3. Get rid of the copyright footer and the “Texto Anterior” and “Próximo Texto” bits. DONE
Improved recipe (also attached):
Code:
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag, NavigableString
import string, 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.]'
INDEX = 'http://www1.folha.uol.com.br/fsp/indices/'
language = 'pt'
no_stylesheets = True
max_articles_per_feed = 40
remove_javascript = True
needs_subscription = True
remove_tags_before = dict(name='b')
remove_tags = [dict(name='td', attrs={'align':'center'})]
remove_attributes = ['height','width']
masthead_url = 'http://f.i.uol.com.br/fsp/furniture/images/lgo-fsp-430x50-ffffff.gif'
# 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'}
# 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'<BR><BR>Texto Anterior:.*<!--/NOTICIA-->',
re.DOTALL|re.IGNORECASE), lambda match: r''),
(re.compile(r'<BR><BR>Próximo Texto:.*<!--/NOTICIA-->',
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
raw = br.submit().read()
## if 'Please try again' in raw:
## raise Exception('Your username and password are incorrect')
return br
def parse_index(self):
soup = self.index_to_soup(self.INDEX)
cover = None
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']
if url.startswith('/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 'Preambulo' section
del feeds[0]
# creating the url for the cover image
coverurl = feeds[0][1][0]['url']
coverurl = coverurl.replace('/opiniao/fz', '/images/cp')
coverurl = coverurl.replace('01.htm', '.jpg')
self.cover_url = coverurl
# 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