calibre/recipes/natgeohis.recipe
2024-02-02 18:55:15 +05:30

171 lines
6.2 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
from __future__ import absolute_import, division, print_function, unicode_literals
import json
from calibre.web.feeds.news import BasicNewsRecipe
from calibre import prepare_string_for_xml as escape
from calibre.utils.iso8601 import parse_iso8601
def classes(classes):
q = frozenset(classes.split(' '))
return dict(attrs={
'class': lambda x: x and frozenset(x.split()).intersection(q)})
def extract_json(raw):
s = raw.find("window['__natgeo__']")
script = raw[s:raw.find('</script>', s)]
return json.loads(
script[script.find('{'):].rstrip(';'))['page']['content']['article']
def parse_contributors(grp):
for item in grp:
line = '<div class="auth">' + escape(item['title']) + ' '
for c in item['contributors']:
line += escape(c['displayName'])
yield line + '</div>'
def parse_lead_image(media):
if 'dsc' in media['image']:
yield '<p><div><img src="{}" alt="{}"></div>'.format(
escape(media['image']['src'], True), escape(media['image']['dsc'], True))
else:
yield '<p><div><img src="{}"></div>'.format(escape(media['image']['src'], True))
if 'caption' in media:
yield '<div class="cap">' + media['caption'] + '</div>'
if 'credit' in media:
yield '<div class="cred">' + media['credit'] + '</div>'
yield '</p>'
def parse_body(item):
c = item['cntnt']
if item.get('type') == 'inline':
if c.get('cmsType') == 'listicle':
if 'title' in c:
yield '<h3>' + escape(c['title']) + '</h3>'
yield c['text']
elif c.get('cmsType') == 'image':
for line in parse_lead_image(c):
yield line
elif c.get('cmsType') == 'imagegroup':
for imgs in c['images']:
for line in parse_lead_image(imgs):
yield line
elif c.get('cmsType') == 'pullquote':
if 'quote' in c:
yield '<blockquote>' + c['quote'] + '</blockquote>'
elif c.get('cmsType') == 'editorsNote':
if 'note' in c:
yield '<blockquote>' + c['note'] + '</blockquote>'
else:
if c['mrkup'].strip().startswith('<'):
yield c['mrkup']
else:
yield '<{tag}>{markup}</{tag}>'.format(
tag=item['type'], markup=c['mrkup'])
def parse_article(edg):
sc = edg['schma']
yield '<h3 class="sub">' + escape(edg['sctn']) + '</h3>'
yield '<h1>' + escape(sc['sclTtl']) + '</h1>'
yield '<div class="byline">' + escape(sc['sclDsc']) + '</div><br>'
for line in parse_contributors(edg['cntrbGrp']):
yield line
ts = parse_iso8601(edg['mdDt'], as_utc=False).strftime('%B %d, %Y')
yield '<div class="time">Published: ' + escape(ts) + '</div>'
if 'readTime' in edg:
yield '<div class="time">' + escape(edg['readTime']) + '</div><br>'
if edg.get('ldMda', {}).get('cmsType') == 'image':
for line in parse_lead_image(edg['ldMda']):
yield line
for item in edg['bdy']:
for line in parse_body(item):
yield line
def article_parse(data):
yield "<html><body>"
for frm in data['frms']:
if not frm:
continue
for mod in frm.get('mods', ()):
for edg in mod.get('edgs', ()):
if edg.get('cmsType') == 'ImmersiveLeadTile':
if 'image' in edg.get('cmsImage', {}):
for line in parse_lead_image(edg['cmsImage']):
yield line
if edg.get('cmsType') == 'ArticleBodyTile':
for line in parse_article(edg):
yield line
yield "</body></html>"
class NatGeo(BasicNewsRecipe):
title = u'National Geographic History'
description = (
'From Caesar to Napoleon, the Pyramids to the Parthenon, the Trojan War to the Civil War—National Geographic '
'HISTORY draws readers in with more than 5,000 years of people, places, and things to explore.'
)
language = 'en'
encoding = 'utf8'
publisher = 'nationalgeographic.com'
category = 'science, nat geo'
__author__ = 'Kovid Goyal'
description = 'Inspiring people to care about the planet since 1888'
timefmt = ' [%a, %d %b, %Y]'
no_stylesheets = True
use_embedded_content = False
remove_attributes = ['style']
remove_javascript = False
masthead_url = 'https://i.natgeofe.com/n/e76f5368-6797-4794-b7f6-8d757c79ea5c/ng-logo-2fl.png?w=600&h=600'
resolve_internal_links = True
extra_css = '''
.sub, blockquote { color:#404040; }
.byline, i { font-style:italic; color:#202020; }
.cap {text-align:center; font-size:small; }
.cred {text-align:center; font-size:small; color:#404040; }
.auth, .time { font-size:small; color:#5c5c5c; }
'''
def get_cover_url(self):
soup = self.index_to_soup('https://ngsingleissues.nationalgeographic.com/history')
wrap = soup.find(attrs={'class':'product-image-wrapper'})
return wrap.img['src']
def parse_index(self):
soup = self.index_to_soup('https://www.nationalgeographic.com/history/history-magazine')
ans = []
for article in soup.findAll('article'):
a = article.find('a')
url = a['href']
if url.startswith('/'):
url = 'https://www.nationalgeographic.com' + url
title = self.tag_to_string(article.find(**classes('PromoTile__Title--truncated')))
ans.append({'title': title, 'url': url})
self.log(title, ' ', url)
return [('Articles', ans)]
def preprocess_raw_html(self, raw_html, url):
data = extract_json(raw_html)
return '\n'.join(article_parse(data))
def preprocess_html(self, soup):
for img in soup.findAll('img', src=True):
# for high res images use '?w=2000&h=2000'
img['src'] = img['src'] + '?w=1000&h=1000'
return soup
def populate_article_metadata(self, article, soup, first):
summ = soup.find(attrs={'class':'byline'})
if summ:
article.summary = self.tag_to_string(summ)
article.text_summary = self.tag_to_string(summ)