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

Fix #874643 (Updated recipe for La Repubblica)

Browse Source
This commit is contained in:
Kovid Goyal 2011-10-18 19:17:11 +05:30
parent c559b73962
commit 186b781835
1 changed files with 53 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

44
recipes/la_republica.recipe
View File

@ -1,13 +1,14 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__author__ = 'Lorenzo Vigentini, based on Darko Miletic, Gabriele Marini' __author__ = 'Lorenzo Vigentini, based on Darko Miletic, Gabriele Marini'
__copyright__ = '2009-2011, Darko Miletic <darko.miletic at gmail.com>, Lorenzo Vigentini <l.vigentini at gmail.com>' __copyright__ = '2009-2011, Darko Miletic <darko.miletic at gmail.com>, Lorenzo Vigentini <l.vigentini at gmail.com>'
description = 'Italian daily newspaper - v1.01 (04, January 2010); 16.05.2010 new version' description = 'Italian daily newspaper - v1.01 (04, January 2010); 16.05.2010 new version; 17.10.2011 new version'
''' '''
http://www.repubblica.it/ http://www.repubblica.it/
''' '''
import re import re
from calibre.ptempfile import PersistentTemporaryFile
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class LaRepubblica(BasicNewsRecipe): class LaRepubblica(BasicNewsRecipe):
@ -22,12 +23,16 @@ class LaRepubblica(BasicNewsRecipe):
oldest_article = 5 oldest_article = 5
encoding = 'utf8' encoding = 'utf8'
use_embedded_content = False use_embedded_content = False
#recursion = 10
no_stylesheets = True no_stylesheets = True
publication_type = 'newspaper'
articles_are_obfuscated = True
temp_files = []
extra_css = """ extra_css = """
img{display: block} img{display: block}
""" """
remove_attributes = ['width','height','lang','xmlns:og','xmlns:fb']
preprocess_regexps = [ preprocess_regexps = [
(re.compile(r'.*?<head>', re.DOTALL|re.IGNORECASE), lambda match: '<head>'), (re.compile(r'.*?<head>', re.DOTALL|re.IGNORECASE), lambda match: '<head>'),
(re.compile(r'<head>.*?<title>', re.DOTALL|re.IGNORECASE), lambda match: '<head><title>'), (re.compile(r'<head>.*?<title>', re.DOTALL|re.IGNORECASE), lambda match: '<head><title>'),
@ -35,10 +40,27 @@ class LaRepubblica(BasicNewsRecipe):
] ]
def get_article_url(self, article): def get_article_url(self, article):
link = article.get('id', article.get('guid', None)) link = BasicNewsRecipe.get_article_url(self, article)
if link is None: if link and not '.repubblica.it/' in link:
return article link2 = article.get('id', article.get('guid', None))
return link if link2:
link = link2
return link.rpartition('?')[0]
def get_obfuscated_article(self, url):
count = 0
while (count < 10):
try:
response = self.browser.open(url)
html = response.read()
count = 10
except:
print "Retrying download..."
count += 1
self.temp_files.append(PersistentTemporaryFile('_fa.html'))
self.temp_files[-1].write(html)
self.temp_files[-1].close()
return self.temp_files[-1].name
keep_only_tags = [ keep_only_tags = [
dict(attrs={'class':'articolo'}), dict(attrs={'class':'articolo'}),
@ -49,7 +71,7 @@ class LaRepubblica(BasicNewsRecipe):
remove_tags = [ remove_tags = [
dict(name=['object','link','meta']), dict(name=['object','link','meta','iframe','embed']),
dict(name='span',attrs={'class':'linkindice'}), dict(name='span',attrs={'class':'linkindice'}),
dict(name='div', attrs={'class':'bottom-mobile'}), dict(name='div', attrs={'class':'bottom-mobile'}),
dict(name='div', attrs={'id':['rssdiv','blocco']}), dict(name='div', attrs={'id':['rssdiv','blocco']}),
@ -80,3 +102,11 @@ class LaRepubblica(BasicNewsRecipe):
(u'Edizione Palermo', u'feed://palermo.repubblica.it/rss/rss2.0.xml') (u'Edizione Palermo', u'feed://palermo.repubblica.it/rss/rss2.0.xml')
] ]
def preprocess_html(self, soup):
for item in soup.findAll(['hgroup','deresponsabilizzazione','per']):
item.name = 'div'
item.attrs = []
for item in soup.findAll(style=True):
del item['style']
return soup