calibre/recipes/cgm_pl.recipe

from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup


class CGM(BasicNewsRecipe):
    title = u'CGM'
    oldest_article = 7
    __author__ = 'fenuks'
    description = u'Codzienna Gazeta Muzyczna'
    masthead_url = 'http://www.cgm.pl/img/header/logo.gif'
    cover_url = 'http://www.krafcy.com/foto/tinymce/Image/cgm%281%29.jpg'
    category = 'music'
    language = 'pl'
    use_embedded_content = False
    remove_empty_feeds = True
    max_articles_per_feed = 100
    no_stylesheets = True
    extra_css = 'div {color:black;} strong {color:black;} span {color:black;} p {color:black;} h2 {color:black;} img {display: block;} ul.galleryImagesList {list-style: none;} li.item {float: left;} .calibrenavbar {clear: both;}'  # noqa
    remove_tags_before = dict(id='mainContent')
    remove_tags_after = dict(name='div', attrs={'class': 'fbContainer'})
    remove_tags = [dict(name='div', attrs={'class': ['fbContainer', 'socials']}),
                   dict(name='p', attrs={
                        'class': ['tagCloud', 'galleryAuthor']}),
                   dict(id=['movieShare', 'container']), dict(name='br')]
    feeds = [(u'Informacje', u'http://www.cgm.pl/rss.xml'), (u'Polecamy', u'http://www.cgm.pl/rss,4,news.xml'),
             (u'Recenzje', u'http://www.cgm.pl/rss,1,news.xml')]

    def preprocess_html(self, soup):
        gallery = soup.find('div', attrs={'class': 'galleryFlash'})
        if gallery and gallery.div:
            img = gallery.div
            gallery.img.extract()
            if img:
                img = img['style']
                img = 'http://www.cgm.pl' + \
                    img[img.find('url(') + 4:img.find(')')]
                gallery.contents[1].name = 'img'
                gallery.contents[1]['src'] = img
                pos = len(gallery.contents)
                gallery.insert(pos, BeautifulSoup('<br />'))

        for item in soup.findAll(style=True):
            del item['style']
        ad = soup.findAll('a')
        for r in ad:
            if 'www.hustla.pl' in r['href'] or 'www.ebilet.pl' in r['href']:
                r.extract()
        return soup