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 
Fixes #1518080 [Le Devoir feed no longer works](https://bugs.launchpad.net/calibre/+bug/1518080)
This commit is contained in:
Kovid Goyal 2015-12-12 11:05:10 +05:30
parent 30b0783a4e
commit 8421468d24
1 changed files with 5 additions and 55 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

60
recipes/ledevoir.recipe
View File

@ -9,8 +9,6 @@ __description__ = 'Canadian Paper '
http://www.ledevoir.com/ http://www.ledevoir.com/
''' '''
import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class ledevoir(BasicNewsRecipe): class ledevoir(BasicNewsRecipe):
@ -36,17 +34,14 @@ class ledevoir(BasicNewsRecipe):
compress_news_images = True compress_news_images = True
compress_news_images_auto_size = 4 compress_news_images_auto_size = 4
filterDuplicates = False
url_list = [] url_list = []
remove_javascript = True remove_javascript = True
no_stylesheets = True no_stylesheets = True
preprocess_regexps = [(re.compile(r'(title|alt)=".*?>.*?"', re.DOTALL), lambda m: '')]
keep_only_tags = [ keep_only_tags = [
#dict(name='div', attrs={'id':'article_detail'}), # dict(name='div', attrs={'id':'article_detail'}),
#dict(name='div', attrs={'id':'colonne_principale'}), # dict(name='div', attrs={'id':'colonne_principale'}),
dict(name='article', attrs={'id':'article', 'class':'clearfix'}), dict(name='article', attrs={'id':'article', 'class':'clearfix'}),
dict(name='article', attrs={'id':'article', 'class':'clearfix portrait'}) dict(name='article', attrs={'id':'article', 'class':'clearfix portrait'})
] ]
@ -83,57 +78,12 @@ class ledevoir(BasicNewsRecipe):
(u'Art de vivre', 'http://www.ledevoir.com/rss/section/art-de-vivre.xml?id=50') (u'Art de vivre', 'http://www.ledevoir.com/rss/section/art-de-vivre.xml?id=50')
] ]
extra_css = '''
h1 {color:#1C1E7C;font-family:Times,Georgia,serif;font-size:1.85em;font-size-adjust:none;font-stretch:normal;font-style:normal;font-variant:normal;font-weight:bold;line-height:1.2em;margin:0 0 5px;}
h2 {color:#333333;font-family:Times,Georgia,serif;font-size:1.5em;font-size-adjust:none;font-stretch:normal;font-style:normal;font-variant:normal;font-weight:normal;line-height:1.2em;margin:0 0 5px;}
h3 {color:#4D4D4D;font-family:Arial,Helvetica,sans-serif; font-size:15px; font-size-adjust:none; font-stretch:normal; font-style:normal; font-variant:normal; font-weight:bold; line-height:14px;}
h4 {color:#333333; font-family:Arial,Helvetica,sans-serif;font-size:13px; font-size-adjust:none; font-stretch:normal; font-style:normal; font-variant:normal; font-weight:bold; line-height:14px; }
h5 {color:#333333; font-family:Arial,Helvetica,sans-serif; font-size:11px; font-size-adjust:none; font-stretch:normal; font-style:normal; font-variant:normal; font-weight:bold; line-height:14px; text-transform:uppercase;}
.specs {line-height:1em;margin:1px 0;}
.specs span.auteur {font:0.85em/1.1em Arial, Verdana, sans-serif;color:#787878;}
.specs span.auteur a,
.specs span.auteur span {text-transform:uppercase;color:#787878;}
.specs .date {font:0.85em/1.1em Arial, Verdana, sans-serif;color:#787878;}
ul#ariane {list-style-type:none;margin:0;padding:5px 0 8px 0;font:0.85em/1.2em Arial, Verdana, sans-serif;color:#2E2E2E;border-bottom:10px solid #fff;}
ul#ariane li {display:inline;}
ul#ariane a {color:#2E2E2E;text-decoration:underline;}
.credit {color:#787878;font-size:0.71em;line-height:1.1em;font-weight:bold;}
.texte {font-size:1.15em;line-height:1.4em;margin-bottom:17px;}
'''
def get_browser(self): def get_browser(self):
br = BasicNewsRecipe.get_browser(self) br = BasicNewsRecipe.get_browser(self)
if self.username is not None and self.password is not None: if self.username is not None and self.password is not None:
br.open('http://www.ledevoir.com') br.open('http://www.ledevoir.com')
br.select_form(nr=0) br.select_form(nr=1)
br['login_popup[courriel]'] = self.username br['login[courriel]'] = self.username
br['login_popup[password]'] = self.password br['login[password]'] = self.password
br.submit() br.submit()
return br return br
def print_version(self, url):
if self.filterDuplicates:
if url in self.url_list:
return
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
'''