Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-06-23 15:30:45 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Private Eye

Browse Source
This commit is contained in:
Kovid Goyal 2014-04-29 17:42:35 +05:30
parent 29f11510e2
commit c7d84b206d
2 changed files with 23 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
recipes/icons/private_eye.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 2.8 KiB

39
recipes/private_eye.recipe
View File

@ -1,31 +1,38 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1359406781(BasicNewsRecipe):
title = u'Private Eye'
oldest_article = 15
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'
__author__ = 'Martyn Pritchard'
encoding = 'iso-8859-1'
compress_news_images = True
compress_news_images_auto_size = 8
scale_news_images_to_device = False
scale_news_images = (220, 300)
encoding = 'iso-8859-1'
__author__ = u'MartynPritchard@yahoo.com'
__copyright__ = '2014, Martyn Pritchard <MartynPritchard@yahoo.com>'
def get_cover_url(self):
soup = self.index_to_soup('http://www.private-eye.co.uk')
cov = soup.find(attrs={'width' : '180', 'border' : '0'})
cover_url = 'http://www.private-eye.co.uk/'+cov['src']
return cover_url
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
keep_only_tags = [dict(name='table', attrs={'width':['100%'], 'border':['0'], 'align': ['center'], 'cellspacing':['0'], 'cellpadding':['0']}),
dict(name='table', attrs={'width':['480'], 'cellspacing':['0'], 'cellpadding':['0']}),
dict(name='table', attrs={'width':['490'], 'border':['0'], 'align': ['left'], 'cellspacing':['0'], 'cellpadding':['1']}),
dict(name='table', attrs={'width':['500'], 'cellspacing':['0'], 'cellpadding':['0']}),
]
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')]