mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
Merge from trunk
This commit is contained in:
Charles Haley
commit
b08ae690fa
@ -59,10 +59,10 @@
|
||||
<a href="http://calibre-ebook.com"><img class="logo" src="{{ pathto('_static/' + logo, 1) }}" alt="Logo"/></a>
|
||||
</p>
|
||||
|
||||
<form action="https://www.paypal.com/cgi-bin/webscr" method="post">
|
||||
<form action="https://www.paypal.com/cgi-bin/webscr" method="post" title="Contribute to support calibre development">
|
||||
<input type="hidden" name="cmd" value="_s-xclick" />
|
||||
<input type="hidden" name="hosted_button_id" value="AF4H3B8QVDG6N" />
|
||||
<input type="image" src="http://manual.calibre-ebook.com/simple_donate_button.gif" border="0" name="submit" alt="Donate to support calibre development" style="border:0pt" />
|
||||
<input type="image" src="http://manual.calibre-ebook.com/simple_donate_button.gif" border="0" name="submit" alt="Contribute to support calibre development" style="border:0pt" />
|
||||
<img alt="" border="0" src="https://www.paypalobjects.com/en_GB/i/scr/pixel.gif" width="1" height="1" />
|
||||
</form>
|
||||
<hr/>
|
||||
|
||||
@ -1,45 +1,37 @@
|
||||
from __future__ import with_statement
|
||||
__license__ = 'GPL 3'
|
||||
__copyright__ = 'Original 2009, Kovid Goyal <kovid@kovidgoyal.net>'
|
||||
__copyright__= 'Modified 2011, Josh Hall <jwtheiv@gmail.com>'
|
||||
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
|
||||
__copyright__ = '2012 Josh Hall<jwtheiv@gmail.com>'
|
||||
__docformat__ = 'restructuredtext en'
|
||||
|
||||
'''
|
||||
www.baltimoresun.com
|
||||
'''
|
||||
|
||||
import urllib, re
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class BaltimoreSun(BasicNewsRecipe):
|
||||
|
||||
title = 'The Baltimore Sun'
|
||||
__author__ = 'Josh Hall'
|
||||
description = 'Politics, local and business news from Baltimore'
|
||||
language = 'en'
|
||||
|
||||
description = 'Complete local news and blogs from Baltimore'
|
||||
language = 'en'
|
||||
version = 2
|
||||
oldest_article = 1
|
||||
max_articles_per_feed = 100
|
||||
remove_empty_feeds = True
|
||||
use_embedded_content = False
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
#masthead_url = 'http://www.baltimoresun.com/images/thirdpartylogo.gif'
|
||||
|
||||
remove_tags_before = dict(name='div', attrs={'class':['story', 'entry']})
|
||||
remove_tags_after = [
|
||||
{'class':['photo_article',]},
|
||||
dict(name='div', attrs={'class':'shirttail-promo right clearfix'}),
|
||||
]
|
||||
use_embedded_content = False
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
recursions = 1
|
||||
|
||||
keep_only_tags = [dict(name='div', attrs={'class':["story","entry-asset asset hentry"]}),
|
||||
dict(name='div', attrs={'id':["pagebody","story","maincontentcontainer"]}),
|
||||
]
|
||||
remove_tags_after = [{'class':['photo_article',]}]
|
||||
|
||||
match_regexps = [r'page=[0-9]+']
|
||||
|
||||
remove_tags = [{'id':["moduleArticleTools","content-bottom","rail","articleRelates module","toolSet","relatedrailcontent","div-wrapper","beta","atp-comments","footer","article-promo"]},
|
||||
{'class':["entry-footer-left","entry-footer-right","shirttail-promo right clearfix","clearfix","relatedTitle","articleRelates module","asset-footer","tools","comments","featurePromo","featurePromo fp-topjobs brownBackground","clearfix fullSpan brownBackground","curvedContent","toppaginate","module","module-header","module-content"]},
|
||||
dict(name='font',attrs={'id':["cr-other-headlines"]}),
|
||||
dict(name=['iframe']),
|
||||
]
|
||||
remove_tags = [{'id':["moduleArticleTools","content-bottom","rail","articleRelates module","toolSet","relatedrailcontent","div-wrapper","beta","atp-comments","footer",'gallery-subcontent','subFooter']},
|
||||
{'class':["clearfix","relatedTitle","articleRelates module","asset-footer","tools","comments","featurePromo","featurePromo fp-topjobs brownBackground","clearfix fullSpan brownBackground","curvedContent",'nextgen-share-tools','outbrainTools', 'google-ad-story-bottom']},
|
||||
dict(name='font',attrs={'id':["cr-other-headlines"]})]
|
||||
extra_css = '''
|
||||
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
|
||||
h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
|
||||
@ -53,8 +45,9 @@ class BaltimoreSun(BasicNewsRecipe):
|
||||
.maincontentcontainer{font-family:Arial,Helvetica,sans-serif;font-size:small;}
|
||||
.story-body{font-family:Arial,Helvetica,sans-serif;font-size:small;}
|
||||
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
|
||||
'''
|
||||
'''
|
||||
feeds = [
|
||||
## News ##
|
||||
(u'Top Headlines', u'http://www.baltimoresun.com/rss2.0.xml'),
|
||||
(u'Breaking News', u'http://www.baltimoresun.com/news/breaking/rss2.0.xml'),
|
||||
(u'Top Maryland', u'http://www.baltimoresun.com/news/maryland/rss2.0.xml'),
|
||||
@ -69,10 +62,10 @@ class BaltimoreSun(BasicNewsRecipe):
|
||||
(u'Local Politics', u'http://www.baltimoresun.com/news/maryland/politics/rss2.0.xml'),
|
||||
(u'Weather', u'http://www.baltimoresun.com/news/weather/rss2.0.xml'),
|
||||
#(u'Traffic', u'http://www.baltimoresun.com/features/commuting/rss2.0.xml'),
|
||||
(u'Nation/world', u'http://feeds.chicagotribune.com/chicagotribune/news/nationworld/'),
|
||||
(u'Nation/world', u'http://feeds.feedburner.com/baltimoresun/news/nationworld/rss2'),
|
||||
(u'Weird News', u'http://www.baltimoresun.com/news/offbeat/rss2.0.xml'),
|
||||
|
||||
|
||||
##Sports##
|
||||
(u'Top Sports', u'http://www.baltimoresun.com/sports/rss2.0.xml'),
|
||||
(u'Orioles/Baseball', u'http://www.baltimoresun.com/sports/orioles/rss2.0.xml'),
|
||||
(u'Ravens/Football', u'http://www.baltimoresun.com/sports/ravens/rss2.0.xml'),
|
||||
@ -85,6 +78,7 @@ class BaltimoreSun(BasicNewsRecipe):
|
||||
#(u'High School', u'http://www.baltimoresun.com/sports/high-school/rss2.0.xml'),
|
||||
#(u'Outdoors', u'http://www.baltimoresun.com/sports/outdoors/rss2.0.xml'),
|
||||
|
||||
## Entertainment ##
|
||||
(u'Celebrity News', u'http://www.baltimoresun.com/entertainment/celebrities/rss2.0.xml'),
|
||||
(u'Arts & Theater', u'http://www.baltimoresun.com/entertainment/arts/rss2.0.xml'),
|
||||
(u'Movies', u'http://www.baltimoresun.com/entertainment/movies/rss2.0.xml'),
|
||||
@ -92,14 +86,16 @@ class BaltimoreSun(BasicNewsRecipe):
|
||||
(u'Restaurants & Food', u'http://www.baltimoresun.com/entertainment/dining/rss2.0.xml'),
|
||||
(u'TV/Media', u'http://www.baltimoresun.com/entertainment/tv/rss2.0.xml'),
|
||||
|
||||
## Life ##
|
||||
(u'Health&Wellness', u'http://www.baltimoresun.com/health/rss2.0.xml'),
|
||||
(u'Home & Garden', u'http://www.baltimoresun.com/features/home-garden/rss2.0.xml'),
|
||||
(u'Living Green', u'http://www.baltimoresun.com/features/green/rss2.0.xml'),
|
||||
(u'Parenting', u'http://www.baltimoresun.com/features/parenting/rss2.0.xml'),
|
||||
(u'Fashion', u'http://www.baltimoresun.com/features/fashion/rss2.0.xml'),
|
||||
(u'Travel', u'http://www.baltimoresun.com/travel/rss2.0.xml'),
|
||||
(u'Faith', u'http://www.baltimoresun.com/features/faith/rss2.0.xml'),
|
||||
#(u'Faith', u'http://www.baltimoresun.com/features/faith/rss2.0.xml'),
|
||||
|
||||
## Business ##
|
||||
(u'Top Business', u'http://www.baltimoresun.com/business/rss2.0.xml'),
|
||||
(u'Technology', u'http://www.baltimoresun.com/business/technology/rss2.0.xml'),
|
||||
(u'Personal finance', u'http://www.baltimoresun.com/business/money/rss2.0.xml'),
|
||||
@ -109,12 +105,14 @@ class BaltimoreSun(BasicNewsRecipe):
|
||||
(u'Consumer Safety', u'http://www.baltimoresun.com/business/consumer-safety/rss2.0.xml'),
|
||||
(u'Investing', u'http://www.baltimoresun.com/business/money/rss2.0.xml'),
|
||||
|
||||
## Opinion##
|
||||
(u'Sun Editorials', u'http://www.baltimoresun.com/news/opinion/editorial/rss2.0.xml'),
|
||||
(u'Op/Ed', u'http://www.baltimoresun.com/news/opinion/oped/rss2.0.xml'),
|
||||
(u'Readers Respond', u'http://www.baltimoresun.com/news/opinion/readersrespond/'),
|
||||
|
||||
(u'Kevin Cowherd', 'http://www.baltimoresun.com/sports/bal-columnist-cowherd,0,6829726.columnist-rss2.0.xml'),
|
||||
(u'Jay Hancock', u'http://www.baltimoresun.com/business/money/bal-columnist-hancock,0,6673611.columnist-rss2.0.xml'),
|
||||
## Columnists ##
|
||||
(u'Kevin Cowherd', u'http://www.baltimoresun.com/sports/bal-columnist-cowherd,0,6829726.columnist-rss2.0.xml'),
|
||||
(u'Robert Ehrlich', u'http://www.baltimoresun.com/news/opinion/columnists/bal-columnist-ehrlich,0,1825227.columnist-rss2.0.xml'),
|
||||
(u'Jacques Kelly', u'http://www.baltimoresun.com/news/maryland/bal-columnist-kelly,0,1154701.columnist-rss2.0.xml'),
|
||||
(u'Marta H. Mossburg', u'http://www.baltimoresun.com/news/opinion/oped/bal-columnist-mossburg,0,7982155.columnist-rss2.0.xml'),
|
||||
(u'Mike Preston', u'http://www.baltimoresun.com/sports/bal-columnist-preston,0,6169796.columnist-rss2.0.xml'),
|
||||
@ -122,59 +120,80 @@ class BaltimoreSun(BasicNewsRecipe):
|
||||
(u'Dan Rodricks', u'http://www.baltimoresun.com/news/maryland/bal-columnist-rodricks,0,7089843.columnist-rss2.0.xml'),
|
||||
(u'Thomas F. Schaller', u'http://www.baltimoresun.com/news/opinion/columnists/bal-columnist-schaller,0,897397.columnist-rss2.0.xml'),
|
||||
(u'Peter Schmuck', u'http://www.baltimoresun.com/sports/bal-columnist-schmuck,0,7485088.columnist-rss2.0.xml'),
|
||||
(u'Ron Smith', u'http://www.baltimoresun.com/news/opinion/bal-columnist-ronsmith,0,3964803.columnist-rss2.0.xml'),
|
||||
|
||||
(u'Baltimore Crime Beat', u'http://weblogs.baltimoresun.com/news/crime/blog/index.xml'),
|
||||
(u'Getting There', u'http://weblogs.baltimoresun.com/news/traffic/index.xml'),
|
||||
(u'InsideEd', u'http://weblogs.baltimoresun.com/news/education/blog/index.xml'),
|
||||
(u'Maryland Politics', u'http://weblogs.baltimoresun.com/news/local/politics/index.xml'),
|
||||
(u'Maryland Weather', u'http://weblogs.marylandweather.com/index.xml'),
|
||||
(u'Second Opinion', u'http://weblogs.baltimoresun.com/news/opinion/index.xml'),
|
||||
(u'You Dont Say', u'http://weblogs.baltimoresun.com/news/mcintyre/blog/index.xml'),
|
||||
## News Blogs ##
|
||||
(u'Baltimore Crime Beat', u'http://baltimore.feedsportal.com/c/34255/f/623075/index.rss'),
|
||||
(u'InsideEd', u'http://www.baltimoresun.com/news/maryland/education/blog/rss2.0.xml'),
|
||||
(u'Maryland Politics', u'http://www.baltimoresun.com/news/maryland/politics/blog/rss2.0.xml'),
|
||||
(u'Maryland Weather', u'http://www.baltimoresun.com/news/weather/weather-blog/rss2.0.xml'),
|
||||
(u'Second Opinion', u'http://www.baltimoresun.com/news/opinion/second-opinion-blog/rss2.0.xml'),
|
||||
(u'Sun Investigates', u'http://www.baltimoresun.com/news/maryland/sun-investigates/rss2.0.xml'),
|
||||
(u'You Dont Say', u'http://www.baltimoresun.com/news/language-blog/rss2.0.xml'),
|
||||
|
||||
(u'BaltTech', u'http://weblogs.baltimoresun.com/news/technology/index.xml'),
|
||||
(u'Consuming Interests', u'http://weblogs.baltimoresun.com/business/consuminginterests/blog/index.xml'),
|
||||
(u'Jay Hancocks Blog', u'http://weblogs.baltimoresun.com/business/hancock/blog/index.xml'),
|
||||
(u'The Real Estate Wonk', u'http://weblogs.baltimoresun.com/business/realestate/blog/index.xml'),
|
||||
## Business Blogs ##
|
||||
(u'BaltTech', u'http://www.baltimoresun.com/business/technology/blog/rss2.0.xml'),
|
||||
(u'Consuming Interests', u'http://www.baltimoresun.com/business/consuming-interests-blog/rss2.0.xml'),
|
||||
(u'The Real Estate Wonk', u'http://www.baltimoresun.com/business/real-estate/wonk/rss2.0.xml'),
|
||||
|
||||
(u'Clef Notes', 'http://weblogs.baltimoresun.com/entertainment/classicalmusic/index.xml'),
|
||||
(u'Dining at Large', u'http://weblogs.baltimoresun.com/entertainment/dining/reviews/blog/index.xml'),
|
||||
(u'Midnight Sun', u'http://weblogs.baltimoresun.com/entertainment/midnight_sun/blog/index.xml'),
|
||||
(u'Mike Sragow Gets Reel', u'http://weblogs.baltimoresun.com/entertainment/movies/blog/index.xml'),
|
||||
(u'Read Street', u'http://weblogs.baltimoresun.com/entertainment/books/blog/index.xml'),
|
||||
(u'Reality Check', u'http://weblogs.baltimoresun.com/entertainment/realitycheck/blog/index.xml'),
|
||||
(u'Z on TV', u'http://weblogs.baltimoresun.com/entertainment/zontv/index.xml'),
|
||||
## Entertainment Blogs ##
|
||||
(u'Clef Notes & Drama Queens', 'http://weblogs.baltimoresun.com/entertainment/classicalmusic/index.xml'),
|
||||
(u'Baltimore Diner', u'http://baltimore.feedsportal.com/c/34255/f/623088/index.rss'),
|
||||
(u'Midnight Sun', u'http://www.baltimoresun.com/entertainment/music/midnight-sun-blog/rss2.0.xml'),
|
||||
(u'Read Street', u'http://www.baltimoresun.com/features/books/read-street/rss2.0.xml'),
|
||||
(u'Z on TV', u'http://www.baltimoresun.com/entertainment/tv/z-on-tv-blog/rss2.0.xml'),
|
||||
|
||||
## Life Blogs ##
|
||||
(u'BMore Green', u'http://weblogs.baltimoresun.com/features/green/index.xml'),
|
||||
(u'Charm City Moms', u'http://weblogs.baltimoresun.com/features/baltimoremomblog/index.xml'),
|
||||
(u'Exercists', u'http://weblogs.baltimoresun.com/health/fitness/index.xml'),
|
||||
(u'Garden Variety', 'http://weblogs.baltimoresun.com/features/gardening/index.xml'),
|
||||
#(u'In Good Faith', u'http://weblogs.baltimoresun.com/news/faith/index.xml'),
|
||||
(u'Picture of Health', u'http://weblogs.baltimoresun.com/health/index.xml'),
|
||||
(u'Baltimore Insider',u'http://www.baltimoresun.com/features/baltimore-insider-blog/rss2.0.xml'),
|
||||
(u'Homefront', u'http://www.baltimoresun.com/features/parenting/homefront/rss2.0.xml'),
|
||||
(u'Picture of Health', u'http://www.baltimoresun.com/health/blog/rss2.0.xml'),
|
||||
(u'Unleashed', u'http://weblogs.baltimoresun.com/features/mutts/blog/index.xml'),
|
||||
|
||||
## b the site blogs ##
|
||||
(u'Game Cache', u'http://www.baltimoresun.com/entertainment/bthesite/game-cache/rss2.0.xml'),
|
||||
(u'TV Lust', u'http://www.baltimoresun.com/entertainment/bthesite/tv-lust/rss2.0.xml'),
|
||||
|
||||
## Sports Blogs ##
|
||||
(u'Baltimore Sports Blitz', u'http://baltimore.feedsportal.com/c/34255/f/623097/index.rss'),
|
||||
#(u'Faceoff', u'http://weblogs.baltimoresun.com/sports/lacrosse/blog/index.xml'),
|
||||
#(u'MMA Stomping Grounds', u'http://weblogs.baltimoresun.com/sports/mma/blog/index.xml'),
|
||||
(u'Orioles Insider', u'http://weblogs.baltimoresun.com/sports/orioles/blog/index.xml'),
|
||||
#(u'Outdoors Girl', u'http://weblogs.baltimoresun.com/sports/outdoors/blog/index.xml'),
|
||||
(u'Ravens Insider', u'http://weblogs.baltimoresun.com/sports/ravens/blog/index.xml'),
|
||||
(u'Orioles Insider', u'http://baltimore.feedsportal.com/c/34255/f/623100/index.rss'),
|
||||
(u'Ravens Insider', u'http://www.baltimoresun.com/sports/ravens/ravens-insider/rss2.0.xml'),
|
||||
#(u'Recruiting Report', u'http://weblogs.baltimoresun.com/sports/college/recruiting/index.xml'),
|
||||
#(u'Ring Posts', u'http://weblogs.baltimoresun.com/sports/wrestling/blog/index.xml'),
|
||||
(u'The Schmuck Stops Here', u'http://weblogs.baltimoresun.com/sports/schmuck/index.xml'),
|
||||
(u'Toy Department', u'http://weblogs.baltimoresun.com/sports/thetoydepartment/index.xml'),
|
||||
(u'The Schmuck Stops Here', u'http://www.baltimoresun.com/sports/schmuck-blog/rss2.0.xml'),
|
||||
#(u'Tracking the Terps', u'http://weblogs.baltimoresun.com/sports/college/maryland_terps/blog/index.xml'),
|
||||
#(u'Varsity Letters', u'http://weblogs.baltimoresun.com/sports/highschool/varsityletters/index.xml'),
|
||||
(u'Virtual Vensanity', u'http://weblogs.baltimoresun.com/entertainment/bthesite/vensel/index.xml'),
|
||||
|
||||
]
|
||||
|
||||
|
||||
def get_article_url(self, article):
|
||||
print article.get('feedburner_origlink', article.get('guid', article.get('link')))
|
||||
return article.get('feedburner_origlink', article.get('guid', article.get('link')))
|
||||
ans = None
|
||||
try:
|
||||
s = article.summary
|
||||
ans = urllib.unquote(
|
||||
re.search(r'href=".+?bookmark.cfm.+?link=(.+?)"', s).group(1))
|
||||
except:
|
||||
pass
|
||||
if ans is None:
|
||||
ans = article.get('feedburner_origlink', article.get('guid', article.get('link')))
|
||||
if ans is not None:
|
||||
return ans.replace('?track=rss', '')
|
||||
|
||||
def skip_ad_pages(self, soup):
|
||||
text = soup.find(text='click here to continue to article')
|
||||
if text:
|
||||
a = text.parent
|
||||
url = a.get('href')
|
||||
if url:
|
||||
return self.index_to_soup(url, raw=True)
|
||||
|
||||
def postprocess_html(self, soup, first_fetch):
|
||||
# Remove the navigation bar. It was kept until now to be able to follow
|
||||
# the links to further pages. But now we don't need them anymore.
|
||||
for nav in soup.findAll(attrs={'class':['toppaginate','article-nav clearfix']}):
|
||||
nav.extract()
|
||||
|
||||
for t in soup.findAll(['table', 'tr', 'td']):
|
||||
t.name = 'div'
|
||||
|
||||
@ -182,5 +201,3 @@ class BaltimoreSun(BasicNewsRecipe):
|
||||
tag.extract()
|
||||
for tag in soup.findAll('font', dict(attrs={'id':["cr-other-headlines"]})):
|
||||
tag.extract()
|
||||
|
||||
return soup
|
||||
|
||||
@ -1,3 +1,4 @@
|
||||
import re
|
||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
||||
from collections import OrderedDict
|
||||
|
||||
@ -14,7 +15,8 @@ class Chronicle(BasicNewsRecipe):
|
||||
dict(name='div', attrs={'class':'article'}),
|
||||
]
|
||||
remove_tags = [dict(name='div',attrs={'class':['related module1','maintitle']}),
|
||||
dict(name='div', attrs={'id':['section-nav','icon-row']})]
|
||||
dict(name='div', attrs={'id':['section-nav','icon-row', 'enlarge-popup']}),
|
||||
dict(name='a', attrs={'class':'show-enlarge enlarge'})]
|
||||
no_javascript = True
|
||||
no_stylesheets = True
|
||||
|
||||
@ -31,7 +33,6 @@ class Chronicle(BasicNewsRecipe):
|
||||
return br
|
||||
|
||||
def parse_index(self):
|
||||
|
||||
#Go to the issue
|
||||
soup0 = self.index_to_soup('http://chronicle.com/section/Archives/39/')
|
||||
issue = soup0.find('ul',attrs={'class':'feature-promo-list'}).li
|
||||
@ -42,9 +43,12 @@ class Chronicle(BasicNewsRecipe):
|
||||
self.timefmt = u' [%s]'%dates
|
||||
|
||||
#Find cover
|
||||
cover=soup0.find('div',attrs={'class':'promo'}).findNext('div')
|
||||
self.cover_url="http://chronicle.com"+cover.find('img')['src']
|
||||
|
||||
cover=soup0.find('div',attrs={'class':'side-content'}).find(attrs={'src':re.compile("photos/biz/Current")})
|
||||
if cover is not None:
|
||||
if "chronicle.com" in cover['src']:
|
||||
self.cover_url=cover['src']
|
||||
else:
|
||||
self.cover_url="http://chronicle.com" + cover['src']
|
||||
#Go to the main body
|
||||
soup = self.index_to_soup(issueurl)
|
||||
div = soup.find ('div', attrs={'id':'article-body'})
|
||||
@ -74,8 +78,10 @@ class Chronicle(BasicNewsRecipe):
|
||||
def preprocess_html(self,soup):
|
||||
#process all the images
|
||||
for div in soup.findAll('div', attrs={'class':'tableauPlaceholder'}):
|
||||
|
||||
noscripts=div.find('noscript').a
|
||||
div.replaceWith(noscripts)
|
||||
for div0 in soup.findAll('div',text='Powered by Tableau'):
|
||||
div0.extract()
|
||||
return soup
|
||||
|
||||
|
||||
@ -41,7 +41,7 @@ class ElPais_RSS(BasicNewsRecipe):
|
||||
,dict(attrs={'class':['firma','columna_texto','entrevista_p_r']})
|
||||
]
|
||||
remove_tags = [
|
||||
dict(name=['meta','link','base','iframe','embed','object'])
|
||||
dict(name=['iframe','embed','object'])
|
||||
,dict(attrs={'class':'disposicion_vertical'})
|
||||
]
|
||||
|
||||
@ -74,13 +74,14 @@ class ElPais_RSS(BasicNewsRecipe):
|
||||
,(u'Justicia y Leyes' , u'http://elpais.com/tag/rss/justicia/a/' )
|
||||
,(u'Guerras y conflictos' , u'http://elpais.com/tag/rss/conflictos/a/' )
|
||||
,(u'Politica' , u'http://ep00.epimg.net/rss/politica/portada.xml' )
|
||||
,(u'Opinion' , u'http://ep01.epimg.net/rss/politica/opinion.xml' )
|
||||
,(u'Opinion' , u'http://ep01.epimg.net/rss/elpais/opinion.xml' )
|
||||
]
|
||||
|
||||
def get_article_url(self, article):
|
||||
url = BasicNewsRecipe.get_article_url(self, article)
|
||||
if url and (not('/album/' in url) and not('/futbol/partido/' in url)):
|
||||
return url
|
||||
urlverified = self.browser.open_novisit(url).geturl()
|
||||
return urlverified
|
||||
self.log('Skipping non-article', url)
|
||||
return None
|
||||
|
||||
@ -107,3 +108,7 @@ class ElPais_RSS(BasicNewsRecipe):
|
||||
for item in soup.findAll('img',alt=False):
|
||||
item['alt'] = 'image'
|
||||
return soup
|
||||
|
||||
def preprocess_raw_html(self, raw, url):
|
||||
return '<html><head><title>Untitled</title>'+raw[raw.find('</head>'):]
|
||||
|
||||
@ -1,5 +1,5 @@
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2010-2011, Darko Miletic <darko.miletic at gmail.com>'
|
||||
__copyright__ = '2010-2012, Darko Miletic <darko.miletic at gmail.com>'
|
||||
'''
|
||||
www.ft.com/uk-edition
|
||||
'''
|
||||
@ -51,10 +51,15 @@ class FinancialTimes(BasicNewsRecipe):
|
||||
return br
|
||||
|
||||
keep_only_tags = [
|
||||
dict(name='div', attrs={'class':['fullstory fullstoryHeader', 'ft-story-header']})
|
||||
,dict(name='div', attrs={'class':'standfirst'})
|
||||
,dict(name='div', attrs={'id' :'storyContent'})
|
||||
,dict(name='div', attrs={'class':['ft-story-body','index-detail']})
|
||||
dict(name='div' , attrs={'class':['fullstory fullstoryHeader', 'ft-story-header']})
|
||||
,dict(name='div' , attrs={'class':'standfirst'})
|
||||
,dict(name='div' , attrs={'id' :'storyContent'})
|
||||
,dict(name='div' , attrs={'class':['ft-story-body','index-detail']})
|
||||
,dict(name='div' , attrs={'class':['ft-story-body','index-detail']})
|
||||
,dict(name='h2' , attrs={'class':'entry-title'} )
|
||||
,dict(name='span', attrs={'class':lambda x: x and 'posted-on' in x.split()} )
|
||||
,dict(name='span', attrs={'class':'author_byline'} )
|
||||
,dict(name='div' , attrs={'class':'entry-content'} )
|
||||
]
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'id':'floating-con'})
|
||||
@ -83,10 +88,9 @@ class FinancialTimes(BasicNewsRecipe):
|
||||
if self.test and count > 2:
|
||||
return articles
|
||||
rawlink = item['href']
|
||||
if rawlink.startswith('http://'):
|
||||
url = rawlink
|
||||
else:
|
||||
url = self.PREFIX + rawlink
|
||||
url = rawlink
|
||||
if not rawlink.startswith('http://'):
|
||||
url = self.PREFIX + rawlink
|
||||
urlverified = self.browser.open_novisit(url).geturl() # resolve redirect.
|
||||
title = self.tag_to_string(item)
|
||||
date = strftime(self.timefmt)
|
||||
@ -106,20 +110,20 @@ class FinancialTimes(BasicNewsRecipe):
|
||||
wide = soup.find('div',attrs={'class':'wide'})
|
||||
if not wide:
|
||||
return feeds
|
||||
strest = wide.findAll('h3', attrs={'class':'section'})
|
||||
if not strest:
|
||||
allsections = wide.findAll(attrs={'class':lambda x: x and 'footwell' in x.split()})
|
||||
if not allsections:
|
||||
return feeds
|
||||
st = wide.findAll('h4',attrs={'class':'section-no-arrow'})
|
||||
if st:
|
||||
st.extend(strest)
|
||||
count = 0
|
||||
for item in st:
|
||||
for item in allsections:
|
||||
count = count + 1
|
||||
if self.test and count > 2:
|
||||
return feeds
|
||||
ftitle = self.tag_to_string(item)
|
||||
fitem = item.h3
|
||||
if not fitem:
|
||||
fitem = item.h4
|
||||
ftitle = self.tag_to_string(fitem)
|
||||
self.report_progress(0, _('Fetching feed')+' %s...'%(ftitle))
|
||||
feedarts = self.get_artlinks(item.parent.ul)
|
||||
feedarts = self.get_artlinks(item.ul)
|
||||
feeds.append((ftitle,feedarts))
|
||||
return feeds
|
||||
|
||||
@ -166,7 +170,8 @@ class FinancialTimes(BasicNewsRecipe):
|
||||
except:
|
||||
print "Retrying download..."
|
||||
count += 1
|
||||
self.temp_files.append(PersistentTemporaryFile('_fa.html'))
|
||||
self.temp_files[-1].write(html)
|
||||
self.temp_files[-1].close()
|
||||
return self.temp_files[-1].name
|
||||
tfile = PersistentTemporaryFile('_fa.html')
|
||||
tfile.write(html)
|
||||
tfile.close()
|
||||
self.temp_files.append(tfile)
|
||||
return tfile.name
|
||||
|
||||
BIN
recipes/icons/monitor.png
Normal file
BIN
recipes/icons/monitor.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 1.1 KiB |
@ -34,20 +34,21 @@ class macWorld(BasicNewsRecipe):
|
||||
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
auto_cleanup = True
|
||||
|
||||
keep_only_tags = [
|
||||
dict(name='div', attrs={'id':'content'})
|
||||
]
|
||||
#keep_only_tags = [
|
||||
#dict(name='div', attrs={'id':'content'})
|
||||
#]
|
||||
|
||||
remove_tags = [
|
||||
{'class':['toolBar','mac_tags','toolBar btmTools','textAds']},
|
||||
dict(name='p', attrs={'class':'breadcrumbs'}),
|
||||
dict(id=['breadcrumb','sidebar','comments','topContentWrapper',
|
||||
'rightColumn', 'aboveFootPromo', 'storyCarousel']),
|
||||
{'class':lambda x: x and ('tools' in x or 'toolBar'
|
||||
in x)}
|
||||
#remove_tags = [
|
||||
#{'class':['toolBar','mac_tags','toolBar btmTools','textAds']},
|
||||
#dict(name='p', attrs={'class':'breadcrumbs'}),
|
||||
#dict(id=['breadcrumb','sidebar','comments','topContentWrapper',
|
||||
#'rightColumn', 'aboveFootPromo', 'storyCarousel']),
|
||||
#{'class':lambda x: x and ('tools' in x or 'toolBar'
|
||||
#in x)}
|
||||
|
||||
]
|
||||
#]
|
||||
|
||||
feeds = [
|
||||
(u'MacWorld Headlines', u'http://rss.macworld.com/macworld/news'),
|
||||
@ -82,3 +83,4 @@ class macWorld(BasicNewsRecipe):
|
||||
.articleInfo {color:#4D4D4D;font-family:Arial,Helvetica,sans-serif;font-size:10px; font-size-adjust:none; font-stretch:normal; font-style:bold; font-variant:normal; font-weight:bold; line-height:10px; text-decoration:none;}
|
||||
img {align:left;}
|
||||
'''
|
||||
|
||||
|
||||
@ -1,4 +1,3 @@
|
||||
from calibre.ptempfile import PersistentTemporaryFile
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class AdvancedUserRecipe1276930924(BasicNewsRecipe):
|
||||
@ -14,30 +13,30 @@ class AdvancedUserRecipe1276930924(BasicNewsRecipe):
|
||||
use_embedded_content = False
|
||||
no_stylesheets = True
|
||||
language = 'en'
|
||||
temp_files = []
|
||||
articles_are_obfuscated = True
|
||||
feeds = [(u'News', u'http://www.maximumpc.com/articles/4/feed'),
|
||||
auto_cleanup = True
|
||||
feeds = [#(u'News', u'http://www.maximumpc.com/articles/all/feed'),
|
||||
(u'News', u'http://www.maximumpc.com/articles/4/feed'),
|
||||
(u'Reviews', u'http://www.maximumpc.com/articles/40/feed'),
|
||||
(u'Editors Blog', u'http://www.maximumpc.com/articles/6/feed'),
|
||||
(u'How-to', u'http://www.maximumpc.com/articles/32/feed'),
|
||||
(u'Features', u'http://www.maximumpc.com/articles/31/feed'),
|
||||
(u'From the Magazine', u'http://www.maximumpc.com/articles/72/feed')
|
||||
]
|
||||
keep_only_tags = [
|
||||
dict(name='div', attrs={'class':['print-title','article_body']}),
|
||||
]
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'class':'comments-tags-actions'}),
|
||||
]
|
||||
remove_tags_before = dict(name='div', attrs={'class':'print-title'})
|
||||
remove_tags_after = dict(name='div', attrs={'class':'meta-content'})
|
||||
#keep_only_tags = [
|
||||
#dict(name='div', attrs={'class':['print-title','article_body']}),
|
||||
#]
|
||||
#remove_tags = [
|
||||
#dict(name='div', attrs={'class':'comments-tags-actions'}),
|
||||
#]
|
||||
#remove_tags_before = dict(name='div', attrs={'class':'print-title'})
|
||||
#remove_tags_after = dict(name='div', attrs={'class':'meta-content'})
|
||||
|
||||
def get_obfuscated_article(self, url):
|
||||
br = self.get_browser()
|
||||
br.open(url)
|
||||
response = br.follow_link(url_regex = r'/print/[0-9]+', nr = 0)
|
||||
html = response.read()
|
||||
self.temp_files.append(PersistentTemporaryFile('_fa.html'))
|
||||
self.temp_files[-1].write(html)
|
||||
self.temp_files[-1].close()
|
||||
return self.temp_files[-1].name
|
||||
#def get_obfuscated_article(self, url):
|
||||
#br = self.get_browser()
|
||||
#br.open(url)
|
||||
#response = br.follow_link(url_regex = r'/print/[0-9]+', nr = 0)
|
||||
#html = response.read()
|
||||
#self.temp_files.append(PersistentTemporaryFile('_fa.html'))
|
||||
#self.temp_files[-1].write(html)
|
||||
#self.temp_files[-1].close()
|
||||
#return self.temp_files[-1].name
|
||||
|
||||
@ -1,99 +1,66 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
|
||||
__copyright__ = '2009-2012, Darko Miletic <darko.miletic at gmail.com>'
|
||||
|
||||
'''
|
||||
monitorcg.com
|
||||
www.monitor.co.me
|
||||
'''
|
||||
|
||||
import re
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
from calibre.ebooks.BeautifulSoup import Tag
|
||||
|
||||
class MonitorCG(BasicNewsRecipe):
|
||||
title = 'Monitor online'
|
||||
title = 'MONITOR online'
|
||||
__author__ = 'Darko Miletic'
|
||||
description = 'News from Montenegro'
|
||||
publisher = 'MONITOR d.o.o. Podgorica'
|
||||
description = 'Nezavisni nedjeljnik Monitor'
|
||||
publisher = '"Monitor" D.O.O. Podgorica'
|
||||
category = 'news, politics, Montenegro'
|
||||
oldest_article = 15
|
||||
max_articles_per_feed = 150
|
||||
no_stylesheets = True
|
||||
encoding = 'utf-8'
|
||||
auto_cleanup = False
|
||||
use_embedded_content = False
|
||||
language = 'sr'
|
||||
|
||||
lang ='sr-Latn-Me'
|
||||
INDEX = 'http://www.monitorcg.com'
|
||||
|
||||
extra_css = ' @font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} body{font-family: serif1, serif} '
|
||||
language = 'sr'
|
||||
remove_empty_feeds = True
|
||||
extra_css = """
|
||||
@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)}
|
||||
@font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)}
|
||||
h2{font-family: Cambria,"Times New Roman",Times,serif1,serif}
|
||||
body{font-family: Arial,sans1,sans-serif}
|
||||
img{display: block}
|
||||
"""
|
||||
|
||||
conversion_options = {
|
||||
'comment' : description
|
||||
, 'tags' : category
|
||||
, 'publisher' : publisher
|
||||
, 'language' : lang
|
||||
, 'pretty_print' : True
|
||||
'comment' : description
|
||||
, 'tags' : category
|
||||
, 'publisher' : publisher
|
||||
, 'language' : language
|
||||
, 'pretty_print': True
|
||||
}
|
||||
|
||||
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
|
||||
keep_only_tags = [dict(attrs={'class':['contentheading','article-meta','article-content']})]
|
||||
remove_attributes = ['width','height','font','border','align']
|
||||
|
||||
keep_only_tags = [dict(name='div', attrs={'id':'ja-current-content'})]
|
||||
|
||||
remove_tags = [ dict(name=['object','link','embed'])
|
||||
, dict(attrs={'class':['buttonheading','article-section']})]
|
||||
|
||||
remove_attributes = ['style','width','height','font','border','align']
|
||||
|
||||
def adeify_images2(cls, soup):
|
||||
for item in soup.findAll('img'):
|
||||
for attrib in ['height','width','border','align','style']:
|
||||
if item.has_key(attrib):
|
||||
del item[attrib]
|
||||
oldParent = item.parent
|
||||
if oldParent.name == 'a':
|
||||
oldParent.name == 'p'
|
||||
myIndex = oldParent.contents.index(item)
|
||||
brtag = Tag(soup,'br')
|
||||
oldParent.insert(myIndex+1,brtag)
|
||||
return soup
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
soup.html['xml:lang'] = self.lang
|
||||
soup.html['lang'] = self.lang
|
||||
mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)])
|
||||
soup.html.insert(0,mlang)
|
||||
return self.adeify_images2(soup)
|
||||
|
||||
def parse_index(self):
|
||||
totalfeeds = []
|
||||
soup = self.index_to_soup(self.INDEX)
|
||||
cover_item = soup.find('div',attrs={'class':'ja-catslwi'})
|
||||
if cover_item:
|
||||
dt = cover_item['onclick'].partition("location.href=")[2]
|
||||
curl = self.INDEX + dt.strip("'")
|
||||
lfeeds = [(u'Svi clanci', curl)]
|
||||
for feedobj in lfeeds:
|
||||
feedtitle, feedurl = feedobj
|
||||
self.report_progress(0, _('Fetching feed')+' %s...'%(feedtitle if feedtitle else feedurl))
|
||||
articles = []
|
||||
soup = self.index_to_soup(feedurl)
|
||||
contitem = soup.find('div',attrs={'class':'article-content'})
|
||||
if contitem:
|
||||
img = contitem.find('img')
|
||||
if img:
|
||||
self.cover_url = self.INDEX + img['src']
|
||||
for item in contitem.findAll('a'):
|
||||
url = self.INDEX + item['href']
|
||||
title = self.tag_to_string(item)
|
||||
articles.append({
|
||||
'title' :title
|
||||
,'date' :''
|
||||
,'url' :url
|
||||
,'description':''
|
||||
})
|
||||
totalfeeds.append((feedtitle, articles))
|
||||
return totalfeeds
|
||||
|
||||
feeds = [
|
||||
(u'Danas, Sjutra' , u'http://www.monitor.co.me/index.php?option=com_content&view=section&layout=blog&id=5&Itemid=27&format=feed&type=rss')
|
||||
,(u'Duhankesa' , u'http://www.monitor.co.me/index.php?option=com_content&view=section&layout=blog&id=13&Itemid=37&format=feed&type=rss')
|
||||
,(u'Znaci prepoznavanja', u'http://www.monitor.co.me/index.php?option=com_content&view=section&layout=blog&id=6&Itemid=358&format=feed&type=rss')
|
||||
,(u'Paralele' , u'http://www.monitor.co.me/index.php?option=com_content&view=section&layout=blog&id=8&Itemid=359&format=feed&type=rss')
|
||||
,(u'Razbijeno ogledalo' , u'http://www.monitor.co.me/index.php?option=com_content&view=section&layout=blog&id=18&Itemid=354&format=feed&type=rss')
|
||||
,(u'Tržište' , u'http://www.monitor.co.me/index.php?option=com_content&view=section&layout=blog&id=26&Itemid=371&format=feed&type=rss')
|
||||
,(u'Feljton' , u'http://www.monitor.co.me/index.php?option=com_content&view=section&layout=blog&id=29&Itemid=471&format=feed&type=rss')
|
||||
,(u'Monitor' , u'http://www.monitor.co.me/index.php?option=com_content&view=section&layout=blog&id=1&Itemid=1852&format=feed&type=rss')
|
||||
,(u'Altervizija' , u'http://www.monitor.co.me/index.php?option=com_content&view=section&layout=blog&id=31&Itemid=2623&format=feed&type=rss')
|
||||
,(u'Fenomeni' , u'http://www.monitor.co.me/index.php?option=com_content&view=section&layout=blog&id=35&Itemid=3549&format=feed&type=rss')
|
||||
,(u'Fokus' , u'http://www.monitor.co.me/index.php?option=com_content&view=section&layout=blog&id=19&Itemid=252&format=feed&type=rss')
|
||||
,(u'Monitoring' , u'http://www.monitor.co.me/index.php?option=com_content&view=section&layout=blog&id=19&Itemid=252&format=feed&type=rss')
|
||||
,(u'Profil' , u'http://www.monitor.co.me/index.php?option=com_content&view=section&layout=blog&id=21&Itemid=256&format=feed&type=rss')
|
||||
,(u'Intervju' , u'http://www.monitor.co.me/index.php?option=com_content&view=section&layout=blog&id=27&Itemid=404&format=feed&type=rss')
|
||||
,(u'Društvo' , u'http://www.monitor.co.me/index.php?option=com_content&view=section&layout=blog&id=14&Itemid=2&format=feed&type=rss')
|
||||
,(u'Region' , u'http://www.monitor.co.me/index.php?option=com_content&view=section&layout=blog&id=12&Itemid=53&format=feed&type=rss')
|
||||
,(u'Svijet' , u'http://www.monitor.co.me/index.php?option=com_content&view=section&layout=blog&id=11&Itemid=360&format=feed&type=rss')
|
||||
,(u'Kultura' , u'http://www.monitor.co.me/index.php?option=com_content&view=section&layout=blog&id=9&Itemid=361&format=feed&type=rss')
|
||||
]
|
||||
|
||||
|
||||
21
recipes/pubblico_giornale.recipe
Normal file
21
recipes/pubblico_giornale.recipe
Normal file
@ -0,0 +1,21 @@
|
||||
#!/usr/bin/env python
|
||||
__license__ = 'GPL v3'
|
||||
__author__ = 'iusvar'
|
||||
__description__ = 'Pubblico giornale'
|
||||
|
||||
'''
|
||||
http://pubblicogiornale.it/
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class Pubblicogiornale(BasicNewsRecipe):
|
||||
description = 'Italian newspaper directed by Luca Telese'
|
||||
cover_url = 'http://pubblicogiornale.it/wp-content/uploads/logo_n.png?84cd58'
|
||||
title = u'Pubblico giornale'
|
||||
publisher = 'PUBBLICO EDIZIONI Srl'
|
||||
category = 'News'
|
||||
language = 'it'
|
||||
__author__ = 'iusvar'
|
||||
|
||||
feeds = [(u'Pubblico giornale', u'http://pubblicogiornale.it/feed/')]
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 1.6 KiB After Width: | Height: | Size: 5.7 KiB |
@ -230,7 +230,7 @@ class ANDROID(USBMS):
|
||||
'THINKPAD_TABLET', 'SGH-T989', 'YP-G70', 'STORAGE_DEVICE',
|
||||
'ADVANCED', 'SGH-I727', 'USB_FLASH_DRIVER', 'ANDROID',
|
||||
'S5830I_CARD', 'MID7042', 'LINK-CREATE', '7035', 'VIEWPAD_7E',
|
||||
'NOVO7']
|
||||
'NOVO7', 'MB526']
|
||||
WINDOWS_CARD_A_MEM = ['ANDROID_PHONE', 'GT-I9000_CARD', 'SGH-I897',
|
||||
'FILE-STOR_GADGET', 'SGH-T959_CARD', 'SGH-T959', 'SAMSUNG_ANDROID', 'GT-P1000_CARD',
|
||||
'A70S', 'A101IT', '7', 'INCREDIBLE', 'A7EB', 'SGH-T849_CARD',
|
||||
|
||||
@ -288,7 +288,7 @@ class KINDLE2(KINDLE):
|
||||
name = 'Kindle 2/3/4/Touch Device Interface'
|
||||
description = _('Communicate with the Kindle 2/3/4/Touch eBook reader.')
|
||||
|
||||
FORMATS = ['azw3'] + KINDLE.FORMATS + ['pdf', 'azw4', 'pobi']
|
||||
FORMATS = ['azw', 'mobi', 'azw3', 'prc', 'azw1', 'tpz', 'azw4', 'pobi', 'pdf', 'txt']
|
||||
DELETE_EXTS = KINDLE.DELETE_EXTS + ['.mbp1', '.mbs', '.sdr', '.han']
|
||||
# On the Touch, there's also .asc files, but not using the same basename (for X-Ray & End Actions), azw3f & azw3r files, but all of them are in the .sdr sidecar folder
|
||||
|
||||
@ -450,7 +450,7 @@ class KINDLE_DX(KINDLE2):
|
||||
name = 'Kindle DX Device Interface'
|
||||
description = _('Communicate with the Kindle DX eBook reader.')
|
||||
|
||||
FORMATS = KINDLE2.FORMATS[1:]
|
||||
FORMATS = ['azw', 'mobi', 'prc', 'azw1', 'tpz', 'azw4', 'pobi', 'pdf', 'txt']
|
||||
PRODUCT_ID = [0x0003]
|
||||
BCD = [0x0100]
|
||||
|
||||
@ -462,7 +462,7 @@ class KINDLE_FIRE(KINDLE2):
|
||||
name = 'Kindle Fire Device Interface'
|
||||
description = _('Communicate with the Kindle Fire')
|
||||
gui_name = 'Fire'
|
||||
FORMATS = list(KINDLE2.FORMATS)
|
||||
FORMATS = ['azw3', 'azw', 'mobi', 'prc', 'azw1', 'tpz', 'azw4', 'pobi', 'pdf', 'txt']
|
||||
|
||||
PRODUCT_ID = [0x0006]
|
||||
BCD = [0x216, 0x100]
|
||||
|
||||
@ -169,6 +169,7 @@ class MTP_DEVICE(MTPDeviceBase):
|
||||
try:
|
||||
self.dev = self.create_device(connected_device)
|
||||
except Exception as e:
|
||||
self.blacklisted_devices.add(connected_device)
|
||||
raise OpenFailed('Failed to open %s: Error: %s'%(
|
||||
connected_device, as_unicode(e)))
|
||||
|
||||
@ -195,6 +196,19 @@ class MTP_DEVICE(MTPDeviceBase):
|
||||
self.current_serial_num = snum
|
||||
self.currently_connected_dev = connected_device
|
||||
|
||||
@synchronous
|
||||
def device_debug_info(self):
|
||||
ans = self.get_gui_name()
|
||||
ans += '\nSerial number: %s'%self.current_serial_num
|
||||
ans += '\nManufacturer: %s'%self.dev.manufacturer_name
|
||||
ans += '\nModel: %s'%self.dev.model_name
|
||||
ans += '\nids: %s'%(self.dev.ids,)
|
||||
ans += '\nDevice version: %s'%self.dev.device_version
|
||||
ans += '\nStorage:\n'
|
||||
storage = sorted(self.dev.storage_info, key=operator.itemgetter('id'))
|
||||
ans += pprint.pformat(storage)
|
||||
return ans
|
||||
|
||||
@property
|
||||
def filesystem_cache(self):
|
||||
if self._filesystem_cache is None:
|
||||
|
||||
@ -84,8 +84,8 @@ PyObject* get_storage_info(IPortableDevice *device) { // {{{
|
||||
PWSTR object_ids[10];
|
||||
GUID guid;
|
||||
ULONGLONG capacity, free_space, capacity_objects, free_objects;
|
||||
ULONG access;
|
||||
LPWSTR storage_desc = NULL;
|
||||
ULONG access, storage_type = WPD_STORAGE_TYPE_UNDEFINED;
|
||||
LPWSTR storage_desc = NULL, st = NULL;
|
||||
|
||||
storage = PyList_New(0);
|
||||
if (storage == NULL) { PyErr_NoMemory(); goto end; }
|
||||
@ -116,6 +116,7 @@ PyObject* get_storage_info(IPortableDevice *device) { // {{{
|
||||
hr = storage_properties->Add(WPD_STORAGE_FREE_SPACE_IN_OBJECTS);
|
||||
hr = storage_properties->Add(WPD_STORAGE_ACCESS_CAPABILITY);
|
||||
hr = storage_properties->Add(WPD_STORAGE_FILE_SYSTEM_TYPE);
|
||||
hr = storage_properties->Add(WPD_STORAGE_TYPE);
|
||||
hr = storage_properties->Add(WPD_OBJECT_NAME);
|
||||
Py_END_ALLOW_THREADS;
|
||||
if (FAILED(hr)) {hresult_set_exc("Failed to create collection of properties for storage query", hr); goto end; }
|
||||
@ -145,6 +146,7 @@ PyObject* get_storage_info(IPortableDevice *device) { // {{{
|
||||
values->GetUnsignedLargeIntegerValue(WPD_STORAGE_CAPACITY_IN_OBJECTS, &capacity_objects);
|
||||
values->GetUnsignedLargeIntegerValue(WPD_STORAGE_FREE_SPACE_IN_BYTES, &free_space);
|
||||
values->GetUnsignedLargeIntegerValue(WPD_STORAGE_FREE_SPACE_IN_OBJECTS, &free_objects);
|
||||
values->GetUnsignedIntegerValue(WPD_STORAGE_TYPE, &storage_type);
|
||||
desc = Py_False;
|
||||
if (SUCCEEDED(values->GetUnsignedIntegerValue(WPD_STORAGE_ACCESS_CAPABILITY, &access)) && access == WPD_STORAGE_ACCESS_CAPABILITY_READWRITE) desc = Py_True;
|
||||
soid = PyUnicode_FromWideChar(object_ids[i], wcslen(object_ids[i]));
|
||||
@ -167,6 +169,25 @@ PyObject* get_storage_info(IPortableDevice *device) { // {{{
|
||||
if (desc != NULL) { PyDict_SetItemString(so, "filesystem", desc); Py_DECREF(desc);}
|
||||
CoTaskMemFree(storage_desc); storage_desc = NULL;
|
||||
}
|
||||
switch(storage_type) {
|
||||
case WPD_STORAGE_TYPE_REMOVABLE_RAM:
|
||||
st = L"removable_ram";
|
||||
break;
|
||||
case WPD_STORAGE_TYPE_REMOVABLE_ROM:
|
||||
st = L"removable_rom";
|
||||
break;
|
||||
case WPD_STORAGE_TYPE_FIXED_RAM:
|
||||
st = L"fixed_ram";
|
||||
break;
|
||||
case WPD_STORAGE_TYPE_FIXED_ROM:
|
||||
st = L"fixed_rom";
|
||||
break;
|
||||
default:
|
||||
st = L"unknown_unknown";
|
||||
}
|
||||
desc = PyUnicode_FromWideChar(st, wcslen(st));
|
||||
if (desc != NULL) {PyDict_SetItemString(so, "type", desc); Py_DECREF(desc);}
|
||||
desc = NULL;
|
||||
PyList_Append(storage, so);
|
||||
Py_DECREF(so);
|
||||
}
|
||||
|
||||
@ -13,7 +13,7 @@ from future_builtins import zip
|
||||
from itertools import chain
|
||||
|
||||
from calibre import as_unicode, prints
|
||||
from calibre.constants import plugins, __appname__, numeric_version
|
||||
from calibre.constants import plugins, __appname__, numeric_version, isxp
|
||||
from calibre.ptempfile import SpooledTemporaryFile
|
||||
from calibre.devices.errors import OpenFailed, DeviceError, BlacklistedDevice
|
||||
from calibre.devices.mtp.base import MTPDeviceBase, debug
|
||||
@ -52,10 +52,15 @@ class MTP_DEVICE(MTPDeviceBase):
|
||||
self.start_thread = None
|
||||
self._filesystem_cache = None
|
||||
self.eject_dev_on_next_scan = False
|
||||
self.current_device_data = {}
|
||||
|
||||
def startup(self):
|
||||
self.start_thread = threading.current_thread()
|
||||
self.wpd, self.wpd_error = plugins['wpd']
|
||||
if isxp:
|
||||
self.wpd = None
|
||||
self.wpd_error = _('MTP devices are not supported on Windows XP')
|
||||
else:
|
||||
self.wpd, self.wpd_error = plugins['wpd']
|
||||
if self.wpd is not None:
|
||||
try:
|
||||
self.wpd.init(__appname__, *(numeric_version[:3]))
|
||||
@ -196,6 +201,12 @@ class MTP_DEVICE(MTPDeviceBase):
|
||||
if not devdata.get('has_storage', False): return False
|
||||
has_rw_storage = False
|
||||
for s in devdata.get('storage', []):
|
||||
if s.get('filesystem', None) == 'DCF':
|
||||
# DCF filesystem indicates a camera or an iPhone
|
||||
# See https://bugs.launchpad.net/calibre/+bug/1054562
|
||||
continue
|
||||
if s.get('type', 'unknown_unknown').split('_')[-1] == 'rom':
|
||||
continue # Read only storage
|
||||
if s.get('rw', False):
|
||||
has_rw_storage = True
|
||||
break
|
||||
@ -280,6 +291,8 @@ class MTP_DEVICE(MTPDeviceBase):
|
||||
raise BlacklistedDevice(
|
||||
'The %s device has been blacklisted by the user'%(connected_device,))
|
||||
|
||||
storage.sort(key=lambda x:x.get('id', 'zzzzz'))
|
||||
|
||||
self._main_id = storage[0]['id']
|
||||
if len(storage) > 1:
|
||||
self._carda_id = storage[1]['id']
|
||||
@ -291,6 +304,11 @@ class MTP_DEVICE(MTPDeviceBase):
|
||||
_('Unknown MTP device'))
|
||||
self.currently_connected_pnp_id = connected_device
|
||||
self.current_serial_num = snum
|
||||
self.current_device_data = devdata.copy()
|
||||
|
||||
def device_debug_info(self):
|
||||
import pprint
|
||||
return pprint.pformat(self.current_device_data)
|
||||
|
||||
@same_thread
|
||||
def get_basic_device_information(self):
|
||||
|
||||
@ -687,7 +687,7 @@ class PRST1(USBMS):
|
||||
'WHERE _id = ?')
