mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
39 lines
1.7 KiB
Plaintext
39 lines
1.7 KiB
Plaintext
import re
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
class AdvancedUserRecipe1359406781(BasicNewsRecipe):
|
|
title = u'Private Eye'
|
|
publication_type = 'magazine'
|
|
description = u'Private Eye is a fortnightly British satirical and current affairs magazine, edited by Ian Hislop'
|
|
oldest_article = 13
|
|
max_articles_per_feed = 100
|
|
remove_empty_feeds = True
|
|
remove_javascript = True
|
|
no_stylesheets = True
|
|
ignore_duplicate_articles = {'title'}
|
|
language = 'en_GB'
|
|
encoding = 'iso-8859-1'
|
|
__author__ = u'MartynPritchard@yahoo.com'
|
|
__copyright__ = '2014, Martyn Pritchard <MartynPritchard@yahoo.com>'
|
|
|
|
def get_cover_url(self):
|
|
cover_url = None
|
|
soup = self.index_to_soup('http://www.private-eye.co.uk/current_issue.php')
|
|
for citem in soup.findAll('img'):
|
|
if citem['src'].endswith('big.jpg'):
|
|
return 'http://www.private-eye.co.uk/' + citem['src']
|
|
return cover_url
|
|
|
|
remove_tags_before = {'class':"sub_dave"}
|
|
remove_tags = [dict(name='td', attrs={'class':'sub_dave'})]
|
|
|
|
preprocess_regexps = [
|
|
(re.compile(r'../grfx', re.DOTALL|re.IGNORECASE), lambda match: 'http://www.private-eye.co.uk/grfx'),
|
|
(re.compile(r'More From This Issue.*</body>', re.DOTALL|re.IGNORECASE), lambda match: '</body>'),
|
|
(re.compile(r'More top stories in the latest issue:.*</body>', re.DOTALL|re.IGNORECASE), lambda match: '</body>'),
|
|
(re.compile(r'Also Available Online.*</body>', re.DOTALL|re.IGNORECASE), lambda match: '</body>'),
|
|
]
|
|
|
|
feeds = [(u'Private Eye', u'http://www.private-eye.co.uk/rss/rss.php')]
|