mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
Update Le Monde
Fixes #1713040 [recipe le monde abonnés](https://bugs.launchpad.net/calibre/+bug/1713040)
This commit is contained in:
Kovid Goyal
parent
7e5555845b
commit
bce0c6296c
@ -3,10 +3,15 @@ __copyright__ = '2012'
|
||||
'''
|
||||
lemonde.fr
|
||||
'''
|
||||
import re
|
||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
||||
|
||||
|
||||
def classes(classes):
|
||||
q = frozenset(classes.split(' '))
|
||||
return dict(attrs={
|
||||
'class': lambda x: x and frozenset(x.split()).intersection(q)})
|
||||
|
||||
|
||||
class LeMonde(BasicNewsRecipe):
|
||||
title = 'Le Monde'
|
||||
__author__ = 'veezh'
|
||||
@ -20,100 +25,24 @@ class LeMonde(BasicNewsRecipe):
|
||||
category = 'news, France, world'
|
||||
language = 'fr'
|
||||
extra_css = '''
|
||||
h1{font-size:130%;}
|
||||
h2{font-size:100%;}
|
||||
blockquote.aside {background-color: #DDD; padding: 0.5em;}
|
||||
.ariane{font-size:xx-small;}
|
||||
.source{font-size:xx-small;}
|
||||
/*.href{font-size:xx-small;}*/
|
||||
/*.figcaption style{color:#666666; font-size:x-small;}*/
|
||||
/*.main-article-info{font-family:Arial,Helvetica,sans-serif;}*/
|
||||
/*full-contents{font-size:small; font-family:Arial,Helvetica,sans-serif;font-weight:normal;}*/
|
||||
/*match-stats-summary{font-size:small; font-family:Arial,Helvetica,sans-serif;font-weight:normal;}*/
|
||||
'''
|
||||
conversion_options = {
|
||||
'comments': description, 'tags': category, 'language': language, 'publisher': publisher, 'linearize_tables': True
|
||||
}
|
||||
|
||||
remove_empty_feeds = True
|
||||
|
||||
filterDuplicates = True
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for aside in soup.findAll('aside'):
|
||||
aside.name = 'blockquote'
|
||||
aside['class'] = "aside"
|
||||
for alink in soup.findAll('a'):
|
||||
if alink.string is not None:
|
||||
tstr = alink.string
|
||||
alink.replaceWith(tstr)
|
||||
return soup
|
||||
|
||||
preprocess_regexps = [
|
||||
(re.compile(r'([0-9])%'), lambda m: m.group(1) + ' %'),
|
||||
(re.compile(r'([0-9])([0-9])([0-9]) ([0-9])([0-9])([0-9])'), lambda m: m.group(
|
||||
1) + m.group(2) + m.group(3) + ' ' + m.group(4) + m.group(5) + m.group(6)),
|
||||
(re.compile(r'([0-9]) ([0-9])([0-9])([0-9])'), lambda m: m.group(1) +
|
||||
' ' + m.group(2) + m.group(3) + m.group(4)),
|
||||
(re.compile(r'<span>'), lambda match: ' <span>'),
|
||||
(re.compile(r'\("'), lambda match: '(« '),
|
||||
(re.compile(r'"\)'), lambda match: ' »)'),
|
||||
(re.compile(r'“'), lambda match: '(« '),
|
||||
(re.compile(r'”'), lambda match: ' »)'),
|
||||
(re.compile(r'>\''), lambda match: '>‘'),
|
||||
(re.compile(r' \''), lambda match: ' ‘'),
|
||||
(re.compile(r' "'), lambda match: ' « '),
|
||||
(re.compile(r'>"'), lambda match: '>« '),
|
||||
(re.compile(r'"<'), lambda match: ' »<'),
|
||||
(re.compile(r'" '), lambda match: ' » '),
|
||||
(re.compile(r'",'), lambda match: ' »,'),
|
||||
(re.compile(r'\''), lambda match: '’'),
|
||||
(re.compile(r'"<em>'), lambda match: '<em>« '),
|
||||
(re.compile(r'"<em>"</em><em>'), lambda match: '<em>« '),
|
||||
(re.compile(r'"<a href='), lambda match: '« <a href='),
|
||||
(re.compile(r'</em>"'), lambda match: ' »</em>'),
|
||||
(re.compile(r'</a>"'), lambda match: ' »</a>'),
|
||||
(re.compile(r'"</'), lambda match: ' »</'),
|
||||
(re.compile(r'>"'), lambda match: '>« '),
|
||||
(re.compile(r'"<'), lambda match: ' »<'),
|
||||
(re.compile(r'’"'), lambda match: '’« '),
|
||||
(re.compile(r' "'), lambda match: ' « '),
|
||||
(re.compile(r'" '), lambda match: ' » '),
|
||||
(re.compile(r'"\.'), lambda match: ' ».'),
|
||||
(re.compile(r'",'), lambda match: ' »,'),
