| 1 |
#!/usr/bin/env python |
| 2 |
__license__ = 'GPL v3' |
| 3 |
''' |
| 4 |
''' |
| 5 |
|
| 6 |
from calibre.web.feeds.recipes import BasicNewsRecipe |
| 7 |
|
| 8 |
|
| 9 |
def classes(classes): |
| 10 |
q = frozenset(classes.split(' ')) |
| 11 |
return dict(attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)}) |
| 12 |
|
| 13 |
|
| 14 |
class ReadersDigest(BasicNewsRecipe): |
| 15 |
title = 'Readers Digest' |
| 16 |
__author__ = 'BrianG, Gobelinus' |
| 17 |
language = 'en' |
| 18 |
description = 'Readers Digest Feeds' |
| 19 |
no_stylesheets = True |
| 20 |
use_embedded_content = False |
| 21 |
oldest_article = 60 |
| 22 |
max_articles_per_feed = 200 |
| 23 |
|
| 24 |
remove_javascript = True |
| 25 |
remove_attributes = ['style'] |
| 26 |
|
| 27 |
extra_css = ''' h1 {font-family:georgia,serif;color:#000000;} |
| 28 |
.mainHd{font-family:georgia,serif;color:#000000;} |
| 29 |
h2 {font-family:Arial,Sans-serif;} |
| 30 |
.name{font-family:Arial,Sans-serif; font-size:x-small;font-weight:bold; } |
| 31 |
.date{font-family:Arial,Sans-serif; font-size:x-small ;color:#999999;} |
| 32 |
.byline{font-family:Arial,Sans-serif; font-size:x-small ;} |
| 33 |
.photoBkt{ font-size:x-small ;} |
| 34 |
.vertPhoto{font-size:x-small ;} |
| 35 |
.credits{font-family:Arial,Sans-serif; font-size:x-small ;color:gray;} |
| 36 |
.credit{font-family:Arial,Sans-serif; font-size:x-small ;color:gray;} |
| 37 |
.artTxt{font-family:georgia,serif;} |
| 38 |
.caption{font-family:georgia,serif; font-size:x-small;color:#333333;} |
| 39 |
.credit{font-family:georgia,serif; font-size:x-small;color:#999999;} |
| 40 |
a:link{color:#CC0000;} |
| 41 |
.breadcrumb{font-family:Arial,Sans-serif;font-size:x-small;} |
| 42 |
''' |
| 43 |
|
| 44 |
feeds = [ |
| 45 |
('Food', 'http://www.rd.com/food/feed'), |
| 46 |
('Health', 'http://www.rd.com/health/feed'), |
| 47 |
('Home', 'http://www.rd.com/home/feed'), |
| 48 |
# ('Family', 'http://www.rd.com/family/feed'), |
| 49 |
# ('Money', 'http://www.rd.com/money/feed'), |
| 50 |
# ('Travel', 'http://www.rd.com/travel/feed'), |
| 51 |
('True Stories', 'http://www.rd.com/true-stories/feed'), |
| 52 |
('Advice', 'http://www.rd.com/advice/feed'), |
| 53 |
] |
| 54 |
|
| 55 |
keep_only_tags = [classes('post-title post-author post-updated-date post-date featured-image post-body entry-title dek listicle-card')] |
| 56 |
|
| 57 |
remove_tags = [classes('single-card ad brand-info pure-g')] |
| 58 |
|
| 59 |
def preprocess_html(self, soup): |
| 60 |
for img in soup.findAll('img', attrs={'data-lazy-src': True}): |
| 61 |
img['src'] = img['data-lazy-src'] |
| 62 |
return soup |