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 La Republica. Fixes #904387 (Updated recipe for La Repubblica)

Browse Source
This commit is contained in:
Kovid Goyal 2011-12-15 08:32:28 +05:30
parent 9a2f9517f7
commit c14fd982e4
1 changed files with 17 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
recipes/la_republica.recipe
View File

@ -1,13 +1,12 @@
__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; 17.10.2011 new version' description = 'Italian daily newspaper - v1.01 (04, January 2010); 16.05.2010 new version; 17.10.2011 new version; 14.12.2011 new version'
''' '''
http://www.repubblica.it/ http://www.repubblica.it/
''' '''
import re
from calibre.ptempfile import PersistentTemporaryFile from calibre.ptempfile import PersistentTemporaryFile
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
@ -25,27 +24,21 @@ class LaRepubblica(BasicNewsRecipe):
use_embedded_content = False use_embedded_content = False
no_stylesheets = True no_stylesheets = True
publication_type = 'newspaper' publication_type = 'newspaper'
articles_are_obfuscated = True articles_are_obfuscated = True
temp_files = [] temp_files = []
extra_css = """ extra_css = """
img{display: block} img{display: block}
""" """
remove_attributes = ['width','height','lang','xmlns:og','xmlns:fb'] remove_attributes = ['width','height','lang','xmlns:og','xmlns:fb']
preprocess_regexps = [
(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'</title>.*?</head>', re.DOTALL|re.IGNORECASE), lambda match: '</title></head>')
]
def get_article_url(self, article): def get_article_url(self, article):
link = BasicNewsRecipe.get_article_url(self, article) link = BasicNewsRecipe.get_article_url(self, article)
if link and not '.repubblica.it/' in link: if link and not '.repubblica.it/' in link:
link2 = article.get('id', article.get('guid', None)) link2 = article.get('id', article.get('guid', None))
if link2: if link2:
link = link2 link = link2
return link.rpartition('?')[0] return link.rpartition('?')[0]
def get_obfuscated_article(self, url): def get_obfuscated_article(self, url):
count = 0 count = 0
@ -56,12 +49,12 @@ class LaRepubblica(BasicNewsRecipe):
count = 10 count = 10
except: except:
print "Retrying download..." print "Retrying download..."
count += 1 count += 1
self.temp_files.append(PersistentTemporaryFile('_fa.html')) self.temp_files.append(PersistentTemporaryFile('_fa.html'))
self.temp_files[-1].write(html) self.temp_files[-1].write(html)
self.temp_files[-1].close() self.temp_files[-1].close()
return self.temp_files[-1].name return self.temp_files[-1].name
keep_only_tags = [ keep_only_tags = [
dict(attrs={'class':'articolo'}), dict(attrs={'class':'articolo'}),
dict(attrs={'class':'body-text'}), dict(attrs={'class':'body-text'}),
@ -73,15 +66,15 @@ class LaRepubblica(BasicNewsRecipe):
remove_tags = [ remove_tags = [
dict(name=['object','link','meta','iframe','embed']), 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','adv adv-middle-inline']}),
dict(name='div', attrs={'id':['rssdiv','blocco']}), dict(name='div', attrs={'id':['rssdiv','blocco','fb-like-head']}),
dict(name='div', attrs={'class':'utility'}), dict(name='div', attrs={'class':['utility','fb-like-button','archive-button']}),
dict(name='div', attrs={'class':'generalbox'}), dict(name='div', attrs={'class':'generalbox'}),
dict(name='ul', attrs={'id':'hystory'}) dict(name='ul', attrs={'id':'hystory'})
] ]
feeds = [ feeds = [
(u'Rilievo', u'http://www.repubblica.it/rss/homepage/rss2.0.xml'), (u'Homepage', u'http://www.repubblica.it/rss/homepage/rss2.0.xml'),
(u'Cronaca', u'http://www.repubblica.it/rss/cronaca/rss2.0.xml'), (u'Cronaca', u'http://www.repubblica.it/rss/cronaca/rss2.0.xml'),
(u'Esteri', u'http://www.repubblica.it/rss/esteri/rss2.0.xml'), (u'Esteri', u'http://www.repubblica.it/rss/esteri/rss2.0.xml'),
(u'Economia', u'http://www.repubblica.it/rss/economia/rss2.0.xml'), (u'Economia', u'http://www.repubblica.it/rss/economia/rss2.0.xml'),
@ -105,8 +98,10 @@ class LaRepubblica(BasicNewsRecipe):
def preprocess_html(self, soup): def preprocess_html(self, soup):
for item in soup.findAll(['hgroup','deresponsabilizzazione','per']): for item in soup.findAll(['hgroup','deresponsabilizzazione','per']):
item.name = 'div' item.name = 'div'
item.attrs = [] item.attrs = []
for item in soup.findAll(style=True): for item in soup.findAll(style=True):
del item['style'] del item['style']
return soup return soup
def preprocess_raw_html(self, raw, url):
return '<html><head>'+raw[raw.find('</head>'):]