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 Le Devoir

Browse Source
This commit is contained in:
Kovid Goyal 2013-03-24 00:48:24 +05:30
parent c72c2c8649
commit 20333cff39
1 changed files with 36 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

47
recipes/ledevoir.recipe
View File

@ -2,7 +2,7 @@ __license__ = 'GPL v3'
__author__ = 'Lorenzo Vigentini and Olivier Daigle'
__copyright__ = '2012, Lorenzo Vigentini <l.vigentini at gmail.com>, Olivier Daigle <odaigle _at nuvucameras __dot__ com>'
__version__ = 'v1.01'
__date__ = '22, December 2012'
__date__ = '17, March 2013'
__description__ = 'Canadian Paper '
'''
@ -12,6 +12,7 @@ http://www.ledevoir.com/
import re
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.utils.magick import Image
class ledevoir(BasicNewsRecipe):
author = 'Lorenzo Vigentini'
@ -28,10 +29,14 @@ class ledevoir(BasicNewsRecipe):
oldest_article = 1
max_articles_per_feed = 200
min_articles_per_feed = 0
use_embedded_content = False
recursion = 10
needs_subscription = 'optional'
compress_news_images = True
compress_news_images_auto_size = 4
filterDuplicates = False
url_list = []
@ -66,16 +71,16 @@ class ledevoir(BasicNewsRecipe):
feeds = [
(u'A la une', 'http://www.ledevoir.com/rss/manchettes.xml'),
# (u'Édition complete', 'http://feeds2.feedburner.com/fluxdudevoir'),
# (u'Opinions', 'http://www.ledevoir.com/rss/opinions.xml'),
# (u'Chroniques', 'http://www.ledevoir.com/rss/chroniques.xml'),
# (u'Politique', 'http://www.ledevoir.com/rss/section/politique.xml?id=51'),
# (u'International', 'http://www.ledevoir.com/rss/section/international.xml?id=76'),
# (u'Culture', 'http://www.ledevoir.com/rss/section/culture.xml?id=48'),
# (u'Environnement', 'http://www.ledevoir.com/rss/section/environnement.xml?id=78'),
# (u'Societe', 'http://www.ledevoir.com/rss/section/societe.xml?id=52'),
# (u'Economie', 'http://www.ledevoir.com/rss/section/economie.xml?id=49'),
# (u'Sports', 'http://www.ledevoir.com/rss/section/sports.xml?id=85'),
(u'Édition complete', 'http://feeds2.feedburner.com/fluxdudevoir'),
(u'Opinions', 'http://www.ledevoir.com/rss/opinions.xml'),
(u'Chroniques', 'http://www.ledevoir.com/rss/chroniques.xml'),
(u'Politique', 'http://www.ledevoir.com/rss/section/politique.xml?id=51'),
(u'International', 'http://www.ledevoir.com/rss/section/international.xml?id=76'),
(u'Culture', 'http://www.ledevoir.com/rss/section/culture.xml?id=48'),
(u'Environnement', 'http://www.ledevoir.com/rss/section/environnement.xml?id=78'),
(u'Societe', 'http://www.ledevoir.com/rss/section/societe.xml?id=52'),
(u'Economie', 'http://www.ledevoir.com/rss/section/economie.xml?id=49'),
(u'Sports', 'http://www.ledevoir.com/rss/section/sports.xml?id=85'),
(u'Art de vivre', 'http://www.ledevoir.com/rss/section/art-de-vivre.xml?id=50')
]
@ -113,3 +118,23 @@ class ledevoir(BasicNewsRecipe):
self.url_list.append(url)
return url
'''
def postprocess_html(self, soup, first):
#process all the images. assumes that the new html has the correct path
if first == 0:
return soup
for tag in soup.findAll(lambda tag: tag.name.lower()=='img' and tag.has_key('src')):
iurl = tag['src']
img = Image()
img.open(iurl)
# width, height = img.size
# print 'img is: ', iurl, 'width is: ', width, 'height is: ', height
if img < 0:
raise RuntimeError('Out of memory')
img.set_compression_quality(30)
img.save(iurl)
return soup
'''