Merge from trunk

This commit is contained in:
Charles Haley 2010-08-29 18:15:41 +01:00
commit 2902ff6a67
5 changed files with 112 additions and 2 deletions

View File

@ -0,0 +1,55 @@
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1282101454(BasicNewsRecipe):
title = 'West Hawaii Today'
language = 'en'
__author__ = 'Tony Stegall'
description = 'Westhawaiitoday.com'
publisher = 'West Hawaii '
category = 'news,Hawaii,USA'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
remove_javascript = True
masthead_url = 'http://images.townnews.com/westhawaiitoday.com/art/whttoplogo.gif'
feeds = [
('Local News', 'http://www.westhawaiitoday.com/?rss=local/'),
('Local Sports', 'http://www.westhawaiitoday.com/?rss=sports/local_sports/'),
('Big Fish List', 'http://www.westhawaiitoday.com/?rss=sports/big_fish_list/'),
('Local Features' 'http://www.westhawaiitoday.com/?rss=features/'),
('Obituaries', 'http://www.westhawaiitoday.com/?rss=obituaries/'),
('Letters To Editor', 'http://www.westhawaiitoday.com/?rss=opinion/letters_-_your_voice/'),
('Editorial', 'http://www.westhawaiitoday.com/?rss=opinion/editorial/'),
('Columns', 'http://www.westhawaiitoday.com/?rss=opinion/columns/'),
('Volcano Update Sunday', 'http://www.westhawaiitoday.com/?rss=volcano/')
]
def print_version(self, url):
split1 = url.split("//")
url1 = split1[1]
xxx = split1[2]
split2 = xxx.split(".")
artid = split2[0]
print 'ARTICLE ID IS: ', artid
#example of link to convert
#Original link: http://www.westhawaiitoday.com/articles/2010/08/27/local//local01.txt
#print version: http://www.westhawaiitoday.com/articles/2010/08/27/local//local01.prt
print_url = 'http://' + url1 + '//' + artid + '.prt'
print 'print_url is: ', print_url
return print_url
#test with ebook-convert hawaii.recipe output_dir --test -vv > myrecipe.txt

View File

@ -0,0 +1,50 @@
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1282101454(BasicNewsRecipe):
title = 'Marietta Daily Journal'
__author__ = 'Tony Stegall'
language = 'en'
description = 'Marietta Ga and Metro Atlanta News'
publisher = 'MDJ'
category = 'news,politics,Georgia,USA'
oldest_article = 1
max_articles_per_feed = 100
no_stylesheets = True
remove_javascript = True
masthead_url = 'http://assets.matchbin.com/sites/624/assets/logo.gif'
keep_only_tags = [
dict(name='div', attrs={'id':['print_content_container']})
]
feeds = [
('Local News', 'http://mdjonline.com/rss/rss/Local+News?content_type=article&tags=news&page_name=rss&tag_inclusion=or&offset=0&limit=10&instance=Local+News'),
('Sports', 'http://mdjonline.com/rss/rss/Sports?content_type=article&tags=sports&page_name=rss&tag_inclusion=or&offset=0&limit=10&instance=Sports'),
('Obits', 'http://mdjonline.com/rss/rss/Obits?content_type=article&tags=obits&page_name=rss&tag_inclusion=or&offset=0&limit=20&instance=Obits'),
('Editorial & oped', 'http://mdjonline.com/rss/rss/Editorial+and+OPED?content_type=article&tags=oped+editorial&page_name=rss&tag_inclusion=or&offset=0&limit=10&instance=Editorial+and+OPED'),
('Lifestyle', 'http://mdjonline.com/rss/rss/Lifestyle?content_type=article&tags=lifestyle&page_name=rss&tag_inclusion=or&offset=0&limit=10&instance=Lifestyle'),
('Blogs', 'http://mdjonline.com/rss/rss/Lifestyle?content_type=article&tags=lifestyle&page_name=rss&tag_inclusion=or&offset=0&limit=10&instance=Lifestyle')
]
def print_version(self, url):
split1 = url.split("/")
artid = split1[4]
#example of link to convert
#Original link: http://mdjonline.com/bookmark/9274197
#print version: http://mdjonline.com/printer_friendly/9274197
print_url = 'http://mdjonline.com/printer_friendly/' + artid
return print_url
#test with ebook-convert nejm.recipe output_dir --test -vv > myrecipe.txt

View File

@ -491,6 +491,9 @@ class HTMLInput(InputFormatPlugin):
return (None, raw)
def preprocess_html(self, html):
if not hasattr(self, 'log'):
from calibre.utils.logging import default_log
self.log = default_log
self.log("********* Preprocessing HTML *********")
# Detect Chapters to match the xpath in the GUI
chapdetect = re.compile(r'(?=</?(br|p|span))(</?(br|p|span)[^>]*>)?\s*(?P<chap>(<(i|b)><(i|b)>|<(i|b)>)?(.?Chapter|Epilogue|Prologue|Book|Part|Dedication)\s*([\d\w-]+(\s\w+)?)?(</(i|b)></(i|b)>|</(i|b)>)?)(</?(p|br|span)[^>]*>)', re.IGNORECASE)

View File

@ -21,7 +21,8 @@ class SimilarBooksAction(InterfaceAction):
m = QMenu(self.gui)
for text, icon, target, shortcut in [
(_('Books by same author'), 'user_profile.svg', 'authors', _('Alt+A')),
(_('Books in this series'), 'books_in_series.svg', 'series', _('Alt+S')),
(_('Books in this series'), 'books_in_series.svg', 'series',
_('Alt+Shift+S')),
(_('Books by this publisher'), 'publisher.png', 'publisher', _('Alt+P')),
(_('Books with the same tags'), 'tags.svg', 'tag', _('Alt+T')),]:
ac = self.create_action(spec=(text, icon, None, shortcut),

View File

@ -195,7 +195,8 @@ class NavBarTemplate(Template):
if bottom:
navbar.append(HR())
text = 'This article was downloaded by '
p = PT(text, STRONG(__appname__), A(url, href=url), style='text-align:left')
p = PT(text, STRONG(__appname__), A(url, href=url),
style='text-align:left; max-width: 100%; overflow: hidden;')
p[0].tail = ' from '
navbar.append(p)
navbar.append(BR())