Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Daily Mirror and Birmingham Evening Mail

Browse Source
This commit is contained in:
Kovid Goyal 2014-05-01 12:19:33 +05:30
parent 2386a575f9
commit 99cec1b571
2 changed files with 53 additions and 56 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
recipes/birmingham_evening_mail.recipe
View File

@ -5,30 +5,36 @@ import re
class AdvancedUserRecipe1306097511(BasicNewsRecipe):
title = u'Birmingham Evening Mail'
description = 'News for Birmingham UK'
#timefmt = ''
# timefmt = ''
__author__ = 'Dave Asbury'
# v1 21/12/13
# 1/5/14
masthead_url = 'http://images.icnetwork.co.uk/upl/icbirmingham/apr2004/6/5/0007417F-982A-107F-969980BFB6FA0000.jpg'
oldest_article = 1
oldest_article = 2
max_articles_per_feed = 10
#linearize_tables = True
# linearize_tables = True
remove_empty_feeds = True
remove_javascript = True
no_stylesheets = True
remove_attributes = ['style']
#auto_cleanup = True
# auto_cleanup = True
language = 'en_GB'
compress_news_images = True
compress_news_images_max_size = 30
ignore_duplicate_articles = {'title', 'url'}
remove_tags = [
dict(attrs={'class' : 'gallery-data'}),
dict(attrs={'class' : 'ir btn-fullscreen'}),
dict(attrs={'class' : 'tools clearfix'}),
dict(attrs={'class' : 'gallery-data'}),
dict(attrs={'class' : 'ir btn-fullscreen'}),
dict(attrs={'class' : 'tools clearfix'}),
dict(attrs={'class' : 'shareButtons'}),
]
keep_only_tags = [
dict(attrs={'class' : 'tmCol article'}),]
dict(name='h1'),
dict(attrs={'class' : 'lead-text'}),
# dict(attrs={'class' : 'styleGroup article-header'}),
# dict(attrs={'class' : 'body '}),
dict(attrs={'class' : 'tmCol article'}),]
feeds = [
(u'Local News', u'http://www.birminghammail.co.uk/news/local-news/rss.xml'),
@ -38,11 +44,15 @@ class AdvancedUserRecipe1306097511(BasicNewsRecipe):
(u'Lifestyle',u'http://www.birminghammail.co.uk/lifestyle/rss.xml'),
]
extra_css = '''
h1{font-weight:bold;font-size: 175%;}
h2{font-weight:normal;font-size:75%;}
figure {font-size:50%;}
img {display: block;margin-left: auto;margin-right: auto;width:100%;font-size:50%;}
'''
h1{font-weight:bold;}
h2{font-weight:normal;font-size:75%;}
figure {font-size:50%;}
#body{font-size:14px;}
#.photo-caption {display: block;margin-left: auto;margin-right: auto;width:100%;font-size:40%;}
#.publish-info {font-size:50%;}
img {display: block;margin-left: auto;margin-right: auto;width:100%;font-size:50%;}
'''
def get_cover_url(self):
soup = self.index_to_soup('http://www.birminghammail.co.uk')
cov = soup.find(attrs={'src' : re.compile('http://images.icnetwork.co.uk/upl/birm')})

