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

Merge branch 'master' of https://github.com/saurabhnanda/calibre

Browse Source
This commit is contained in:
Kovid Goyal 2024-09-04 13:58:53 +05:30
commit fdb4f5feff
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 13 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
recipes/hackernews.recipe
View File

@ -15,13 +15,14 @@ import re
class HNWithCommentsLink(BasicNewsRecipe): class HNWithCommentsLink(BasicNewsRecipe):
title = 'HN With Comments Link' title = 'HN With Actual Comments'
__author__ = 'Tom Scholl & David Kerschner' __author__ = 'Tom Scholl & David Kerschner'
description = u'Hacker News, run by Y Combinator. Anything that good hackers would find interesting, with a focus on programming and startups.' description = u'Hacker News, run by Y Combinator. Anything that good hackers would find interesting, with a focus on programming and startups.'
publisher = 'Y Combinator' publisher = 'Y Combinator'
category = 'news, programming, it, technology' category = 'news, programming, it, technology'
delay = 1 delay = 1
max_articles_per_feed = 30 max_articles_per_feed = 20
oldest_article = 3
use_embedded_content = False use_embedded_content = False
no_stylesheets = True no_stylesheets = True
encoding = 'utf-8' encoding = 'utf-8'
@ -29,7 +30,8 @@ class HNWithCommentsLink(BasicNewsRecipe):
requires_version = (0, 8, 16) requires_version = (0, 8, 16)
feeds = [ feeds = [
(u'Hacker News', 'https://news.ycombinator.com/rss') (u'Hacker News Frontpage', 'https://hnrss.org/frontpage'),
(u'Ask Hacker News', 'https://hnrss.org/ask')
] ]
temp_files = [] temp_files = []
@ -49,8 +51,10 @@ class HNWithCommentsLink(BasicNewsRecipe):
soup = self.index_to_soup(url) soup = self.index_to_soup(url)
main = soup.find('tr').findNextSiblings('tr', limit=2)[1].td main = soup.find('tr').findNextSiblings('tr', limit=2)[1].td
title = self.tag_to_string(main.find('td', 'title')) title_element = main.select('td.title .titleline a')[0]
link = main.find('td', 'title').find('a')['href'] title = self.tag_to_string(title_element)
link = title_element['href']
# link = main.find('td', 'title').find('a')['href']
if link.startswith('item?'): if link.startswith('item?'):
link = 'https://news.ycombinator.com/' + link link = 'https://news.ycombinator.com/' + link
readable_link = link.rpartition('http://')[2].rpartition('https://')[2] readable_link = link.rpartition('http://')[2].rpartition('https://')[2]
@ -88,11 +92,12 @@ class HNWithCommentsLink(BasicNewsRecipe):
return u'<html><title>' + title + u'</title><body>' + body + '</body></html>' return u'<html><title>' + title + u'</title><body>' + body + '</body></html>'
def parse_feeds(self): def parse_feeds(self):
a = super(HNWithCommentsLink, self).parse_feeds() a = super(HNWithCommentsLinkAlt, self).parse_feeds()
self.hn_articles = a[0].articles self.hn_articles = a[0].articles
return a return a
def get_obfuscated_article(self, url): def get_obfuscated_article(self, url):
self.log('get_obfuscated_article with url=' + url)
if url.startswith('https://news.ycombinator.com'): if url.startswith('https://news.ycombinator.com'):
content = self.get_hn_content(url) content = self.get_hn_content(url)
else: else:
@ -114,8 +119,8 @@ class HNWithCommentsLink(BasicNewsRecipe):
if a.url == url: if a.url == url:
article = a article = a
content = re.sub(r'</body>\s*</html>\s*$', '', content) + \ # content = re.sub(r'</body>\s*</html>\s*$', '', content) + \
article.summary + '</body></html>' # article.summary + '</body></html>'
if not isinstance(content, bytes): if not isinstance(content, bytes):
content = content.encode('utf-8') content = content.encode('utf-8')