New Recipe for Revista El Cultural(Spain)

[jefferson_frantz]

Here is a recipe for spanish magazine 'El Cultural'

Spoiler:

from calibre.web.feeds.recipes import BasicNewsRecipe
from BeautifulSoup import BeautifulSoup, Tag

class RevistaElCultural(BasicNewsRecipe):

    title       = 'Revista El Cultural'
    __author__  = 'Jefferson Frantz'
    description = 'Revista de cultura'
    timefmt = ' [%d %b, %Y]'
    language = 'es_ES'

    no_stylesheets = True
    remove_javascript = True

    extra_css              = 'h1{ font-family: sans-serif; font-size: large; font-weight: bolder; text-align: justify } h2{ font-family: sans-serif; font-size: small; font-weight: 500; text-align: justify } h3{ font-family: sans-serif; font-size: small; font-weight: 500; text-align: justify } h4{ font-family: sans-serif; font-weight: lighter; font-size: medium; font-style: italic; text-align: justify } .rtsArticuloFirma{ font-family: sans-serif; font-size: small; text-align: justify } .column span-13 last{ font-family: sans-serif; font-size: medium; text-align: justify } .rtsImgArticulo{font-family: serif; font-size: small; color: #000000; text-align: justify}'


    def preprocess_html(self, soup):
            for item in soup.findAll(style=True):
               del item['style']

            return soup

    keep_only_tags = [dict(name='div', attrs={'class':['column span-13 last']}),dict(name='div', attrs={'class':['rtsImgArticulo']})]

    remove_tags        = [
                             dict(name=['object','link','script','ul'])
                            ,dict(name='div', attrs={'class':['rtsRating']})

                         ]


    #TO GET ARTICLES IN SECTION
    def ec_parse_section(self, url, titleSection):
            print 'Section: '+ titleSection
            soup = self.index_to_soup(url)
            div = soup.find(attrs={'id':'gallery'})
            current_articles = []
            
            for a in div.findAllNext('a', href=True):
                    if a is None:
                        continue
                    title = self.tag_to_string(a)

                    url = a.get('href', False)
                    if not url or not title:
                        continue

                    if not url.startswith('/version_papel/'+titleSection+'/'):
                        if len(current_articles) > 0 and not url.startswith('/secciones/'):
                            break
                        continue

                    if url.startswith('/version_papel/'+titleSection+'/'):
                         url = 'http://www.elcultural.es'+url

                    self.log('\t\tFound article:', title[0:title.find("|")-1])
                    self.log('\t\t\t', url)
                    current_articles.append({'title': title[0:title.find("|")-1], 'url':url,
                        'description':'', 'date':''})

            return current_articles


    # To GET SECTIONS
    def parse_index(self):
            feeds = []
            for title, url in [
                ('LETRAS',
                 'http://www.elcultural.es/pdf_sumario/cultural/Sumario_El_Cultural_en_PDF'),
                ('ARTE',
                 'http://www.elcultural.es/pdf_sumario/cultural/Sumario_El_Cultural_en_PDF'),
                ('CINE',
                 'http://www.elcultural.es/pdf_sumario/cultural/Sumario_El_Cultural_en_PDF'),
                ('CIENCIA',
                 'http://www.elcultural.es/pdf_sumario/cultural/Sumario_El_Cultural_en_PDF'),
##                ('OPINION',
##                 'http://www.elcultural.es/pdf_sumario/cultural/Sumario_El_Cultural_en_PDF'),
                ('ESCENARIOS',
                 'http://www.elcultural.es/pdf_sumario/cultural/Sumario_El_Cultural_en_PDF'),
             ]:
               articles = self.ec_parse_section(url,title)
               if articles:
                   feeds.append((title, articles))

            
            return feeds

Jeff.