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

Added title to each article and minimum_recipes support

Browse Source
This commit is contained in:
Alayn Gortazar 2012-04-16 23:05:06 +02:00
parent 2b826c4974
commit b81deec83a
1 changed files with 28 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
recipes/readitlater.recipe
View File

@ -3,7 +3,10 @@ readitlaterlist.com
'''
__license__ = 'GPL v3'
__copyright__ = '''
2010, Darko Miletic <darko.miletic at gmail.com>
2011, Przemyslaw Kryger <pkryger at gmail.com>
2011, Keith Callenberg <keithcallenberg@gmail.com>
2012, tBunnyMan <Wag That Tail At Me dot com>
2012, Alayn Gortazar <zutoin at gmail dot com>
'''
@ -14,16 +17,17 @@ import json
import urllib
import urllib2
class Readitlaterv2(BasicNewsRecipe):
title = 'Read It Later v2'
__author__ = 'Keith Callenberg'
class Readitlater(BasicNewsRecipe):
title = 'Read It Later'
__author__ = 'Darko Miletic, Przemyslaw Kryger, Keith Callenberg, tBunnyMan, Alayn Gortazar'
description = '''Personalized news feeds. Go to readitlaterlist.com to
setup up your news. Fill in your account
username, and optionally you can add your password.'''
publisher = 'readitlaterlist.com'
category = 'news, custom'
oldest_article = 7
max_articles_per_feed = 100
max_articles_per_feed = 50
minimum_articles = 1
no_stylesheets = True
use_embedded_content = False
needs_subscription = True
@ -51,7 +55,10 @@ class Readitlaterv2(BasicNewsRecipe):
def parse_index(self):
index = self.INDEX + 'v2/get?'
index += 'apikey=' + self.KEY
index += '&username=' + self.username + '&password=' + self.password
if self.username is not None:
index += '&username=' + self.username
if self.password is not None:
index += '&password=' + self.password
index += '&state=unread'
index += '&count=' + str(self.max_articles_per_feed)
@ -62,10 +69,12 @@ class Readitlaterv2(BasicNewsRecipe):
raise RuntimeError('Could not fetch index!')
json_obj = json.loads(results)
if len(json_obj['list']) > 0:
if len(json_obj['list']) >= self.minimum_articles:
for item in json_obj['list'].iteritems():
dataurl = "https://readitlaterlist.com/a/x/getArticle.php?itemId=" + item[1]['item_id']
# TODO: This URL should be modified by it's corresponding API call in a future.
# Actually is not possible to get the Article View potential throught an API call (12/04/2012)
dataurl = self.INDEX + "a/x/getArticle.php?itemId=" + item[1]['item_id']
self.articles.append({
'title':item[1]['title'],
'date':item[1]['time_added'],
@ -73,6 +82,9 @@ class Readitlaterv2(BasicNewsRecipe):
'description':item[1]['item_id'],
'real_url':item[1]['url']
})
else:
raise Exception("Not enough articles in RIL! Change minimum_articles or add more.")
return [('Unread', self.articles)]
def preprocess_raw_html(self, raw_html, url):
@ -81,23 +93,25 @@ class Readitlaterv2(BasicNewsRecipe):
self.images = {}
for image in json_obj['article']['images']:
self.images[image] = json_obj['article']['images'][image]['src']
return json_obj['article']['article']
title = '<h1>{title}</h1>'.format(title=json_obj['article']['title'])
link = '<p>Original: <a href="{url}">{url}</a></p>'.format(url=json_obj['article']['resolvedUrl'])
return link + title + json_obj['article']['article']
def preprocess_html(self, soup):
# Insert images on RIL_IMG_# divs
for key, url in self.images.iteritems():
tag = Tag(soup, 'img')
tag['src'] = url
imgtag = Tag(soup, 'img')
imgtag['src'] = url
div = soup.find('div', attrs={'id':'RIL_IMG_' + key})
div.insert(0, tag)
div.insert(0, imgtag)
return soup
def cleanup(self):
# From a list of urls, create a human-readable JSON string
# suitable for passing to the ReadItLater SEND::READ method.
self.markAsRead(self.createMarkList(self.articles))
#self.markAsRead(self.createMarkList(self.articles))
return
def createMarkList(self, articles):
urls = []