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

Waco Tribune Herald by rty

Browse Source
This commit is contained in:
Kovid Goyal 2010-07-14 09:01:01 -06:00
parent 9a4b661ac6
commit 8a5a5e2ad1
3 changed files with 104 additions and 70 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

70
resources/recipes/greader.recipe
View File

@ -1,35 +1,35 @@
import urllib, re, mechanize import urllib, re, mechanize
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
from calibre import __appname__ from calibre import __appname__
class GoogleReader(BasicNewsRecipe): class GoogleReader(BasicNewsRecipe):
title = 'Google Reader' title = 'Google Reader'
description = 'This recipe fetches from your Google Reader account unread Starred items and unread Feeds you have placed in a folder via the manage subscriptions feature.' description = 'This recipe fetches from your Google Reader account unread Starred items and unread Feeds you have placed in a folder via the manage subscriptions feature.'
needs_subscription = True needs_subscription = True
__author__ = 'davec, rollercoaster, Starson17' __author__ = 'davec, rollercoaster, Starson17'
base_url = 'http://www.google.com/reader/atom/' base_url = 'http://www.google.com/reader/atom/'
oldest_article = 365 oldest_article = 365
max_articles_per_feed = 250 max_articles_per_feed = 250
get_options = '?n=%d&xt=user/-/state/com.google/read' % max_articles_per_feed get_options = '?n=%d&xt=user/-/state/com.google/read' % max_articles_per_feed
use_embedded_content = True use_embedded_content = True
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:
request = urllib.urlencode([('Email', self.username), ('Passwd', self.password), request = urllib.urlencode([('Email', self.username), ('Passwd', self.password),
('service', 'reader'), ('accountType', 'HOSTED_OR_GOOGLE'), ('source', __appname__)]) ('service', 'reader'), ('accountType', 'HOSTED_OR_GOOGLE'), ('source', __appname__)])
response = br.open('https://www.google.com/accounts/ClientLogin', request) response = br.open('https://www.google.com/accounts/ClientLogin', request)
auth = re.search('Auth=(\S*)', response.read()).group(1) auth = re.search('Auth=(\S*)', response.read()).group(1)
cookies = mechanize.CookieJar() cookies = mechanize.CookieJar()
br = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookies)) br = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookies))
br.addheaders = [('Authorization', 'GoogleLogin auth='+auth)] br.addheaders = [('Authorization', 'GoogleLogin auth='+auth)]
return br return br
def get_feeds(self): def get_feeds(self):
feeds = [] feeds = []
soup = self.index_to_soup('http://www.google.com/reader/api/0/tag/list') soup = self.index_to_soup('http://www.google.com/reader/api/0/tag/list')
for id in soup.findAll(True, attrs={'name':['id']}): for id in soup.findAll(True, attrs={'name':['id']}):
url = id.contents[0] url = id.contents[0]
feeds.append((re.search('/([^/]*)$', url).group(1), feeds.append((re.search('/([^/]*)$', url).group(1),
self.base_url + urllib.quote(url.encode('utf-8')) + self.get_options)) self.base_url + urllib.quote(url.encode('utf-8')) + self.get_options))
return feeds return feeds

70
resources/recipes/greader_uber.recipe
View File

@ -1,35 +1,35 @@
import urllib, re, mechanize import urllib, re, mechanize
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
from calibre import __appname__ from calibre import __appname__
class GoogleReaderUber(BasicNewsRecipe): class GoogleReaderUber(BasicNewsRecipe):
title = 'Google Reader uber' title = 'Google Reader uber'
description = 'Fetches all feeds from your Google Reader account including the uncategorized items.' description = 'Fetches all feeds from your Google Reader account including the uncategorized items.'
needs_subscription = True needs_subscription = True
__author__ = 'davec, rollercoaster, Starson17' __author__ = 'davec, rollercoaster, Starson17'
base_url = 'http://www.google.com/reader/atom/' base_url = 'http://www.google.com/reader/atom/'
oldest_article = 365 oldest_article = 365
max_articles_per_feed = 250 max_articles_per_feed = 250
get_options = '?n=%d&xt=user/-/state/com.google/read' % max_articles_per_feed get_options = '?n=%d&xt=user/-/state/com.google/read' % max_articles_per_feed
use_embedded_content = True use_embedded_content = True
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:
request = urllib.urlencode([('Email', self.username), ('Passwd', self.password), request = urllib.urlencode([('Email', self.username), ('Passwd', self.password),
('service', 'reader'), ('accountType', 'HOSTED_OR_GOOGLE'), ('source', __appname__)]) ('service', 'reader'), ('accountType', 'HOSTED_OR_GOOGLE'), ('source', __appname__)])
response = br.open('https://www.google.com/accounts/ClientLogin', request) response = br.open('https://www.google.com/accounts/ClientLogin', request)
auth = re.search('Auth=(\S*)', response.read()).group(1) auth = re.search('Auth=(\S*)', response.read()).group(1)
cookies = mechanize.CookieJar() cookies = mechanize.CookieJar()
br = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookies)) br = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookies))
br.addheaders = [('Authorization', 'GoogleLogin auth='+auth)] br.addheaders = [('Authorization', 'GoogleLogin auth='+auth)]
return br return br
def get_feeds(self): def get_feeds(self):
feeds = [] feeds = []
soup = self.index_to_soup('http://www.google.com/reader/api/0/tag/list') soup = self.index_to_soup('http://www.google.com/reader/api/0/tag/list')
for id in soup.findAll(True, attrs={'name':['id']}): for id in soup.findAll(True, attrs={'name':['id']}):
url = id.contents[0].replace('broadcast','reading-list') url = id.contents[0].replace('broadcast','reading-list')
feeds.append((re.search('/([^/]*)$', url).group(1), feeds.append((re.search('/([^/]*)$', url).group(1),
self.base_url + urllib.quote(url.encode('utf-8')) + self.get_options)) self.base_url + urllib.quote(url.encode('utf-8')) + self.get_options))
return feeds return feeds

34
resources/recipes/waco_tribune.recipe Normal file
View File

@ -0,0 +1,34 @@
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1278773519(BasicNewsRecipe):
title = u'Waco Tribune Herald'
__author__ = 'rty'
pubisher = 'A Robinson Media Company'
description = 'Waco, Texas, Newspaper'
category = 'News, Texas, Waco'
oldest_article = 7
max_articles_per_feed = 100
feeds = [
(u'News', u'http://www.wacotrib.com/news/index.rss2'),
(u'Sports', u'http://www.wacotrib.com/sports/index.rss2'),
(u'AccessWaco', u'http://www.wacotrib.com/accesswaco/index.rss2'),
(u'Opinions', u'http://www.wacotrib.com/opinion/index.rss2')
]
remove_javascript = True
use_embedded_content = False
no_stylesheets = True
language = 'en'
encoding = 'utf-8'
conversion_options = {'linearize_tables':True}
masthead_url = 'http://media.wacotrib.com/designimages/wacotrib_logo.jpg'
keep_only_tags = [
dict(name='div', attrs={'class':'twoColumn left'}),
]
remove_tags = [
dict(name='div', attrs={'class':'right blueLinks'}),
]
remove_tags_after = [
dict(name='div', attrs={'class':'dottedRule'}),
]