#!/usr/bin/env python
# vim:fileencoding=utf-8
import string
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup

class AnalyseUndKritik(BasicNewsRecipe):
    title          = 'Analyse & Kritik'
    language = 'de'
    description = u'Zeitung für linke Debatte & Praxis'
    publisher = u'Verein für Politische Bildung, Analyse & Kritik e.V.'
    category = 'politics, Germany'

    auto_cleanup   = True
    needs_subscription = True
    remove_tags = [dict(name='div', attrs={'class': 'wp-block-quote-container'}),
                   dict(name='section', attrs={'class': 'wp-block-ak-banner'}),
                   dict(name='svg', attrs={'class': 'wp-block-paragraph__end-icon'}),
                   dict(name='figure', attrs={'class': 'wp-block-embed'})]
    
    def get_browser(self):
        br = BasicNewsRecipe.get_browser(self)
        if self.username is not None and self.password is not None:
            br.open('https://www.akweb.de/login/')
            br.select_form(action='https://www.akweb.de/wp-login.php')
            br['log']   = self.username
            br['pwd'] = self.password
            br.submit()
        return br
    
    def parse_index(self):
        issues = self.index_to_soup('https://www.akweb.de/ausgaben/')
        issue = issues.find('li', attrs={'class': 'issues__issue'})
        if issue:
            issue_url = issue.find('a', href=True)['href']
            issue_url_split = issue_url.split('/')
            if len(issue_url_split) >= 5:
                issue_number = issue_url_split[4]
                self.title = self.title + ' ' + issue_number
            return self.parse_issue(issue_url)

    def parse_issue(self, issue_url):
        soup = self.index_to_soup(issue_url)

        def feed_title(div):
            return ''.join(div.findAll(text=True, recursive=False)).strip()

        articles = {}
        key = None
        ans = []
        for el in soup.findAll(True,
             attrs={'class':['column',  'wp-block-ak-topic-container__title', 'article-item']}):

             if 'column' in el['class'] or 'wp-block-ak-topic-container__title' in el['class']:
                 key = string.capwords(feed_title(el))
                 articles[key] = []
                 ans.append(key)

             elif 'article-item' in el['class']:
                 a = el.find('a', href=True)
                 if not a:
                     continue
                 url = a['href']
                 title = self.tag_to_string(a, use_alt=False).strip()
                 description = ''
                 pubdate = strftime('%a, %d %b')
                 summary = el.find(True, attrs={'class':'wp-block-ak-unterzeile'})
                 if summary:
                     description = self.tag_to_string(summary, use_alt=False)

                 feed = key if key is not None else 'Uncategorized'
                 if feed not in articles:
                     articles[feed] = []
                     
                 articles[feed].append(
                        dict(title=title, url=url, date=pubdate,
                                description=description,
                                content=''))
        ans = [(key, articles[key]) for key in articles]

        return ans