mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
Remove non-working recipes
This commit is contained in:
Kovid Goyal
parent
a7d1f4c88f
commit
ac0d67ee6f
Binary file not shown.
|
Before Width: | Height: | Size: 620 B |
Binary file not shown.
|
Before Width: | Height: | Size: 430 B |
@ -1,72 +0,0 @@
|
||||
# vim:fileencoding=utf-8
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
|
||||
class AdjectiveSpecies(BasicNewsRecipe):
|
||||
title = u'Российская Газета'
|
||||
__author__ = 'bug_me_not'
|
||||
cover_url = u'http://img.rg.ru/img/d/logo2012.png'
|
||||
description = 'Российская Газета'
|
||||
publisher = 'Правительство Российской Федерации'
|
||||
category = 'news'
|
||||
language = 'ru'
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
oldest_article = 300
|
||||
max_articles_per_feed = 100
|
||||
|
||||
remove_tags_before = dict(name='h1')
|
||||
remove_tags_after = dict(name='div', attrs={'class': 'ar-citate'})
|
||||
remove_tags = [dict(name='div', attrs={'class': 'insert_left'}),
|
||||
dict(name='a', attrs={'href': '#comments'}),
|
||||
dict(name='div', attrs={'class': 'clear'}),
|
||||
dict(name='div', attrs={'class': 'ar-citate'}),
|
||||
dict(name='div', attrs={'class': 'ar-social red'}),
|
||||
dict(name='div', attrs={'class': 'clear clear-head'}), ]
|
||||
|
||||
feeds = [
|
||||
(u'Все материалы', u'http://www.rg.ru/tema/rss.xml'),
|
||||
(u'Еженедельный выпуск',
|
||||
u'http://www.rg.ru/tema/izd-subbota/rss.xml'),
|
||||
(u'Государство',
|
||||
u'http://www.rg.ru/tema/gos/rss.xml'),
|
||||
(u'Экономика',
|
||||
u'http://www.rg.ru/tema/ekonomika/rss.xml'),
|
||||
(u'Бизнес',
|
||||
u'http://www.rg.ru/tema/izd-biznes/rss.xml'),
|
||||
(u'В мире', u'http://www.rg.ru/tema/mir/rss.xml'),
|
||||
(u'Происшествия',
|
||||
u'http://www.rg.ru/tema/bezopasnost/rss.xml'),
|
||||
(u'Общество',
|
||||
u'http://www.rg.ru/tema/obshestvo/rss.xml'),
|
||||
(u'Культура',
|
||||
u'http://www.rg.ru/tema/kultura/rss.xml'),
|
||||
(u'Спорт', u'http://www.rg.ru/tema/sport/rss.xml'),
|
||||
(u'Документы', u'http://rg.ru/tema/doc-any/rss.xml'),
|
||||
(u'РГ: Башкортостан',
|
||||
u'http://www.rg.ru/org/filial/bashkortostan/rss.xml'),
|
||||
(u'РГ: Волга-Кама',
|
||||
u'http://www.rg.ru/org/filial/volga-kama/rss.xml'),
|
||||
(u'РГ: Восточная Сибирь',
|
||||
u'http://www.rg.ru/org/filial/enisey/rss.xml'),
|
||||
(u'РГ: Дальний Восток',
|
||||
u'http://www.rg.ru/org/filial/dvostok/rss.xml'),
|
||||
(u'РГ: Кубань. Северный Кавказ',
|
||||
u'http://www.rg.ru/org/filial/kuban/rss.xml'),
|
||||
(u'РГ: Пермский край',
|
||||
u'http://www.rg.ru/org/filial/permkray/rss.xml'),
|
||||
(u'РГ: Приволжье',
|
||||
u'http://www.rg.ru/org/filial/privolzhe/rss.xml'),
|
||||
(u'РГ: Северо-Запад',
|
||||
u'http://www.rg.ru/org/filial/szapad/rss.xml'),
|
||||
(u'РГ: Сибирь',
|
||||
u'http://www.rg.ru/org/filial/sibir/rss.xml'),
|
||||
(u'РГ: Средняя Волга',
|
||||
u'http://www.rg.ru/org/filial/svolga/rss.xml'),
|
||||
