Debian Codegraph @

recipes/zerodeux.recipe

raw
1 #!/usr/bin/env python
2
3 """
4 zerodeux.fr
5 """
6
7 from calibre.web.feeds.news import BasicNewsRecipe
8
9
10 class ZeroDeuxRecipe(BasicNewsRecipe):
11 title = 'Zérodeux'
12 __author__ = 'Kabonix'
13 description = "Revue d'art contemporain trimestrielle"
14 publisher = 'Zérodeux'
15 category = 'art, contemporary art, criticism'
16 language = 'fr'
17 encoding = 'utf-8'
18 oldest_article = 60
19 max_articles_per_feed = 25
20
21 no_stylesheets = True
22 remove_javascript = True
23 auto_cleanup = False
24
25 feeds = [
26 ('Essais', 'https://www.zerodeux.fr/category/essais/feed/'),
27 ('Guests', 'https://www.zerodeux.fr/category/guests/feed/'),
28 ('Interviews', 'https://www.zerodeux.fr/category/interviews/feed/'),
29 ('Reviews', 'https://www.zerodeux.fr/category/reviews/feed/'),
30 ('News', 'https://www.zerodeux.fr/category/news/feed/'),
31 ('Special Web', 'https://www.zerodeux.fr/category/specialweb/feed/'),
32 ]
33
34 def get_cover_url(self):
35 soup = self.index_to_soup('https://www.zerodeux.fr')
36 cover_div = soup.find('div', {'id': 'responsive_lightbox_image_widget-2'})
37 if cover_div:
38 cover_img = cover_div.find('img', {'class': 'rl-image-widget-image'})
39 if cover_img and 'src' in cover_img.attrs:
40 return cover_img['src']
41 return None
42
43 keep_only_tags = [dict(name='article', attrs={'id': 'single-post'})]
44
45 remove_tags = [
46 dict(name='div', attrs={'class': ['single-associate', 'single-info', 'transition']}),
47 dict(name='div', attrs={'id': ['sidebar', 'menu_footer']}),
48 dict(name='ul', attrs={'class': ['single-info']}), # Supprime le bloc "Partage"
49 dict(name='li', text='Du même auteur :'), # Supprime le titre "Du même auteur"
50 dict(name='p', attrs={'class': ['recomand']}), # Supprime "articles liés"
51 ]
52
53 def preprocess_html(self, soup):
54 # Nettoyage des styles
55 for tag in soup.findAll(True):
56 if 'style' in tag.attrs:
57 del tag['style']
58
59 # Nettoyage des images
60 for img in soup.findAll('img'):
61 for attr in ['srcset', 'sizes', 'loading', 'class', 'width', 'height', 'decoding', 'fetchpriority']:
62 if attr in img.attrs:
63 del img[attr]
64
65 if img.get('src', '').startswith('/'):
66 img['src'] = 'https://www.zerodeux.fr' + img['src']
67
68 # Suppression du texte "Partage :" et "Du même auteur :"
69 for text in soup.findAll(text=True):
70 if text.strip() in ['Partage :', 'Du même auteur :']:
71 text.extract()
72
73 return soup
74
75 extra_css = '''
76 h1 { font-size: 1.8em; font-weight: bold; margin: 0 0 1em 0; }
77 h2 { font-size: 1.4em; font-weight: bold; margin: 1em 0; }
78 .single-author { font-style: italic; margin-bottom: 1.5em; color: #666; }
79 img { max-width: 100%; height: auto; margin: 1em auto; }
80 figcaption { font-size: 0.9em; font-style: italic; color: #666; margin: 0.5em 0 1.5em 0; }
81 p { margin-bottom: 1em; line-height: 1.5; }
82 ol { margin: 1em 0 1em 2em; }
83 blockquote { margin: 1em 0; padding: 0 1em; border-left: 3px solid #ccc; }
84 .wp-block-image { margin: 1.5em 0; }
85 .has-small-font-size { font-size: 0.9em; }
86 '''
87
88 def populate_article_metadata(self, article, soup, first):
89 author_div = soup.find('div', {'class': 'single-author'})
90 if author_div:
91 author = author_div.get_text().strip()
92 if author.startswith('par '):
93 author = author[4:]
94 article.author = author