mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
112 lines
4.4 KiB
Python
112 lines
4.4 KiB
Python
#!/usr/bin/env python
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = u'2020, Tomasz Jozwiak <tjozwiakgm@gmail.com>'
|
|
__author__ = u'Tomasz Jozwiak'
|
|
'''
|
|
gazetaprawna.pl
|
|
'''
|
|
|
|
import re
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class gazetaprawna(BasicNewsRecipe):
|
|
version = 2
|
|
title = u'Gazeta Prawna'
|
|
__author__ = u'Tomasz Jozwiak'
|
|
publisher = u'Infor Biznes'
|
|
max_articles_per_feed = 30
|
|
no_stylesheets = True
|
|
remove_javascript = True
|
|
remove_empty_feeds = True
|
|
category = 'newspaper'
|
|
publication_type = 'newspaper'
|
|
description = 'Polski dziennik gospodarczy'
|
|
language = 'pl'
|
|
encoding = 'utf-8'
|
|
ignore_duplicate_articles = {'title', 'url'}
|
|
use_embedded_content = False
|
|
oldest_article = 1
|
|
|
|
extra_css = '''
|
|
.psavBigImgTitle {font-size:50%;}
|
|
.psavImgContent {font-size:50%;}
|
|
.leadDiv {font-weight: bold;}
|
|
.date {font-size:50%;}
|
|
.articleGate {font-style: italic; font-weight: normal; font-size:50%;}
|
|
'''
|
|
|
|
remove_tags_before = [
|
|
dict(name='div', attrs={'class': ['article']}),
|
|
dict(name='div', attrs={'itemprop': ['breadcrumb']})
|
|
]
|
|
|
|
remove_tags_after = [
|
|
dict(name='div', attrs={'class': ['articleBody', 'artPayWall', 'contentGalBottom', 'komentarze-forum']}),
|
|
]
|
|
|
|
remove_tags = [
|
|
dict(name='span', attrs={'class': ['psav_bigphoto', 'psav_speclinkarea', 'psav_video_target']}),
|
|
dict(name='div', attrs={'class': ['shareArticleButtons nowe2', 'artPayWall', 'contentGalBottom', 'contentGalTop', 'video-target', 'komentarze-forum']}),
|
|
dict(name=['link', 'meta', 'style']),
|
|
dict(name='div', attrs={'itemprop': ['breadcrumb']}),
|
|
dict(name='section', attrs={'class': ['videoSection']})
|
|
]
|
|
|
|
feeds = [
|
|
(u'Z ostatniej chwili', u'http://rss.gazetaprawna.pl/GazetaPrawna'),
|
|
(u'Biznes i prawo gospodarcze', u'http://rss.gazetaprawna.pl/GazetaPrawna-Biznes'),
|
|
(u'Prawo i wymiar sprawiedliwo\u015bci', u'http://rss.gazetaprawna.pl/GazetaPrawna-Prawo'),
|
|
(u'Praca i ubezpieczenia', u'http://rss.gazetaprawna.pl/GazetaPrawna-Praca'),
|
|
(u'Podatki i rachunkowo\u015b\u0107', u'http://rss.gazetaprawna.pl/GazetaPrawna-Podatki'),
|
|
(u'Finanse - waluty i notowania', u'http://rss.gazetaprawna.pl/GazetaPrawna-Finanse'),
|
|
]
|
|
|
|
def parse_feeds(self):
|
|
self.log(_('Gazeta Prawna overrided parse_feeds()'))
|
|
parsed_feeds = BasicNewsRecipe.parse_feeds(self)
|
|
for n, feed in enumerate(parsed_feeds):
|
|
for a, article in enumerate(feed):
|
|
article.text_summary = re.sub(r'<\!\[CDATA\[', "", article.text_summary)
|
|
article.text_summary = re.sub(r'\]\]', "", article.text_summary)
|
|
article.summary = article.text_summary
|
|
|
|
return parsed_feeds
|
|
|
|
def preprocess_html(self, soup):
|
|
for Img in soup.findAll(name='div', attrs={'class': ['psavBigImg']}):
|
|
for img_tag in Img.findAll(name='img', attrs={'data-src': True}):
|
|
img_tag['src'] = img_tag['data-src']
|
|
del img_tag['data-src']
|
|
# print(Img.prettify())
|
|
|
|
for span in soup.findAll(name='span'):
|
|
if len(self.tag_to_string(span)) > 1:
|
|
span.append(" ")
|
|
|
|
for locked in soup.findAll(name='div', attrs={'class': ['articleGate']}):
|
|
locked.append(u"Przejd\u017a do artyku\u0142u na GazetaPrawna.pl aby zalogowa\u0107 si\u0119 lub wykupi\u0107 dost\u0119p")
|
|
|
|
return soup
|
|
|
|
def populate_article_metadata(self, article, soup, first):
|
|
Img = soup.find(name='div', attrs={'class': ['psavBigImg']})
|
|
if Img:
|
|
img_tag = Img.find(name='img', attrs={'src': True})
|
|
if img_tag:
|
|
self.add_toc_thumbnail(article, img_tag['src'])
|
|
self.log(_('adding thumbnail: %s to Article') % (img_tag['src']))
|
|
article.author = 'Gazeta prawna.pl'
|
|
if len(article.title) > 80:
|
|
title = article.title[:80]
|
|
title = title.rsplit(None, 1)
|
|
article.title = title[0]
|
|
self.log(_('The title cuting in %s to keep the thumbnail visible') % (article.url))
|
|
|
|
def get_cover_url(self):
|
|
soup = self.index_to_soup(
|
|
'http://www.egazety.pl/infor/e-wydanie-dziennik-gazeta-prawna.html')
|
|
self.cover_url = soup.find("a", {"class": "image cover-preview"}).img['src']
|
|
return getattr(self, 'cover_url', self.cover_url)
|