calibre/recipes/nikkei_news.recipe

#!/usr/bin/env python2
# vim:fileencoding=utf-8
from calibre.web.feeds.recipes import BasicNewsRecipe
import re

import unicodedata

# import pprint, sys
# pp = pprint.PrettyPrinter(indent=4)


class NikkeiNet_paper_subscription(BasicNewsRecipe):
    title = u'\u65E5\u672C\u7D4C\u6E08\u65B0\u805E\uFF08\u671D\u520A\u30FB\u5915\u520A\uFF09'
    __author__ = 'Ado Nishimura'
    description = u'\u65E5\u7D4C\u96FB\u5B50\u7248\u306B\u3088\u308B\u65E5\u672C\u7D4C\u6E08\u65B0\u805E\u3002\u671D\u520A\u30FB\u5915\u520A\u306F\u53D6\u5F97\u6642\u9593\u306B\u3088\u308A\u5207\u308A\u66FF\u308F\u308A\u307E\u3059\u3002\u8981\u8CFC\u8AAD'  # noqa
    needs_subscription = True
    oldest_article = 1
    max_articles_per_feed = 30
    language = 'ja'
    no_stylesheets = True
    # cover_url       = 'http://parts.nikkei.com/parts/ds/images/common/logo_r1.svg'
    cover_url = 'http://cdn.nikkei.co.jp/parts/ds/images/common/st_nikkei_r1_20101003_1.gif'
    # masthead_url    = 'http://parts.nikkei.com/parts/ds/images/common/logo_r1.svg'
    masthead_url = 'http://cdn.nikkei.co.jp/parts/ds/images/common/st_nikkei_r1_20101003_1.gif'
    cover_margins = (10, 188, '#ffffff')

    remove_tags_before = {'class': "cmn-indent"}
    remove_tags = [
        #                       {'class':"cmn-article_move"},
        #                       {'class':"cmn-pr_list"},
        #                       {'class':"cmnc-zoom"},
        {'class': "cmn-hide"},
        {'name': 'form'},
        {'class': 'cmn-print_headline cmn-clearfix'},
        {'id': 'ABOUT_NIKKEI'},
    ]
    remove_tags_after = {'class': "cmn-indent"}

    def get_browser(self):
        br = BasicNewsRecipe.get_browser(self)

        # pp.pprint(self.parse_index())
        # exit(1)

        # br.set_debug_http(True)
        # br.set_debug_redirects(True)
        # br.set_debug_responses(True)

        if self.username is not None and self.password is not None:
            print "-------------------------open top page-------------------------------------"
            br.open('http://www.nikkei.com/')
            print "-------------------------open first login form-----------------------------"
            try:
                url = br.links(
                    url_regex="www.nikkei.com/etc/accounts/login").next().url
            except StopIteration:
                url = 'http://www.nikkei.com/etc/accounts/login?dps=3&pageflag=top&url=http%3A%2F%2Fwww.nikkei.com%2F'
            br.open(url)  # br.follow_link(link)
            # response = br.response()
            # print response.get_data()
            print "-------------------------JS redirect(send autoPostForm)--------------------"
            br.select_form(name='autoPostForm')
            br.submit()
            # response = br.response()
            print "-------------------------got login form------------------------------------"
            br.select_form(name='LA7010Form01')
            br['LA7010Form01:LA7010Email'] = self.username
            br['LA7010Form01:LA7010Password'] = self.password
            br.submit()
            # response = br.response()
            print "-------------------------JS redirect---------------------------------------"
            br.select_form(nr=0)
            br.submit()

            # br.set_debug_http(False)
            # br.set_debug_redirects(False)
            # br.set_debug_responses(False)
        return br

    def cleanup(self):
        print "-------------------------logout--------------------------------------------"
        self.browser.open('https://regist.nikkei.com/ds/etc/accounts/logout')

    def parse_index(self):
        print "-------------------------get index of paper--------------------------------"
        result = []
        soup = self.index_to_soup('http://www.nikkei.com/paper/')
        # soup = self.index_to_soup(self.test_data())
        sections = soup.findAll(
            'div', 'cmn-section kn-special JSID_baseSection')
        if len(sections) == 0:
            sections = soup.findAll('div', 'cmn-section kn-special')
        for sect in sections:
            sect_title = sect.find('h3', 'cmnc-title').string
            sect_result = []
            for elem in sect.findAll(attrs={'class': ['cmn-article_title']}):
                if elem.span.a is None or elem.span.a['href'].startswith('javascript'):
                    continue
                url = 'http://www.nikkei.com' + elem.span.a['href']
                # print version.
                url = re.sub("/article/", "/print-article/", url)
                span = elem.span.a.span
                if ((span is not None) and (len(span.contents) > 1)):
                    title = span.contents[1].string
                    sect_result.append(dict(title=title, url=url, date='',
                                            description='', content=''))
            result.append([sect_title, sect_result])
        return result

    def populate_article_metadata(self, article, soup, first):
        try:
            elms = soup.findAll(
                'div', {"class": "cmn-article_text JSID_key_fonttxt"})
            elm_text = u'◆'.join(
                [self.tag_to_string(elm).strip() for elm in elms])
            elm_text = unicodedata.normalize('NFKC', elm_text)
            article.summary = article.text_summary = elm_text
        except:
            self.log("Error: Failed to get article summary.")
            return