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

Browse Source
This commit is contained in:
Kovid Goyal 2013-08-28 08:04:15 +05:30
parent 097ea82129
commit 4954e91a62
1 changed files with 29 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
recipes/daily_mirror.recipe
View File

@ -7,50 +7,50 @@ class AdvancedUserRecipe1306061239(BasicNewsRecipe):
description = 'News as provided by The Daily Mirror -UK'
__author__ = 'Dave Asbury'
# last updated 19/10/12
# last updated 27/8/13
language = 'en_GB'
#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
oldest_article = 1
max_articles_per_feed = 12
compress_news_images_max_size = 30
oldest_article = 1.5
max_articles_per_feed = 10
remove_empty_feeds = True
remove_javascript = True
no_stylesheets = True
ignore_duplicate_articles = {'title'}
ignore_duplicate_articles = {'url'}
# auto_cleanup = True
#auto_cleanup = True
#conversion_options = { 'linearize_tables' : True }
keep_only_tags = [ dict(name='h1'),
keep_only_tags = [dict(name='h1'),
dict(name='div',attrs={'class' : 'lead-text'}),
dict(name='div',attrs={'class' : 'styleGroup clearfix'}),
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'),
# dict(name='p'),
]
remove_tags = [
dict(attrs={'class' : ['article sa-teaser type-opinion','image-gallery','gallery-caption']}),
dict(attrs={'class' : ['article sa-teaser type-opinion','last','gallery-caption','gallery-data','ir btn-fullscreen','avatar']}), # ,'image-gallery'
dict(attrs={'class' : 'comment'}),
dict(name='title'),
dict(name='ul',attrs={'class' : 'clearfix breadcrumbs '}),
dict(name='ul',attrs={'id' : 'login-201109171215'}),
dict(name='div',attrs={'class' : ['inline-ad span-16 last','caption']}),#'widget navigation breadcrumb widget-editable viziwyg-section-198 inpage-widget-80721 span-17','image-credit'
#'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: '')]
feeds = [
(u'News',u'http://www.mirror.co.uk/news/rss.xml'),
(u'Sports',u'http://www.mirror.co.uk/sport/rss.xml'),
@ -63,26 +63,31 @@ class AdvancedUserRecipe1306061239(BasicNewsRecipe):
# 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: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;}
'''
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%}
'''
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)
cov2 = re.findall('http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', cov)
cov2 = str(cov2)
cov2=cov2[2:len(cov2)-2]
#cov2 now is pic url, now go back to original function
# cov2 now is pic url, now go back to original function
br = browser()
br.set_handle_redirect(False)
try: