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:
Sengian
commit
44d8667ce8
@ -1,73 +1,92 @@
|
|||||||
#!/usr/bin/env python
|
|
||||||
|
|
||||||
__license__ = 'GPL v3'
|
__license__ = 'GPL v3'
|
||||||
__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
|
__copyright__ = '2008-2011, Darko Miletic <darko.miletic at gmail.com>'
|
||||||
'''
|
'''
|
||||||
latimes.com
|
www.latimes.com
|
||||||
'''
|
'''
|
||||||
|
|
||||||
from calibre.web.feeds.news import BasicNewsRecipe
|
from calibre.web.feeds.news import BasicNewsRecipe
|
||||||
|
|
||||||
class LATimes(BasicNewsRecipe):
|
class LATimes(BasicNewsRecipe):
|
||||||
title = u'The Los Angeles Times'
|
title = 'Los Angeles Times'
|
||||||
__author__ = u'Darko Miletic and Sujata Raman'
|
__author__ = 'Darko Miletic'
|
||||||
description = u'News from Los Angeles'
|
description = 'The Los Angeles Times is a leading source of news on Southern California, entertainment, movies, television, music, politics, business, health, technology, travel, sports, environment, economics, autos, jobs, real estate and other topics affecting California'
|
||||||
oldest_article = 7
|
publisher = 'Tribune Company'
|
||||||
max_articles_per_feed = 100
|
category = 'news, politics, USA, Los Angeles, world'
|
||||||
language = 'en'
|
oldest_article = 2
|
||||||
|
max_articles_per_feed = 200
|
||||||
no_stylesheets = True
|
no_stylesheets = True
|
||||||
|
encoding = 'utf8'
|
||||||
use_embedded_content = False
|
use_embedded_content = False
|
||||||
encoding = 'utf-8'
|
language = 'en'
|
||||||
lang = 'en-US'
|
remove_empty_feeds = True
|
||||||
|
publication_type = 'newspaper'
|
||||||
|
masthead_url = 'http://www.latimes.com/images/logo.png'
|
||||||
|
cover_url = 'http://www.latimes.com/includes/sectionfronts/A1.pdf'
|
||||||
|
extra_css = """
|
||||||
|
body{font-family: Georgia,"Times New Roman",Times,serif }
|
||||||
|
img{margin-bottom: 0.4em; margin-top: 0.8em; display:block}
|
||||||
|
h2{font-size: 1.1em}
|
||||||
|
.deckhead{font-size: small; text-transform: uppercase}
|
||||||
|
.small{color: gray; font-size: small}
|
||||||
|
.date,.time,.copyright{font-size: x-small; color:gray; font-style:italic;}
|
||||||
|
"""
|
||||||
|
|
||||||
conversion_options = {
|
conversion_options = {
|
||||||
'comment' : description
|
'comment' : description
|
||||||
, 'language' : lang
|
, 'tags' : category
|
||||||
}
|
, 'publisher' : publisher
|
||||||
|
, 'language' : language
|
||||||
|
, 'linearize_tables' : 'Yes'
|
||||||
|
}
|
||||||
|
|
||||||
extra_css = '''
|
keep_only_tags = [
|
||||||
h1{font-family :Georgia,"Times New Roman",Times,serif; font-size:large; }
|
dict(name='div', attrs={'class':'story'})
|
||||||
h2{font-family :Georgia,"Times New Roman",Times,serif; font-size:x-small;}
|
,dict(attrs={'class':['entry-header','time','entry-content']})
|
||||||
.story{font-family :Georgia,"Times New Roman",Times,serif; font-size: x-small;}
|
]
|
||||||
.entry-body{font-family :Georgia,"Times New Roman",Times,serif; font-size: x-small;}
|
remove_tags_after=dict(name='p', attrs={'class':'copyright'})
|
||||||
.entry-more{font-family :Georgia,"Times New Roman",Times,serif; font-size: x-small;}
|
remove_tags = [
|
||||||
.credit{color:#666666; font-family :Georgia,"Times New Roman",Times,serif; font-size: xx-small;}
|
dict(name=['meta','link','iframe','object','embed'])
|
||||||
.small{color:#666666; font-family :Georgia,"Times New Roman",Times,serif; font-size: xx-small;}
|
,dict(attrs={'class':['toolSet','articlerail','googleAd','entry-footer-left','entry-footer-right','entry-footer-social','google-ad-story-bottom','sphereTools']})
|
||||||
.byline{font-family :Georgia,"Times New Roman",Times,serif; font-size: xx-small;}
|
,dict(attrs={'id':['article-promo','googleads','moduleArticleToolsContainer','gallery-subcontent']})
|
||||||
.date{font-family :Georgia,"Times New Roman",Times,serif; font-size: xx-small;color:#930000; font-style:italic;}
|
]
|
||||||
.time{font-family :Georgia,"Times New Roman",Times,serif; font-size: xx-small;color:#930000; font-style:italic;}
|
remove_attributes=['lang','xmlns:fb','xmlns:og','border','xtags','i','article_body']
|
||||||
.copyright{font-family :Georgia,"Times New Roman",Times,serif; font-size: xx-small;color:#930000; }
|
|
||||||
.subhead{font-family :Georgia,"Times New Roman",Times,serif; font-size:x-small;}
|
|
||||||
'''
|
|
||||||
|
|
||||||
# recursions = 1
|
|
||||||
# match_regexps = [r'http://www.latimes.com/.*page=[2-9]']
|
|
||||||
|
|
||||||
keep_only_tags = [dict(name='div', attrs={'class':["story" ,"entry"] })]
|
|
||||||
|
|
||||||
|
|
||||||
remove_tags = [ dict(name='div', attrs={'class':['articlerail',"sphereTools","tools","toppaginate","entry-footer-left","entry-footer-right"]}),
|
feeds = [
|
||||||
dict(name='div', attrs={'id':["moduleArticleToolsContainer",]}),
|
(u'Top News' , u'http://feeds.latimes.com/latimes/news' )
|
||||||
dict(name='p', attrs={'class':["entry-footer",]}),
|
,(u'Local News' , u'http://feeds.latimes.com/latimes/news/local' )
|
||||||
dict(name='ul', attrs={'class':"article-nav clearfix"}),
|
,(u'National' , u'http://feeds.latimes.com/latimes/news/nationworld/nation' )
|
||||||
dict(name=['iframe'])
|
,(u'National Politics' , u'http://feeds.latimes.com/latimes/news/politics/' )
|
||||||
]
|
,(u'Business' , u'http://feeds.latimes.com/latimes/business' )
|
||||||
|
,(u'Education' , u'http://feeds.latimes.com/latimes/news/education' )
|
||||||
|
,(u'Environment' , u'http://feeds.latimes.com/latimes/news/science/environment' )
|
||||||
feeds = [(u'News', u'http://feeds.latimes.com/latimes/news')
|
,(u'Religion' , u'http://feeds.latimes.com/latimes/features/religion' )
|
||||||
,(u'Local','http://feeds.latimes.com/latimes/news/local')
|
,(u'Science' , u'http://feeds.latimes.com/latimes/news/science' )
|
||||||
,(u'MostEmailed','http://feeds.latimes.com/MostEmailed')
|
,(u'Technology' , u'http://feeds.latimes.com/latimes/technology' )
|
||||||
,(u'Politics','http://feeds.latimes.com/latimes/news/local/politics/cal/')
|
,(u'Africa' , u'http://feeds.latimes.com/latimes/africa' )
|
||||||
,('OrangeCounty','http://feeds.latimes.com/latimes/news/local/orange/')
|
,(u'Asia' , u'http://feeds.latimes.com/latimes/asia' )
|
||||||
,('National','http://feeds.latimes.com/latimes/news/nationworld/nation')
|
,(u'Europe' , u'http://feeds.latimes.com/latimes/europe' )
|
||||||
,('Politics','http://feeds.latimes.com/latimes/news/politics/')
|
,(u'Latin America' , u'http://feeds.latimes.com/latimes/latinamerica' )
|
||||||
,('Business','http://feeds.latimes.com/latimes/business')
|
,(u'Middle East' , u'http://feeds.latimes.com/latimes/middleeast' )
|
||||||
,('Sports','http://feeds.latimes.com/latimes/sports/')
|
,(u'Arts&Culture' , u'http://feeds.feedburner.com/latimes/entertainment/news/arts' )
|
||||||
,('Entertainment','http://feeds.latimes.com/latimes/entertainment/')
|
,(u'Entertainment News' , u'http://feeds.feedburner.com/latimes/entertainment/news/' )
|
||||||
]
|
,(u'Movie News' , u'http://feeds.feedburner.com/latimes/entertainment/news/movies/' )
|
||||||
|
,(u'Movie Reviews' , u'http://feeds.feedburner.com/movies/reviews/' )
|
||||||
|
,(u'Music News' , u'http://feeds.feedburner.com/latimes/entertainment/news/music/' )
|
||||||
|
,(u'Pop Album Reviews' , u'http://feeds.feedburner.com/latimes/pop-album-reviews' )
|
||||||
|
,(u'Restaurant Reviews' , u'http://feeds.feedburner.com/latimes/restaurant/reviews' )
|
||||||
|
,(u'Theatar and Dance' , u'http://feeds.feedburner.com/latimes/theaterdance' )
|
||||||
|
,(u'Autos' , u'http://feeds.latimes.com/latimes/classified/automotive/highway1/')
|
||||||
|
,(u'Books' , u'http://feeds.latimes.com/features/books' )
|
||||||
|
,(u'Food' , u'http://feeds.latimes.com/latimes/features/food/' )
|
||||||
|
,(u'Health' , u'http://feeds.latimes.com/latimes/features/health/' )
|
||||||
|
,(u'Real Estate' , u'http://feeds.latimes.com/latimes/classified/realestate/' )
|
||||||
|
,(u'Commentary' , u'http://feeds2.feedburner.com/latimes/news/opinion/commentary/' )
|
||||||
|
,(u'Sports' , u'http://feeds.latimes.com/latimes/sports/' )
|
||||||
|
]
|
||||||
|
|
||||||
def get_article_url(self, article):
|
def get_article_url(self, article):
|
||||||
ans = article.get('feedburner_origlink').rpartition('?')[0]
|
ans = BasicNewsRecipe.get_article_url(self, article).rpartition('?')[0]
|
||||||
|
|
||||||
try:
|
try:
|
||||||
self.log('Looking for full story link in', ans)
|
self.log('Looking for full story link in', ans)
|
||||||
@ -83,4 +102,22 @@ class LATimes(BasicNewsRecipe):
|
|||||||
pass
|
pass
|
||||||
return ans
|
return ans
|
||||||
|
|
||||||
|
def preprocess_html(self, soup):
|
||||||
|
for item in soup.findAll(style=True):
|
||||||
|
del item['style']
|
||||||
|
for item in soup.findAll('img'):
|
||||||
|
if not item.has_key('alt'):
|
||||||
|
item['alt'] = 'image'
|
||||||
|
for item in soup.findAll('a'):
|
||||||
|
limg = item.find('img')
|
||||||
|
if item.string is not None:
|
||||||
|
str = item.string
|
||||||
|
item.replaceWith(str)
|
||||||
|
else:
|
||||||
|
if limg:
|
||||||
|
item.name ='div'
|
||||||
|
item.attrs =[]
|
||||||
|
else:
|
||||||
|
str = self.tag_to_string(item)
|
||||||
|
item.replaceWith(str)
|
||||||
|
return soup
|
||||||
|
|||||||
@ -323,4 +323,4 @@ class RTFInput(InputFormatPlugin):
|
|||||||
|
|
||||||
#ebook-convert "bad.rtf" test.epub -v -d "D:\Mes eBooks\Developpement\debug"
|
#ebook-convert "bad.rtf" test.epub -v -d "D:\Mes eBooks\Developpement\debug"
|
||||||
# os.makedirs('D:\\Mes eBooks\\Developpement\\rtfdebug')
|
# os.makedirs('D:\\Mes eBooks\\Developpement\\rtfdebug')
|
||||||
# debug_dir = 'D:\\Mes eBooks\\Developpement\\rtfdebug'
|
# debug_dir = 'D:\\Mes eBooks\\Developpement\\rtfdebug'
|
||||||
|
|||||||
@ -191,7 +191,7 @@ class Tokenize:
|
|||||||
#read
|
#read
|
||||||
with open(self.__file, 'r') as read_obj:
|
with open(self.__file, 'r') as read_obj:
|
||||||
input_file = read_obj.read()
|
input_file = read_obj.read()
|
||||||
|
|
||||||
#process simple replacements and split giving us a correct list
|
#process simple replacements and split giving us a correct list
|
||||||
#remove '' and \n in the process
|
#remove '' and \n in the process
|
||||||
tokens = self.__sub_reg_split(input_file)
|
tokens = self.__sub_reg_split(input_file)
|
||||||
@ -201,7 +201,7 @@ class Tokenize:
|
|||||||
tokens = filter(lambda x: len(x) > 0, tokens)
|
tokens = filter(lambda x: len(x) > 0, tokens)
|
||||||
#handles bothersome cases
|
#handles bothersome cases
|
||||||
tokens = map(self.__correct_spliting, tokens)
|
tokens = map(self.__correct_spliting, tokens)
|
||||||
|
|
||||||
#write
|
#write
|
||||||
with open(self.__write_to, 'wb') as write_obj:
|
with open(self.__write_to, 'wb') as write_obj:
|
||||||
write_obj.write('\n'.join(tokens))
|
write_obj.write('\n'.join(tokens))
|
||||||
@ -211,7 +211,7 @@ class Tokenize:
|
|||||||
copy_obj.copy_file(self.__write_to, "tokenize.data")
|
copy_obj.copy_file(self.__write_to, "tokenize.data")
|
||||||
copy_obj.rename(self.__write_to, self.__file)
|
copy_obj.rename(self.__write_to, self.__file)
|
||||||
os.remove(self.__write_to)
|
os.remove(self.__write_to)
|
||||||
|
|
||||||
#self.__special_tokens = [ '_', '~', "'", '{', '}' ]
|
#self.__special_tokens = [ '_', '~', "'", '{', '}' ]
|
||||||
|
|
||||||
# import sys
|
# import sys
|
||||||
@ -227,4 +227,4 @@ class Tokenize:
|
|||||||
|
|
||||||
|
|
||||||
# if __name__ == '__main__':
|
# if __name__ == '__main__':
|
||||||
# sys.exit(main())
|
# sys.exit(main())
|
||||||
|
|||||||
@ -379,7 +379,7 @@ class BIBTEX(CatalogPlugin): # {{{
|
|||||||
if calibre_files:
|
if calibre_files:
|
||||||
files = [u':%s:%s' % (format, format.rpartition('.')[2].upper())\
|
files = [u':%s:%s' % (format, format.rpartition('.')[2].upper())\
|
||||||
for format in item]
|
for format in item]
|
||||||
bibtex_entry.append(u'files = "%s"' % u', '.join(files))
|
bibtex_entry.append(u'file = "%s"' % u', '.join(files))
|
||||||
|
|
||||||
elif field == 'series_index' :
|
elif field == 'series_index' :
|
||||||
bibtex_entry.append(u'volume = "%s"' % int(item))
|
bibtex_entry.append(u'volume = "%s"' % int(item))
|
||||||
@ -551,6 +551,7 @@ class BIBTEX(CatalogPlugin): # {{{
|
|||||||
as outfile:
|
as outfile:
|
||||||
#File header
|
#File header
|
||||||
nb_entries = len(data)
|
nb_entries = len(data)
|
||||||
|
|
||||||
#check in book strict if all is ok else throw a warning into log
|
#check in book strict if all is ok else throw a warning into log
|
||||||
if bib_entry == 'book' :
|
if bib_entry == 'book' :
|
||||||
nb_books = len(filter(check_entry_book_valid, data))
|
nb_books = len(filter(check_entry_book_valid, data))
|
||||||
|
|||||||
Loading…
x
Reference in New Issue
Block a user