|
||||
t = (collectionId,)
|
||||
cursor.execute(query, t)
|
||||
debug_print('Deleted Collection: ' + collection)
|
||||
debug_print('Deleted Collection: ' + repr(collection))
|
||||
|
||||
connection.commit()
|
||||
cursor.close()
|
||||
|
||||
@ -902,10 +902,16 @@ class SMART_DEVICE_APP(DeviceConfig, DevicePlugin):
|
||||
return False
|
||||
|
||||
def get_gui_name(self):
|
||||
if self.client_device_kind:
|
||||
if getattr(self, 'client_device_kind', None):
|
||||
return self.gui_name_template%(self.gui_name, self.client_device_kind)
|
||||
return self.gui_name
|
||||
|
||||
def config_widget(self):
|
||||
from calibre.gui2.device_drivers.configwidget import ConfigWidget
|
||||
cw = ConfigWidget(self.settings(), self.FORMATS, self.SUPPORTS_SUB_DIRS,
|
||||
self.MUST_READ_METADATA, self.SUPPORTS_USE_AUTHOR_SORT,
|
||||
self.EXTRA_CUSTOMIZATION_MESSAGE, self)
|
||||
return cw
|
||||
|
||||
@synchronous('sync_lock')
|
||||
def get_device_information(self, end_session=True):
|
||||
|
||||
@ -14,6 +14,8 @@ import os
|
||||
from calibre.customize.conversion import OutputFormatPlugin, \
|
||||
OptionRecommendation
|
||||
from calibre.ptempfile import TemporaryDirectory
|
||||
from calibre.constants import iswindows
|
||||
from calibre import walk
|
||||
|
||||
UNITS = [
|
||||
'millimeter',
|
||||
@ -148,6 +150,16 @@ class PDFOutput(OutputFormatPlugin):
|
||||
oeb_output = plugin_for_output_format('oeb')
|
||||
oeb_output.convert(oeb_book, oeb_dir, self.input_plugin, self.opts, self.log)
|
||||
|
||||
if iswindows:
|
||||
# On windows Qt generates an image based PDF if the html uses
|
||||
# embedded fonts. See https://launchpad.net/bugs/1053906
|
||||
for f in walk(oeb_dir):
|
||||
if f.rpartition('.')[-1].lower() in {'ttf', 'otf'}:
|
||||
self.log.warn('Found embedded font %s, removing it, as '
|
||||
'embedded fonts on windows are not supported by '
|
||||
'the PDF Output plugin'%os.path.basename(f))
|
||||
os.remove(f)
|
||||
|
||||
opfpath = glob.glob(os.path.join(oeb_dir, '*.opf'))[0]
|
||||
opf = OPF(opfpath, os.path.dirname(opfpath))
|
||||
|
||||
|
||||
@ -792,19 +792,16 @@ class OPF(object): # {{{
|
||||
remove = list(self.authors_path(self.metadata))
|
||||
for elem in remove:
|
||||
elem.getparent().remove(elem)
|
||||
elems = []
|
||||
for author in val:
|
||||
attrib = {'{%s}role'%self.NAMESPACES['opf']: 'aut'}
|
||||
elem = self.create_metadata_element('creator', attrib=attrib)
|
||||
# Ensure new author element is at the top of the list
|
||||
# for broken implementations that always use the first
|
||||
# <dc:creator> element with no attention to the role
|
||||
for author in reversed(val):
|
||||
elem = self.metadata.makeelement('{%s}creator'%
|
||||
self.NAMESPACES['dc'], nsmap=self.NAMESPACES)
|
||||
elem.tail = '\n'
|
||||
self.metadata.insert(0, elem)
|
||||
elem.set('{%s}role'%self.NAMESPACES['opf'], 'aut')
|
||||
self.set_text(elem, author.strip())
|
||||
# Ensure new author element is at the top of the list
|
||||
# for broken implementations that always use the first
|
||||
# <dc:creator> element with no attention to the role
|
||||
elems.append(elem)
|
||||
for elem in reversed(elems):
|
||||
parent = elem.getparent()
|
||||
parent.remove(elem)
|
||||
parent.insert(0, elem)
|
||||
|
||||
return property(fget=fget, fset=fset)
|
||||
|
||||
@ -1020,9 +1017,8 @@ class OPF(object): # {{{
|
||||
def fset(self, val):
|
||||
matches = self.bkp_path(self.metadata)
|
||||
if not matches:
|
||||
attrib = {'{%s}role'%self.NAMESPACES['opf']: 'bkp'}
|
||||
matches = [self.create_metadata_element('contributor',
|
||||
attrib=attrib)]
|
||||
matches = [self.create_metadata_element('contributor')]
|
||||
matches[0].set('{%s}role'%self.NAMESPACES['opf'], 'bkp')
|
||||
self.set_text(matches[0], unicode(val))
|
||||
return property(fget=fget, fset=fset)
|
||||
|
||||
@ -1155,7 +1151,7 @@ class OPF(object): # {{{
|
||||
def smart_update(self, mi, replace_metadata=False):
|
||||
for attr in ('title', 'authors', 'author_sort', 'title_sort',
|
||||
'publisher', 'series', 'series_index', 'rating',
|
||||
'isbn', 'tags', 'category', 'comments',
|
||||
'isbn', 'tags', 'category', 'comments', 'book_producer',
|
||||
'pubdate', 'user_categories', 'author_link_map'):
|
||||
val = getattr(mi, attr, None)
|
||||
if val is not None and val != [] and val != (None, None):
|
||||
|
||||
@ -10,6 +10,7 @@ __docformat__ = 'restructuredtext en'
|
||||
import re
|
||||
from collections import namedtuple
|
||||
from functools import partial
|
||||
from xml.sax.saxutils import escape
|
||||
|
||||
from lxml import etree
|
||||
|
||||
@ -289,6 +290,7 @@ class Chunker(object):
|
||||
self.chunk_selector = ('S', aid)
|
||||
|
||||
def chunk_up_text(self, text):
|
||||
text = escape(text)
|
||||
text = text.encode('utf-8')
|
||||
ans = []
|
||||
|
||||
|
||||
@ -853,7 +853,7 @@ class DeviceMixin(object): # {{{
|
||||
self.connect_to_folder_named(tweaks['auto_connect_to_folder'])
|
||||
|
||||
def allow_connect(self, name, icon):
|
||||
return question_dialog(self, _('Mange the %s?')%name,
|
||||
return question_dialog(self, _('Manage the %s?')%name,
|
||||
_('Detected the <b>%s</b>. Do you want calibre to manage it?')%
|
||||
name, show_copy_button=False,
|
||||
override_icon=QIcon(icon))
|
||||
|
||||
@ -12,7 +12,8 @@ import weakref
|
||||
from PyQt4.Qt import (QWidget, QListWidgetItem, Qt, QToolButton, QLabel,
|
||||
QTabWidget, QGridLayout, QListWidget, QIcon, QLineEdit, QVBoxLayout,
|
||||
QPushButton, QGroupBox, QScrollArea, QHBoxLayout, QComboBox,
|
||||
pyqtSignal, QSizePolicy, QDialog, QDialogButtonBox)
|
||||
pyqtSignal, QSizePolicy, QDialog, QDialogButtonBox, QPlainTextEdit,
|
||||
QApplication)
|
||||
|
||||
from calibre.ebooks import BOOK_EXTENSIONS
|
||||
from calibre.gui2 import error_dialog
|
||||
@ -372,15 +373,19 @@ class MTPConfig(QTabWidget):
|
||||
_('&Ignore the %s in calibre')%device.current_friendly_name,
|
||||
self.base)
|
||||
b.clicked.connect(self.ignore_device)
|
||||
self.show_debug_button = bd = QPushButton(QIcon(I('debug.png')),
|
||||
_('Show device information'))
|
||||
bd.clicked.connect(self.show_debug_info)
|
||||
|
||||
l.addWidget(b, 0, 0, 1, 2)
|
||||
l.addWidget(la, 1, 0, 1, 1)
|
||||
l.addWidget(self.formats, 2, 0, 3, 1)
|
||||
l.addWidget(self.formats, 2, 0, 4, 1)
|
||||
l.addWidget(self.send_to, 2, 1, 1, 1)
|
||||
l.addWidget(self.template, 3, 1, 1, 1)
|
||||
l.setRowStretch(4, 10)
|
||||
l.addWidget(r, 5, 0, 1, 2)
|
||||
l.setRowStretch(5, 100)
|
||||
l.addWidget(self.show_debug_button, 4, 1, 1, 1)
|
||||
l.setRowStretch(5, 10)
|
||||
l.addWidget(r, 6, 0, 1, 2)
|
||||
l.setRowStretch(6, 100)
|
||||
|
||||
self.igntab = IgnoredDevices(self.device.prefs['history'],
