Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 10:14:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

...

Browse Source
This commit is contained in:
Kovid Goyal 2011-09-28 12:12:23 -06:00
parent 9a366a92d9
commit 488069faad
1 changed files with 12 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
recipes/folhadesaopaulo_sub.recipe
View File

@ -1,19 +1,21 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
import re
class FSP(BasicNewsRecipe): class FSP(BasicNewsRecipe):
title = u'Folha de S\xE3o Paulo - Jornal' title = u'Folha de S\xE3o Paulo'
__author__ = 'fluzao' __author__ = 'fluzao'
description = u'Printed edition contents. UOL subscription required (Folha subscription currently not supported).' + \ 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.]' u' [Conte\xfado completo da edi\xe7\xe3o impressa. Somente para assinantes UOL.]'
INDEX = 'http://www1.folha.uol.com.br/fsp/indices/' INDEX = 'http://www1.folha.uol.com.br/fsp/indices/'
language = 'pt' language = 'pt'
no_stylesheets = True no_stylesheets = True
max_articles_per_feed = 30 max_articles_per_feed = 40
remove_javascript = True remove_javascript = True
needs_subscription = True needs_subscription = True
remove_tags_before = dict(name='b') remove_tags_before = dict(name='b')
remove_tags_after = dict(name='!--/NOTICIA--') remove_tags = [dict(name='td', attrs={'align':'center'})]
remove_attributes = ['height','width'] remove_attributes = ['height','width']
masthead_url = 'http://f.i.uol.com.br/fsp/furniture/images/lgo-fsp-430x50-ffffff.gif' masthead_url = 'http://f.i.uol.com.br/fsp/furniture/images/lgo-fsp-430x50-ffffff.gif'
@ -26,6 +28,13 @@ class FSP(BasicNewsRecipe):
# this solves the problem with truncated content in Kindle # this solves the problem with truncated content in Kindle
conversion_options = {'linearize_tables' : True} 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>Pr&oacute;ximo Texto:.*<!--/NOTICIA-->',
re.DOTALL|re.IGNORECASE), lambda match: r'')]
def get_browser(self): def get_browser(self):
br = BasicNewsRecipe.get_browser() br = BasicNewsRecipe.get_browser()
if self.username is not None and self.password is not None: if self.username is not None and self.password is not None: