| 1 |
#!/usr/bin/env python |
| 2 |
## |
| 3 |
# Title: SatMagazine |
| 4 |
## |
| 5 |
# License: GNU General Public License v3 - http://www.gnu.org/copyleft/gpl.html |
| 6 |
## |
| 7 |
# Written: Feb 2012 |
| 8 |
# Last Edited: Mar 2012 |
| 9 |
## |
| 10 |
|
| 11 |
# Feb 2012: Initial release |
| 12 |
|
| 13 |
__license__ = 'GNU General Public License v3 - http://www.gnu.org/copyleft/gpl.html' |
| 14 |
|
| 15 |
''' |
| 16 |
satmagazine.com |
| 17 |
''' |
| 18 |
|
| 19 |
import re |
| 20 |
|
| 21 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 22 |
|
| 23 |
|
| 24 |
class SatMagazine(BasicNewsRecipe): |
| 25 |
title = 'SatMagazine' |
| 26 |
description = 'North American Satellite Markets...' |
| 27 |
publisher = 'Satnews Publishers' |
| 28 |
publication_type = 'magazine' |
| 29 |
INDEX = 'http://www.satmagazine.com/cgi-bin/display_edition.cgi' |
| 30 |
__author__ = 'kiavash' |
| 31 |
|
| 32 |
language = 'en' |
| 33 |
asciiize = True |
| 34 |
timeout = 120 |
| 35 |
simultaneous_downloads = 2 |
| 36 |
|
| 37 |
# Flattens all the tables to make it compatible with Nook |
| 38 |
conversion_options = {'linearize_tables': True} |
| 39 |
|
| 40 |
keep_only_tags = [dict(name='span', attrs={'class': 'story'})] |
| 41 |
|
| 42 |
no_stylesheets = True |
| 43 |
remove_javascript = True |
| 44 |
|
| 45 |
remove_attributes = ['border', 'cellspacing', 'align', 'cellpadding', 'colspan', 'valign', 'vspace', 'hspace', 'alt', 'width', 'height'] |
| 46 |
|
| 47 |
# Specify extra CSS - overrides ALL other CSS (IE. Added last). |
| 48 |
extra_css = '''body { font-family: verdana, helvetica, sans-serif; } |
| 49 |
.introduction, .first { font-weight: bold; } |
| 50 |
.cross-head { font-weight: bold; font-size: 125%; } |
| 51 |
.cap, .caption { display: block; font-size: 80%; font-style: italic; } |
| 52 |
.cap, .caption, .caption img, .caption span { display: block; margin: 5px auto; } |
| 53 |
.byl, .byd, .byline img, .byline-name, .byline-title, .author-name, .author-position, |
| 54 |
.correspondent-portrait img, .byline-lead-in, .name, .bbc-role { display: block; |
| 55 |
font-size: 80%; font-style: italic; margin: 1px auto; } |
| 56 |
.story-date, .published { font-size: 80%; } |
| 57 |
table { width: 100%; } |
| 58 |
td img { display: block; margin: 5px auto; } |
| 59 |
ul { padding-top: 10px; } |
| 60 |
ol { padding-top: 10px; } |
| 61 |
li { padding-top: 5px; padding-bottom: 5px; } |
| 62 |
h1 { font-size: 175%; font-weight: bold; } |
| 63 |
h2 { font-size: 150%; font-weight: bold; } |
| 64 |
h3 { font-size: 125%; font-weight: bold; } |
| 65 |
h4, h5, h6 { font-size: 100%; font-weight: bold; }''' |
| 66 |
|
| 67 |
# Remove the line breaks, href links and float left/right and picture |
| 68 |
# width/height. |
| 69 |
preprocess_regexps = [ |
| 70 |
(re.compile(r'<br[ ]*/>', re.IGNORECASE), lambda m: ''), |
| 71 |
(re.compile(r'<br[ ]*clear.*/>', re.IGNORECASE), lambda m: ''), |
