calibre/recipes/world_archeology.recipe

#!/usr/bin/env python
# vim:fileencoding=utf-8
'''
https://www.world-archaeology.com
'''
from calibre import browser
from calibre.web.feeds.news import BasicNewsRecipe


class worldarch(BasicNewsRecipe):
    title = 'The Past: Current World Archaeology'
    language = 'en'
    __author__ = 'unkn0wn'
    description = (
        'Travel the globe with Current World Archaeology, the magazine that brings you up-to-date with the latest archaeological discoveries. '
        'Explore sites – and sights – through our exclusive features and eye-popping photography. We bring you the stories from the '
        'archaeologists themselves, so you learn first-hand from the experts about the latest finds and most up-to-date research. '
        'Published six times a year.'
    )
    no_stylesheets = True
    use_embedded_content = False
    remove_attributes = ['style', 'height', 'width']
    ignore_duplicate_articles = {'url'}
    resolve_internal_links = True
    masthead_url = 'https://i0.wp.com/www.world-archaeology.com/wp-content/uploads/2016/02/cwa-logo.png'
    simultaneous_downloads = 1

    extra_css = '''
        [class^="meta"], [class~="__author__text"], [class~="__date"] { font-size:small; }
        .post-subtitle { font-style: italic; color:#202020; }
        .wp-block-image { font-size:small; text-align:center; }
    '''

    keep_only_tags = [
        dict(attrs={'class': lambda x: x and any(tag in x for tag in [
            '__image', '__header', '__background',
            '__body_area', '__author__text', '__date'
        ])})
    ]

    remove_tags = [
        dict(attrs={'class':'ad-break'}),
        dict(attrs={'class': lambda x: x and any(cls in x.split()
        for cls in ['avatar', 'what-mag-row'])}),
        dict(attrs={'class':lambda x: x and '--share' in x})
    ]

    def preprocess_html(self, soup):
        for img in soup.findAll('img', attrs={'src': True}):
            if '?w=' in img['src']:
                res = '?w=600'
                w = self.recipe_specific_options.get('res')
                if w and isinstance(w, str):
                    res = '?w=' + w
                img['src'] = img['src'].split('?')[0] + res
        exp = soup.find(attrs={'class':lambda x: x and 'post-subtitle' in x.split()})
        if exp:
            exp.name = 'p'
        return soup

    recipe_specific_options = {
        'issue': {
            'short': 'Enter the Issue Number you want to download ',
            'long': 'For example, 136'
        },
        'res': {
            'short': 'For hi-res images, select a resolution from the\nfollowing options: 800, 1000, 1200 or 1500',
            'long': 'This is useful for non e-ink devices, and for a lower file size\nthan the default, use 400 or 300.',
            'default': '600',
        },
    }

    def parse_index(self):
        soup = self.index_to_soup('https://the-past.com/category/magazines/cwa/')
        art = soup.find('article', attrs={'class':lambda x: x and 'tag-magazines' in x.split()})
        url = art.h2.a['href']

        d = self.recipe_specific_options.get('issue')
        if d and isinstance(d, str):
            url = 'https://the-past.com/magazines/current-world-archaeology-' + d + '/'

        issue = self.index_to_soup(url)
        ti = issue.find('h1', attrs={'class':lambda x: x and 'post-title' in x.split()})
        if ti:
            self.title = self.tag_to_string(ti).strip()
        dt = soup.find(attrs={'class':lambda x: x and '__date' in x})
        if dt:
            self.timefmt = ' [' + self.tag_to_string(dt).strip() + ']'
        edit = issue.find('h2', attrs={'id':'from-the-editor'})
        if edit and edit.findParent('div'):
            self.description = self.tag_to_string(edit.findParent('div'))
        cov = issue.find('figure', attrs={'class':lambda x: x and 'wp-block-image' in x.split()})
        if cov:
            self.cover_url = cov.img['src'].split('?')[0] + '?w=600'
        div = issue.find('div', attrs={'class':lambda x: x and 'entry-content' in x.split()})

        feeds = []

        h2 = div.findAll('h2', attrs={'class':lambda x: x and 'wp-block-heading' in x.split()})
        lt = div.findAll(attrs={'class':'display-posts-listing'})
        for x, y in zip(h2, lt):
            section = self.tag_to_string(x).strip()
            self.log(section)
            articles = []
            for a in y.findAll('a', href=True, attrs={'class':'title'}):
                url = a['href']
                title = self.tag_to_string(a).strip()
                desc = ''
                exp = a.findNext(attrs={'class':'excerpt'})
                if exp:
                    desc = self.tag_to_string(exp).strip()
                self.log('\t', title, '\n\t', desc, '\n\t\t', url)
                articles.append({'title': title, 'description':desc, 'url': url})
            if articles:
                feeds.append((section, articles))
        return feeds

    def get_browser(self, *args, **kwargs):
        return self

    def clone_browser(self, *args, **kwargs):
        return self.get_browser()

    def open_novisit(self, *args, **kwargs):
        br = browser()
        return br.open_novisit(*args, **kwargs)

    open = open_novisit