mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
Il Post by frafra
This commit is contained in:
parent
b7181cfd37
commit
790c6c67e3
35
recipes/il_post.recipe
Normal file
35
recipes/il_post.recipe
Normal file
@ -0,0 +1,35 @@
|
|||||||
|
#!/usr/bin/env python2
|
||||||
|
|
||||||
|
from __future__ import absolute_import, division, print_function, unicode_literals
|
||||||
|
from calibre.web.feeds.news import BasicNewsRecipe
|
||||||
|
|
||||||
|
prefixes = {"Permalink to", "Commenta"}
|
||||||
|
|
||||||
|
|
||||||
|
class IlPost(BasicNewsRecipe):
|
||||||
|
title = "Il Post"
|
||||||
|
language = "it"
|
||||||
|
__author__ = 'frafra'
|
||||||
|
tags = "news"
|
||||||
|
cover_url = "https://www.ilpost.it/wp-content/themes/ilpost/images/ilpost.svg"
|
||||||
|
ignore_duplicate_articles = {"url"}
|
||||||
|
no_stylesheets = True
|
||||||
|
keep_only_tags = [dict(id=["expanding", "singleBody"])]
|
||||||
|
|
||||||
|
def parse_index(self):
|
||||||
|
soup = self.index_to_soup("https://www.ilpost.it/")
|
||||||
|
entries = []
|
||||||
|
for link in soup.findAll('a', href=True, title=True):
|
||||||
|
if not link["href"].startswith("https://www.ilpost.it/20"):
|
||||||
|
continue
|
||||||
|
title = link["title"]
|
||||||
|
for prefix in prefixes:
|
||||||
|
if title.startswith(prefix):
|
||||||
|
title = title.lstrip(prefix)
|
||||||
|
break
|
||||||
|
title = title.strip()
|
||||||
|
entries.append({
|
||||||
|
"url": link["href"],
|
||||||
|
"title": title,
|
||||||
|
})
|
||||||
|
return [("Il Post", entries)]
|
Loading…
x
Reference in New Issue
Block a user