__license__ = 'GPL v3'
__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'

'''
english.aljazeera.net
'''
from calibre.web.feeds.news import BasicNewsRecipe


def has_cls(x):
    return dict(attrs={'class': lambda cls: cls and x in cls.split()})


class AlJazeera(BasicNewsRecipe):
    title = 'Al Jazeera in English'
    __author__ = 'Darko Miletic'
    description = 'News from Middle East'
    language = 'en'
    publisher = 'Al Jazeera'
    category = 'news, politics, middle east'
    delay = 1
    oldest_article = 2
    max_articles_per_feed = 100
    no_stylesheets = True
    use_embedded_content = False
    extra_css              = """
                                body{font-family: Arial,sans-serif}
                                #ctl00_cphBody_dvSummary{font-weight: bold}
                                #dvArticleDate{font-size: small; color: #999999}
                             """
    conversion_options = {
        'comment': description, 'tags': category,
        'publisher': publisher, 'language': language
    }
    keep_only_tags = [
        dict(id='main-story'),
    ]

    remove_tags = [
        has_cls('MoreOnTheStory'), has_cls(
            'ArticleBottomToolbar'), dict(smtitle="ShowMore"),
        dict(name=['object', 'link', 'table',
                   'meta', 'base', 'iframe', 'embed']),
    ]

    feeds = [(u'Al Jazeera English',
              u'http://www.aljazeera.com/xml/rss/all.xml')]

    def get_article_url(self, article):
        artlurl = article.get('link',  None)
        return artlurl.replace('http://english.aljazeera.net//', 'http://english.aljazeera.net/')

    def preprocess_html(self, soup):
        for item in soup.findAll(style=True):
            del item['style']
        for item in soup.findAll(face=True):
            del item['face']
        td = soup.find('td', attrs={'class': 'DetailedSummary'})
        if td:
            td.name = 'div'
        spn = soup.find('span', attrs={'id': 'DetailedTitle'})
        if spn:
            spn.name = 'h1'
        for itm in soup.findAll('span', attrs={'id': ['dvArticleDate', 'ctl00_cphBody_lblDate']}):
            itm.name = 'div'
        for alink in soup.findAll('a'):
            if alink.string is not None:
                tstr = alink.string
                alink.replaceWith(tstr)
        return soup