Update Le Monde

This commit is contained in:
Kovid Goyal 2012-12-10 07:17:56 +05:30
parent 12f19a4200
commit 4e4884c91b

View File

@ -22,13 +22,15 @@ class LeMonde(BasicNewsRecipe):
#publication_type = 'newsportal'
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;}
/*.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;}*/
'''
#preprocess_regexps = [(re.compile(r'<!--.*?-->', re.DOTALL), lambda m: '')]
conversion_options = {
@ -44,6 +46,9 @@ class LeMonde(BasicNewsRecipe):
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
@ -107,7 +112,9 @@ class LeMonde(BasicNewsRecipe):
]
remove_tags = [
dict(name='div', attrs={'class':['bloc_base meme_sujet']}),
dict(attrs={'class':['rubriques_liees']}),
dict(attrs={'class':['sociaux']}),
dict(attrs={'class':['bloc_base meme_sujet']}),
dict(name='p', attrs={'class':['lire']})
]