Calibre Recipe for Doctrine2 Manual

gistfile1.py

#!/usr/bin/env  python

import string, re

from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag, NavigableString

class Doctrine2(BasicNewsRecipe):

    title      = 'Doctrine2'
    __author__ = 'Doctrine PRoject'
    description = 'Documentation for Doctrine2'
    INDEX = 'http://www.doctrine-project.org/projects/orm/2.0/docs/reference/en'
    language = 'en'

    remove_tags_before = dict(name='div', id='documentation')
    remove_tags_after  = dict(name='div', id='documentation')
    remove_tags        = [dict(name='div', attrs={'class':'chapter-nav'})]

    no_stylesheets = True

    def parse_index(self):
        articles = []

        soup = self.index_to_soup(self.INDEX)

        contents = soup.find('div', attrs={'id':'documentation'})
        chapters = contents.find('ul')
        
        articles = [];
        
        for chapter in chapters.findAll('li'):
            a = chapter.find('a', href=True)
            url = a['href']
            if url.startswith('/'):
                url = 'http://www.doctrine-project.org'+url

            articles.append({'title':self.tag_to_string(a), 'url':url, 'description':self.tag_to_string(a),
                    'date':''})
        feeds = []
        feeds.append(('Documentation', articles))
        return feeds