Debian Codegraph @

recipes/nasa.recipe

raw
1 # Copyright (C) 2008 B.Scott Wxby [bswxby] &
2 # Copyright (C) 2007 David Chen SonyReader<at>DaveChen<dot>org
3 ##
4 # This program is free software; you can redistribute it and/or modify
5 # it under the terms of the GNU General Public License as published by
6 # the Free Software Foundation; either version 2 of the License, or
7 # (at your option) any later version.
8 ##
9 # This program is distributed in the hope that it will be useful,
10 # but WITHOUT ANY WARRANTY; without even the implied warranty of
11 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
12 # GNU General Public License for more details.
13 ##
14 # Version 0.3-2008_2_28
15 # Based on WIRED.py by David Chen, 2007, and newsweek.py, bbc.py, nytimes.py by Kovid Goyal
16 ##
17 # Usage:
18 # >web2lrf --user-profile nasa.py
19 # Comment out the RSS feeds you don't want in the last section below
20 ##
21 # Output:
22 # NASA [YearMonthDate Time].lrf
23 ##
24 """
25 Custom User Profile to download RSS News Feeds and Articles from Wired.com
26 """
27
28 import re
29
30 from calibre.web.feeds.news import BasicNewsRecipe
31
32
33 class NASA(BasicNewsRecipe):
34 title = 'NASA'
35 timefmt = ' [%Y%b%d %H%M]'
36 language = 'en'
37
38 description = 'News from NASA'
39 __author__ = 'Scott Wxby & David Chen'
40 no_stylesheets = True
41
42 # Don't grab articles more than 30 days old
43 oldest_article = 30
44
45 preprocess_regexps = [
46 (re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1])
47 for i in [
48 # Fix the encoding to UTF-8
49 (r'<meta http-equiv="Content-Type" content="text/html; charset=(\S+)"', lambda match: match.group().replace(match.group(1), 'UTF-8')),
50 # Remove any banners/links/ads/cruft before the body of the article.
51 (
52 r'<body.*?((<div id="article_body">)|(<div id="st-page-maincontent">)|(<div id="containermain">)|(<p class="ap-story-p">)|(<!-- img_nav -->))',
53 lambda match: '<body><div>',
54 ), # noqa: E501
55 # Remove any links/ads/comments/cruft from the end of the body
56 # of the article.
57 (
58 (
59 r'((<!-- end article content -->)|(<div id="st-custom-afterpagecontent">)'
60 r'|(<p class="ap-story-p">&copy;)|(<div class="entry-footer">)'
61 r'|(<div id="see_also">)|(<p>Via <a href=)|(<div id="ss_nav">)).*?</html>'
62 ),
63 lambda match: '</div></body></html>',
64 ),
65 # Correctly embed in-line images by removing the surrounding
66 # javascript that will be ignored in the conversion
67 (
68 r'<a.*?onclick.*?>.*?(<img .*?>)',
69 lambda match: match.group(1),
70 ),
71 # This removes header and footer information from each print
72 # version.
73 (r'<!-- Top Header starts -->.*?<!-- Body starts -->', lambda match: '<New Stuff>'),
74 (r'<hr align="center" width="200"><p align="center">.*?<!-- Press Release standard text ends -->', lambda match: '<New Stuff>'),
75 (r'<!-- Top Header starts -->.*?<!---->', lambda match: '<New Stuff>'),
76 # This removes the "download image" of various sizes from the Image of
77 # the day.
78 (r'<div id="download_image_box_print">.*?<div id="caption_region_print">', lambda match: '<New Stuff>'),
79 ]
80 ]
81
82 # NASA's print pages differ only by the ending "_prt.htm", so I've
83 # replaced them below.
84
85 def print_version(self, url):
86 return url.replace('.html', '_prt.htm')
87
88 # Comment out the feeds you don't want retrieved.
89 # Or add any new new RSS feed URL's here, sorted alphabetically when converted to LRF
90 # If you want one of these at the top, append a space in front of the name.
91 # Mars feed may not work, as it is now considered "legacy" by NASA.
92
93 feeds = [
94 (' Breaking News', 'https://www.nasa.gov/rss/dyn/breaking_news.rss'),
95 ('Image of the Day', 'https://www.nasa.gov/rss/dyn/lg_image_of_the_day.rss'),
96 ('Mars Exploration', 'https://marsmobile.jpl.nasa.gov/rss/?feed=news&category=all'),
97 ('Shuttle and Station News', 'https://www.nasa.gov/rss/dyn/shuttle_station.rss'),
98 ('Solar System and Beyond News', 'https://www.nasa.gov/rss/dyn/solar_system.rss'),
99 ('Education News', 'https://www.nasa.gov/rss/dyn/educationnews.rss'),
100 ('Earth News', 'https://www.nasa.gov/rss/dyn/earth.rss'),
101 ('Aeronautics News', 'https://www.nasa.gov/rss/dyn/aeronautics.rss'),
102 ]