cache-control': 'public, max-age=5', 'x-api-key': b64.decode(), 'accept-encoding': 'gzip', 'user-agent': 'okhttp/4.11.0'}
152 api = 'https://arc.api.liberation.fr/content/v4/?' + urlencode(query, safe='()!', quote_via=quote)
153 rq = Request(url=api, headers=headers)
154 raw = br.open(rq).read()
155 data = {'data': json_to_html(raw), 'url': url}
156 return data
157
158 def get_cover_url(self):
159 soup = self.index_to_soup('https://journal.liberation.fr/')
160 cover = soup.find(name='img', attrs={'class': 'ui image'})
161 if cover:
162 return 'https:' + cover['src']