Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2026-03-05 08:23:42 -05:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'kovidgoyal/master'

Browse Source
This commit is contained in:
Charles Haley 2013-09-17 14:28:09 +02:00
commit 9c3e61cee2
4 changed files with 28 additions and 142 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

60
recipes/liberation.recipe
View File

@ -21,42 +21,10 @@ class Liberation(BasicNewsRecipe):
max_articles_per_feed = 15
no_stylesheets = True
remove_empty_feeds = True
filterDuplicates = True
needs_subscription = 'optional'
extra_css = '''
h1, h2, h3 {font-size:xx-large; font-family:Arial,Helvetica,sans-serif;}
p.subtitle {font-size:xx-small; font-family:Arial,Helvetica,sans-serif;}
h4, h5, h2.rubrique, {font-size:xx-small; color:#4D4D4D; font-family:Arial,Helvetica,sans-serif;}
.ref, .date, .author, .legende {font-size:xx-small; color:#4D4D4D; font-family:Arial,Helvetica,sans-serif;}
.mna-body, entry-body {font-size:medium; font-family:Arial,Helvetica,sans-serif;}
'''
keep_only_tags = [
dict(name='div', attrs={'class':'article'})
,dict(name='div', attrs={'class':'text-article m-bot-s1'})
,dict(name='div', attrs={'class':'entry'})
,dict(name='div', attrs={'class':'col_contenu'})
]
remove_tags_after = [
dict(name='div',attrs={'class':['object-content text text-item', 'object-content', 'entry-content', 'col01', 'bloc_article_01']})
,dict(name='p',attrs={'class':['chapo']})
,dict(id='_twitter_facebook')
]
remove_tags = [
dict(name='iframe')
,dict(name='a', attrs={'class':'lnk-comments'})
,dict(name='div', attrs={'class':'toolbox'})
,dict(name='ul', attrs={'class':'share-box'})
,dict(name='ul', attrs={'class':'tool-box'})
,dict(name='ul', attrs={'class':'rub'})
,dict(name='p',attrs={'class':['chapo']})
,dict(name='p',attrs={'class':['tag']})
,dict(name='div',attrs={'class':['blokLies']})
,dict(name='div',attrs={'class':['alire']})
,dict(id='_twitter_facebook')
]
keep_only_tags = [dict(name='article')]
remove_tags = [dict(attrs={'class':['tool-bar']})]
feeds = [
(u'La une', u'http://rss.liberation.fr/rss/9/')
@ -69,6 +37,16 @@ class Liberation(BasicNewsRecipe):
,(u'Sports', u'http://www.liberation.fr/rss/12/')
]
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
if self.username is not None and self.password is not None:
br.open('http://token.liberation.fr/accounts/login/')
br.select_form(nr=0)
br['email'] = self.username
br['password'] = self.password
br.submit()
return br
def get_masthead_url(self):
masthead = 'http://s0.libe.com/libe/img/common/logo-liberation-150.png'
br = BasicNewsRecipe.get_browser(self)
@ -78,3 +56,15 @@ class Liberation(BasicNewsRecipe):
self.log("\nCover unavailable")
masthead = None
return masthead
def get_article_url(self, article):
url = BasicNewsRecipe.get_article_url(self, article)
url = url.split('/')[-2]
encoding = {'0B': '.', '0C': '/', '0A': '0', '0F': '=', '0G': '&',
'0D': '?', '0E': '-', '0N': '.com', '0L': 'http://', '0S':
'www.', '0I': '_'}
for k, v in encoding.iteritems():
url = url.replace(k, v)
return url.partition('?')[0]