(u'РГ: Урал и Западная Сибирь',
|
||||
u'http://www.rg.ru/org/filial/ural/rss.xml'),
|
||||
(u'РГ: Центральная Россия',
|
||||
u'http://www.rg.ru/org/filial/roscentr/rss.xml'),
|
||||
(u'РГ: Юг России',
|
||||
u'http://www.rg.ru/org/filial/jugrossii/rss.xml'),
|
||||
]
|
||||
@ -1,207 +0,0 @@
|
||||
#!/usr/bin/env python2
|
||||
|
||||
u'''
|
||||
Ведомости
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.feedparser import parse
|
||||
from calibre.ebooks.BeautifulSoup import Tag
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
|
||||
def new_tag(soup, name, attrs=()):
|
||||
impl = getattr(soup, 'new_tag', None)
|
||||
if impl is not None:
|
||||
return impl(name, attrs=dict(attrs))
|
||||
return Tag(soup, name, attrs=attrs or None)
|
||||
|
||||
|
||||
class VedomostiRecipe(BasicNewsRecipe):
|
||||
title = u'Ведомости'
|
||||
__author__ = 'Nikolai Kotchetkov'
|
||||
publisher = 'vedomosti.ru'
|
||||
category = 'press, Russia'
|
||||
description = u'Ежедневная деловая газета'
|
||||
oldest_article = 3
|
||||
max_articles_per_feed = 100
|
||||
|
||||
masthead_url = u'http://motorro.com/imgdir/logos/ved_logo_black2_cropped.gif'
|
||||
cover_url = u'http://motorro.com/imgdir/logos/ved_logo_black2_cropped.gif'
|
||||
|
||||
# Add feed names if you want them to be sorted (feeds of this list appear
|
||||
# first)
|
||||
sortOrder = [u'_default', u'Первая полоса', u'Власть и деньги']
|
||||
|
||||
encoding = 'cp1251'
|
||||
language = 'ru'
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
recursions = 0
|
||||
|
||||
conversion_options = {
|
||||
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
|
||||
}
|
||||
|
||||
keep_only_tags = [dict(name='td', attrs={'class': ['second_content']})]
|
||||
|
||||
remove_tags_after = [dict(name='div', attrs={'class': 'article_text'})]
|
||||
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'class': ['sep', 'choice', 'articleRightTbl']})]
|
||||
|
||||
feeds = [u'http://www.vedomosti.ru/newspaper/out/rss.xml']
|
||||
|
||||
# base URL for relative links
|
||||
base_url = u'http://www.vedomosti.ru'
|
||||
|
||||
extra_css = 'h1 {font-size: 1.5em; margin: 0em 0em 0em 0em; text-align: center;}'\
|
||||
'h2 {font-size: 1.0em; margin: 0em 0em 0em 0em;}'\
|
||||
'h3 {font-size: 0.8em; margin: 0em 0em 0em 0em;}'\
|
||||
'.article_date {font-size: 0.5em; color: gray; font-family: monospace; text-align:right;}'\
|
||||
'.article_authors {font-size: 0.5em; color: gray; font-family: monospace; text-align:right;}'\
|
||||
'.article_img {width:100%; text-align: center; padding: 3px 3px 3px 3px;}'\
|
||||
'.article_img_desc {width:100%; text-align: center; font-size: 0.5em; color: gray; font-family: monospace;}'\
|
||||
'.article_desc {font-size: 1em; font-style:italic;}'
|
||||
|
||||
def parse_index(self):
|
||||
try:
|
||||
feedData = parse(self.feeds[0])
|
||||
if not feedData:
|
||||
raise NotImplementedError
|
||||
self.log("parse_index: Feed loaded successfully.")
