[Rackamouth]

Hi,

Here's an interesting one. The following recipe produces a perfectly decent .epub, but if using .mobi (even when converting the good .epub to .mobi), almost all of the article somehow disappear... Of course I have kindle, so I can't use epub. Does it make sense to anyone?

Thanks.

The recipe:

import string, re
from calibre import strftime
from calibre.web.feeds.recipes import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup

class WV(BasicNewsRecipe):

	title       = 'Workers Vanguard'
	description = 'Current issue of Workers Vanguard'
	needs_subscription = False
	no_stylesheets = True    
    
	def print_version(self, url):
		return string.join(["http://www.spartacist.org/print/english/wv/", url],'')

	def parse_index(self):
		soup = self.index_to_soup('http://spartacist.org/english/wv/index.html')
		articles = []
		
		# find print URL of main article in index page
		for div in soup.findAll(text=re.compile("Printable")):
			a = div.findParent('a', href=True)
			if not a: continue 
			else: 
				url1 = string.split(re.sub(r'\?.*', '', a['href']), '/')
				url = string.join([url1[-2], '/', url1[-1]],'')
						
		# get issue number and date. Note we could find issue number from the URLs...
		for div in soup.findAll(id='folio'):
			a = div.string
			if a:
				date = a
				print string.join(['Found date: ', date])
				self.timefmt = date
			else:
				pubname = div.i.string
				print(pubname)
				issuenostring = div.i.findNextSibling(text=True)
				print string.join(['Found issue number string: ', issuenostring]) 
				self.title = string.join([pubname, issuenostring], '')
		
		# find headline of main article in index page
		for div in soup.findAll(id='headline'):
			headline = div.string
			print(string.join(['Found article ', headline, 'at url', url]))
			articles.append({'title':headline, 'url':url, 'description':'', 'date':date})
		
		# find following articles articles (parsing Table of Content at right of index page)
		for div in soup.findAll(id='smlheadline'):
			a = div.find('a', href=True)
			if not a: continue 
			else: 
				url = re.sub(r'\?.*', '', a['href'])
				headline = a.string
				print(string.join(['Found article', headline, 'at url', url]))
				articles.append({'title':headline, 'url':url, 'description':'', 'date':date})
				
		return [(string.join(['Workers Vanguard', issuenostring], ''), articles)]
		
	def postprocess_html(self, soup, first):
		for div in soup.findAll(id='headline'):
			div.name = 'h1'
		for div in soup.findAll(id='kicker'):
			div.name = 'h2'
		for div in soup.findAll(id='subhead'):
			div.name = 'h3'
		for div in soup.findAll(id='nytimes'):
			div.name = 'h3'
		for div in soup.findAll(id='wvquote'):
			div.name = 'blockquote'
		for div in soup.findAll(id='wvcite'):
			div.name = 'blockquote'
		return soup