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 Common Dreams

Browse Source
This commit is contained in:
Kovid Goyal 2014-09-02 17:13:53 +05:30
parent bc8753c7b5
commit 8659089df7
1 changed files with 33 additions and 44 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
recipes/common_dreams.recipe
View File

@ -1,8 +1,9 @@
#!/usr/bin/env python
##
## Title: Common Dreams
# Title: Common Dreams
##
## License: GNU General Public License v3 - http://www.gnu.org/copyleft/gpl.html
# License: GNU General Public License v3 -
# http://www.gnu.org/copyleft/gpl.html
# Feb 2012: Cleaned up the output to have only the main article
@ -14,6 +15,7 @@ commondreams.org
import re
from calibre.web.feeds.news import BasicNewsRecipe
class CommonDreams(BasicNewsRecipe):
# Identify the recipe
@ -29,12 +31,6 @@ class CommonDreams(BasicNewsRecipe):
no_stylesheets = True
remove_javascript = True
# Flattens all the tables to make it compatible with Nook
conversion_options = {'linearize_tables' : True}
remove_attributes = [ 'border', 'cellspacing', 'align', 'cellpadding', 'colspan',
'valign', 'vspace', 'hspace', 'alt', 'width', 'height' ]
# Specify extra CSS - overrides ALL other CSS (IE. Added last).
extra_css = 'body { font-family: verdana, helvetica, sans-serif; } \
.introduction, .first { font-weight: bold; } \
@ -57,7 +53,8 @@ class CommonDreams(BasicNewsRecipe):
# Remove the line breaks and float left/right and picture width/height.
preprocess_regexps = [(re.compile(r'<br[ ]*/>', re.IGNORECASE), lambda m: ''),
(re.compile(r'<br[ ]*clear.*/>', re.IGNORECASE), lambda m: ''),
(re.compile(
r'<br[ ]*clear.*/>', re.IGNORECASE), lambda m: ''),
(re.compile(r'float:.*?'), lambda m: ''),
(re.compile(r'width:.*?px'), lambda m: ''),
(re.compile(r'height:.*?px'), lambda m: ''),
@ -65,25 +62,17 @@ class CommonDreams(BasicNewsRecipe):
(re.compile(r'</a>'), lambda m: ''),
]
# Main article is inside this tag
keep_only_tags = [
dict(name='div', attrs={'id':lambda x: x and 'node-' in x}),
keep_only_tags = [dict(name='h1', attrs={'class': 'node__title managed-node-title'}),
dict(name='div', attrs={'class': ['field field--name-field-article-img field--type-image field--label-hidden',
'field field--name-body field--type-text-with-summary field--label-hidden']}),
]
remove_tags = [
dict(name='div', attrs={'class':'node-links clear-block'}), # remove Share options
]
# Identify the news feeds
feeds = [(u'Headlines', u'https://www.commondreams.org/feed/headlines_rss'),
(u'Further News Articles', u'https://www.commondreams.org/feed/further_rss'),
(u'Further News Articles',
u'https://www.commondreams.org/feed/further_rss'),
(u'Views', u'https://www.commondreams.org/feed/views_rss'),
(u'Progressive Newswire', u'https://www.commondreams.org/feed/newswire_rss')]
def print_version(self, url):
url = url + '?print'
return url