Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

New recipe for Money Control by kwetal

Browse Source
This commit is contained in:
Kovid Goyal 2009-12-01 23:51:05 +00:00
parent 8cfbd3c603
commit a70957c75e
2 changed files with 62 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

57
resources/recipes/moneycontrol.recipe Normal file
View File

@ -0,0 +1,57 @@
from calibre.web.feeds.news import BasicNewsRecipe
#from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
class MoneyControlRecipe(BasicNewsRecipe):
__license__ = 'GPL v3'
__author__ = 'kwetal'
language = 'en_IN'
locale = 'en_IN'
encoding = 'iso-8859-1'
version = 1
title = u'Money Control'
publisher = u'moneycontrol.com'
category = u'News, Financial, India'
description = u'Financial news from India'
oldest_article = 7
max_articles_per_feed = 100
use_embedded_content = False
no_stylesheets = True
remove_javascript = True
feeds = []
feeds.append((u'Latest News', u'http://www.moneycontrol.com/rss/latestnews.xml'))
feeds.append((u'All Stories', u'http://www.moneycontrol.com/rss/allstories.xml'))
def print_version(self, url):
return url.replace('/stocksnews.php?', '/news_print.php?') + '&sr_no=0'
# The articles contain really horrible html. More than one <body> and <head> section, not properly closed tags, lots and lots of
# <font> tags and some weird <o:p></o:p> markup that crashes the conversion to ebook. Needs some drastic sanitizing
'''def preprocess_html(self, soup):
freshSoup = BeautifulSoup('<html><head></head><body></body></html>')
headline = soup.find('td', attrs = {'class': 'heading'})
if headline:
h1 = Tag(freshSoup, 'h1')
# Convert to string before adding it to the document!
h1.append(self.tag_to_string(headline))
freshSoup.body.append(h1)
for p in soup.findAll('p'):
if p.has_key('class'):
if p['class'] == 'MsoNormal':
# We have some weird pagebreak marker here; it will not find all of them however
continue
para = Tag(freshSoup, 'p')
# Convert to string; this will loose all formatting but also all illegal markup
para.append(self.tag_to_string(p))
freshSoup.body.append(para)
return freshSoup
'''

5
src/calibre/ebooks/oeb/base.py
View File

@ -861,6 +861,11 @@ class Manifest(object):
data = re.compile(r'<!--.*?-->', re.DOTALL).sub('', data = re.compile(r'<!--.*?-->', re.DOTALL).sub('',
data) data)
data = re.sub(r'<meta\s+[^>]+?>', '', data) data = re.sub(r'<meta\s+[^>]+?>', '', data)
open('/tmp/t.html', 'wb').write(data.encode('utf-8'))
data = data.replace(
"<?xml version='1.0' encoding='utf-8'?><o:p></o:p>",
'')
data = data.replace("<?xml version='1.0' encoding='utf-8'??>", '')
data = etree.fromstring(data) data = etree.fromstring(data)
elif namespace(data.tag) != XHTML_NS: elif namespace(data.tag) != XHTML_NS:
# OEB_DOC_NS, but possibly others # OEB_DOC_NS, but possibly others