Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

update Washington Post Print

Browse Source
This commit is contained in:
unkn0w7n 2023-10-09 22:27:17 +05:30
parent c4c2575096
commit b22c7fddf8
1 changed files with 39 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

54
recipes/wash_post_print.recipe
View File

@ -2,7 +2,9 @@
washingtonpost.com
'''
from calibre.web.feeds.news import BasicNewsRecipe, classes
from calibre.web.feeds.news import BasicNewsRecipe
from html5_parser import parse
import json
class wapoprint(BasicNewsRecipe):
title = 'The Washington Post | Print Edition'
@ -22,18 +24,11 @@ class wapoprint(BasicNewsRecipe):
remove_attributes = ['style', 'height', 'width']
publication_type = 'newspaper'
ignore_duplicate_articles = {'title', 'url'}
keep_only_tags = [
dict(name=['h1', 'figure']),
dict(attrs={'data-qa': 'lede-art'}),
classes('byline article-body'),
]
remove_tags = [
dict(name=['meta', 'link', 'svg']),
classes('inline-video author-tooltip author-image powa-wrapper'),
dict(attrs={'data-qa': ['article-body-ad', 'subscribe-promo', 'interstitial-link-wrapper']}),
]
extra_css = '''
.img { text-align:center; font-size:small; }
.auth { font-weight:bold; font-size:small; }
.time { font-size:small; color: #202020; }
'''
def parse_index(self):
soup = self.index_to_soup('https://www.washingtonpost.com/todays_paper/updates/')
@ -58,7 +53,36 @@ class wapoprint(BasicNewsRecipe):
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 = '<h1>' + data['headlines']['basic'] + '</h1>'
subhead = '<h3>' + data['description'].get('basic', '') + '</h3>'
author = ''
if 'credits' in data:
author = '<div><span class="auth">' + 'By ' + ', '.join(x['name'] for x in data['credits']['by']) \
+ '</span> | <span class="time">' + data['publish_date'][:-14] + '</span></div>'
body = ''
for x in data['content_elements']:
if x['type'] == 'text':
body += '<p>' + x['content'] + '</p>'
elif x['type'] == 'video':
if 'promo_image' in x:
body += '<p><div class="img"><img src="{}"><div>{}</div></div></p>'.format(
x['promo_image']['url'], x['description'].get('basic', '')
)
elif x['type'] == 'image':
body += '<p><div class="img"><img src="{}"><div>{}</div></div></p>'.format(x['url'], x['credits_caption_display'])
return '<html><body><div>' + title + subhead + author + body + '</div></body></html>'
def preprocess_html(self, soup):
for img in soup.findAll('img', srcset=True):
img['src'] = img['srcset'].split()[0]
for img in soup.findAll('img', attrs={'src':True}):
img['src'] = 'https://www.washingtonpost.com/wp-apps/imrs.php?src=' + img['src'] + '&w=540'
return soup