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 Metro UK and New Musical Express

Browse Source
This commit is contained in:
Kovid Goyal 2012-06-09 18:24:42 +05:30
parent 84163b3de9
commit 75c5478973
2 changed files with 39 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
recipes/metro_uk.recipe
View File

@ -4,6 +4,7 @@ class AdvancedUserRecipe1306097511(BasicNewsRecipe):
description = 'News as provide by The Metro -UK'
#timefmt = ''
__author__ = 'Dave Asbury'
#last update 9/6/12
cover_url = 'http://profile.ak.fbcdn.net/hprofile-ak-snc4/276636_117118184990145_2132092232_n.jpg'
#no_stylesheets = True
oldest_article = 1
@ -11,7 +12,7 @@ class AdvancedUserRecipe1306097511(BasicNewsRecipe):
remove_empty_feeds = True
remove_javascript = True
auto_cleanup = True
encoding = 'UTF-8'
language = 'en_GB'
masthead_url = 'http://e-edition.metro.co.uk/images/metro_logo.gif'

43
recipes/nme.recipe
View File

@ -1,23 +1,47 @@
from calibre.web.feeds.news import BasicNewsRecipe
from calibre import browser
class AdvancedUserRecipe1306061239(BasicNewsRecipe):
title = u'New Musical Express Magazine'
__author__ = "scissors"
language = 'en'
description = 'Author D.Asbury. UK Rock & Pop Mag. '
__author__ = 'Dave Asbury'
# last updated 9/6/12
remove_empty_feeds = True
remove_javascript = True
no_stylesheets = True
oldest_article = 7
max_articles_per_feed = 100
max_articles_per_feed = 20
#auto_cleanup = True
language = 'en_GB'
def get_cover_url(self):
soup = self.index_to_soup('http://www.magazinesdirect.com/categories/mens/tv-and-music/')
cov = soup.find(attrs={'title' : 'NME magazine subscriptions'})
cov2 = 'http://www.magazinesdirect.com'+cov['src']
print '***cov = ',cov2,' ***'
cover_url = str(cov2)
# print '**** Cov url =*', cover_url,'***'
#print '**** Cov url =*','http://www.magazinesdirect.com/article_images/articledir_3138/1569221/1_largelisting.jpg','***'
br = browser()
br.set_handle_redirect(False)
try:
br.open_novisit(cov2)
cover_url = str(cov2)
except:
cover_url = 'http://tawanda3000.files.wordpress.com/2011/02/nme-logo.jpg'
return cover_url
masthead_url = 'http://tawanda3000.files.wordpress.com/2011/02/nme-logo.jpg'
remove_tags = [
dict( attrs={'class':'clear_icons'}),
dict( attrs={'class':'share_links'}),
dict( attrs={'id':'right_panel'}),
dict( attrs={'class':'today box'})
dict( attrs={'class':'today box'}),
]
]
keep_only_tags = [
@ -28,7 +52,9 @@ class AdvancedUserRecipe1306061239(BasicNewsRecipe):
dict(attrs={'class' : 'bPosts'}),
dict(attrs={'class' : 'text'}),
dict(attrs={'id' : 'article_gallery'}),
#dict(attrs={'class' : 'image'}),
dict(attrs={'class' : 'article_text'})
]
@ -36,7 +62,8 @@ class AdvancedUserRecipe1306061239(BasicNewsRecipe):
feeds = [
(u'NME News', u'http://feeds2.feedburner.com/nmecom/rss/newsxml'),
(u'Reviews', u'http://feeds2.feedburner.com/nme/SdML'),
(u'Blogs', u'http://www.nme.com/blog/index.php?blog=140&tempskin=_rss2'),
#(u'Reviews', u'http://feeds2.feedburner.com/nme/SdML'),
(u'Reviews',u'http://feed43.com/4138608576351646.xml'),
(u'Bloggs',u'http://feed43.com/3326754333186048.xml'),
]