103
recipes/liberation_sub.recipe
View File

@ -1,103 +0,0 @@
#!/usr/bin/env python
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
__license__ = 'GPL v3'
__copyright__ = '2012, Rémi Vanicat <vanicat at debian.org>'
'''
liberation.fr
'''
# The cleanning is from the Liberation recipe, by Darko Miletic
from calibre.web.feeds.news import BasicNewsRecipe
class Liberation(BasicNewsRecipe):
title = u'Libération: Édition abonnés'
__author__ = 'Rémi Vanicat'
description = u'Actualités'
category = 'Actualités, France, Monde'
language = 'fr'
needs_subscription = True
use_embedded_content = False
no_stylesheets = True
remove_empty_feeds = True
extra_css = '''
h1, h2, h3 {font-size:xx-large; font-family:Arial,Helvetica,sans-serif;}
p.subtitle {font-size:xx-small; font-family:Arial,Helvetica,sans-serif;}
h4, h5, h2.rubrique, {font-size:xx-small; color:#4D4D4D; font-family:Arial,Helvetica,sans-serif;}
.ref, .date, .author, .legende {font-size:xx-small; color:#4D4D4D; font-family:Arial,Helvetica,sans-serif;}
.mna-body, entry-body {font-size:medium; font-family:Arial,Helvetica,sans-serif;}
'''
keep_only_tags = [
dict(name='div', attrs={'class':'article'})
,dict(name='div', attrs={'class':'text-article m-bot-s1'})
,dict(name='div', attrs={'class':'entry'})
,dict(name='div', attrs={'class':'col_contenu'})
]
remove_tags_after = [
dict(name='div',attrs={'class':['object-content text text-item', 'object-content', 'entry-content', 'col01', 'bloc_article_01']})
,dict(name='p',attrs={'class':['chapo']})
,dict(id='_twitter_facebook')
]
remove_tags = [
dict(name='iframe')
,dict(name='a', attrs={'class':'lnk-comments'})
,dict(name='div', attrs={'class':'toolbox'})
,dict(name='ul', attrs={'class':'share-box'})
,dict(name='ul', attrs={'class':'tool-box'})
,dict(name='ul', attrs={'class':'rub'})
,dict(name='p',attrs={'class':['chapo']})
,dict(name='p',attrs={'class':['tag']})
,dict(name='div',attrs={'class':['blokLies']})
,dict(name='div',attrs={'class':['alire']})
,dict(id='_twitter_facebook')
]
index = 'http://www.liberation.fr/abonnes/'
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
if self.username is not None and self.password is not None:
br.open('http://www.liberation.fr/jogger/login/')
br.select_form(nr=0)
br['email'] = self.username
br['password'] = self.password
br.submit()
return br
def parse_index(self):
soup=self.index_to_soup(self.index)
content = soup.find('div', { 'class':'block-content' })
articles = []
cat_articles = []
for tag in content.findAll(recursive=False):
if(tag['class']=='headrest headrest-basic-rounded'):
cat_articles = []
articles.append((tag.find('h5').contents[0],cat_articles))
else:
title = tag.find('h3').contents[0]
url = tag.find('a')['href']
print(url)
descripion = tag.find('p',{ 'class':'subtitle' }).contents[0]
article = {
'title': title,
'url': url,
'descripion': descripion,
'content': ''
}
cat_articles.append(article)
return articles
# Local Variables:
# mode: python
# End:

2
src/calibre/devices/teclast/driver.py
View File

@ -72,7 +72,7 @@ class IPAPYRUS(TECLAST_K3):
FORMATS = ['epub', 'pdf', 'txt']
VENDOR_NAME = ['E_READER', 'EBOOKREA']
VENDOR_NAME = ['E_READER', 'EBOOKREA', 'ICARUS']
WINDOWS_MAIN_MEM = ''
class SOVOS(TECLAST_K3):

5
src/calibre/gui2/dialogs/tag_editor.py
View File

@ -63,13 +63,13 @@ class TagEditor(QDialog, Ui_TagEditor):
if geom is not None:
self.restoreGeometry(geom)
def delete_tags(self, item=None):
confirms, deletes = [], []
items = self.available_tags.selectedItems() if item is None else [item]
if not items:
error_dialog(self, 'No tags selected', 'You must select at least one tag from the list of Available tags.').exec_()
return
pos = self.available_tags.verticalScrollBar().value()
for item in items:
used = self.db.is_tag_used(unicode(item.text())) \
if self.key is None else \
@ -93,7 +93,7 @@ class TagEditor(QDialog, Ui_TagEditor):
label=self.key)
self.db.refresh_ids(bks)
self.available_tags.takeItem(self.available_tags.row(item))
self.available_tags.verticalScrollBar().setValue(pos)
def apply_tags(self, item=None):
items = self.available_tags.selectedItems() if item is None else [item]
@ -116,7 +116,6 @@ class TagEditor(QDialog, Ui_TagEditor):
item = self.available_tags.item(row)
self.available_tags.scrollToItem(item)
def unapply_tags(self, item=None):
items = self.applied_tags.selectedItems() if item is None else [item]
for item in items: