Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 18:24:30 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Private Eye

Browse Source
This commit is contained in:
Kovid Goyal 2016-08-09 07:30:19 +05:30
parent 0cb677fb90
commit c7c1b175f3
1 changed files with 16 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
recipes/private_eye.recipe
View File

@ -1,44 +1,42 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1359406781(BasicNewsRecipe):
title = u'Private Eye'
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
remove_javascript = True
no_stylesheets = True
ignore_duplicate_articles = {'title'}
language = 'en_GB'
encoding = 'iso-8859-1'
encoding = 'cp1252'
__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')
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'})]
remove_tags_before = {'class':"article"}
remove_tags_after = {'id' : "nav-box-sections-mobile"}
remove_tags_after = {'class' : "gap-biggest"}
remove_tags_after = {'id' : "subscribe-here"}
remove_tags = [dict(name='td', attrs={'class':'sub_dave'})]
remove_tags = [dict(name='div', attrs={'class':'footer-block'})]
remove_tags = [dict(name='div', attrs={'class':'sub-nav-bar'})]
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>'),
(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')]
feeds = [(u'Private Eye', u'https://dl.dropboxusercontent.com/u/10483931/PrivateEyeStat.xml')]