Quote:
Originally Posted by scissors
D'oh!
Thanks Kovid.
Here's the recipe for anyone from the midlands uk who may fancy it
Spoiler:
Code:
from calibre.web.feeds.news import BasicNewsRecipe
from calibre import browser
import re
import mechanize
from calibre.utils.magick import Image
class AdvancedUserRecipe1306097511(BasicNewsRecipe):
title = u'Birmingham Evening Mail'
description = 'News for Birmingham UK'
#timefmt = ''
__author__ = 'Dave Asbury'
# v1 21/12/13
masthead_url = 'http://images.icnetwork.co.uk/upl/icbirmingham/apr2004/6/5/0007417F-982A-107F-969980BFB6FA0000.jpg'
oldest_article = 1
max_articles_per_feed = 10
#linearize_tables = True
remove_empty_feeds = True
remove_javascript = True
no_stylesheets = True
remove_attributes = ['style']
#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'}),
]
keep_only_tags = [
#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'),
(u'UK News', u'http://www.birminghammail.co.uk/news/uk-news/rss.xml'),
(u'Sport', u'http://www.birminghammail.co.uk/sport/rss.xml'),
(u'Whats On', u'http://www.birminghammail.co.uk/whats-on/rss.xml'),
(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%;}
#p{font-size:14px;}
#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%;}
'''
def get_cover_url(self):
print '============Cover ================='
print
soup = self.index_to_soup('http://www.birminghammail.co.uk')
cov = soup.find(attrs={'src' : re.compile('http://images.icnetwork.co.uk/upl/birmpost/')})
cov=str(cov)
print '^^^^^^^', cov
cov2 = re.findall('http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', cov)
cov=str(cov2)
cov=cov[2:len(cov)-2]
print '&&&&&&&&',cov,'***'
cover_url=cov
br = browser()
br.set_handle_redirect(False)
try:
br.open_novisit(cov)
cover_url = cov
except:
cover_url ='http://s.birminghammail.co.uk/skins/birminghammail/gfx/follow-media.jpg'
return cover_url
|
Corrected cover fetch code
Spoiler:
Code:
from calibre.web.feeds.news import BasicNewsRecipe
from calibre import browser
import re
import mechanize
from calibre.utils.magick import Image
class AdvancedUserRecipe1306097511(BasicNewsRecipe):
title = u'Birmingham Evening Mail'
description = 'News for Birmingham UK'
#timefmt = ''
__author__ = 'Dave Asbury'
# v1 21/12/13
masthead_url = 'http://images.icnetwork.co.uk/upl/icbirmingham/apr2004/6/5/0007417F-982A-107F-969980BFB6FA0000.jpg'
oldest_article = 1
max_articles_per_feed = 10
#linearize_tables = True
remove_empty_feeds = True
remove_javascript = True
no_stylesheets = True
remove_attributes = ['style']
#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'}),
]
keep_only_tags = [
#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'),
(u'UK News', u'http://www.birminghammail.co.uk/news/uk-news/rss.xml'),
(u'Sport', u'http://www.birminghammail.co.uk/sport/rss.xml'),
(u'Whats On', u'http://www.birminghammail.co.uk/whats-on/rss.xml'),
(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%;}
#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):
print '============Cover ================='
print
soup = self.index_to_soup('http://www.birminghammail.co.uk')
cov = soup.find(attrs={'src' : re.compile('http://images.icnetwork.co.uk/upl/birm')})
cov=str(cov)
print '^^^^^^^', cov
cov2 = re.findall('http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', cov)
cov=str(cov2)
cov=cov[2:len(cov)-2]
print '&&&&&&&&',cov,'***'
cover_url=cov
br = browser()
br.set_handle_redirect(False)
try:
br.open_novisit(cov)
cover_url = cov
except:
cover_url ='http://s.birminghammail.co.uk/skins/birminghammail/gfx/follow-media.jpg'
return cover_url