|
||||
try:
|
||||
if feedData.feed.title:
|
||||
self.title = feedData.feed.title
|
||||
self.log("parse_index: Title updated to: ", self.title)
|
||||
except Exception:
|
||||
pass
|
||||
try:
|
||||
if feedData.feed.description:
|
||||
self.description = feedData.feed.description
|
||||
self.log("parse_index: Description updated to: ",
|
||||
self.description)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
def get_virtual_feed_articles(feed):
|
||||
if feed in feeds:
|
||||
return feeds[feed][1]
|
||||
self.log("Adding new feed: ", feed)
|
||||
articles = []
|
||||
feeds[feed] = (feed, articles)
|
||||
return articles
|
||||
|
||||
feeds = {}
|
||||
|
||||
# Iterate feed items and distribute articles using tags
|
||||
for item in feedData.entries:
|
||||
link = item.get('link', '')
|
||||
title = item.get('title', '')
|
||||
if '' == link or '' == title:
|
||||
continue
|
||||
article = {'title': title, 'url': link, 'description': item.get(
|
||||
'description', ''), 'date': item.get('date', ''), 'content': ''}
|
||||
if not item.get('tags'): # noqa
|
||||
get_virtual_feed_articles('_default').append(article)
|
||||
continue
|
||||
for tag in item.tags:
|
||||
addedToDefault = False
|
||||
term = tag.get('term', '')
|
||||
if '' == term:
|
||||
if (not addedToDefault):
|
||||
get_virtual_feed_articles(
|
||||
'_default').append(article)
|
||||
continue
|
||||
get_virtual_feed_articles(term).append(article)
|
||||
|
||||
# Get feed list
|
||||
# Select sorted feeds first of all
|
||||
result = []
|
||||
for feedName in self.sortOrder:
|
||||
if (not feeds.get(feedName)):
|
||||
continue
|
||||
result.append(feeds[feedName])
|
||||
del feeds[feedName]
|
||||
result = result + feeds.values()
|
||||
|
||||
return result
|
||||
|
||||
except Exception as err:
|
||||
self.log(err)
|
||||
raise NotImplementedError
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
return self.adeify_images(soup)
|
||||
|
||||
def postprocess_html(self, soup, first_fetch):
|
||||
|
||||
# Find article
|
||||
contents = soup.find('div', {'class': ['article_text']})
|
||||
if not contents:
|
||||
self.log('postprocess_html: article div not found!')
|
||||
return soup
|
||||
contents.extract()
|
||||
|
||||
# Find title
|
||||
title = soup.find('h1')
|
||||
if title:
|
||||
contents.insert(0, title)
|
||||
|
||||
# Find article image
|
||||
newstop = soup.find('div', {'class': ['newstop']})
|
||||
if newstop:
|
||||
img = newstop.find('img')
|
||||
if img:
|
||||
imgDiv = new_tag(soup, 'div')
|
||||
imgDiv['class'] = 'article_img'
|
||||
|
||||
if img.get('width'):
|
||||
del(img['width'])
|
||||
if img.get('height'):
|
||||
del(img['height'])
|
||||
|
||||
# find description
|
||||
element = img.parent.nextSibling
|
||||
|
||||
img.extract()
|
||||
imgDiv.insert(0, img)
|
||||
|
||||
while element:
|
||||
if not isinstance(element, Tag):
|
||||
continue
|
||||
nextElement = element.nextSibling
|
||||
if 'p' == element.name:
|
||||
element.extract()
|
||||
element['class'] = 'article_img_desc'
|
||||
imgDiv.insert(len(imgDiv.contents), element)
|
||||
element = nextElement
|
||||
|
||||
contents.insert(1, imgDiv)
|
||||
|
||||
# find article abstract
|
||||
abstract = soup.find('p', {'class': ['subhead']})
|
||||
if abstract:
|
||||
abstract['class'] = 'article_desc'
|
||||
contents.insert(2, abstract)
|
||||
|
||||
# Find article authors
|
||||
authorsDiv = soup.find('div', {'class': ['autors']})
|
||||
if authorsDiv:
|
||||
authorsP = authorsDiv.find('p')
|
||||
if authorsP:
|
||||
authorsP['class'] = 'article_authors'
|
||||
contents.insert(len(contents.contents), authorsP)
|
||||
|
||||
# Fix urls that use relative path
|
||||
urls = contents.findAll('a', href=True)
|
||||
if urls:
|
||||
for url in urls:
|
||||
if '/' == url['href'][0]:
|
||||
url['href'] = self.base_url + url['href']
|
||||
|
||||
body = soup.find('td', {'class': ['second_content']})
|
||||
if body:
|
||||
body.replaceWith(contents)
|
||||
|
||||
self.log('Result: ', soup.prettify())
|
||||
return soup
|
||||
Loading…
x
Reference in New Issue
Block a user