| 72 |
(re.compile(r'<a.*?>'), lambda h1: ''), |
| 73 |
(re.compile(r'</a>'), lambda h2: ''), |
| 74 |
(re.compile(r'float:.*?'), lambda h3: ''), |
| 75 |
(re.compile(r'width:.*?px'), lambda h4: ''), |
| 76 |
(re.compile(r'height:.*?px'), lambda h5: ''), |
| 77 |
] |
| 78 |
|
| 79 |
def parse_index(self): |
| 80 |
|
| 81 |
article_info = [] |
| 82 |
feeds = [] |
| 83 |
|
| 84 |
soup = self.index_to_soup(self.INDEX) |
| 85 |
|
| 86 |
# Find Cover image |
| 87 |
cover = soup.find('img', src=True, alt='Cover Image') |
| 88 |
if cover is not None: |
| 89 |
self.cover_url = cover['src'] |
| 90 |
self.log('Found Cover image:', self.cover_url) |
| 91 |
|
| 92 |
# main part of the site that has the articles |
| 93 |
soup = soup.find('div', attrs={'id': 'middlecontent'}) |
| 94 |
|
| 95 |
# Find the Magazine date |
| 96 |
# contains the string with the date |
| 97 |
ts = soup.find('span', attrs={'class': 'master_heading'}) |
| 98 |
ds = ' '.join(self.tag_to_string(ts).strip().split()[:2]) |
| 99 |
self.log('Found Current Issue:', ds) |
| 100 |
self.timefmt = ' [%s]' % ds |
| 101 |
|
| 102 |
articles = soup.findAll('span', attrs={'class': 'heading'}) |
| 103 |
|
| 104 |
descriptions = soup.findAll('span', attrs={'class': 'story'}) |
| 105 |
|
| 106 |
title_number = 0 |
| 107 |
|
| 108 |
# Goes through all the articles one by one and sort them out |
| 109 |
for article in articles: |
| 110 |
title = self.tag_to_string(article) |
| 111 |
url = article.find('a').get('href') |
| 112 |
|
| 113 |
self.log('\tFound article:', title, 'at', url) |
| 114 |
desc = self.tag_to_string(descriptions[title_number]) |
| 115 |
|
| 116 |
article_info.append({'title': title, 'url': url, 'description': desc, 'date': self.timefmt}) |
| 117 |
|
| 118 |
title_number = title_number + 1 |
| 119 |
|
| 120 |
if article_info: |
| 121 |
feeds.append((self.title, article_info)) |
| 122 |
|
| 123 |
return feeds |
| 124 |
|
| 125 |
def preprocess_html(self, soup): |
| 126 |
|
| 127 |
# Finds all the images |
| 128 |
for figure in soup.findAll('img', attrs={'src': True}): |
| 129 |
# if the image is an ad then remove it. |
| 130 |
if (figure['alt'].find('_ad_') >= 0) or (figure['alt'].find('_snipe_') >= 0): |
| 131 |
del figure['src'] |
| 132 |
del figure['alt'] |
| 133 |
del figure['border'] |
| 134 |
del figure['hspace'] |
| 135 |
del figure['vspace'] |
| 136 |
del figure['align'] |
| 137 |
del figure['size'] |
| 138 |
figure.name = 'font' |
| 139 |
continue |
| 140 |
|
| 141 |
# adds /n before and after the image |
| 142 |
figure['style'] = 'display:block' |
| 143 |
|
| 144 |
# Makes the title standing out |
| 145 |
for title in soup.findAll('b'): |
| 146 |
title.name = 'h3' |
| 147 |
|
| 148 |
# Removes all unrelated links |
| 149 |
for link in soup.findAll('a', attrs={'href': True}): |
| 150 |
link.name = 'font' |
| 151 |
del link['href'] |
| 152 |
del link['target'] |
| 153 |
|
| 154 |
return soup |