Debian Codegraph @

recipes/epw.recipe

raw
1 #!/usr/bin/env python
2 # vim:fileencoding=utf-8
3 # License: GPLv3 Copyright: 2015, Kovid Goyal <kovid at kovidgoyal.net>
4
5 from collections import OrderedDict
6
7 from calibre.web.feeds.news import BasicNewsRecipe
8
9
10 def absurl(x):
11 if x.startswith('/'):
12 x = 'http://www.epw.in' + x
13 return x
14
15
16 class EconomicAndPoliticalWeekly(BasicNewsRecipe):
17 title = 'Economic and Political Weekly'
18 __author__ = 'Kovid Goyal'
19 description = 'Economic and Political news from India'
20 publisher = 'epw.in'
21 category = 'news, finances, politics, India'
22 oldest_article = 7
23 max_articles_per_feed = 100
24 no_stylesheets = True
25 use_embedded_content = False
26 simultaneous_downloads = 1
27 encoding = 'utf-8'
28 language = 'en_IN'
29 publication_type = 'newspaper'
30 masthead_url = 'http://www.epw.in/system/files/epw_masthead.png'
31
32 keep_only_tags = [
33 dict(id=['block-system-main', 'page-title']),
34 ]
35
36 def parse_index(self):
37 soup = self.index_to_soup('http://www.epw.in/')
38 main = soup.find('div', id='main-content')
39 sections = OrderedDict()
40 current_section = None
41
42 for div in main.findAll(attrs={'class': lambda x: x and 'views-field-title' in x.split()}):
43 section = self.tag_to_string(div.findParent(attrs={'class': 'block-inner'}).find('h2'))
44 if section != current_section:
45 current_section = section
46 if section not in sections:
47 sections[section] = []
48 self.log('\n\n' + section)
49 title = self.tag_to_string(div)
50 a = div.find('a', href=True)
51 url = absurl(a['href'])
52 desc = ''
53 if a.get('title'):
54 desc = a['title']
55 else:
56 d = div.findNextSibling(attrs={'class': lambda x: x and 'views-field-body' in x.split()})
57 if d is not None:
58 desc = self.tag_to_string(d)
59 self.log('\t', title, url)
60 self.log('\t\t', desc)
61 sections[current_section].append({'title': title, 'url': url, 'description': desc})
62
63 current_section = 'Web Exclusive'
64 sections[current_section] = []
65 self.log('\n\n' + current_section)
66 for div in main.findAll(attrs={'class': lambda x: x and 'views-field-nothing' in x.split()}):
67 title = self.tag_to_string(div)
68 elems = div.findAll('a', href=True)
69 if len(elems) == 2:
70 desc, title = map(self.tag_to_string, elems)
71 else:
72 title, desc = self.tag_to_string(elems[0]), ''
73 url = absurl(elems[-1]['href'])
74 self.log('\t', title, url)
75 self.log('\t\t', desc)
76 sections[current_section].append({'title': title, 'url': url, 'description': desc})
77
78 return [(t, articles) for t, articles in sections.items() if articles]