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 times_online.recipe

Browse Source 
remove google feeds
This commit is contained in:
unkn0w7n 2024-08-27 12:54:17 +05:30
parent ab9a27f6fd
commit a01b02ad66
1 changed files with 30 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

60
recipes/times_online.recipe
View File

@ -1,7 +1,7 @@
from urllib.parse import quote
#!/usr/bin/env python
import random
from calibre.ebooks.BeautifulSoup import BeautifulSoup
from calibre.scraper.simple import read_url
from calibre.web.feeds.news import BasicNewsRecipe, prefixed_classes
@ -11,6 +11,11 @@ def resize(x):
elif '?crop=' in x:
return x + '&resize=600'
def absurl(url):
if url.startswith('/'):
url = 'https://www.thetimes.com' + url
return url
class times(BasicNewsRecipe):
title = 'The Times and Sunday Times'
__author__ = 'unkn0wn'
@ -30,8 +35,7 @@ class times(BasicNewsRecipe):
remove_empty_feeds = True
resolve_internal_links = True
simultaneous_downloads = 1
oldest_article = 1 # days
web_url = ''
browser_type = 'webengine'
def get_cover_url(self):
soup = self.index_to_soup('https://www.frontpages.com/the-times/')
@ -88,36 +92,34 @@ class times(BasicNewsRecipe):
fig['class'] = 'sub'
return soup
articles_are_obfuscated = True
def parse_index(self):
soup = self.index_to_soup('https://www.thetimes.com/')
main = soup.find('div', attrs={'id':'main-container', 'data-edition-date':True})
self.timefmt = ' [%s]' % main['data-edition-date']
def get_obfuscated_article(self, url):
soup = self.index_to_soup(url)
link = soup.a['href']
skip_sections =[ # add sections you want to skip
'/video/', '/videos/', '/multimedia/',
]
if any(x in link for x in skip_sections):
self.abort_article('skipping video links ', link)
self.web_url = link
html = self.index_to_soup(link, raw=True)
return ({ 'data': html, 'url': link })
feeds = []
feeds = []
when = oldest_article*24
index = 'https://www.thetimes.com/'
sections = [
'politics', 'world', 'uk/politics', 'uk/scotland', 'uk', 'comment', 'business-money', 'sport',
'life-style', 'culture', 'magazine', 'travel', 'sunday-times', 'edition', 'article'
]
for sec in sections:
a = 'https://news.google.com/rss/search?q=when:{}h+allinurl:{}&hl=en-GB&gl=GB&ceid=GB:en'
feeds.append((sec.capitalize(), a.format(when, quote(index + sec, safe=''))))
feeds.append(('Others', a.format(when, quote(index, safe=''))))
for sec in main.findAll('section', attrs={'id':lambda x: x and x.startswith('section-')}, recursive=False):
section = sec['id'].replace('section-', '').capitalize()
self.log(section)
articles = []
for a in sec.findAll(**prefixed_classes('Item-headline')):
if not a.find('a'):
continue
url = absurl(a.a['href']).split('?')[0]
title = self.tag_to_string(a)
self.log(' ', title, '\n\t', url)
articles.append({'title': title, 'url': url})
feeds.append((section, articles))
return feeds
def preprocess_raw_html(self, raw, url):
access = '"userState":{"isLoggedIn":false,"isMetered":false,"hasAccess":true}'
if access not in raw and 'comment/cartoons' not in url:
raw_ar = read_url([], 'https://archive.is/latest/' + url)
dom = random.choice(('fo', 'is', 'li', 'md', 'ph', 'vn'))
raw_ar = self.index_to_soup('https://archive.' + dom + '/latest/' + url)
archive = BeautifulSoup(str(raw_ar))
if archive.find('div', attrs={'id':'top'}):
content = archive.find('article', attrs={'id':False})
@ -133,9 +135,7 @@ class times(BasicNewsRecipe):
return raw
def populate_article_metadata(self, article, soup, first):
article.title = article.title.replace(' - The Times', '')
desc = soup.find(**prefixed_classes('responsive__StandfirstContainer-'))
if desc:
article.summary = self.tag_to_string(desc)
article.text_summary = article.summary
article.url = self.web_url