Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 10:44:09 -04:00
Code Issues Packages Projects Releases Wiki Activity

Improved Independent

Browse Source
This commit is contained in:
Kovid Goyal 2011-11-07 07:41:37 +05:30
parent 1ce331c2aa
commit 89c3ed5c5f
1 changed files with 73 additions and 43 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

66
recipes/independent.recipe
View File

@ -1,8 +1,9 @@
# adapted from old recipe by Darko Miletic <darko.miletic at gmail.com>
import re
import string, re
from calibre import strftime
from calibre.web.feeds.recipes import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag, NavigableString
from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag, NavigableString
class TheIndependentNew(BasicNewsRecipe):
@ -82,15 +83,16 @@ class TheIndependentNew(BasicNewsRecipe):
img['src'] = item['href']
#insert heading
tag = Tag(soup,'h3')
text = NavigableString('Caption: ' + img['title'])
tag.insert(0,text)
#insert caption if available
if img['title'] is not None and (len(img['title']) > 1):
tag = Tag(soup,'h3')
text = NavigableString(img['title'])
tag.insert(0,text)
#picture before text
img.extract()
item.insert(0,img)
item.insert(1,tag)
#picture before text
img.extract()
item.insert(0,img)
item.insert(1,tag)
# remove link
item.name = "div"
@ -99,16 +101,41 @@ class TheIndependentNew(BasicNewsRecipe):
#remove empty subtitles
"""
currently the subtitle is located in first paragraph after
sibling <h3 class="subtitle"> tag. This may be 'fixed' at
some point.
"""
subtitle = soup.find('h3',attrs={'class' : 'subtitle'})
subtitleText = subtitle.findNext('p')
if subtitleText is not None:
if len(subtitleText.contents[0]) <= 1 :
subtitleText.extract()
subtitle.extract()
if subtitle is not None:
subtitleText = subtitle.findNext('p')
if subtitleText is not None:
if len(subtitleText.contents[0]) <= 1 :
subtitleText.extract()
subtitle.extract()
return soup
def postprocess_html(self,soup, first_fetch):
#find broken images and remove captions
for item in soup.findAll('div', attrs={'class' : 'byline'}):
img = item.findNext('img')
if img is not None and img['src'] is not None:
# broken images still point to remote url
pattern = re.compile('http://www.independent.co.uk.*')
if pattern.match(img["src"]) is not None:
caption = img.findNextSibling('h3')
if caption is not None:
caption.extract()
img.extract()
return soup
feeds = [
(u'News - UK',
u'http://www.independent.co.uk/news/uk/?service=rss'),
@ -125,7 +152,7 @@ class TheIndependentNew(BasicNewsRecipe):
(u'News - Education',
u'http://www.independent.co.uk/news/education/?service=rss'),
(u'News - Obituaries',
u'http://rss.feedsportal.com/c/266/f/3531/index.rss'),
u'http://www.independent.co.uk/news/obituaries/?service=rss'),
(u'News - Corrections',
u'http://www.independent.co.uk/news/corrections/?service=rss'
),
@ -146,11 +173,11 @@ class TheIndependentNew(BasicNewsRecipe):
u'http://www.independent.co.uk/sport/motor-racing/?service=rss'
),
(u'Sport - Olympics',
u'http://rss.feedsportal.com/c/266/f/3800/index.rss'),
u'http://www.independent.co.uk/sport/olympics/?service=rss'),
(u'Sport - Racing',
u'http://www.independent.co.uk/sport/racing/?service=rss'),
(u'Sport - Rugby League',
u'http://rss.feedsportal.com/c/266/f/3795/index.rss'),
u'http://www.independent.co.uk/sport/general/rugby-league/?service=rss'),
(u'Sport - Rugby Union',
u'http://www.independent.co.uk/sport/rugby/rugby-union/?service=rss'
),
@ -216,3 +243,6 @@ class TheIndependentNew(BasicNewsRecipe):
u'http://www.independent.co.uk/extras/indybest/?service=rss'),
]