mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-31 14:33:54 -04:00
Washington Post
Updated both wash_post and wash_post_print recipes to improve article formatting. Added support for displaying article labels, promo images, and list items.
This commit is contained in:
unkn0w7n
parent
dc71439ad7
commit
fc42e81b6d
@ -1,7 +1,5 @@
|
||||
#!/usr/bin/env python
|
||||
# vim:fileencoding=utf-8
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>'
|
||||
'''
|
||||
www.washingtonpost.com
|
||||
'''
|
||||
@ -15,7 +13,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class TheWashingtonPost(BasicNewsRecipe):
|
||||
title = 'The Washington Post'
|
||||
__author__ = 'Darko Miletic, unkn0wn'
|
||||
__author__ = 'unkn0wn'
|
||||
description = (
|
||||
'Leading source for news, video and opinion on politics, business, '
|
||||
'world and national news, science, travel, entertainment and more. '
|
||||
@ -33,6 +31,7 @@ class TheWashingtonPost(BasicNewsRecipe):
|
||||
use_embedded_content = False
|
||||
language = 'en_US'
|
||||
remove_empty_feeds = True
|
||||
resolve_internal_links = True
|
||||
ignore_duplicate_articles = {'url'}
|
||||
masthead_url = 'https://upload.wikimedia.org/wikipedia/commons/9/93/The_Logo_of_The_Washington_Post_Newspaper.svg'
|
||||
publication_type = 'newspaper'
|
||||
@ -56,6 +55,7 @@ class TheWashingtonPost(BasicNewsRecipe):
|
||||
.img { text-align:center; font-size:small; }
|
||||
.auth { font-weight:bold; font-size:small; }
|
||||
.time { font-size:small; color: #202020; }
|
||||
.subt { font-style: italic; }
|
||||
'''
|
||||
|
||||
def get_cover_url(self):
|
||||
@ -100,8 +100,22 @@ class TheWashingtonPost(BasicNewsRecipe):
|
||||
data = json.loads(m[0].text)
|
||||
data = data['props']['pageProps']['globalContent']
|
||||
|
||||
text = data.get('label', {}).get('basic', {}).get('text', '')
|
||||
label = f'<p class="time">{text}</p>' if text else ''
|
||||
if data.get('headlines'):
|
||||
title = '<h1>' + data['headlines']['basic'] + '</h1>'
|
||||
subhead = '<h3>' + data['description'].get('basic', '') + '</h3>'
|
||||
elif data.get('metadata'):
|
||||
title = '<h1>' + data['metadata']['headlines']['basic'] + '</h1>'
|
||||
subhead = '<p class="subt">' + data['description'].get('basic', '') + '</h3>'
|
||||
|
||||
promo_img = ''
|
||||
if data.get('promo_items', {}).get('basic', {}).get('type', '') == 'image':
|
||||
pi = data['promo_items']['basic']
|
||||
promo_img = (
|
||||
'<p><div class="img"><img src="{}"><div>{}</div></div></p>'.format(
|
||||
pi['url'], pi['credits_caption_display']
|
||||
)
|
||||
)
|
||||
|
||||
author = ''
|
||||
if 'credits' in data:
|
||||
@ -124,14 +138,29 @@ class TheWashingtonPost(BasicNewsRecipe):
|
||||
x['promo_image']['url'], x['description'].get('basic', '')
|
||||
)
|
||||
elif x['type'] == 'image':
|
||||
body += (
|
||||
img_ = (
|
||||
'<p><div class="img"><img src="{}"><div>{}</div></div></p>'.format(
|
||||
x['url'], x['credits_caption_display']
|
||||
)
|
||||
)
|
||||
if img_ != promo_img:
|
||||
body += img_
|
||||
elif x['type'] == 'list':
|
||||
body += '<ul>'
|
||||
for li in x['items']:
|
||||
if li.get('content', '') != '':
|
||||
body += f'<li>{li["content"]}</li>'
|
||||
body += '</ul>'
|
||||
|
||||
return (
|
||||
'<html><body><div>' + title + subhead + author + body + '</div></body></html>'
|
||||
'<html><body><div>'
|
||||
+ label
|
||||
+ title
|
||||
+ subhead
