View Single Post
Old 11-13-2011, 08:02 PM   #7
fluzao
Member
fluzao began at the beginning.
 
Posts: 15
Karma: 10
Join Date: Apr 2011
Device: Kindle
Ok guys, problem solved. Fixed - and slightly improved - recipe below and attached. Kovid, please update it in the database when you have a chance.

Code:
from calibre.web.feeds.news import BasicNewsRecipe

import re

class FSP(BasicNewsRecipe):

    title      = u'Folha de S\xE3o Paulo'
    __author__ = 'fluzao'
    description = u'Printed edition contents. UOL subscription required (Folha subscription currently not supported).' + \
                  u' [Conte\xfado completo da edi\xe7\xe3o impressa. Somente para assinantes UOL.]'

    #found this to be the easiest place to find the index page (13-Nov-2011).
    #  searching for the "Indice Geral" link
    HOMEPAGE = 'http://www1.folha.uol.com.br/fsp/'
    masthead_url = 'http://f.i.uol.com.br/fsp/furniture/images/lgo-fsp-430x50-ffffff.gif'

    language = 'pt'
    no_stylesheets = True
    max_articles_per_feed  = 40
    remove_javascript     = True
    needs_subscription = True

    remove_tags_before = dict(name='p')
    remove_tags  = [dict(name='td', attrs={'align':'center'})]
    remove_attributes = ['height','width']
    # fixes the problem with the section names
    section_dict = {'cotidian' : 'cotidiano', 'ilustrad': 'ilustrada', \
                    'quadrin': 'quadrinhos' , 'opiniao' : u'opini\xE3o', \
                    'ciencia' : u'ci\xeancia' , 'saude' : u'sa\xfade', \
                    'ribeirao' : u'ribeir\xE3o' , 'equilibrio' : u'equil\xedbrio', \
                    'imoveis' : u'im\xf3veis', 'negocios' : u'neg\xf3cios', \
                    'veiculos' : u've\xedculos', 'corrida' : 'folha corrida'}

    # this solves the problem with truncated content in Kindle
    conversion_options = {'linearize_tables' : True}

    # this bit removes the footer where there are links for Proximo Texto, Texto Anterior,
    #    Indice e Comunicar Erros
    preprocess_regexps = [(re.compile(r'<!--/NOTICIA-->.*Comunicar Erros</a>',
                                      re.DOTALL|re.IGNORECASE), lambda match: r'')]

    def get_browser(self):
        br = BasicNewsRecipe.get_browser()
        if self.username is not None and self.password is not None:
            br.open('https://acesso.uol.com.br/login.html')
            br.form = br.forms().next()
            br['user']   = self.username
            br['pass'] = self.password
            br.submit().read()
##            if 'Please try again' in raw:
##                raise Exception('Your username and password are incorrect')
        return br


    def parse_index(self):
        #Searching for the index page on the HOMEPAGE
        hpsoup = self.index_to_soup(self.HOMEPAGE)
        indexref = hpsoup.find('a', href=re.compile('^indices.*'))
        self.log('--> tag containing the today s index: ', indexref)     
        INDEX = indexref['href']
        INDEX = 'http://www1.folha.uol.com.br/fsp/'+INDEX
        self.log('--> INDEX after extracting href and adding prefix: ', INDEX)
        # ... and taking the opportunity to get the cover image link
        coverurl = hpsoup.find('a', href=re.compile('^cp.*'))['href']
        if coverurl:
            self.log('--> tag containing the today s cover: ', coverurl)
            coverurl = coverurl.replace('htm', 'jpg')
            coverurl = 'http://www1.folha.uol.com.br/fsp/images/'+coverurl
            self.log('--> coverurl after extracting href and adding prefix: ', coverurl)
            self.cover_url = coverurl
        
        #soup = self.index_to_soup(self.INDEX)
        soup = self.index_to_soup(INDEX)

        feeds = []
        articles = []
        section_title = "Preambulo"
        for post in soup.findAll('a'):
            # if name=True => new section
            strpost = str(post)
            if strpost.startswith('<a name'):
                if articles:
                    feeds.append((section_title, articles))
                    self.log()
                    self.log('--> new section found, creating old section feed: ', section_title)
                section_title = post['name']
                if section_title in self.section_dict:
                    section_title = self.section_dict[section_title]
                articles = []
                self.log('--> new section title:   ', section_title)
            if strpost.startswith('<a href'):
                url = post['href']
                #this bit is kept if they ever go back to the old format (pre Nov-2011)
                if url.startswith('/fsp'):
                    url = 'http://www1.folha.uol.com.br'+url
                #
                if url.startswith('http://www1.folha.uol.com.br/fsp'):
                    #url = 'http://www1.folha.uol.com.br'+url
                    title = self.tag_to_string(post)
                    self.log()
                    self.log('--> post:  ', post)
                    self.log('--> url:   ', url)
                    self.log('--> title: ', title)
                    articles.append({'title':title, 'url':url})
        if articles:
            feeds.append((section_title, articles))

        # keeping the front page url
        minha_capa = feeds[0][1][1]['url']

        # removing the first section (now called 'top')
        del feeds[0]

        # inserting the cover page as the first article (nicer for kindle users)
        feeds.insert(0,(u'primeira p\xe1gina', [{'title':u'Primeira p\xe1gina' , 'url':minha_capa}]))
        return feeds
Attached Files
File Type: zip folhadesaopaulo_sub.zip (2.0 KB, 296 views)
fluzao is offline   Reply With Quote