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

Merge branch 'master' of github.com:kovidgoyal/calibre

Browse Source
This commit is contained in:
Kovid Goyal 2013-08-05 21:07:52 +05:30
commit 31666454f3
2 changed files with 34 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
recipes/icons/le_monde_sub.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 510 B

55
recipes/le_monde_sub.recipe
View File

@ -13,7 +13,7 @@ class LeMonde(BasicNewsRecipe):
title = u'Le Monde: Édition abonnés'
__author__ = 'Sylvain Durand'
description = u'Disponible du lundi au samedi à partir de 14 heures environ, avec tous ses cahiers.'
description = u'La version papier du quotidien Le Monde, disponible du lundi au samedi à partir de 14 heures environ, avec tous ses cahiers.'
language = 'fr'
encoding = 'utf8'
@ -65,28 +65,41 @@ class LeMonde(BasicNewsRecipe):
url = time.strftime(self.journal_url,self.date)
soup = self.index_to_soup(url).sommaire
sections = []
for sec in soup.findAll("section"):
articles = []
if sec['cahier'] != "Le Monde":
for col in sec.findAll("fnts"):
col.extract()
if sec['cahier']=="Le Monde Magazine":
continue
for art in sec.findAll("art"):
if art.txt.string and art.ttr.string:
if art.find(['url']):
art.insert(6,'<div id="photo"><img src="'+art.find(['url']).string+'" /></div>')
if art.find(['lgd']) and art.find(['lgd']).string:
art.insert(7,'<div id="lgd">'+art.find(['lgd']).string+'</div>')
article = "<html><head></head><body>"+unicode(art)+"</body></html>"
article = article.replace('<![CDATA[','').replace(']]>','').replace(' oC ','°C ')
article = article.replace('srttr>','h3>').replace('ssttr>','h2>').replace('ttr>','h1>')
f = PersistentTemporaryFile()
f.write(article)
articles.append({'title':art.ttr.string,'url':"file:///"+f.name})
sections.append((sec['nom'], articles))
try:
for sec in soup.findAll("section"):
articles = []
if sec['cahier'] != "Le Monde":
for col in sec.findAll("fnts"):
col.extract()
if sec['cahier']=="Le Monde Magazine":
continue
for art in sec.findAll("art"):
if art.txt.string and art.ttr.string:
if art.find(['url']):
art.insert(6,'<div id="photo"><img src="'+art.find(['url']).string+'" /></div>')
if art.find(['lgd']) and art.find(['lgd']).string:
art.insert(7,'<div id="lgd">'+art.find(['lgd']).string+'</div>')
def guillemets(match):
if match.group(1) == u"=":
return match.group(0)
return u'%s«&nbsp;%s&nbsp;»' % (match.group(1), match.group(2))
article = "<html><head></head><body>"+unicode(art)+"</body></html>"
article = article.replace('<![CDATA[','').replace(']]>','').replace(' oC ','°C ')
article = article.replace('srttr>','h3>').replace('ssttr>','h2>').replace('ttr>','h1>')
article = article.replace("'" , u'\u2019')
article = re.sub('(.|^)"([^"]+)"', guillemets, article)
f = PersistentTemporaryFile()
f.write(article)
articles.append({'title':art.ttr.string,'url':"file:///"+f.name})
sections.append((sec['nom'], articles))
except AttributeError:
self.log("Vos identifiants sont incorrects, ou votre abonnement LeMonde.fr ne vous permet pas de télécharger le journal.")
return sections
def preprocess_html(self, soup):
for lgd in soup.findAll(id="lgd"):
lgd.contents[-1].extract()