-
-
Notifications
You must be signed in to change notification settings - Fork 2.2k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
002886b
commit 9a9daa7
Showing
1 changed file
with
43 additions
and
77 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,85 +1,51 @@ | ||
#!/usr/bin/env python | ||
__license__ = 'GPL v3' | ||
from calibre.web.feeds.recipes import BasicNewsRecipe | ||
|
||
import re | ||
from calibre.web.feeds.news import BasicNewsRecipe | ||
|
||
class FocusRecipe(BasicNewsRecipe): | ||
class NYTimes(BasicNewsRecipe): | ||
|
||
__author__ = u'Artur Stachecki <artur.stachecki@gmail.com>' | ||
title = 'Focus' | ||
__author__ = 'Krittika Goyal' | ||
language = 'pl' | ||
version = 1 | ||
description = 'Polish scientific monthly magazine' | ||
timefmt = ' [%d %b, %Y]' | ||
needs_subscription = False | ||
|
||
title = u'Focus' | ||
publisher = u'Gruner + Jahr Polska' | ||
category = u'News' | ||
description = u'Focus.pl - pierwszy w Polsce portal społecznościowy dla miłośników nauki. Tematyka: nauka, historia, cywilizacja, technika, przyroda, sport, gadżety' | ||
category = 'magazine' | ||
cover_url = '' | ||
remove_empty_feeds = True | ||
no_stylesheets = True | ||
oldest_article = 7 | ||
max_articles_per_feed = 100000 | ||
recursions = 0 | ||
|
||
no_stylesheets = True | ||
remove_javascript = True | ||
encoding = 'utf-8' | ||
# Seems to work best, but YMMV | ||
simultaneous_downloads = 5 | ||
|
||
r = re.compile('.*(?P<url>http:\/\/(www.focus.pl)|(rss.feedsportal.com\/c)\/.*\.html?).*') | ||
keep_only_tags = [] | ||
keep_only_tags.append(dict(name='div', attrs={'id': 'cll'})) | ||
|
||
remove_tags = [] | ||
remove_tags.append(dict(name='div', attrs={'class': 'ulm noprint'})) | ||
remove_tags.append(dict(name='div', attrs={'class': 'txb'})) | ||
remove_tags.append(dict(name='div', attrs={'class': 'h2'})) | ||
remove_tags.append(dict(name='ul', attrs={'class': 'txu'})) | ||
remove_tags.append(dict(name='div', attrs={'class': 'ulc'})) | ||
|
||
extra_css = ''' | ||
body {font-family: verdana, arial, helvetica, geneva, sans-serif ;} | ||
h1{text-align: left;} | ||
h2{font-size: medium; font-weight: bold;} | ||
p.lead {font-weight: bold; text-align: left;} | ||
.authordate {font-size: small; color: #696969;} | ||
.fot{font-size: x-small; color: #666666;} | ||
''' | ||
|
||
feeds = [ | ||
('Nauka', 'http://www.focus.pl/nauka/rss/'), | ||
('Historia', 'http://www.focus.pl/historia/rss/'), | ||
('Cywilizacja', 'http://www.focus.pl/cywilizacja/rss/'), | ||
('Sport', 'http://www.focus.pl/sport/rss/'), | ||
('Technika', 'http://www.focus.pl/technika/rss/'), | ||
('Przyroda', 'http://www.focus.pl/przyroda/rss/'), | ||
('Technologie', 'http://www.focus.pl/gadzety/rss/') | ||
keep_only_tags = dict(name='article', attrs={'class': 'content'}) | ||
remove_tags_after = dict(name='div', attrs={'class': 'inner_article'}) | ||
remove_tags = [ | ||
dict(name='div', attrs={'class': ['social_btns']}), | ||
] | ||
|
||
def skip_ad_pages(self, soup): | ||
if ('advertisement' in soup.find('title').string.lower()): | ||
href = soup.find('a').get('href') | ||
return self.index_to_soup(href, raw=True) | ||
else: | ||
return None | ||
|
||
def get_cover_url(self): | ||
soup = self.index_to_soup('http://www.focus.pl/magazyn/') | ||
tag = soup.find(name='div', attrs={'class': 'clr fl'}) | ||
if tag: | ||
self.cover_url = 'http://www.focus.pl/' + tag.a['href'] | ||
return getattr(self, 'cover_url', self.cover_url) | ||
|
||
def print_version(self, url): | ||
if url.count('focus.pl.feedsportal.com'): | ||
u = url.find('focus0Bpl') | ||
u = 'http://www.focus.pl/' + url[u + 11:] | ||
u = u.replace('0C', '/') | ||
u = u.replace('A', '') | ||
u = u.replace('0E', '-') | ||
u = u.replace('/nc/1//story01.htm', '/do-druku/1') | ||
else: | ||
u = url.replace('/nc/1', '/do-druku/1') | ||
return u | ||
# TO GET ARTICLE TOC | ||
def nejm_get_index(self): | ||
return self.index_to_soup('http://www.focus.pl/') | ||
|
||
# To parse artice toc | ||
def parse_index(self): | ||
soup = self.nejm_get_index() | ||
|
||
toc = soup.find('div', id='wrapper') | ||
|
||
articles = [] | ||
feeds = [] | ||
section_title = 'Focus Articles' | ||
for x in toc.findAll(True): | ||
if x.name == 'h1': | ||
# Article found | ||
a = x.find('a') | ||
if a is None: | ||
continue | ||
title = self.tag_to_string(a) | ||
url = a.get('href', False) | ||
if not url or not title: | ||
continue | ||
# if url.startswith('story'): | ||
url = 'http://www.focus.pl' + url | ||
self.log('\t\tFound article:', title) | ||
self.log('\t\t\t', url) | ||
articles.append({'title': title, 'url': url, | ||
'description': '', 'date': ''}) | ||
feeds.append((section_title, articles)) | ||
|
||
return feeds |