71
recipes/daily_mirror.recipe
View File

@ -7,80 +7,70 @@ class AdvancedUserRecipe1306061239(BasicNewsRecipe):
description = 'News as provided by The Daily Mirror -UK'
__author__ = 'Dave Asbury'
# last updated 27/8/13
# last updated 1/5/14
language = 'en_GB'
#cover_url = 'http://yookeo.com/screens/m/i/mirror.co.uk.jpg'
# cover_url = 'http://yookeo.com/screens/m/i/mirror.co.uk.jpg'
masthead_url = 'http://www.nmauk.co.uk/nma/images/daily_mirror.gif'
#recursions = 10
compress_news_images = True
compress_news_images_max_size = 30
oldest_article = 1.5
max_articles_per_feed = 10
max_articles_per_feed = 12
remove_empty_feeds = True
remove_javascript = True
no_stylesheets = True
ignore_duplicate_articles = {'url'}
ignore_duplicate_articles = {'title'}
#auto_cleanup = True
#conversion_options = { 'linearize_tables' : True }
keep_only_tags = [dict(name='h1'),
dict(name='div',attrs={'class' : 'lead-text'}),
dict(attrs={'class' : 'tools clearfix'}),
dict(name='div',attrs={'class' : 'widget relatedContents pictures widget-editable viziwyg-section-245 inpage-widget-158123'}),
# dict(name='figure',attrs={'class' : 'clearfix'}),
dict(name='div',attrs={'class' :'body '}),
dict(name='div',attrs={'class' :'thumb'}),
dict(attrs={'img alt' : ['Perishers','Horace']}),
#dict(attrs={'class' : 'tmRow span-15-5 col-1 article-page'}),
#dict(attrs={'class' : ['article-attr','byline append-1','published']}),
# dict(name='p'),
]
keep_only_tags = [
dict(name='h1'),
dict(name='div',attrs={'class' : 'lead-text'}),
dict(name='figure',attrs={'class' : 'inline-image clearfix '}),
dict(name='div',attrs={'class' : 'styleGroup clearfix'}),
dict(name='div',attrs={
'class' : 'widget relatedContents pictures widget-editable viziwyg-section-70 inpage-widget-2230659'}),
dict(name='div',attrs={'class' :'body '}),
]
remove_tags = [
dict(attrs={'class' : ['article sa-teaser type-opinion','last','gallery-caption','gallery-data','ir btn-fullscreen','avatar']}), # ,'image-gallery'
dict(attrs={'class' : ['article sa-teaser type-opinion','image-gallery','gallery-caption']}),
dict(attrs={'class' : 'comment'}),
dict(name='title'),
dict(name='ul'),
dict(name='ul',attrs={'class' : 'clearfix breadcrumbs '}),
dict(name='ul',attrs={'id' : 'login-201109171215'}),
#'widget navigation breadcrumb widget-editable viziwyg-section-198 inpage-widget-80721 span-17','image-credit'
dict(name='div',attrs={'class' : ['inline-ad span-16 last','caption']}),
]
]
preprocess_regexps = [
(re.compile(r'- mirror.co.uk', re.IGNORECASE | re.DOTALL), lambda match: '')]
(re.compile(r'- mirror.co.uk', re.IGNORECASE | re.DOTALL), lambda match: ''),
(re.compile(r'<span class="image-credit">Getty</span>', re.IGNORECASE | re.DOTALL), lambda match: ''),
]
feeds = [
(u'News',u'http://www.mirror.co.uk/news/rss.xml'),
(u'UK News',u'http://www.mirror.co.uk/news/uk-news/rss.xml'),
(u'world News',u'http://www.mirror.co.uk/news/world-news/rss.xml'),
(u'Sports',u'http://www.mirror.co.uk/sport/rss.xml'),
(u'3AM',u'http://www.mirror.co.uk/3am/rss.xml'),
(u'Lifestyle',u'http://www.mirror.co.uk/lifestyle/rss.xml')
# example of commented out feed not needed ,(u'Travel','http://www.mirror.co.uk/advice/travel/rss.xml')
# example of commented out feed not needed ,(u'Travel','http://www.mirror.co.uk/advice/travel/rss.xml')
]
extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:170%;}
.article figure figcaption {display: block;margin-left: auto;margin-right: auto;
width:100%;font-family:Arial,Helvetica,sans-serif;font-size:40%;}
#h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;}
p{font-family:Arial,Helvetica,sans-serif;}
body{font-family:Helvetica,Arial,sans-serif;}
.article figure{display: block;margin-left: auto;margin-right: auto;width:100%;}
.lead-text p {font-size:150%}
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
'''
def get_cover_url(self):
soup = self.index_to_soup('http://www.politicshome.com/uk/latest_frontpage.html')
# look for the block containing the mirror button and url
# look for the block containing the mirror button and url
cov = soup.find(attrs={'style' : 'background-image: url(http://www.politicshome.com/images/sources/source_frontpage_button_92.gif);'})
cov2 = str(cov)
cov2='http://www.politicshome.com'+cov2[9:-142]
# cov2 now contains url of the page containing pic
# cov2 now contains url of the page containing pic
soup = self.index_to_soup(cov2)
cov = soup.find(attrs={'id' : 'large'})
cov=str(cov)
@ -96,7 +86,4 @@ class AdvancedUserRecipe1306061239(BasicNewsRecipe):
except:
cover_url ='http://profile.ak.fbcdn.net/hprofile-ak-snc4/373019_6149699161_1710984811_n.jpg'
# print '******** string is ', cov2,' ***'
#cover_url = cov2
#cover_url = 'http://www.thesun.co.uk/img/global/new-masthead-logo.png'
return cover_url