mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
118 lines
4.2 KiB
Plaintext
118 lines
4.2 KiB
Plaintext
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 News Live'
|
|
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.cynewslive.com'
|
|
|
|
feeds = []
|
|
feeds.append(
|
|
('News: Cyprus', 'http://www.cynewslive.com/main/92,0,0,0-CYPRUS.aspx'))
|
|
feeds.append(
|
|
('News: World', 'http://www.cynewslive.com/main/78,0,0,0-UKWORLD.aspx'))
|
|
feeds.append(
|
|
('Sport: Football', 'http://www.cynewslive.com/main/82,0,0,0-FOOTBALL.aspx'))
|
|
feeds.append(
|
|
('Sport: Rugby', 'http://www.cynewslive.com/main/83,0,0,0-RUGBY.aspx'))
|
|
feeds.append(
|
|
('Sport: Cricket', 'http://www.cynewslive.com/main/85,0,0,0-CRICKET.aspx'))
|
|
feeds.append(
|
|
('Sport: Tennis', 'http://www.cynewslive.com/main/84,0,0,0-TENNIS.aspx'))
|
|
feeds.append(
|
|
('Sport: Other', 'http://www.cynewslive.com/main/86,0,0,0-OTHER.aspx'))
|
|
feeds.append(
|
|
('Business: Local', 'http://www.cynewslive.com/main/100,0,0,0-LOCAL.aspx'))
|
|
feeds.append(
|
|
('Business: Foreign', 'http://www.cynewslive.com/main/101,0,0,0-FOREIGN.aspx'))
|
|
feeds.append(
|
|
('Environment', 'http://www.cynewslive.com/main/93,0,0,0-ENVIRONMENT.aspx'))
|
|
feeds.append(
|
|
('Culture', 'http://www.cynewslive.com/main/208,0,0,0-CULTURE.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
|