Debian Codegraph @

recipes/galaxys_edge.recipe

raw
1 #!/usr/bin/env python
2 # vim:fileencoding=utf-8
3 from __future__ import absolute_import, division, print_function, unicode_literals
4
5 import re
6 import shutil
7
8 try:
9 from urllib.parse import urlencode
10 except ImportError:
11 from urllib import urlencode
12 from calibre.ptempfile import PersistentTemporaryDirectory, PersistentTemporaryFile
13 from calibre.web.feeds.news import BasicNewsRecipe
14
15
16 class AdvancedUserRecipe1515196393(BasicNewsRecipe):
17 title = "The Galaxy's Edge"
18 __author__ = 'andyh2000'
19 delay = 2
20 oldest_article = 7
21 max_articles_per_feed = 100
22 auto_cleanup = True
23 language = 'en'
24 encoding = 'utf8'
25 no_stylesheets = True
26
27 extra_css = '.photo-caption { font-size: smaller }'
28
29 def parse_index(self):
30 soup = self.index_to_soup('http://www.galaxysedge.com/')
31 cover_image = soup.find('div', attrs={'class': 'ci-img'})
32 cover_image = cover_image.find('img')
33 self.cover_url = cover_image['src']
34 issue_title = soup.find('h1')
35 self.title = "Galaxy's Edge: " + self.tag_to_string(issue_title).lower().title()
36 toc = soup.find('div', attrs={'class': 'nav-tabs'})
37 current_section = 'Articles'
38 current_articles = []
39 feeds = []
40 br = self.get_browser()
41 self.ctdir = PersistentTemporaryDirectory()
42 for x in toc.findAll(['li'], attrs={'class': re.compile(r'.*get_content.*')}):
43 edwo = x.find('a')
44 title = self.tag_to_string(edwo)
45 self.log('\t\tFound article:', title)
46 post_id = x['data-post-id']
47 cat_id = x['data-cat-id']
48 parent_id = x['data-parent-id']
49 self.log('\t\tdata-parent-id', parent_id)
50 self.log('\t\tdata-cat-id', cat_id)
51 self.log('\t\tdata-post-id', post_id)
52 data = urlencode({'action': 'get_content', 'cat_id': cat_id, 'parent_id': parent_id, 'post_id': post_id})
53 r = br.open('http://www.galaxysedge.com/wp-content/themes/galaxyedge/get_content.php', data)
54 content_file = PersistentTemporaryFile(suffix='.html', dir=self.ctdir)
55 content_file.write(r.read())
56 content_file.close()
57 current_articles.append({'title': title, 'url': 'file://' + content_file.name, 'description': '', 'date': ''})
58 if current_articles and current_section:
59 feeds.append((current_section, current_articles))
60
61 return feeds
62
63 def cleanup(self):
64 self.log('Deleting temp files...')
65 shutil.rmtree(self.ctdir)