Update The Hindu

This commit is contained in:
Kovid Goyal 2012-12-23 11:29:33 +05:30
parent 68bca92457
commit 67cc77eb8a

View File

@ -16,10 +16,14 @@ class TheHindu(BasicNewsRecipe):
keep_only_tags = [dict(id='content')]
remove_tags = [dict(attrs={'class':['article-links', 'breadcr']}),
dict(id=['email-section', 'right-column', 'printfooter'])]
dict(id=['email-section', 'right-column', 'printfooter', 'topover',
'slidebox', 'th_footer'])]
extra_css = '.photo-caption { font-size: smaller }'
def preprocess_raw_html(self, raw, url):
return raw.replace('<body><p>', '<p>').replace('</p></body>', '</p>')
def postprocess_html(self, soup, first_fetch):
for t in soup.findAll(['table', 'tr', 'td','center']):
t.name = 'div'