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 profiles for Washington Post and United Press International

Browse Source
This commit is contained in:
Kovid Goyal 2008-02-14 05:13:03 +00:00
parent 0c61a51a1b
commit 45d114bc32
3 changed files with 84 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
src/libprs500/ebooks/lrf/web/__init__.py
View File

@ -34,13 +34,15 @@ from libprs500.ebooks.lrf.web.profiles.ap import AssociatedPress
from libprs500.ebooks.lrf.web.profiles.newyorker import NewYorker
from libprs500.ebooks.lrf.web.profiles.jutarnji import Jutarnji
from libprs500.ebooks.lrf.web.profiles.usatoday import USAToday
from libprs500.ebooks.lrf.web.profiles.upi import UnitedPressInternational
from libprs500.ebooks.lrf.web.profiles.wash_post import WashingtonPost
builtin_profiles = [Atlantic, AssociatedPress, Barrons, BBC,
ChristianScienceMonitor, CNN, Dilbert, Economist, FazNet,
JerusalemPost, Jutarnji, Newsweek, NewYorker,
NewYorkReviewOfBooks, NYTimes, USAToday,
NewYorkReviewOfBooks, NYTimes, UnitedPressInternational, USAToday,
Portfolio, Reuters, SpiegelOnline, WallStreetJournal,
ZeitNachrichten,
WashingtonPost, ZeitNachrichten,
]
available_profiles = [i.__module__.rpartition('.')[2] for i in builtin_profiles]

36
src/libprs500/ebooks/lrf/web/profiles/upi.py Normal file
View File

@ -0,0 +1,36 @@
import re
from libprs500.ebooks.lrf.web.profiles import DefaultProfile
class UnitedPressInternational(DefaultProfile):
title = 'United Press International'
max_recursions = 2
max_articles_per_feed = 15
html2lrf_options = ['--override-css= "H1 {font-family: Arial; font-weight: bold; color: #000000; size: 10pt;}"']
preprocess_regexps = [ (re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
[
(r'<HEAD>.*?</HEAD>' , lambda match : '<HEAD></HEAD>'),
(r'<div id="apple-rss-sidebar-background">.*?<!-- start Entries -->', lambda match : ''),
(r'<!-- end apple-rss-content-area -->.*?</body>', lambda match : '</body>'),
(r'<script.*?>.*?</script>', lambda match : ''),
(r'<body onload=.*?>.*?<a href="http://www.upi.com">', lambda match : '<body style="font: 8pt arial;">'),
##(r'<div class=\'headerDIV\'><h2><a style="color: #990000;" href="http://www.upi.com/NewsTrack/Top_News/">Top News</a></h2></div>.*?<br clear="all">', lambda match : ''),
(r'<script src="http://www.g.*?>.*?</body>', lambda match : ''),
(r'<span style="font: 16pt arial', lambda match : '<span style="font: 12pt arial'),
]
]
def get_feeds(self):
return [ ('Top Stories', 'http://www.upi.com/rss/NewsTrack/Top_News/'),
('Science', 'http://www.upi.com/rss/NewsTrack/Science/'),
('Heatlth', 'http://www.upi.com/rss/NewsTrack/Health/'),
('Quirks', 'http://www.upi.com/rss/NewsTrack/Quirks/'),
]
def print_version(self, url):
return (url + 'print_view/')

44
src/libprs500/ebooks/lrf/web/profiles/wash_post.py Normal file
View File

@ -0,0 +1,44 @@
import re
from libprs500.ebooks.lrf.web.profiles import DefaultProfile
class WashingtonPost(DefaultProfile):
title = 'Washington Post'
max_recursions = 2
max_articles_per_feed = 20
use_pubdate = False
preprocess_regexps = [ (re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
[
(r'<HEAD>.*?</HEAD>' , lambda match : '<HEAD></HEAD>'),
(r'<div id="apple-rss-sidebar-background">.*?<!-- start Entries -->', lambda match : ''),
(r'<!-- end apple-rss-content-area -->.*?</body>', lambda match : '</body>'),
(r'<script.*?>.*?</script>', lambda match : ''),
(r'<body.*?>.*?.correction {', lambda match : '<body><style>.correction {'),
(r'<span class="display:none;" name="pubDate".*?>.*?</body>', lambda match : '<body>'),
]
]
def get_feeds(self):
return [ ('Today\'s Highlights', 'http://www.washingtonpost.com/wp-dyn/rss/linkset/2005/03/24/LI2005032400102.xml'),
('Politics', 'http://www.washingtonpost.com/wp-dyn/rss/politics/index.xml'),
('Nation', 'http://www.www.washingtonpost.com/wp-dyn/rss/nation/index.xml'),
('World', 'http://www.washingtonpost.com/wp-dyn/rss/world/index.xml'),
('Business', 'http://www.washingtonpost.com/wp-dyn/rss/business/index.xml'),
('Technology', 'http://www.washingtonpost.com/wp-dyn/rss/technology/index.xml'),
('Health', 'http://www.washingtonpost.com/wp-dyn/rss/health/index.xml'),
('Education', 'http://www.washingtonpost.com/wp-dyn/rss/education/index.xml'),
('Editorials', 'http://www.washingtonpost.com/wp-dyn/rss/linkset/2005/05/30/LI2005053000331.xml'),
]
def print_version(self, url):
return (url.rpartition('.')[0] + '_pf.html')