|
||||
+ promo_img
|
||||
+ author
|
||||
+ body
|
||||
+ '</div></body></html>'
|
||||
)
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
@ -139,6 +168,6 @@ class TheWashingtonPost(BasicNewsRecipe):
|
||||
img['src'] = (
|
||||
'https://www.washingtonpost.com/wp-apps/imrs.php?src='
|
||||
+ img['src']
|
||||
+ '&w=916'
|
||||
+ '&w=600'
|
||||
)
|
||||
return soup
|
||||
|
||||
@ -30,12 +30,14 @@ class wapoprint(BasicNewsRecipe):
|
||||
language = 'en_US'
|
||||
remove_attributes = ['style', 'height', 'width']
|
||||
publication_type = 'newspaper'
|
||||
resolve_internal_links = True
|
||||
ignore_duplicate_articles = {'title', 'url'}
|
||||
masthead_url = 'https://upload.wikimedia.org/wikipedia/commons/9/93/The_Logo_of_The_Washington_Post_Newspaper.svg'
|
||||
extra_css = '''
|
||||
.img { text-align:center; font-size:small; }
|
||||
.auth { font-weight:bold; font-size:small; }
|
||||
.time { font-size:small; color: #202020; }
|
||||
.subt { font-style: italic; }
|
||||
'''
|
||||
|
||||
def get_browser(self, *args, **kwargs):
|
||||
@ -85,8 +87,22 @@ class wapoprint(BasicNewsRecipe):
|
||||
data = json.loads(m[0].text)
|
||||
data = data['props']['pageProps']['globalContent']
|
||||
|
||||
text = data.get('label', {}).get('basic', {}).get('text', '')
|
||||
label = f'<p class="time">{text}</p>' if text else ''
|
||||
if data.get('headlines'):
|
||||
title = '<h1>' + data['headlines']['basic'] + '</h1>'
|
||||
subhead = '<h3>' + data['description'].get('basic', '') + '</h3>'
|
||||
elif data.get('metadata'):
|
||||
title = '<h1>' + data['metadata']['headlines']['basic'] + '</h1>'
|
||||
subhead = '<p class="subt">' + data['description'].get('basic', '') + '</h3>'
|
||||
|
||||
promo_img = ''
|
||||
if data.get('promo_items', {}).get('basic', {}).get('type', '') == 'image':
|
||||
pi = data['promo_items']['basic']
|
||||
promo_img = (
|
||||
'<p><div class="img"><img src="{}"><div>{}</div></div></p>'.format(
|
||||
pi['url'], pi['credits_caption_display']
|
||||
)
|
||||
)
|
||||
|
||||
author = ''
|
||||
if 'credits' in data:
|
||||
@ -109,14 +125,29 @@ class wapoprint(BasicNewsRecipe):
|
||||
x['promo_image']['url'], x['description'].get('basic', '')
|
||||
)
|
||||
elif x['type'] == 'image':
|
||||
body += (
|
||||
img_ = (
|
||||
'<p><div class="img"><img src="{}"><div>{}</div></div></p>'.format(
|
||||
x['url'], x['credits_caption_display']
|
||||
)
|
||||
)
|
||||
if img_ != promo_img:
|
||||
body += img_
|
||||
elif x['type'] == 'list':
|
||||
body += '<ul>'
|
||||
for li in x['items']:
|
||||
if li.get('content', '') != '':
|
||||
body += f'<li>{li["content"]}</li>'
|
||||
body += '</ul>'
|
||||
|
||||
return (
|
||||
'<html><body><div>' + title + subhead + author + body + '</div></body></html>'
|
||||
'<html><body><div>'
|
||||
+ label
|
||||
+ title
|
||||
+ subhead
|
||||
+ promo_img
|
||||
+ author
|
||||
+ body
|
||||
+ '</div></body></html>'
|
||||
)
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
@ -124,10 +155,9 @@ class wapoprint(BasicNewsRecipe):
|
||||
img['src'] = (
|
||||
'https://www.washingtonpost.com/wp-apps/imrs.php?src='
|
||||
+ img['src']
|
||||
+ '&w=916'
|
||||
+ '&w=600'
|
||||
)
|
||||
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'))
|
||||
article.summary = article.text_summary = self.tag_to_string(soup.find('p', attrs={'class':'subt'}))
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user