Debian Codegraph @

recipes/the_wire.recipe

raw
1 #!/usr/bin/env python
2 import datetime
3 import json
4
5 from calibre.web.feeds.news import BasicNewsRecipe
6
7
8 def absurl(url):
9 if not url.startswith('http'):
10 return 'https://thewire.in/' + url
11 return url
12
13
14 def json_to_html(js):
15 data = json.loads(js)['post-detail'][0]
16 title = f'<h1>{data["post_title"]}</h1>'
17 exp = auth = image = sec = ''
18 sec = f'<div style="font-size: small;">{data["categories"][0]["slug"]}</div>'
19 if data.get('post_excerpt'):
20 exp = f'<p style="font-style: italic;">{data["post_excerpt"]}</p>'
21 if data.get('post_author_name'):
22 auth = f'<p style="font-size: small;">By {", ".join(x["author_name"] for x in data["post_author_name"])} | {data["post_date"]}</p>'
23 if data.get('featured_image'):
24 image_url = data['featured_image'][0]
25 image = f'<div><img src="{image_url}"><div style="font-size:small;">{data.get("featured_image_caption", "")}</div></div>'
26 return '<html><body>' + sec + title + exp + image + auth + data['post_content'] + '</body></html>'
27
28
29 class TheWire(BasicNewsRecipe):
30 title = 'The Wire'
31 __author__ = 'unkn0wn'
32 description = 'The Wire is an Indian nonprofit news and opinion website'
33 language = 'en_IN'
34 masthead_url = 'https://cdn.thewire.in/wp-content/uploads/thewire-app-images/wire-logo.svg'
35 remove_javascript = True
36 remove_attributes = ['height', 'width']
37 ignore_duplicate_articles = {'url'}
38 resolve_internal_links = True
39 remove_empty_feeds = True
40 extra_css = '[id^="caption"] { font-size: small;}'
41
42 def get_browser(self, *args, **kw):
43 br = BasicNewsRecipe.get_browser(self, *args, **kw)
44 br.addheaders += [('Referer', 'https://thewire.in/')]
45 return br
46
47 def parse_index(self):
48 raw = self.index_to_soup('https://thewirehindi.com/home_data_2.json', raw=True)
49 dmp = json.loads(raw)
50 feeds = []
51 for k, v in dmp.items():
52 if not isinstance(v, dict):
53 continue
54 if k == 'videos':
55 continue
56 section = k.capitalize()
57 self.log(section)
58 articles = []
59
60 for a, b in v.items():
61 if not isinstance(b, dict):
62 continue
63 if not b.get('post_type', '') == 'post':
64 continue
65 now = datetime.now(datetime.timezone.utc) # Ensure 'now' is offset-aware
66 post_date = datetime.strptime(b['post_date'], '%Y-%m-%d %H:%M:%S').replace(tzinfo=datetime.timezone.utc) # Make 'post_date' offset-aware
67 if (now - post_date).days > self.oldest_article:
68 continue
69 title = b['post_title']
70 desc = b['post_excerpt']
71 slg = b['categories'][0]['slug'] + '/' + b['post_name']
72 url = absurl(slg)
73 self.log('\t', title, '\n\t', desc, '\n\t\t', url)
74 articles.append({'title': title, 'description': desc, 'url': url})
75 if articles:
76 feeds.append((section, articles))
77 return feeds
78
79 articles_are_obfuscated = True
80
81 def get_obfuscated_article(self, url):
82 raw_ = self.index_to_soup(
83 'https://cms.thewire.in/wp-json/thewire/v2/posts/detail/' + url.rsplit('/')[-1],
84 raw=True,
85 )
86 return {'data': json_to_html(raw_), 'url': url}