Merge from trunk

This commit is contained in:
Charles Haley 2011-03-01 15:37:00 +00:00
commit 06562f5fa3
6 changed files with 165 additions and 12 deletions

Binary file not shown.

After

Width:  |  Height:  |  Size: 2.1 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 11 KiB

View File

@ -1,6 +1,6 @@
#!/usr/bin/env python
__license__ = 'GPL 3'
__copyright__ = 'zotzot'
__copyright__ = 'zotzo'
__docformat__ = 'restructuredtext en'
'''
http://www.epltalk.com
@ -9,10 +9,9 @@ from calibre.web.feeds.news import BasicNewsRecipe
class EPLTalkRecipe(BasicNewsRecipe):
__license__ = 'GPL v3'
__author__ = u'The Gaffer'
language = 'en'
version = 1
version = 2
__author__ = 'rylsfan'
title = u'EPL Talk'
publisher = u'The Gaffer'
@ -21,17 +20,40 @@ class EPLTalkRecipe(BasicNewsRecipe):
description = u'News and Analysis from the English Premier League'
cover_url = 'http://bit.ly/hJxZPu'
oldest_article = 45
max_articles_per_feed = 150
oldest_article = 3
max_articles_per_feed = 100
use_embedded_content = True
remove_javascript = True
encoding = 'utf8'
remove_tags_after = [dict(name='div', attrs={'class':'pd-rating'})]
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
feeds = [(u'EPL Talk', u'http://feeds.feedburner.com/EPLTalk')]
remove_tags = [
{'class': 'feedflare'},
{'class': 'tweetmeme_button'},
{'class': 'eplrelated'},
{'p': 'Related posts:<ol>'},
]
def preprocess_html(self, soup):
return self.adeify_images(soup)
feeds =[
(u'EPL Talk', u'http://feeds.feedburner.com/EPLTalk'),
(u'MLS Talk', u'http://feeds.feedburner.com/majorleaguesoccertalksite'),
#(),
#(),
#(),
]
extra_css = '''
body{font-family:verdana,arial,helvetica,geneva,sans-serif;}
img {float: left; margin-right: 0.5em;}
'''
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
'''

View File

@ -0,0 +1,55 @@
#!/usr/bin/env python
# encoding: utf-8
from __future__ import with_statement
__license__ = 'GPL 3'
__copyright__ = 'zotzo'
__docformat__ = 'restructuredtext en'
"""
http://fifthdown.blogs.nytimes.com/
http://offthedribble.blogs.nytimes.com/
http://thequad.blogs.nytimes.com/
http://slapshot.blogs.nytimes.com/
http://goal.blogs.nytimes.com/
http://bats.blogs.nytimes.com/
http://straightsets.blogs.nytimes.com/
http://formulaone.blogs.nytimes.com/
http://onpar.blogs.nytimes.com/
"""
from calibre.web.feeds.news import BasicNewsRecipe
class NYTimesSports(BasicNewsRecipe):
title = 'New York Times Sports Beat'
language = 'en'
__author__ = 'rylsfan'
description = 'Indepth sports from the New York Times'
publisher = 'The New York Times'
category = 'Sports'
oldest_article = 3
max_articles_per_feed = 25
no_stylesheets = True
language = 'en'
#cover_url ='http://bit.ly/h8F4DO'
feeds = [
(u'The Fifth Down', u'http://fifthdown.blogs.nytimes.com/feed/'),
(u'Off The Dribble', u'http://offthedribble.blogs.nytimes.com/feed/'),
(u'The Quad', u'http://thequad.blogs.nytimes.com/feed/'),
(u'Slap Shot', u'http://slapshot.blogs.nytimes.com/feed/'),
(u'Goal', u'http://goal.blogs.nytimes.com/feed/'),
(u'Bats', u'http://bats.blogs.nytimes.com/feed/'),
(u'Straight Sets', u'http://straightsets.blogs.nytimes.com/feed/'),
(u'Formula One', u'http://formulaone.blogs.nytimes.com/feed/'),
(u'On Par', u'http://onpar.blogs.nytimes.com/feed/'),
]
keep_only_tags = [dict(name='div', attrs={'id':'header'}),
dict(name='h1'),
dict(name='h2'),
dict(name='div', attrs={'class':'entry-content'})]
extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
'''

View File

@ -0,0 +1,46 @@
#!/usr/bin/env python
# encoding: utf-8
from __future__ import with_statement
__license__ = 'GPL 3'
__copyright__ = 'zotzo'
__docformat__ = 'restructuredtext en'
"""
http://pogue.blogs.nytimes.com/
"""
from calibre.web.feeds.news import BasicNewsRecipe
class NYTimesTechnology(BasicNewsRecipe):
title = 'New York Times Technology Beat'
language = 'en'
__author__ = 'David Pogue'
description = 'The latest in technology from David Pogue'
publisher = 'The New York Times'
category = 'Technology'
oldest_article = 14
max_articles_per_feed = 25
no_stylesheets = True
language = 'en'
cover_url ='http://bit.ly/g0SKJT'
feeds = [
(u'Pogues Posts', u'http://pogue.blogs.nytimes.com/feed/'),
(u'Bits', u'http://bits.blogs.nytimes.com/feed/'),
(u'Gadgetwise', u'http://gadgetwise.blogs.nytimes.com/feed/'),
(u'Open', u'http://open.blogs.nytimes.com/feed/')
]
keep_only_tags = [dict(name='div', attrs={'id':'header'}),
dict(name='h1'),
dict(name='h2'),
dict(name='div', attrs={'class':'entry-content'})]
extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif;
font-weight:bold;font-size:large;}
h2{font-family:Arial,Helvetica,sans-serif;
font-weight:normal;font-size:small;}
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
'''

View File

@ -124,7 +124,10 @@ class Metadata(object):
def __setattr__(self, field, val, extra=None):
_data = object.__getattribute__(self, '_data')
if field in TOP_LEVEL_IDENTIFIERS:
field, val = self._clean_identifier(field, val)
_data['identifiers'].update({field: val})
elif field == 'identifiers':
self.set_identifiers(val)
elif field in STANDARD_METADATA_FIELDS:
if val is None:
val = NULL_VALUES.get(field, None)
@ -189,8 +192,35 @@ class Metadata(object):
ans = {}
return copy.deepcopy(ans)
def _clean_identifier(self, typ, val):
typ = icu_lower(typ).strip().replace(':', '').replace(',', '')
val = val.strip().replace(',', '|').replace(':', '|')
return typ, val
def set_identifiers(self, identifiers):
object.__getattribute__(self, '_data')['identifiers'] = identifiers
'''
Set all identifiers. Note that if you previously set ISBN, calling
this method will delete it.
'''
cleaned = {}
for key, val in identifiers.iteritems():
key, val = self._clean_identifier(key, val)
if key and val:
cleaned[key] = val
object.__getattribute__(self, '_data')['identifiers'] = cleaned
def set_identifier(self, typ, val):
'If val is empty, deletes identifier of type typ'
typ, val = self._clean_identifier(typ, val)
if not typ:
return
identifiers = object.__getattribute__(self,
'_data')['identifiers']
if not val and typ in identifiers:
identifiers.pop(typ)
if val:
identifiers[typ] = val
# field-oriented interface. Intended to be the same as in LibraryDatabase