diff --git a/recipes/united_daily.recipe b/recipes/united_daily.recipe index 25493a43ac..7e2ee22206 100644 --- a/recipes/united_daily.recipe +++ b/recipes/united_daily.recipe @@ -63,7 +63,7 @@ class UnitedDaily(BasicNewsRecipe): extra_css = '''div[id='story_title'] {font-size:200%; font-weight:bold;} td[class='story_title'] {font-size:200%; font-weight:bold;} td[class='story_title'] td[class='story_title']>div {font-size:200%; font-weight:bold;}''' __author__ = 'Eddie Lau' - __version__ = '1.1' + __version__ = '1.2' language = 'zh_TW' publisher = 'United Daily News Group' description = 'United Daily (Taiwan)' @@ -71,16 +71,18 @@ class UnitedDaily(BasicNewsRecipe): remove_javascript = True use_embedded_content = False no_stylesheets = True - encoding = 'big5' + encoding = 'utf-8' conversion_options = {'linearize_tables':True} masthead_url = 'http://udn.com/NEWS/2004/images/logo_udn.gif' cover_url = 'http://udn.com/NEWS/2004/images/logo_udn.gif' - keep_only_tags = [dict(name='td', attrs={'class':['story_title']}), - dict(name='div', attrs={'id':['story_title']}), - dict(name='td', attrs={'class':['story_author']}), - dict(name='div', attrs={'id':['story_author']}), - dict(name='td', attrs={'class':['story']}), - dict(name='div', attrs={'id':['story']}), - ] - remove_tags = [dict(name='div', attrs={'id':['mvouter']})] + auto_cleanup = True + #keep_only_tags = [dict(name='td', attrs={'class':['story_title']}), + # dict(name='div', attrs={'id':['story_title']}), + # dict(name='td', attrs={'class':['story_author']}), + # dict(name='div', attrs={'id':['story_author']}), + # dict(name='td', attrs={'class':['story']}), + # dict(name='div', attrs={'id':['story']}), + # ] + #remove_tags = [dict(name='div', attrs={'id':['mvouter']})] +