Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

* Update Folha de Sao Paulo for 2020 syntax

Browse Source
This commit is contained in:
Leonardo Amaral 2020-11-23 23:15:29 -03:00
parent 1b15c93d64
commit 3da688aff2
1 changed files with 11 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
recipes/folhadesaopaulo_sub.recipe
View File

@ -10,9 +10,9 @@ import datetime
class FSP(BasicNewsRecipe):
title = u'Folha de S\xE3o Paulo'
__author__ = 'Joao Eduardo Bertacchi, lc_addicted '
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.]'
__author__ = 'Joao Eduardo Bertacchi - lc_addicted, 2020 Leonardo Amaral - leleobhz'
description = u'Printed edition contents. Folha subscription required (UOL subscription currently not supported).' + \
u' [Conte\xfado completo da edi\xe7\xe3o impressa. Somente para assinantes Folha. N\xE3o suporta assinantes UOL]'
today = datetime.date.today()
@ -88,18 +88,18 @@ img { background: none !important; float: none; margin: 0px; }
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
if self.username is not None and self.password is not None:
br.open('https://acesso.uol.com.br/login.html')
br.form = list(br.forms())[0]
br['user'] = self.username
br['pass'] = self.password
br.submit().read()
br.open('https://login.folha.com.br/login')
br.select_form(action="https://login.folha.com.br/login")
br['email'] = self.username
br['password'] = self.password
br.submit()
return br
# Parsing the index webpage
def parse_index(self):
# In the last version, the index page has become simpler:
INDEX = 'http://www1.folha.uol.com.br/fsp/'
INDEX = 'https://www1.folha.uol.com.br/fsp/'
self.log('--> INDEX set ', INDEX)
soup = self.index_to_soup(INDEX)
@ -109,7 +109,7 @@ img { background: none !important; float: none; margin: 0px; }
for post in soup.findAll('a'):
strpost = str(post)
if re.match('<a href="http://www1.folha.uol.com.br/.*/"><span.class="', strpost):
if re.match('<a href="https://www1.folha.uol.com.br/.*/"><svg aria-hidden="true" class="icon icon--star"', strpost):
if articles:
feeds.append((section_title, articles))
self.log()
@ -125,7 +125,7 @@ img { background: none !important; float: none; margin: 0px; }
break
elif strpost.startswith('<a href'):
url = post['href']
if url.startswith('http://www1.folha.uol.com.br/'):
if url.startswith('http://www1.folha.uol.com.br/') or url.startswith('https://www1.folha.uol.com.br/') :
title = self.tag_to_string(post)
self.log()
self.log('--> post: ', post)