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 il_post.recipe

Browse Source
This commit is contained in:
unkn0w7n 2023-12-23 18:05:55 +05:30
parent 7f3ccb333d
commit fcc9429727
1 changed files with 25 additions and 44 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

69
recipes/il_post.recipe
View File

@ -11,13 +11,16 @@
from __future__ import absolute_import, division, print_function, unicode_literals
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.utils.magick import Image
from datetime import date, timedelta
dates = [ date.today().strftime('%Y/%m/%d'), (date.today() - timedelta(1)).strftime('%Y/%m/%d') ]
# ----------- CUSTOMIZATION OPTIONS START -----------
# Comment (add # in front) to disable the sections you are not interested in
# Commenta (aggiungi # davanti alla riga) per disabilitare le sezioni che non vuoi scaricare
sections = [
("Prima Pagina", "https://www.ilpost.it/prime-pagine"),
("Italia", "https://www.ilpost.it/italia/"),
("Mondo", "https://www.ilpost.it/mondo/"),
("Politica", "https://www.ilpost.it/politica/"),
("Tecnologia", "https://www.ilpost.it/tecnologia/"),
@ -33,16 +36,11 @@ sections = [
("Konrad", "https://www.ilpost.it/europa/"),
]
# Change this to True if you want grey images
convert_to_grayscale = False
# ----------- CUSTOMIZATION OPTIONS OVER -----------
prefixes = {"Permalink to", "Commenta", "Link all'articolo"}
class IlPost(BasicNewsRecipe):
__author__ = 'Marco Scirea'
__author__ = 'Marco Scirea, unkn0wn'
__license__ = 'GPL v3'
__copyright__ = '2019, Marco Scirea <marco.prolog at gmail.com>'
@ -54,59 +52,42 @@ class IlPost(BasicNewsRecipe):
' la ricetta puo\' essere configurata per tenerle a colori'
)
tags = "news"
cover_url = "https://www.ilpost.it/wp-content/themes/ilpost/images/ilpost.svg"
masthead_url = 'https://www.ilpost.it/error/images/ilpost.svg'
ignore_duplicate_articles = {"title", "url"}
no_stylesheets = True
keep_only_tags = [dict(id=["expanding", "singleBody"])]
extra_css = ' .wp-caption-text { font-size:small; } '
keep_only_tags = [dict(name='main', attrs={'id':lambda x: x and x.startswith('index_main-content__')})]
remove_tags_before = [dict(name='article')]
remove_tags_after = [dict(name='article')]
remove_tags = [
dict(attrs={'class':lambda x: x and x.startswith(
('index_actions__', 'index_il-post-comments___', 'index_art_tag__')
)}),
dict(attrs={'id':'audioPlayerArticle'})
]
def parse_page(self, name, url):
self.log.debug(url)
soup = self.index_to_soup(url)
entries = []
for article in soup.findAll('article'):
for link in article.findAll('a', href=True, title=True):
if not link["href"].startswith("https://www.ilpost.it/20"):
for link in article.findAll('a', href=True):
if not any(x in link['href'] for x in dates):
continue
title = link["title"]
for prefix in prefixes:
if title.startswith(prefix):
title = title.lstrip(prefix)
break
title = title.strip()
entries.append({
title = self.tag_to_string(link.h2)
desc = self.tag_to_string(link.p)
if not title:
continue
self.log('\t', title)
entries.append({
"url": link["href"],
"title": title,
"description": desc
})
return (name, entries)
def populate_article_metadata(self, article, soup, first):
description = soup.find(attrs={"name": "description"})
article.summary = description[
"content"] if description else "No meta description given"
article.text_summary = description[
"content"] if description else "No meta description given"
def parse_index(self):
feeds = []
for section in sections:
feeds.append(self.parse_page(section[0], section[1]))
return feeds
if convert_to_grayscale:
# Image conversion to greyscale by Starson17
# https://www.mobileread.com/forums/showpost.php?p=1814815&postcount=15
def postprocess_html(self, soup, first):
# process all the images
for tag in soup.findAll('img', src=True):
iurl = tag['src']
img = Image()
img.open(iurl)
img.type = "GrayscaleType"
img.save(iurl)
return soup
def preprocess_html(self, soup):
galleryItems = soup.findAll("figure", {"class": "gallery-item"})
if galleryItems:
self.abort_article()
return soup