| 1 |
from calibre.ebooks.BeautifulSoup import Comment |
| 2 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 3 |
|
| 4 |
|
| 5 |
class Dzieje(BasicNewsRecipe): |
| 6 |
title = 'dzieje.pl' |
| 7 |
__author__ = 'fenuks' |
| 8 |
description = 'Dzieje.pl - najlepszy portal informacyjno-edukacyjny dotyczący historii Polski XX wieku. Archiwalne fotografie, filmy, katalog postaci, quizy i konkursy.' # noqa: E501 |
| 9 |
cover_url = 'http://www.dzieje.pl/sites/default/files/dzieje_logo.png' |
| 10 |
category = 'history' |
| 11 |
language = 'pl' |
| 12 |
ignore_duplicate_articles = {'title', 'url'} |
| 13 |
extra_css = '.imagecache-default {float:left; margin-right:20px;}' |
| 14 |
index = 'http://dzieje.pl' |
| 15 |
oldest_article = 8 |
| 16 |
max_articles_per_feed = 100 |
| 17 |
remove_javascript = True |
| 18 |
no_stylesheets = True |
| 19 |
keep_only_tags = [dict(name='h1', attrs={'class': 'title'}), dict(id='content-area')] |
| 20 |
remove_tags = [dict(attrs={'class': 'field field-type-computed field-field-tagi'}), dict(id='dogory'), dict(name='blockquote')] |
| 21 |
|
| 22 |
def append_page(self, soup, appendtag): |
| 23 |
tag = appendtag.find('li', attrs={'class': 'pager-next'}) |
| 24 |
if tag: |
| 25 |
while tag: |
| 26 |
url = tag.a['href'] |
| 27 |
if not url.startswith('http'): |
| 28 |
url = 'http://dzieje.pl' + tag.a['href'] |
| 29 |
soup2 = self.index_to_soup(url) |
| 30 |
pagetext = soup2.find(id='content-area').find(attrs={'class': 'content'}) |
| 31 |
for r in pagetext.findAll( |
| 32 |
attrs={ |
| 33 |
'class': [ |
| 34 |
'fieldgroup group-groupkul', |
| 35 |
'fieldgroup group-zdjeciekult', |
| 36 |
'fieldgroup group-zdjecieciekaw', |
| 37 |
'fieldgroup group-zdjecieksiazka', |
| 38 |
'fieldgroup group-zdjeciedu', |
| 39 |
'field field-type-filefield field-field-zdjecieglownawyd', |
| 40 |
] |
| 41 |
} |
| 42 |
): # noqa: E501 |
| 43 |
r.extract() |
| 44 |
comments = pagetext.findAll(text=lambda text: isinstance(text, Comment)) |
| 45 |
# appendtag.insert(pos, pagetext) |
| 46 |
tag = soup2.find('li', attrs={'class': 'pager-next'}) |
| 47 |
for r in appendtag.findAll( |
| 48 |
attrs={ |
| 49 |
'class': [ |
| 50 |
'item-list', |
| 51 |
'field field-type-computed field-field-tagi', |
| 52 |
] |
| 53 |
} |
| 54 |
): |
| 55 |
r.extract() |
| 56 |
comments = appendtag.findAll(text=lambda text: isinstance(text, Comment)) |
| 57 |
for comment in comments: |
| 58 |
comment.extract() |
| 59 |
|
| 60 |
def find_articles(self, url): |
| 61 |
articles = [] |
| 62 |
soup = self.index_to_soup(url) |
| 63 |
tag = soup.find(id='content-area').div.div |
| 64 |
for i in tag.findAll('div', recursive=False): |
| 65 |
temp = i.find(attrs={'class': 'views-field-title'}).span.a |
| 66 |
title = temp.string |
| 67 |
url = self.index + temp['href'] |
| 68 |
# i.find(attrs={'class':'views-field-created'}).span.string |
| 69 |
date = '' |
| 70 |
articles.append({'title': title, 'url': url, 'date': date, 'description': ''}) |
| 71 |
return articles |
| 72 |
|
| 73 |
def parse_index(self): |
| 74 |
feeds = [] |
| 75 |
feeds.append(('Wiadomości', self.find_articles('http://dzieje.pl/wiadomosci'))) |
| 76 |
feeds.append(('Kultura i sztuka', self.find_articles('http://dzieje.pl/kulturaisztuka'))) |
| 77 |
feeds.append(('Film', self.find_articles('http://dzieje.pl/kino'))) |
| 78 |
feeds.append(('Rozmaitości historyczne', self.find_articles('http://dzieje.pl/rozmaitości'))) |
| 79 |
feeds.append(('Książka', self.find_articles('http://dzieje.pl/ksiazka'))) |
| 80 |
feeds.append(('Wystawa', self.find_articles('http://dzieje.pl/wystawa'))) |
| 81 |
feeds.append(('Edukacja', self.find_articles('http://dzieje.pl/edukacja'))) |
| 82 |
feeds.append(('Dzieje się', self.find_articles('http://dzieje.pl/wydarzenia'))) |
| 83 |
return feeds |
| 84 |
|
| 85 |
def preprocess_html(self, soup): |
| 86 |
for a in soup('a', href=True): |
| 87 |
if not a['href'].startswith('http'): |
| 88 |
a['href'] = self.index + a['href'] |
| 89 |
self.append_page(soup, soup.body) |
| 90 |
return soup |