Updated Sun, Mirror Metro

This commit is contained in:
Kovid Goyal 2012-04-12 14:29:31 +05:30
parent 50e419efd2
commit b24bde150d
3 changed files with 92 additions and 57 deletions

View File

@ -1,20 +1,21 @@
from calibre.web.feeds.news import BasicNewsRecipe
import re
import mechanize
class AdvancedUserRecipe1306061239(BasicNewsRecipe):
title = u'The Daily Mirror'
description = 'News as provide by The Daily Mirror -UK'
__author__ = 'Dave Asbury'
# last updated 11/2/12
# last updated 7/4/12
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'
oldest_article = 1
max_articles_per_feed = 5
max_articles_per_feed = 10
remove_empty_feeds = True
remove_javascript = True
no_stylesheets = True
@ -75,3 +76,28 @@ class AdvancedUserRecipe1306061239(BasicNewsRecipe):
img { display:block}
'''
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
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
soup = self.index_to_soup(cov2)
cov = soup.find(attrs={'id' : 'large'})
cov2 = str(cov)
cov2=cov2[27:-18]
#cov2 now is pic url, now go back to original function
br = mechanize.Browser()
br.set_handle_redirect(False)
try:
br.open_novisit(cov2)
cover_url = cov2
except:
cover_url = 'http://yookeo.com/screens/m/i/mirror.co.uk.jpg'
#cover_url = cov2
#cover_url = 'http://www.thesun.co.uk/img/global/new-masthead-logo.png'
return cover_url

View File

@ -1,52 +1,30 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1306097511(BasicNewsRecipe):
title = u'Metro UK'
description = 'News as provide by The Metro -UK'
#timefmt = ''
__author__ = 'Dave Asbury'
#last update 3/12/11
cover_url = 'http://profile.ak.fbcdn.net/hprofile-ak-snc4/276636_117118184990145_2132092232_n.jpg'
no_stylesheets = True
#no_stylesheets = True
oldest_article = 1
max_articles_per_feed = 20
max_articles_per_feed = 10
remove_empty_feeds = True
remove_javascript = True
auto_cleanup = True
#preprocess_regexps = [(re.compile(r'Tweet'), lambda a : '')]
preprocess_regexps = [
(re.compile(r'<span class="img-cap legend">', re.IGNORECASE | re.DOTALL), lambda match: '<p></p><span class="img-cap legend"> ')]
preprocess_regexps = [
(re.compile(r'tweet', re.IGNORECASE | re.DOTALL), lambda match: '')]
language = 'en_GB'
masthead_url = 'http://e-edition.metro.co.uk/images/metro_logo.gif'
keep_only_tags = [
dict(name='h1'),dict(name='h2', attrs={'class':'h2'}),
dict(attrs={'class':['img-cnt figure']}),
dict(attrs={'class':['art-img']}),
dict(name='div', attrs={'class':'art-lft'}),
dict(name='p')
]
remove_tags = [
dict(name = 'div',attrs={'id' : ['comments-news','formSubmission']}),
dict(name='div', attrs={'class':[ 'news m12 clrd clr-b p5t shareBtm', 'commentForm', 'metroCommentInnerWrap',
'art-rgt','pluck-app pluck-comm','news m12 clrd clr-l p5t', 'flt-r','username','clrd' ]}),
dict(attrs={'class':['username', 'metroCommentFormWrap','commentText','commentsNav','avatar','submDateAndTime','addYourComment','displayName']})
,dict(name='div', attrs={'class' : 'clrd art-fd fd-gr1-b'})
]
feeds = [
(u'News', u'http://www.metro.co.uk/rss/news/'), (u'Money', u'http://www.metro.co.uk/rss/money/'), (u'Sport', u'http://www.metro.co.uk/rss/sport/'), (u'Film', u'http://www.metro.co.uk/rss/metrolife/film/'), (u'Music', u'http://www.metro.co.uk/rss/metrolife/music/'), (u'TV', u'http://www.metro.co.uk/rss/tv/'), (u'Showbiz', u'http://www.metro.co.uk/rss/showbiz/'), (u'Weird News', u'http://www.metro.co.uk/rss/weird/'), (u'Travel', u'http://www.metro.co.uk/rss/travel/'), (u'Lifestyle', u'http://www.metro.co.uk/rss/lifestyle/'), (u'Books', u'http://www.metro.co.uk/rss/lifestyle/books/'), (u'Food', u'http://www.metro.co.uk/rss/lifestyle/restaurants/')]
extra_css = '''
body {font: sans-serif medium;}'
h1 {text-align : center; font-family:Arial,Helvetica,sans-serif; font-size:20px; font-size-adjust:none; font-stretch:normal; font-style:normal; font-variant:normal; font-weight:bold;}
h2 {text-align : center;color:#4D4D4D;font-family:Arial,Helvetica,sans-serif; font-size:15px; font-size-adjust:none; font-stretch:normal; font-style:normal; font-variant:normal; font-weight:bold; }
span{ font-size:9.5px; font-weight:bold;font-style:italic}
p { text-align: justify; font-family:Arial,Helvetica,sans-serif; font-size:11px; font-size-adjust:none; font-stretch:normal; font-style:normal; font-variant:normal; font-weight:normal;}
body{ text-align: justify; font-family:Arial,Helvetica,sans-serif; font-size:11px; font-size-adjust:none; font-stretch:normal; font-style:normal; font-variant:normal; font-weight:normal;}
'''

View File

@ -1,9 +1,8 @@
import re
import re, mechanize
from calibre.web.feeds.recipes import BasicNewsRecipe
class AdvancedUserRecipe1325006965(BasicNewsRecipe):
title = u'The Sun UK'
cover_url = 'http://www.thesun.co.uk/img/global/new-masthead-logo.png'
description = 'A Recipe for The Sun tabloid UK'
__author__ = 'Dave Asbury'
@ -49,7 +48,6 @@ class AdvancedUserRecipe1325006965(BasicNewsRecipe):
feeds = [
#(u'News', u'http://www.thesun.co.uk/sol/homepage/news/rss'),
(u'News','http://feed43.com/2517447382644748.xml'),
(u'Sport', u'http://feed43.com/4283846255668687.xml'),
(u'Bizarre', u'http://feed43.com/0233840304242011.xml'),
@ -58,3 +56,36 @@ class AdvancedUserRecipe1325006965(BasicNewsRecipe):
(u'Sun Woman',u'http://feed43.com/0022626854226453.xml'),
]
def get_cover_url(self):
soup = self.index_to_soup('http://www.politicshome.com/uk/latest_frontpage.html')
# look for the block containing the sun button and url
cov = soup.find(attrs={'style' : 'background-image: url(http://www.politicshome.com/images/sources/source_frontpage_button_84.gif);'})
#cov = soup.find(attrs={'id' : 'large'})
cov2 = str(cov)
cov2='http://www.politicshome.com'+cov2[9:-133]
#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'})
cov2 = str(cov)
cov2=cov2[27:-18]
#cov2 now is pic url, now go back to original function
br = mechanize.Browser()
br.set_handle_redirect(False)
try:
br.open_novisit(cov2)
cover_url = cov2
except:
cover_url = 'http://www.thesun.co.uk/img/global/new-masthead-logo.png'
#cover_url = cov2
#cover_url = 'http://www.thesun.co.uk/img/global/new-masthead-logo.png'
return cover_url