mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
remove old broken recipes
This commit is contained in:
Tomasz Długosz
parent
79d7658ea3
commit
a629a69c6e
@ -1,100 +0,0 @@
|
||||
#!/usr/bin/env python2
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '''2010, matek09, matek09@gmail.com
|
||||
Modified 2011, Mariusz Wolek <mariusz_dot_wolek @ gmail dot com>
|
||||
Modified 2012, Artur Stachecki <artur.stachecki@gmail.com>'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
import re
|
||||
|
||||
|
||||
class Wprost(BasicNewsRecipe):
|
||||
EDITION = 0
|
||||
FIND_LAST_FULL_ISSUE = True
|
||||
EXCLUDE_LOCKED = True
|
||||
ICO_BLOCKED = 'http://www.wprost.pl/G/layout2/ico_blocked.png'
|
||||
title = u'Wprost'
|
||||
__author__ = 'matek09'
|
||||
description = u'Popularny tygodnik ogólnopolski - Wprost. Najlepszy wśród polskich tygodników - opiniotwórczy - społeczno-informacyjny - społeczno-kulturalny.' # noqa
|
||||
encoding = 'ISO-8859-2'
|
||||
no_stylesheets = True
|
||||
language = 'pl'
|
||||
remove_javascript = True
|
||||
recursions = 0
|
||||
remove_tags_before = dict(dict(name='div', attrs={'id': 'print-layer'}))
|
||||
remove_tags_after = dict(dict(name='div', attrs={'id': 'print-layer'}))
|
||||
'''
|
||||
keep_only_tags =[]
|
||||
keep_only_tags.append(dict(name = 'table', attrs = {'id' : 'title-table'}))
|
||||
keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'div-header'}))
|
||||
keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'div-content'}))
|
||||
keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'def element-autor'}))
|
||||
'''
|
||||
|
||||
preprocess_regexps = [(re.compile(r'style="display: none;"'), lambda match: ''),
|
||||
(re.compile(r'display: block;'), lambda match: ''),
|
||||
(re.compile(r'\<td\>\<tr\>\<\/table\>'), lambda match: ''),
|
||||
(re.compile(r'\<table .*?\>'), lambda match: ''),
|
||||
(re.compile(r'\<tr>'), lambda match: ''),
|
||||
(re.compile(r'\<td .*?\>'), lambda match: ''),
|
||||
(re.compile(r'\<div id="footer"\>.*?\</footer\>'), lambda match: '')]
|
||||
|
||||
remove_tags = []
|
||||
remove_tags.append(dict(name='div', attrs={'class': 'def element-date'}))
|
||||
remove_tags.append(dict(name='div', attrs={'class': 'def silver'}))
|
||||
remove_tags.append(
|
||||
dict(name='div', attrs={'id': 'content-main-column-right'}))
|
||||
|
||||
extra_css = '''.div-header {font-size: x-small; font-weight: bold}'''
|
||||
# h2 {font-size: x-large; font-weight: bold}
|
||||
|
||||
def is_blocked(self, a):
|
||||
if a.findNextSibling('img') is None:
|
||||
return False
|
||||
else:
|
||||
return True
|
||||
|
||||
def find_last_issue(self):
|
||||
soup = self.index_to_soup('http://www.wprost.pl/archiwum/')
|
||||
a = 0
|
||||
if self.FIND_LAST_FULL_ISSUE:
|
||||
ico_blocked = soup.findAll('img', attrs={'src': self.ICO_BLOCKED})
|
||||
a = ico_blocked[-1].findNext(
|
||||
'a', attrs={'title': re.compile(r'Spis *', re.IGNORECASE | re.DOTALL)})
|
||||
else:
|
||||
a = soup.find('a', attrs={'title': re.compile(
|
||||
r'Spis *', re.IGNORECASE | re.DOTALL)})
|
||||
self.EDITION = a['href'].replace('/tygodnik/?I=', '')
|
||||
self.EDITION_SHORT = a['href'].replace('/tygodnik/?I=15', '')
|
||||
self.cover_url = a.img['src']
|
||||
|
||||
def parse_index(self):
|
||||
self.find_last_issue()
|
||||
soup = self.index_to_soup(
|
||||
'http://www.wprost.pl/tygodnik/?I=' + self.EDITION)
|
||||
feeds = []
|
||||
headers = soup.findAll(
|
||||
attrs={'class': 'block-header block-header-left mtop20 mbottom20'})
|
||||
articles_list = soup.findAll(attrs={'class': 'standard-box'})
|
||||
for i in range(len(headers)):
|
||||
articles = self.find_articles(articles_list[i])
|
||||
if len(articles) > 0:
|
||||
section = headers[i].find('a').string
|
||||
feeds.append((section, articles))
|
||||
return feeds
|
||||
|
||||
def find_articles(self, main_block):
|
||||
articles = []
|
||||
for a in main_block.findAll('a'):
|
||||
if a.name in "td":
|
||||
break
|
||||
if self.EXCLUDE_LOCKED and self.is_blocked(a):
|
||||
continue
|
||||
articles.append({
|
||||
'title': self.tag_to_string(a),
|
||||
'url': 'http://www.wprost.pl' + a['href'],
|
||||
'date': '',
|
||||
'description': ''
|
||||
})
|
||||
return articles
|
||||
@ -1,51 +0,0 @@
|
||||
#!/usr/bin/env python2
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '''2010, matek09, matek09@gmail.com
|
||||
Modified 2011, Mariusz Wolek <mariusz_dot_wolek @ gmail dot com>
|
||||
Modified 2012, Artur Stachecki <artur.stachecki@gmail.com>'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
|
||||
class Wprost(BasicNewsRecipe):
|
||||
title = u'Wprost (RSS)'
|
||||
__author__ = 'matek09'
|
||||
description = u'Portal informacyjny. Najświeższe wiadomości, najciekawsze komentarze i opinie. Blogi najlepszych publicystów.'
