New recipes for Cyprus Weekly by kwetal and RTE by Robin Phillips

This commit is contained in:
Kovid Goyal 2010-01-01 09:55:20 -07:00
parent bf090b2ba2
commit 9a28d7017f
4 changed files with 127 additions and 1 deletions

View File

@ -0,0 +1,108 @@
from calibre.web.feeds.news import BasicNewsRecipe
from datetime import datetime, timedelta
class CyNewsLiveRecipe(BasicNewsRecipe):
__license__ = 'GPL v3'
__author__ = 'kwetal'
language = 'en_CY'
version = 1
title = u'Cyprus Weekly'
publisher = u'The Cyprus Weekly'
category = u'News, Newspaper'
description = u'News from Cyprus'
use_embedded_content = False
remove_empty_feeds = True
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
remove_javascript = True
pubTime = None
minTime = None
articleCount = 0
INDEX = 'http://www.cyprusweekly.com.cy/main/default.aspx'
feeds = []
feeds.append(('News: Cyprus', 'http://www.cyprusweekly.com.cy/main/92,0,0,0-CYPRUS.aspx'))
feeds.append(('News: World', 'http://www.cyprusweekly.com.cy/main/78,0,0,0-UKWORLD.aspx'))
feeds.append(('Sport: Football', 'http://www.cyprusweekly.com.cy/main/82,0,0,0-FOOTBALL.aspx'))
feeds.append(('Sport: Rugby', 'http://www.cyprusweekly.com.cy/main/83,0,0,0-RUGBY.aspx'))
feeds.append(('Sport: Cricket', 'http://www.cyprusweekly.com.cy/main/85,0,0,0-CRICKET.aspx'))
feeds.append(('Sport: Tennis', 'http://www.cyprusweekly.com.cy/main/84,0,0,0-TENNIS.aspx'))
feeds.append(('Sport: Other', 'http://www.cyprusweekly.com.cy/main/86,0,0,0-OTHER.aspx'))
feeds.append(('Business: Local', 'http://www.cyprusweekly.com.cy/main/100,0,0,0-LOCAL.aspx'))
feeds.append(('Business: Foreign', 'http://www.cyprusweekly.com.cy/main/101,0,0,0-FOREIGN.aspx'))
feeds.append(('Whats On: Places of Interest', 'http://www.cyprusweekly.com.cy/main/123,0,0,0-PLACES-OF-INTEREST.aspx'))
feeds.append(('Whats On: Going Out', 'http://www.cyprusweekly.com.cy/main/153,0,0,0-GOING-OUT.aspx'))
feeds.append(('Whats On: Arts & Entertainment', 'http://www.cyprusweekly.com.cy/main/135,0,0,0-ARTS--and-ENTERTAINMENT.aspx'))
feeds.append(('Whats On: Things To Do', 'http://www.cyprusweekly.com.cy/main/136,0,0,0-THINGS-TO-DO.aspx'))
feeds.append(('Whats On: Shopping Guide', 'http://www.cyprusweekly.com.cy/main/142,0,0,0-SHOPPING-GUIDE.aspx'))
feeds.append(('Culture', 'http://www.cyprusweekly.com.cy/main/208,0,0,0-CULTURE.aspx'))
feeds.append(('Environment', 'http://www.cyprusweekly.com.cy/main/93,0,0,0-ENVIRONMENT.aspx'))
feeds.append(('Info', 'http://www.cyprusweekly.com.cy/main/91,0,0,0-INFO.aspx'))
keep_only_tags = []
keep_only_tags.append(dict(name = 'div', attrs = {'class': 'ArticleCategories'}))
extra_css = '''
body{font-family:verdana,arial,helvetica,geneva,sans-serif ;}
'''
def parse_index(self):
answer = []
for feed in self.feeds:
self.articleCount = 0
articles = []
soup = self.index_to_soup(feed[1])
table = soup.find('table', attrs = {'id': 'ctl00_cp_ctl01_listp'})
if table:
self.pubTime = datetime.now()
self.minTime = self.pubTime - timedelta(days = self.oldest_article)
self.find_articles(table, articles)
answer.append((feed[0], articles))
return answer
def postprocess_html(self, soup, first):
for el in soup.findAll(attrs = {'style': True}):
del el['style']
for el in soup.findAll('font'):
el.name = 'div'
for attr, value in el:
del el[attr]
return soup
def find_articles(self, table, articles):
for div in table.findAll('div', attrs = {'class': 'ListArticle'}):
el = div.find('div', attrs = {'class': 'ListArticle_T'})
title = self.tag_to_string(el.a)
url = self.INDEX + el.a['href']
description = self.tag_to_string(div.find('div', attrs = {'class': 'ListArticle_BODY300'}))
el = div.find('div', attrs = {'class': 'ListArticle_D'})
if el:
dateParts = self.tag_to_string(el).split(' ')
monthNames = {'January': 1, 'February': 2, 'March': 3, 'April': 4, 'May': 5, 'June': 6,
'July': 7, 'August': 8, 'September': 9, 'October': 10, 'November': 11,
'December': 12}
timeParts = dateParts[3].split(':')
self.pubTime = datetime(year = int(dateParts[2]), month = int(monthNames[dateParts[1]]),
day = int(dateParts[0]), hour = int(timeParts[0]),
minute = int(timeParts[1]))
if self.pubTime >= self.minTime and self.articleCount <= self.max_articles_per_feed:
articles.append({'title': title, 'date': self.pubTime, 'url': url, 'description': description})
self.articleCount += 1
else:
return

View File

@ -0,0 +1,15 @@
from calibre.web.feeds.news import BasicNewsRecipe
class RTE(BasicNewsRecipe):
title = u'RTE News'
oldest_article = 7
max_articles_per_feed = 100
__author__ = u'Robin Phillips'
language = 'en_GB'
remove_tags = [dict(attrs={'class':['topAd','botad','previousNextItem','headline','footerLinks','footernav']})]
feeds = [(u'News', u'http://www.rte.ie/rss/news.xml'), (u'Sport', u'http://www.rte.ie/rss/sport.xml'), (u'Soccer', u'http://www.rte.ie/rss/soccer.xml'), (u'GAA', u'http://www.rte.ie/rss/gaa.xml'), (u'Rugby', u'http://www.rte.ie/rss/rugby.xml'), (u'Racing', u'http://www.rte.ie/rss/racing.xml'), (u'Business', u'http://www.rte.ie/rss/business.xml'), (u'Entertainment', u'http://www.rte.ie/rss/entertainment.xml')]
def print_version(self, url):
return url.replace('http://www', 'http://m')

View File

@ -865,6 +865,7 @@ class Device(DeviceConfig, DevicePlugin):
use_subdirs = self.SUPPORTS_SUB_DIRS and settings.use_subdirs
fname = sanitize(fname)
ext = os.path.splitext(fname)[1]
if special_tag is None:
from calibre.library.save_to_disk import get_components
@ -892,6 +893,8 @@ class Device(DeviceConfig, DevicePlugin):
fname = sanitize(self.filename_callback(fname, mdata))
extra_components.append(fname)
extra_components = [str(x) for x in extra_components]
else:
extra_components[-1] += ext
def remove_trailing_periods(x):
ans = x

View File

@ -846,7 +846,7 @@ class DeviceGUI(object):
Upload books to device.
:param files: List of either paths to files or file like objects
'''
titles = [i['title'] for i in metadata]
titles = [i.title for i in metadata]
job = self.device_manager.upload_books(
Dispatcher(self.books_uploaded),
files, names, on_card=on_card,