ate329/kindlerss

unfinished

Hi there 👋

Nice and cute logo designed by SAWARATSUKI

kindlerss's Issues

check this example from calibre

the example from calibre
https://manual.calibre-ebook.com/news.html
'''python
import string, re
from calibre import strftime
from calibre.web.feeds.recipes import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup

class NYTimes(BasicNewsRecipe):

title       = 'The New York Times'
__author__  = 'Kovid Goyal'
description = 'Daily news from the New York Times'
timefmt = ' [%a, %d %b, %Y]'
needs_subscription = True
remove_tags_before = dict(id='article')
remove_tags_after  = dict(id='article')
remove_tags = [dict(attrs={'class':['articleTools', 'post-tools', 'side_tool', 'nextArticleLink clearfix']}),
            dict(id=['footer', 'toolsRight', 'articleInline', 'navigation', 'archive', 'side_search', 'blog_sidebar', 'side_tool', 'side_index']),
            dict(name=['script', 'noscript', 'style'])]
encoding = 'cp1252'
no_stylesheets = True
extra_css = 'h1 {font: sans-serif large;}\n.byline {font:monospace;}'

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.nytimes.com/auth/login')
        br.select_form(name='login')
        br['USERID']   = self.username
        br['PASSWORD'] = self.password
        br.submit()
    return br

def parse_index(self):
    soup = self.index_to_soup('https://www.nytimes.com/pages/todayspaper/index.html')

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

    articles = {}
    key = None
    ans = []
    for div in soup.findAll(True,
         attrs={'class':['section-headline', 'story', 'story headline']}):

         if ''.join(div['class']) == 'section-headline':
             key = string.capwords(feed_title(div))
             articles[key] = []
             ans.append(key)

         elif ''.join(div['class']) in ['story', 'story headline']:
             a = div.find('a', href=True)
             if not a:
                 continue
             url = re.sub(r'\?.*', '', a['href'])
             url += '?pagewanted=all'
             title = self.tag_to_string(a, use_alt=True).strip()
             description = ''
             pubdate = strftime('%a, %d %b')
             summary = div.find(True, attrs={'class':'summary'})
             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] = []
             if not 'podcasts' in url:
                 articles[feed].append(
                           dict(title=title, url=url, date=pubdate,
                                description=description,
                                content=''))
    ans = self.sort_index_by(ans, {'The Front Page':-1, 'Dining In, Dining Out':1, 'Obituaries':2})
    ans = [(key, articles[key]) for key in ans if key in articles]
    return ans

def preprocess_html(self, soup):
    refresh = soup.find('meta', {'http-equiv':'refresh'})
    if refresh is None:
        return soup
    content = refresh.get('content').partition('=')[2]
    raw = self.browser.open('https://www.nytimes.com'+content).read()
    return BeautifulSoup(raw.decode('cp1252', 'replace'))

'''

EbookLib

See https://pypi.org/project/EbookLib/ for an EPUB manipulation and modification library to integrate into the program