|
||||
self.device.prefs['blacklist'])
|
||||
@ -388,6 +393,26 @@ class MTPConfig(QTabWidget):
|
||||
|
||||
self.setCurrentIndex(1 if msg else 0)
|
||||
|
||||
def show_debug_info(self):
|
||||
info = self.device.device_debug_info()
|
||||
d = QDialog(self)
|
||||
d.l = l = QVBoxLayout()
|
||||
d.setLayout(l)
|
||||
d.v = v = QPlainTextEdit()
|
||||
d.setWindowTitle(self.device.get_gui_name())
|
||||
v.setPlainText(info)
|
||||
v.setMinimumWidth(400)
|
||||
v.setMinimumHeight(350)
|
||||
l.addWidget(v)
|
||||
bb = d.bb = QDialogButtonBox(QDialogButtonBox.Close)
|
||||
bb.accepted.connect(d.accept)
|
||||
bb.rejected.connect(d.reject)
|
||||
l.addWidget(bb)
|
||||
bb.addButton(_('Copy to clipboard'), bb.ActionRole)
|
||||
bb.clicked.connect(lambda :
|
||||
QApplication.clipboard().setText(v.toPlainText()))
|
||||
d.exec_()
|
||||
|
||||
def ignore_device(self):
|
||||
self.igntab.ignore_device(self.device.current_serial_num)
|
||||
self.base.b.setEnabled(False)
|
||||
|
||||
@ -97,7 +97,7 @@ class EbookscomStore(BasicStoreConfig, StorePlugin):
|
||||
with closing(br.open(url + id, timeout=timeout)) as nf:
|
||||
pdoc = html.fromstring(nf.read())
|
||||
|
||||
price_l = pdoc.xpath('//span[@class="price"]/text()')
|
||||
price_l = pdoc.xpath('//div[@class="book-info"]/div[@class="price"]/text()')
|
||||
if price_l:
|
||||
price = price_l[0]
|
||||
search_result.price = price.strip()
|
||||
|
||||
@ -5,8 +5,8 @@
|
||||
msgid ""
|
||||
msgstr ""
|
||||
"Project-Id-Version: calibre 0.8.70\n"
|
||||
"POT-Creation-Date: 2012-09-21 09:52+IST\n"
|
||||
"PO-Revision-Date: 2012-09-21 09:52+IST\n"
|
||||
"POT-Creation-Date: 2012-09-21 13:10+IST\n"
|
||||
"PO-Revision-Date: 2012-09-21 13:10+IST\n"
|
||||
"Last-Translator: Automatically generated\n"
|
||||
"Language-Team: LANGUAGE\n"
|
||||
"MIME-Version: 1.0\n"
|
||||
@ -3485,7 +3485,7 @@ msgid ""
|
||||
"Fetch a cover image/social metadata for the book identified by ISBN from LibraryThing.com\n"
|
||||
msgstr ""
|
||||
|
||||
#: /home/kovid/work/calibre/src/calibre/ebooks/metadata/opf2.py:1488
|
||||
#: /home/kovid/work/calibre/src/calibre/ebooks/metadata/opf2.py:1491
|
||||
#: /home/kovid/work/calibre/src/calibre/ebooks/oeb/base.py:1279
|
||||
#: /home/kovid/work/calibre/src/calibre/gui2/metadata/single.py:958
|
||||
#: /home/kovid/work/calibre/src/calibre/gui2/store/search/models.py:41
|
||||
@ -7827,7 +7827,7 @@ msgstr ""
|
||||
|
||||
#: /home/kovid/work/calibre/src/calibre/gui2/device.py:856
|
||||
#, python-format
|
||||
msgid "Mange the %s?"
|
||||
msgid "Manage the %s?"
|
||||
msgstr ""
|
||||
|
||||
#: /home/kovid/work/calibre/src/calibre/gui2/device.py:857
|
||||
@ -17967,7 +17967,7 @@ msgid "select(val, key) -- interpret the value as a comma-separated list of item
|
||||
msgstr ""
|
||||
|
||||
#: /home/kovid/work/calibre/src/calibre/utils/formatter_functions.py:600
|
||||
msgid "approximate_formats() -- return a comma-separated list of formats that at one point were associated with the book. There is no guarantee that this list is correct, although it probably is. This function can be called in template program mode using the template \"{:'approximate_formats()'}. Note that format names are always uppercase, as in EPUB."
|
||||
msgid "approximate_formats() -- return a comma-separated list of formats that at one point were associated with the book. There is no guarantee that this list is correct, although it probably is. This function can be called in template program mode using the template \"{:'approximate_formats()'}\". Note that format names are always uppercase, as in EPUB."
|
||||
msgstr ""
|
||||
|
||||
#: /home/kovid/work/calibre/src/calibre/utils/formatter_functions.py:620
|
||||
|
||||
45
src/calibre/utils/fonts/embedflag.py
Normal file
45
src/calibre/utils/fonts/embedflag.py
Normal file
@ -0,0 +1,45 @@
|
||||
#!/usr/bin/env python
|
||||
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:fdm=marker:ai
|
||||
from __future__ import (unicode_literals, division, absolute_import,
|
||||
print_function)
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2012, Kovid Goyal <kovid at kovidgoyal.net>'
|
||||
__docformat__ = 'restructuredtext en'
|
||||
|
||||
import sys, struct
|
||||
|
||||
class UnsupportedFont(ValueError):
|
||||
pass
|
||||
|
||||
def remove_embed_restriction(raw):
|
||||
sfnt_version = raw[:4]
|
||||
if sfnt_version not in {b'\x00\x01\x00\x00', b'OTTO'}:
|
||||
raise UnsupportedFont('Not a supported font, sfnt_version: %r'%sfnt_version)
|
||||
|
||||
num_tables = struct.unpack_from(b'>H', raw, 4)[0]
|
||||
|
||||
# Find OS/2 table
|
||||
offset = 4 + 4*2 # Start of the Table record entries
|
||||
os2_table_offset = None
|
||||
for i in xrange(num_tables):
|
||||
table_tag = raw[offset:offset+4]
|
||||
offset += 16 # Size of a table record
|
||||
if table_tag == b'OS/2':
|
||||
os2_table_offset = struct.unpack_from(b'>I', raw, offset+8)[0]
|
||||
break
|
||||
if os2_table_offset is None:
|
||||
raise UnsupportedFont('Not a supported font, has no OS/2 table')
|
||||
|
||||
version, = struct.unpack_from(b'>H', raw, os2_table_offset)
|
||||
|
||||
fs_type_offset = os2_table_offset + struct.calcsize(b'>HhHH')
|
||||
fs_type = struct.unpack_from(b'>H', raw, fs_type_offset)[0]
|
||||
if fs_type == 0:
|
||||
return raw
|
||||
|
||||
return raw[:fs_type_offset] + struct.pack(b'>H', 0) + raw[fs_type_offset+2:]
|
||||
|
||||
if __name__ == '__main__':
|
||||
remove_embed_restriction(open(sys.argv[-1], 'rb').read())
|
||||
|
||||
@ -602,7 +602,7 @@ class BuiltinApproximateFormats(BuiltinFormatterFunction):
|
||||
'book. There is no guarantee that this list is correct, '
|
||||
'although it probably is. '
|
||||
'This function can be called in template program mode using '
|
||||
'the template "{:\'approximate_formats()\'}. '
|
||||
'the template "{:\'approximate_formats()\'}". '
|
||||
'Note that format names are always uppercase, as in EPUB.'
|
||||
)
|
||||
|
||||
|
||||
@ -295,10 +295,10 @@ get_all_removable_disks(struct tagDrives *g_drives)
|
||||
|
||||
for(nLoopIndex = 0; nLoopIndex < MAX_DRIVES; nLoopIndex++)
|
||||
{
|
||||
// if a drive is present (we ignore the A and B drives as they are
|
||||
// always present (even if no actual floppy is present) and we dont
|
||||
// care about floppies)
|
||||
if(nLoopIndex > 1 && dwDriveMask & 1)
|
||||
// if a drive is present (we cannot ignore the A and B drives as there
|
||||
// are people out there that think mapping devices to use those letters
|
||||
// is a good idea, sigh)
|
||||
if(dwDriveMask & 1)
|
||||
{
|
||||
caDrive[0] = 'A' + nLoopIndex;
|
||||
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user