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

American Prospect, FactCheck, PolitiFact by Michael Heinz

Browse Source
This commit is contained in:
Kovid Goyal 2010-05-18 18:03:16 -06:00
parent e1b988598c
commit b1287f0a51
6 changed files with 82 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
resources/recipes/aprospect.recipe Executable file
View File

@ -0,0 +1,26 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe
class AmericanProspect(BasicNewsRecipe):
title = u'American Prospect'
__author__ = u'Michael Heinz'
oldest_article = 30
language = 'en'
max_articles_per_feed = 100
recursions = 0
no_stylesheets = True
remove_javascript = True
preprocess_regexps = [
(re.compile(r'<body.*?<div class="pad_10L10R">', re.DOTALL|re.IGNORECASE), lambda match: '<body><div>'),
(re.compile(r'</div>.*</body>', re.DOTALL|re.IGNORECASE), lambda match: '</div></body>'),
(re.compile('\r'),lambda match: ''),
(re.compile(r'<!-- .+? -->', re.DOTALL|re.IGNORECASE), lambda match: ''),
(re.compile(r'<link .+?>', re.DOTALL|re.IGNORECASE), lambda match: ''),
(re.compile(r'<script.*?</script>', re.DOTALL|re.IGNORECASE), lambda match: ''),
(re.compile(r'<noscript.*?</noscript>', re.DOTALL|re.IGNORECASE), lambda match: ''),
(re.compile(r'<meta .*?/>', re.DOTALL|re.IGNORECASE), lambda match: ''),
]
feeds = [(u'Articles', u'feed://www.prospect.org/articles_rss.jsp')]

19
resources/recipes/factcheck.recipe Normal file
View File

@ -0,0 +1,19 @@
from calibre.web.feeds.news import BasicNewsRecipe
class FactCheckOrg(BasicNewsRecipe):
title = u'Factcheck'
__author__ = u'Michael Heinz'
language = 'en'
oldest_article = 7
max_articles_per_feed = 100
recursion = 0
publication_type = 'magazine'
masthead_url = 'http://factcheck.org/wp-content/themes/Streamline/images/headernew.jpg'
cover_url = 'http://factcheck.org/wp-content/themes/Streamline/images/headernew.jpg'
remove_tags = [ dict({'id':['footer','footerabout','sidebar']}) ]
feeds = [(u'Factcheck', u'feed://www.factcheck.org/feed/')]

30
resources/recipes/politifact.recipe Normal file
View File

@ -0,0 +1,30 @@
from calibre.wb.feeds.news import BasicNewsRecipe
class PolitiFactCom(BasicNewsRecipe):
title = u'Politifact'
__author__ = u'Michael Heinz'
oldest_article = 21
max_articles_per_feed = 100
recursion = 0
language = 'en'
no_stylesheets = True
publication_type = 'magazine'
masthead_url = 'http://static.politifact.com.s3.amazonaws.com/images/politifactdotcom-flag-fff_01.png'
cover_url = 'http://static.politifact.com.s3.amazonaws.com/images/politifactdotcom-flag-fff_01.png'
remove_tags = [
dict(name='div', attrs={'class':'pfstoryarchive'}),
dict(name='div', attrs={'class':'pfhead'}),
dict(name='div', attrs={'class':'boxmid'}),
]
keep_only_tags = [dict(name='div', attrs={'class':'pfcontentleft'})]
feeds = [
(u'Articles', u'http://www.politifact.com/feeds/articles/truth-o-meter/'),
(u'Obamameter', u'http://politifact.com/feeds/updates/'),
(u'Statements', u'http://www.politifact.com/feeds/statements/truth-o-meter/')
]

2
src/calibre/devices/manager.py
View File

@ -34,6 +34,6 @@ class Worker(threading.Thread):
def run(self): def run(self):
'''Thread loops taking jobs from the queue as they become available''' '''Thread loops taking jobs from the queue as they become available'''
while True: while True:
job = self.jobs.get(True, None) self.jobs.get(True, None)
# Do job # Do job
self.jobs.task_done() self.jobs.task_done()

2
src/calibre/ebooks/rtf2xml/paragraph_def.py
View File

@ -354,7 +354,6 @@ if another paragraph_def is found, the state changes to collect_tokens.
def __tab_stop_func(self, line): def __tab_stop_func(self, line):
""" """
""" """
type = 'tabs-%s' % self.__tab_type
self.__att_val_dict['tabs'] += '%s:' % self.__tab_type self.__att_val_dict['tabs'] += '%s:' % self.__tab_type
self.__att_val_dict['tabs'] += '%s;' % line[20:-1] self.__att_val_dict['tabs'] += '%s;' % line[20:-1]
self.__tab_type = 'left' self.__tab_type = 'left'
@ -373,7 +372,6 @@ if another paragraph_def is found, the state changes to collect_tokens.
""" """
leader = self.__tab_type_dict.get(self.__token_info) leader = self.__tab_type_dict.get(self.__token_info)
if leader != None: if leader != None:
type = 'tabs-%s' % self.__tab_type
self.__att_val_dict['tabs'] += '%s^' % leader self.__att_val_dict['tabs'] += '%s^' % leader
else: else:
if self.__run_level > 3: if self.__run_level > 3:

2
src/calibre/ebooks/rtf2xml/styles.py
View File

@ -318,7 +318,6 @@ class Styles:
Try to add the number to dictionary entry tabs-left, or tabs-right, etc. Try to add the number to dictionary entry tabs-left, or tabs-right, etc.
If the dictionary entry doesn't exist, create one. If the dictionary entry doesn't exist, create one.
""" """
type = 'tabs-%s' % self.__tab_type
try: try:
if self.__leader_found: if self.__leader_found:
self.__styles_dict['par'][self.__styles_num]['tabs']\ self.__styles_dict['par'][self.__styles_num]['tabs']\
@ -362,7 +361,6 @@ class Styles:
leader = self.__tab_type_dict.get(self.__token_info) leader = self.__tab_type_dict.get(self.__token_info)
if leader != None: if leader != None:
leader += '^' leader += '^'
type = 'tabs-%s' % self.__tab_type
try: try:
self.__styles_dict['par'][self.__styles_num]['tabs'] += ':%s;' % leader self.__styles_dict['par'][self.__styles_num]['tabs'] += ':%s;' % leader
except KeyError: except KeyError: