| 1 |
import re |
| 2 |
|
| 3 |
from calibre import browser |
| 4 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 5 |
|
| 6 |
|
| 7 |
class AdvancedUserRecipe1306061239(BasicNewsRecipe): |
| 8 |
title = 'The Daily Mirror' |
| 9 |
description = 'News as provided by The Daily Mirror -UK' |
| 10 |
|
| 11 |
__author__ = 'Dave Asbury' |
| 12 |
# last updated 1/5/14 |
| 13 |
language = 'en_GB' |
| 14 |
# cover_url = 'http://yookeo.com/screens/m/i/mirror.co.uk.jpg' |
| 15 |
|
| 16 |
masthead_url = 'http://www.nmauk.co.uk/nma/images/daily_mirror.gif' |
| 17 |
|
| 18 |
compress_news_images = True |
| 19 |
compress_news_images_max_size = 15 |
| 20 |
oldest_article = 1.5 |
| 21 |
max_articles_per_feed = 10 |
| 22 |
remove_empty_feeds = True |
| 23 |
remove_javascript = True |
| 24 |
no_stylesheets = True |
| 25 |
ignore_duplicate_articles = {'title'} |
| 26 |
|
| 27 |
keep_only_tags = [ |
| 28 |
dict(name='h1'), |
| 29 |
dict(name='div', attrs={'class': 'lead-text'}), |
| 30 |
dict(name='figure', attrs={'class': 'inline-image clearfix '}), |
| 31 |
dict(name='div', attrs={'class': 'styleGroup clearfix'}), |
| 32 |
dict(name='div', attrs={'class': 'widget relatedContents pictures widget-editable viziwyg-section-70 inpage-widget-2230659'}), |
| 33 |
dict(name='div', attrs={'class': 'body '}), |
| 34 |
] |
| 35 |
|
| 36 |
remove_tags = [ |
| 37 |
dict(attrs={'class': ['article sa-teaser type-opinion', 'image-gallery', 'gallery-caption']}), |
| 38 |
dict(attrs={'class': 'comment'}), |
| 39 |
dict(name='title'), |
| 40 |
dict(name='ul'), |
| 41 |
dict(name='ul', attrs={'class': 'clearfix breadcrumbs '}), |
| 42 |
dict(name='ul', attrs={'id': 'login-201109171215'}), |
| 43 |
dict(name='div', attrs={'class': ['inline-ad span-16 last', 'caption']}), |
| 44 |
] |
| 45 |
|
| 46 |
preprocess_regexps = [ |
| 47 |
(re.compile(r'- mirror.co.uk', re.IGNORECASE | re.DOTALL), lambda match: ''), |
| 48 |
(re.compile(r'<span class="image-credit">Getty</span>', re.IGNORECASE | re.DOTALL), lambda match: ''), |
| 49 |
] |
| 50 |
|
| 51 |
feeds = [ |
| 52 |
('UK News', 'http://www.mirror.co.uk/news/uk-news/rss.xml'), |
| 53 |
('world News', 'http://www.mirror.co.uk/news/world-news/rss.xml'), |
| 54 |
('Sports', 'http://www.mirror.co.uk/sport/rss.xml'), |
| 55 |
('3AM', 'http://www.mirror.co.uk/3am/rss.xml'), |
| 56 |
('Lifestyle', 'http://www.mirror.co.uk/lifestyle/rss.xml'), |
| 57 |
# example of commented out feed not needed |
| 58 |
# (u'Travel','http://www.mirror.co.uk/advice/travel/rss.xml'), |
| 59 |
] |
| 60 |
extra_css = ''' |
| 61 |
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;} |
| 62 |
h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;} |
| 63 |
p{font-family:Arial,Helvetica,sans-serif;font-size:small;} |
| 64 |
body{font-family:Helvetica,Arial,sans-serif;font-size:small;} |
| 65 |
''' |
| 66 |
|
| 67 |
def get_cover_url(self): |
| 68 |
soup = self.index_to_soup('http://www.politicshome.com/uk/latest_frontpage.html') |
| 69 |
# look for the block containing the mirror button and url |
| 70 |
cov = soup.find(attrs={'style': 'background-image: url(http://www.politicshome.com/images/sources/source_frontpage_button_92.gif);'}) |
| 71 |
cov2 = str(cov) |
| 72 |
cov2 = 'http://www.politicshome.com' + cov2[9:-142] |
| 73 |
# cov2 now contains url of the page containing pic |
| 74 |
soup = self.index_to_soup(cov2) |
| 75 |
cov = soup.find(attrs={'id': 'large'}) |
| 76 |
cov = str(cov) |
| 77 |
cov2 = re.findall(r'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', cov) |
| 78 |
cov2 = str(cov2) |
| 79 |
cov2 = cov2[2 : len(cov2) - 2] |
| 80 |
# cov2 now is pic url, now go back to original function |
| 81 |
br = browser() |
| 82 |
br.set_handle_redirect(False) |
| 83 |
try: |
| 84 |
br.open_novisit(cov2) |
| 85 |
cover_url = cov2 |
| 86 |
except Exception: |
| 87 |
cover_url = 'http://profile.ak.fbcdn.net/hprofile-ak-snc4/373019_6149699161_1710984811_n.jpg' |
| 88 |
|
| 89 |
return cover_url |