Debian Codegraph @

recipes/the_baffler.recipe

raw
1 from calibre.web.feeds.news import BasicNewsRecipe, classes
2
3
4 class TheBaffler(BasicNewsRecipe):
5 title = 'The Baffler'
6 __author__ = 'flobotnik and unkn0wn'
7 description = 'This magazine contains left-wing criticism, cultural analysis, shorts stories, poems and art. They publish six print issues annually.'
8 language = 'en'
9 encoding = 'UTF-8'
10 no_javascript = True
11 no_stylesheets = True
12 remove_attributes = ['style', 'height', 'width']
13
14 extra_css = '''
15 .entry-subtitle{color:#202020; font-style:italic; text:align:left;}
16 blockquote{color:gray;}
17 em{color:#404040;}
18 .wp-caption-text{font-size:small; text-align:center;}
19 .lg:text-xs{color:gray; font-size:small; text-align:center;}
20 .author-meta{font-size:small; color:gray;}
21 '''
22
23 keep_only_tags = [dict(name='main', attrs={'id': 'main'})]
24
25 remove_tags = [
26 classes('entry-date issue-number-segment single-article-vertical donation-footer story-footer ml-4 mt-14'),
27 dict(name='footer'),
28 dict(name='a', class_='ml-4 pr-px font-sans text-sm lg:text-xs whitespace-nowrap'),
29 ]
30
31 def get_cover_url(self):
32 soup = self.index_to_soup('https://shop.exacteditions.com/us/the-baffler')
33 tag = soup.find('div', attrs={'class': 'row'})
34 if tag:
35 self.cover_url = tag.find('img')['src']
36 return getattr(self, 'cover_url', self.cover_url)
37
38 def parse_index(self):
39 soup = self.index_to_soup('https://thebaffler.com/issues')
40 issue = soup.find('article')
41 edition = self.tag_to_string(issue.find('h2')).strip().split('—')[1]
42 if edition:
43 self.log('Downloading Issue: ', edition)
44 self.title = 'The Baffler : ' + edition
45 self.timefmt = ' [' + self.tag_to_string(issue.find('div', **classes('font-lion'))).strip() + ']'
46 a = issue.find('a')
47
48 self.description = '\n\n' + self.tag_to_string(a).strip() + '\n\n' + self.description
49
50 soup = self.index_to_soup(a['href'])
51 ans = []
52 main = soup.find('main', attrs={'id': 'main'})
53 for section in main.findAll('section'):
54 current_section = self.tag_to_string(section.h3).strip()
55 self.log(current_section)
56 articles = []
57 for h4 in section.findAll('h4'):
58 title = self.tag_to_string(h4)
59 url = h4.a['href']
60 desc = ''
61 span = h4.findNext('span')
62 if span:
63 desc = self.tag_to_string(span).strip()
64 span2 = span.findNext('span')
65 if span2:
66 desc = self.tag_to_string(span2).strip() + ' | ' + desc
67 self.log('\t', title, '\n\t', desc, '\n\t\t', url)
68 articles.append({'title': title, 'url': url, 'description': desc})
69 if articles:
70 ans.append((current_section, articles))
71 return ans
72
73 def preprocess_html(self, soup):
74 div = soup.find('div', **classes('entry-title'))
75 if div:
76 div.name = 'h1'
77 for p in soup.findAll('p', attrs={'class': 'parasectionhed'}):
78 p.name = 'h4'
79 return soup