Fix #8263 (MSNBC recipe)

This commit is contained in:
Kovid Goyal 2011-01-12 08:54:42 -07:00
parent 32084ebd9a
commit 4dde6b9675

View File

@ -1,5 +1,5 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2010-2011, Darko Miletic <darko.miletic at gmail.com>'
''' '''
msnbc.msn.com msnbc.msn.com
''' '''
@ -19,7 +19,16 @@ class MsNBC(BasicNewsRecipe):
publisher = 'msnbc.com' publisher = 'msnbc.com'
category = 'news, USA, world' category = 'news, USA, world'
language = 'en' language = 'en'
extra_css = ' body{ font-family: sans-serif } .head{font-family: serif; font-size: xx-large; font-weight: bold; color: #CC0000} .abstract{font-weight: bold} .source{font-size: small} .updateTime{font-size: small} ' extra_css = """
body{ font-family: Georgia,Times,serif }
.hide{display: none}
.caption{font-family: Arial,sans-serif; font-size: x-small}
.entry-summary{font-family: Arial,sans-serif}
.copyright{font-size: 0.95em; font-style: italic}
.source-org{font-size: small; font-family: Arial,sans-serif}
img{display: block; margin-bottom: 0.5em}
span.byline{display: none}
"""
conversion_options = { conversion_options = {
'comments' : description 'comments' : description
@ -28,14 +37,20 @@ class MsNBC(BasicNewsRecipe):
,'publisher': publisher ,'publisher': publisher
} }
preprocess_regexps = [ remove_tags_before = dict(name='h1', attrs={'id':'headline'})
(re.compile(r'</style></head>', re.DOTALL|re.IGNORECASE),lambda match: '</style>') remove_tags_after = dict(name='span', attrs={'class':['copyright','Linear copyright']})
,(re.compile(r'<div class="head">', re.DOTALL|re.IGNORECASE),lambda match: '</head><body><div class="head">'), keep_only_tags=[
] dict(attrs={'id':['headline','deck','byline','source','intelliTXT']})
,dict(attrs={'class':['gl_headline','articleText','drawer-content Linear','v-center3','byline','textBodyBlack']})
]
remove_attributes=['property','lang','rel','xmlns:fb','xmlns:v','xmlns:dc','xmlns:dcmitype','xmlns:og','xmlns:media','xmlns:vcard','typeof','itemscope','itemtype','itemprop','about','type','size','width','height','onreadystatechange','data','border','hspace','vspace']
remove_tags = [
dict(name=['iframe','object','link','embed','meta','table'])
,dict(name='span', attrs={'class':['copyright','Linear copyright']})
,dict(name='div', attrs={'class':'social'})
]
remove_tags_before = dict(name='div', attrs={'class':'head'})
remove_tags_after = dict(name='div', attrs={'class':'copyright'})
remove_tags = [dict(name=['iframe','object','link','script','form'])]
feeds = [ feeds = [
(u'US News' , u'http://rss.msnbc.msn.com/id/3032524/device/rss/rss.xml' ) (u'US News' , u'http://rss.msnbc.msn.com/id/3032524/device/rss/rss.xml' )
@ -48,11 +63,26 @@ class MsNBC(BasicNewsRecipe):
,(u'Tech & Science', u'http://rss.msnbc.msn.com/id/3032117/device/rss/rss.xml' ) ,(u'Tech & Science', u'http://rss.msnbc.msn.com/id/3032117/device/rss/rss.xml' )
] ]
def print_version(self, url):
return url + 'print/1/displaymode/1098/'
def preprocess_html(self, soup): def preprocess_html(self, soup):
for item in soup.head.findAll('div'): for item in soup.body.findAll('html'):
item.extract() item.name='div'
for item in soup.body.findAll('div'):
if item.has_key('id') and item['id'].startswith('vine-'):
item.extract()
if item.has_key('class') and ( item['class'].startswith('ad') or item['class'].startswith('vine')):
item.extract()
for item in soup.body.findAll('img'):
if not item.has_key('alt'):
item['alt'] = 'image'
for item in soup.body.findAll('ol'):
if item.has_key('class') and item['class'].startswith('grid'):
item.extract()
for item in soup.body.findAll('span'):
if ( item.has_key('id') and item['id'].startswith('byLine') and item.string is None) or ( item.has_key('class') and item['class'].startswith('inline') ):
item.extract()
for alink in soup.findAll('a'):
if alink.string is not None:
tstr = alink.string
alink.replaceWith(tstr)
return soup return soup