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

Add profile for The New Yorker

Browse Source
This commit is contained in:
Kovid Goyal 2008-02-13 05:13:00 +00:00
parent a1389cfd57
commit c86e9afe5a
2 changed files with 58 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/libprs500/ebooks/lrf/web/__init__.py
View File

@ -31,10 +31,11 @@ from libprs500.ebooks.lrf.web.profiles.jpost import JerusalemPost
from libprs500.ebooks.lrf.web.profiles.reuters import Reuters from libprs500.ebooks.lrf.web.profiles.reuters import Reuters
from libprs500.ebooks.lrf.web.profiles.atlantic import Atlantic from libprs500.ebooks.lrf.web.profiles.atlantic import Atlantic
from libprs500.ebooks.lrf.web.profiles.ap import AssociatedPress from libprs500.ebooks.lrf.web.profiles.ap import AssociatedPress
from libprs500.ebooks.lrf.web.profiles.newyorker import NewYorker
builtin_profiles = [Atlantic, AssociatedPress, Barrons, BBC, builtin_profiles = [Atlantic, AssociatedPress, Barrons, BBC,
ChristianScienceMonitor, CNN, Dilbert, Economist, FazNet, ChristianScienceMonitor, CNN, Dilbert, Economist, FazNet,
JerusalemPost, Newsweek, NewYorkReviewOfBooks, NYTimes, JerusalemPost, Newsweek, NewYorker, NewYorkReviewOfBooks, NYTimes,
Portfolio, Reuters, SpiegelOnline, WallStreetJournal, ZeitNachrichten, Portfolio, Reuters, SpiegelOnline, WallStreetJournal, ZeitNachrichten,
] ]

56
src/libprs500/ebooks/lrf/web/profiles/newyorker.py Normal file
View File

@ -0,0 +1,56 @@
'''
Profile to download Jutarnji.hr
'''
import re
from libprs500.ebooks.lrf.web.profiles import DefaultProfile
class NewYorker(DefaultProfile):
title = 'The New Yorker'
max_recursions = 2
timefmt = ' [%d %b %Y]'
max_articles_per_feed = 20
html_description = True
no_stylesheets = True
oldest_article = 14
## Getting the print version
def print_version(self, url):
return url + '?printable=true'
preprocess_regexps = [
(re.compile(r'<body.*?<!-- start article content -->', re.IGNORECASE | re.DOTALL), lambda match : '<body>'),
(re.compile(r'<div class="utils"'),
lambda match : '<div class="utils" style="display:none"'),
(re.compile(r'<div class="articleRailLinks"'),
lambda match : '<div class="articleRailLinks" style="display:none"'),
(re.compile(r'<div id="keywords"'),
lambda match : '<div id="keywords" style="display:none"'),
(re.compile(r'<!-- end article body -->.*?</body>', re.IGNORECASE | re.DOTALL), lambda match : '</body>'),
(re.compile(r'<!-- start video content -->.*?<!-- end video content -->', re.IGNORECASE | re.DOTALL), lambda match : '<!-- start video content --><!-- end video content -->'),
]
## Comment out the feeds you don't want retrieved.
## Or add any new new RSS feed URL's here, sorted alphabetically when converted to LRF
## If you want one of these at the top, append a space in front of the name.
def get_feeds(self):
return [
('Online Only', 'http://feeds.newyorker.com/services/rss/feeds/online.xml'),
('The Talk Of The Town', 'http://feeds.newyorker.com/services/rss/feeds/talk.xml'),
('Reporting and Essays', 'http://feeds.newyorker.com/services/rss/feeds/reporting.xml'),
('Arts and Culture', 'http://feeds.newyorker.com/services/rss/feeds/arts.xml'),
('Humor', 'http://feeds.newyorker.com/services/rss/feeds/humor.xml'),
('Fiction and Poetry', 'http://feeds.newyorker.com/services/rss/feeds/fiction.xml'),
('Comment', 'http://feeds.newyorker.com/services/rss/feeds/comment.xml'),
('The Financial Page', 'http://feeds.newyorker.com/services/rss/feeds/financial.xml'),
('Politics', 'http://feeds.newyorker.com/services/rss/feeds/politics.xml'),
('Movies', 'http://feeds.newyorker.com/services/rss/feeds/movies.xml'),
('Books', 'http://feeds.newyorker.com/services/rss/feeds/books.xml'),
('Tables For Two', 'http://feeds.newyorker.com/services/rss/feeds/tables.xml'),
]