#!/usr/bin/env python from __future__ import print_function __license__ = 'GPL v3' __copyright__ = '2008, Kovid Goyal ' ''' pagina12.com.ar ''' import re from calibre.web.feeds.news import BasicNewsRecipe from calibre.ebooks.BeautifulSoup import Tag, NavigableString def new_tag(soup, name, attrs=()): impl = getattr(soup, 'new_tag', None) if impl is not None: return impl(name, attrs=dict(attrs)) return Tag(soup, name, attrs=attrs or None) class Pagina12(BasicNewsRecipe): title = 'Pagina/12 - Edicion Impresa' __author__ = 'Pablo Marfil' description = 'Diario argentino' INDEX = 'http://www.pagina12.com.ar/diario/secciones/index.html' language = 'es' encoding = 'cp1252' remove_tags_before = dict(id='fecha') remove_tags_after = dict(id='fin') remove_tags = [dict(id=['fecha', 'fin', 'pageControls', 'logo', 'logo_suple', 'fecha_suple', 'volver'])] masthead_url = 'http://www.pagina12.com.ar/commons/imgs/logo-home.gif' no_stylesheets = True preprocess_regexps = [(re.compile(r']+>', re.I), lambda m:'')] def get_cover_url(self): soup = self.index_to_soup( 'http://www.pagina12.com.ar/diario/principal/diario/index.html') for image in soup.findAll('img', alt=True): if image['alt'].startswith('Tapa de la fecha'): return image['src'] print(image) return None def parse_index(self): articles = [] numero = 1 raw = self.index_to_soup( 'http://www.pagina12.com.ar/diario/secciones/index.html', raw=True) raw = re.sub(r'(?i)]+>', '', raw) soup = self.index_to_soup(raw) feeds = [] seen_titles = set() for section in soup.findAll('div', 'seccionx'): numero += 1 print(numero) section_title = self.tag_to_string(section.find( 'div', 'desplegable_titulo on_principal right')) self.log('Found section:', section_title) articles = [] for post in section.findAll('h2'): h = post.find('a', href=True) title = self.tag_to_string(h) if title in seen_titles: continue seen_titles.add(title) a = post.find('a', href=True) url = a['href'] if url.startswith('/'): url = 'http://pagina12.com.ar/imprimir' + url p = post.find('div', attrs={'h2'}) desc = None self.log('\tFound article:', title, 'at', url) if p is not None: desc = self.tag_to_string(p) self.log('\t\t', desc) articles.append({'title': title, 'url': url, 'description': desc, 'date': ''}) if articles: feeds.append((section_title, articles)) return feeds def postprocess_html(self, soup, first): for table in soup.findAll('table', align='right'): img = table.find('img') if img is not None: img.extract() caption = self.tag_to_string(table).strip() div = new_tag(soup, 'div') div['style'] = 'text-align:center' div.insert(0, img) div.insert(1, new_tag(soup, 'br')) if caption: div.insert(2, NavigableString(caption)) table.replaceWith(div) return soup