#!/usr/bin/env python
# vim:fileencoding=utf-8
'''
washingtonpost.com
'''
import json
from calibre.web.feeds.news import BasicNewsRecipe
from html5_parser import parse
class wapoprint(BasicNewsRecipe):
title = 'The Washington Post | Print Edition'
__author__ = 'unkn0wn'
description = (
'Leading source for news, video and opinion on politics, business, world and national news, science,'
' travel, entertainment and more. Our local coverage includes reporting on education, crime, weather,'
' traffic, real estate, jobs and cars for DC, Maryland and Virginia. Offering award-winning opinion writing,'
' entertainment information and restaurant reviews.'
)
publisher = 'The Washington Post Company'
category = 'news, politics, USA'
no_stylesheets = True
use_embedded_content = False
encoding = 'utf-8'
language = 'en_US'
remove_attributes = ['style', 'height', 'width']
publication_type = 'newspaper'
ignore_duplicate_articles = {'title', 'url'}
masthead_url = 'https://www.washingtonpost.com/pb/resources/img/twp-masthead-415x57.svg'
extra_css = '''
.img { text-align:center; font-size:small; }
.auth { font-weight:bold; font-size:small; }
.time { font-size:small; color: #202020; }
'''
def get_browser(self):
return BasicNewsRecipe.get_browser(
self, verify_ssl_certificates=False, user_agent='Mozilla/5.0 (Windows NT 10.0; rv:128.0) Gecko/20100101 Firefox/128.0')
def parse_index(self):
soup = self.index_to_soup('https://www.washingtonpost.com/todays_paper/updates/')
if img := soup.find('img', attrs={'src':lambda x: x and x.endswith('_FrontPage.png')}):
self.cover_url = img['src']
if h2 := soup.find('h2', attrs={'class':lambda x: x and 'font--subhead' in x.split()}):
self.title = 'WaPo Print | ' + self.tag_to_string(h2)
feeds = []
for div in soup.findAll('section', attrs={'id': True}):
secname = self.tag_to_string(div.find('label')).strip()
self.log(secname)
articles = []
for a in div.findAll('a', href=True):
url = a['href']
title = self.tag_to_string(a).strip()
if not title or not url:
continue
self.log('\t', title)
self.log('\t\t', url)
articles.append({'title': title, 'url': url})
if articles:
feeds.append((secname, articles))
return feeds
def preprocess_raw_html(self, raw, *a):
root = parse(raw)
m = root.xpath('//script[@id="__NEXT_DATA__"]')
data = json.loads(m[0].text)
data = data['props']['pageProps']['globalContent']
title = '' + data['headlines']['basic'] + '
'
subhead = '' + data['description'].get('basic', '') + '
'
author = ''
if 'credits' in data:
author = '' + 'By ' + ', '.join(x['name'] for x in data['credits']['by']) \
+ ' | ' + data['publish_date'][:-14] + '
'
body = ''
for x in data['content_elements']:
if x['type'] == 'text':
body += '' + x['content'] + '
'
elif x['type'] == 'video':
if 'promo_image' in x:
body += '
{}
{}
' + title + subhead + author + body + '
'
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'src':True}):
img['src'] = 'https://www.washingtonpost.com/wp-apps/imrs.php?src=' + img['src'] + '&w=916'
return soup
def populate_article_metadata(self, article, soup, first):
article.summary = self.tag_to_string(soup.find('h3'))
article.text_summary = self.tag_to_string(soup.find('h3'))