calibre/resources/recipes/wsj.recipe

#!/usr/bin/env  python
__license__   = 'GPL v3'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
__docformat__ = 'restructuredtext en'

import string
from calibre.web.feeds.news import BasicNewsRecipe

# http://online.wsj.com/page/us_in_todays_paper.html

class WallStreetJournal(BasicNewsRecipe):

    title = 'The Wall Street Journal (US)'
    __author__ = 'Kovid Goyal and Sujata Raman'
    description = 'News and current affairs'
    needs_subscription = True
    language = 'en'

    max_articles_per_feed = 1000
    timefmt  = ' [%a, %b %d, %Y]'
    no_stylesheets = True

    extra_css      = '''h1{color:#093D72 ; font-size:large ; font-family:Georgia,"Century Schoolbook","Times New Roman",Times,serif; }
                    h2{color:#474537; font-family:Georgia,"Century Schoolbook","Times New Roman",Times,serif; font-size:small; font-style:italic;}
                    .subhead{color:gray; font-family:Georgia,"Century Schoolbook","Times New Roman",Times,serif; font-size:small; font-style:italic;}
                    .insettipUnit {color:#666666; font-family:Arial,Sans-serif;font-size:xx-small }
                    .targetCaption{ font-size:x-small; color:#333333; font-family:Arial,Helvetica,sans-serif}
                    .article{font-family :Arial,Helvetica,sans-serif; font-size:x-small}
                    .tagline {color:#333333; font-size:xx-small}
                    .dateStamp {color:#666666; font-family:Arial,Helvetica,sans-serif}
                        h3{color:blue ;font-family:Arial,Helvetica,sans-serif; font-size:xx-small}
                        .byline{color:blue;font-family:Arial,Helvetica,sans-serif; font-size:xx-small}
                        h6{color:#333333; font-family:Georgia,"Century Schoolbook","Times New Roman",Times,serif; font-size:small;font-style:italic; }
                    .paperLocation{color:#666666; font-size:xx-small}'''

    remove_tags_before = dict(name='h1')
    remove_tags = [
                    dict(id=["articleTabs_tab_article", "articleTabs_tab_comments", "articleTabs_tab_interactive","articleTabs_tab_video","articleTabs_tab_map","articleTabs_tab_slideshow"]),
                    {'class':['footer_columns','network','insetCol3wide','interactive','video','slideshow','map','insettip','insetClose','more_in', "insetContent", 'articleTools_bottom', 'aTools', "tooltip", "adSummary", "nav-inline"]},
                    dict(rel='shortcut icon'),
                    ]
    remove_tags_after = [dict(id="article_story_body"), {'class':"article story"},]


    def get_browser(self):
        br = BasicNewsRecipe.get_browser()
        if self.username is not None and self.password is not None:
            br.open('http://commerce.wsj.com/auth/login')
            br.select_form(nr=0)
            br['user']   = self.username
            br['password'] = self.password
            res = br.submit()
            raw = res.read()
            if 'Welcome,' not in raw:
                raise ValueError('Failed to log in to wsj.com, check your '
                        'username and password')
        return br

    def postprocess_html(self, soup, first):
        for tag in soup.findAll(name=['table', 'tr', 'td']):
            tag.name = 'div'

        for tag in soup.findAll('div', dict(id=["articleThumbnail_1", "articleThumbnail_2", "articleThumbnail_3", "articleThumbnail_4", "articleThumbnail_5", "articleThumbnail_6", "articleThumbnail_7"])):
            tag.extract()

        return soup

    def wsj_get_index(self):
        return self.index_to_soup('http://online.wsj.com/page/us_in_todays_paper.html')

    def parse_index(self):
        soup = self.wsj_get_index()

        date = soup.find('span', attrs={'class':'date-date'})
        if date is not None:
            self.timefmt = ' [%s]'%self.tag_to_string(date)

        sections = {}
        sec_order = []
        for a in soup.findAll('a', attrs={'class':'mjLinkItem'}, href=True):
            container = a.findParent(['li', 'div'])
            if container.name == 'div':
                section = 'Page One'
            else:
                section = ''
                sec = container.find('a', href=lambda x: x and '/search?' in x)
                if sec is not None:
                    section = self.tag_to_string(sec).strip()
                if not section:
                    h = container.find(['h1','h2','h3','h4','h5','h6'])
                    section = self.tag_to_string(h)
            section = string.capitalize(section).replace('U.s.', 'U.S.')
            if section not in sections:
                sections[section] = []
                sec_order.append(section)
            meta = a.find(attrs={'class':'meta_sectionName'})
            if meta is not None:
                meta.extract()
            title = self.tag_to_string(a).strip() + ' [%s]'%self.tag_to_string(meta)
            url = 'http://online.wsj.com'+a['href']
            desc = ''
            p = container.find('p')
            if p is not None:
                desc = self.tag_to_string(p)

            sections[section].append({'title':title, 'url':url,
                'description':desc, 'date':''})

            self.log('Found article:', title)

            a.extract()
            for a in container.findAll('a', href=lambda x: x and '/article/'
                    in x):
                url = a['href']
                if not url.startswith('http:'):
                    url = 'http://online.wsj.com'+url
                title = self.tag_to_string(a).strip()
                if not title or title.startswith('['): continue
                if title:
                    sections[section].append({'title':self.tag_to_string(a),
                        'url':url, 'description':'', 'date':''})
                    self.log('\tFound related:', title)


        feeds = [(sec, sections[sec]) for sec in sec_order]
        return feeds


    def cleanup(self):
        self.browser.open('http://online.wsj.com/logout?url=http://online.wsj.com')