|
||||
(re.compile(r'"\?'), lambda match: ' »?'),
|
||||
(re.compile(r'":'), lambda match: ' »:'),
|
||||
(re.compile(r'";'), lambda match: ' »;'),
|
||||
(re.compile(r'"\!'), lambda match: ' »!'),
|
||||
(re.compile(r' :'), lambda match: ' :'),
|
||||
(re.compile(r' ;'), lambda match: ' ;'),
|
||||
(re.compile(r' \?'), lambda match: ' ?'),
|
||||
(re.compile(r' \!'), lambda match: ' !'),
|
||||
(re.compile(r'\s»'), lambda match: ' »'),
|
||||
(re.compile(r'«\s'), lambda match: '« '),
|
||||
(re.compile(r' %'), lambda match: ' %'),
|
||||
(re.compile(r'\.jpg » width='), lambda match: '.jpg'),
|
||||
(re.compile(r'\.png » width='), lambda match: '.png'),
|
||||
(re.compile(r' – '), lambda match: ' – '),
|
||||
(re.compile(r'figcaption style="display:none"'), lambda match: 'figcaption'),
|
||||
(re.compile(r' – '), lambda match: ' – '),
|
||||
(re.compile(r' - '), lambda match: ' – '),
|
||||
(re.compile(r' -,'), lambda match: ' –,'),
|
||||
(re.compile(r'»:'), lambda match: '» :'),
|
||||
]
|
||||
img{max-width:100%}
|
||||
h1{font-size:1.2em !important; line-height:1.2em !important; }
|
||||
h2{font-size:1em !important; line-height:1em !important; }
|
||||
h3{font-size:1em !important; text-transform:uppercase !important; color:#666;}
|
||||
#photo{text-align:center !important; margin:10px 0 -8px;}
|
||||
#lgd{font-size:1em !important; line-height:1em !important; font-style:italic; color:#333;} '''
|
||||
|
||||
keep_only_tags = [
|
||||
dict(name='article', attrs={})
|
||||
dict(itemprop=['Headline', 'description']),
|
||||
classes('bloc_signature'),
|
||||
dict(itemprop=['articleBody']),
|
||||
]
|
||||
remove_empty_feeds = True
|
||||
|
||||
remove_tags = [
|
||||
dict(attrs={'class': ['rubriques_liees']}),
|
||||
dict(attrs={'class': ['sociaux']}),
|
||||
dict(attrs={'class': ['bloc_base meme_sujet']}),
|
||||
dict(name='p', attrs={'class': ['lire']})
|
||||
]
|
||||
|
||||
remove_tags_after = [dict(id='fb-like')]
|
||||
def preprocess_html(self, soup):
|
||||
for lgd in soup.findAll(id="lgd"):
|
||||
lgd.contents[-1].extract()
|
||||
return soup
|
||||
|
||||
def get_article_url(self, article):
|
||||
url = article.get('guid', None)
|
||||
@ -121,11 +50,6 @@ class LeMonde(BasicNewsRecipe):
|
||||
url = None
|
||||
return url
|
||||
|
||||
# def get_article_url(self, article):
|
||||
# link = article.get('link')
|
||||
# if 'blog' not in link and ('chat' not in link):
|
||||
# return link
|
||||
|
||||
feeds = [
|
||||
('A la une', 'http://www.lemonde.fr/rss/une.xml'),
|
||||
('International', 'http://www.lemonde.fr/rss/tag/international.xml'),
|
||||
|
||||
@ -11,6 +11,12 @@ from calibre.ptempfile import PersistentTemporaryFile
|
||||
from urllib2 import HTTPError
|
||||
|
||||
|
||||
def classes(classes):
|
||||
q = frozenset(classes.split(' '))
|
||||
return dict(attrs={
|
||||
'class': lambda x: x and frozenset(x.split()).intersection(q)})
|
||||
|
||||
|
||||
class LeMonde(BasicNewsRecipe):
|
||||
|
||||
title = u'Le Monde: Édition abonnés'
|
||||
@ -35,7 +41,11 @@ class LeMonde(BasicNewsRecipe):
|
||||
#photo{text-align:center !important; margin:10px 0 -8px;}
|
||||
#lgd{font-size:1em !important; line-height:1em !important; font-style:italic; color:#333;} '''
|
||||
|
||||
keep_only_tags = [dict(name=['h1', 'h2', 'h3', 'div', 'txt'])]
|
||||
keep_only_tags = [
|
||||
dict(itemprop=['Headline', 'description']),
|
||||
classes('bloc_signature'),
|
||||
dict(itemprop=['articleBody']),
|
||||
]
|
||||
|
||||
def __init__(self, options, log, progress_reporter):
|
||||
BasicNewsRecipe.__init__(self, options, log, progress_reporter)
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user