sinopse.recipe

gistfile1.txt

import string, re
from calibre import strftime
from calibre.web.feeds.recipes import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup

class Sinopse(BasicNewsRecipe):

    title       = 'Radiobras'
    __author__  = 'Filipe Fernandes'
    description = 'Radiobras Sinopses'
    timefmt = ' [%a, %d %b, %Y]'
    encoding = 'iso-8859-1'

    def parse_index(self):
        url  = "http://clipping.radiobras.gov.br/clipping/novo/Classes/SinopsesDetail.php"
        soup = self.index_to_soup(url)

        def feed_title(p):
            return ''.join(p.findAll(text=True, recursive=False)).strip()

        articles = {}
        key = None
        ans = []
        for p in soup.findAll(True,
                attrs={'class':['jornal','titulos-chamadas','textos_sinopse']}):

            if p['class'] == 'jornal':
                key = string.upper(feed_title(p))
                articles[key] = []
                ans.append(key)

            elif p['class'] in ['titulos-chamadas', 'textos_sinopse']:
                if p['class'] in ['titulos-chamadas']:
                    title = feed_title(p)
                    description = ''
                    pubdate = strftime('%a, %d %b')
                    url=''
                    summary=''
                if p['class'] in ['textos_sinopse']:
                    description = feed_title(p)

                articles[key].append( dict(title=title, url=url, date=pubdate,
                                          description=description, content='') )

        ans = [(key, articles[key]) for key in ans if articles.has_key(key)]
        return ans