|
||||
encoding = 'ISO-8859-2'
|
||||
no_stylesheets = True
|
||||
language = 'pl'
|
||||
remove_javascript = True
|
||||
use_embedded_content = False
|
||||
ignore_duplicate_articles = {'title', 'url'}
|
||||
remove_empty_feeds = True
|
||||
keep_only_tags = [dict(attrs={'class': 'art-area'})]
|
||||
remove_tags = [dict(attrs={'class': 'add300x250'})]
|
||||
|
||||
extra_css = '''.div-header {font-size: x-small; font-weight: bold}'''
|
||||
# h2 {font-size: x-large; font-weight: bold}
|
||||
|
||||
feeds = [(u'Tylko u nas', u'http://www.wprost.pl/rss/rss_wprostextra.php'),
|
||||
(u'Wydarzenia', u'http://www.wprost.pl/rss/rss.php'),
|
||||
(u'Komentarze', u'http://www.wprost.pl/rss/rss_komentarze.php'),
|
||||
(u'Wydarzenia: Kraj', u'http://www.wprost.pl/rss/rss_kraj.php'),
|
||||
(u'Komentarze: Kraj', u'http://www.wprost.pl/rss/rss_komentarze_kraj.php'),
|
||||
(u'Wydarzenia: Świat', u'http://www.wprost.pl/rss/rss_swiat.php'),
|
||||
(u'Komentarze: Świat', u'http://www.wprost.pl/rss/rss_komentarze_swiat.php'),
|
||||
(u'Wydarzenia: Gospodarka',
|
||||
u'http://www.wprost.pl/rss/rss_gospodarka.php'),
|
||||
(u'Komentarze: Gospodarka',
|
||||
u'http://www.wprost.pl/rss/rss_komentarze_gospodarka.php'),
|
||||
(u'Wydarzenia: Życie', u'http://www.wprost.pl/rss/rss_zycie.php'),
|
||||
(u'Komentarze: Życie', u'http://www.wprost.pl/rss/rss_komentarze_zycie.php'),
|
||||
(u'Wydarzenia: Sport', u'http://www.wprost.pl/rss/rss_sport.php'),
|
||||
(u'Komentarze: Sport', u'http://www.wprost.pl/rss/rss_komentarze_sport.php'),
|
||||
(u'Przegląd prasy', u'http://www.wprost.pl/rss/rss_prasa.php')
|
||||
]
|
||||
|
||||
def get_cover_url(self):
|
||||
soup = self.index_to_soup('http://www.wprost.pl/tygodnik')
|
||||
cover = soup.find(attrs={'class': 'wprost-cover'})
|
||||
if cover:
|
||||
self.cover_url = cover['src']
|
||||
return getattr(self, 'cover_url', self.cover_url)
|
||||
@ -1,60 +0,0 @@
|
||||
#!/usr/bin/env python2
|
||||
__license__ = 'GPL v3'
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
|
||||
class WysokieObcasyRecipe(BasicNewsRecipe):
|
||||
__author__ = u'Artur Stachecki <artur.stachecki@gmail.com>'
|
||||
language = 'pl'
|
||||
version = 1
|
||||
|
||||
title = u'Wysokie Obcasy'
|
||||
publisher = 'Agora SA'
|
||||
description = u'Serwis sobotniego dodatku do Gazety Wyborczej'
|
||||
category = 'magazine'
|
||||
language = 'pl'
|
||||
publication_type = '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
|
||||
simultaneous_downloads = 5
|
||||
|
||||
keep_only_tags = []
|
||||
keep_only_tags.append(dict(name='div', attrs={'id': 'article'}))
|
||||
|
||||
remove_tags = []
|
||||
remove_tags.append(dict(name='img'))
|
||||
remove_tags.append(dict(name='p', attrs={'class': 'info'}))
|
||||
|
||||
extra_css = '''
|
||||
body {font-family: verdana, arial, helvetica, geneva, sans-serif ;}
|
||||
h1{text-align: left;}
|
||||
'''
|
||||
|
||||
feeds = [
|
||||
('Wszystkie Artykuly', 'feed://www.wysokieobcasy.pl/pub/rss/wysokieobcasy.xml'),
|
||||
]
|
||||
|
||||
def print_version(self, url):
|
||||
baseURL = 'http://www.wysokieobcasy.pl/wysokie-obcasy'
|
||||
segments = url.split(',')
|
||||
subPath = '/2029020,'
|
||||
articleURL1 = segments[1]
|
||||
articleURL2 = segments[2]
|
||||
printVerString = articleURL1 + ',' + articleURL2
|
||||
s = baseURL + subPath + printVerString + '.html'
|
||||
return s
|
||||
|
||||
def get_cover_url(self):
|
||||
soup = self.index_to_soup(
|
||||
'http://www.wysokieobcasy.pl/wysokie-obcasy/0,0.html')
|
||||
self.cover_url = soup.find(
|
||||
attrs={'class': 'holder_cr'}).find('img')['src']
|
||||
return getattr(self, 'cover_url', self.cover_url)
|
||||
Loading…
x
Reference in New Issue
Block a user