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 wash_post_print.recipe

Browse Source
This commit is contained in:
unkn0w7n 2025-04-19 08:22:16 +05:30
parent e987f88036
commit 7fe681d98f
1 changed files with 46 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

61
recipes/wash_post_print.recipe
View File

@ -15,10 +15,12 @@ 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.'
'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'
@ -29,22 +31,33 @@ class wapoprint(BasicNewsRecipe):
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'
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; }
'''
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 get_browser(self, *args, **kwargs):
kwargs['user_agent'] = (
'Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)'
)
br = BasicNewsRecipe.get_browser(self, *args, **kwargs)
br.addheaders += [
('Referer', 'https://www.google.com/'),
('X-Forwarded-For', '66.249.66.1'),
]
return br
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')}):
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()}):
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 = []
@ -77,8 +90,14 @@ class wapoprint(BasicNewsRecipe):
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>')
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']:
@ -90,13 +109,23 @@ class wapoprint(BasicNewsRecipe):
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'])
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>'
return (
'<html><body><div>' + title + subhead + author + body + '</div></body></html>'
)
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'
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):