After 3 months of using them with no major problem, I'm ready to make them public:
Dilema Veche.
Code:
class DilemaVeche(BasicNewsRecipe):
title = u'Dilema Veche' # apare vinerea, mai pe dupa-masa,depinde de Luiza cred (care se semneaza ca fiind creatorul fiecarui articol in feed-ul RSS)
__author__ = 'song2' # inspirat din scriptul pentru Le Monde. Inspired from the Le Monde script
description = '"Sint vechi, domnule!" (I.L. Caragiale)'
publisher = 'Adevarul Holding'
oldest_article = 7
max_articles_per_feed = 200
encoding = 'utf8'
language = 'ro'
masthead_url = 'http://www.dilemaveche.ro/sites/all/themes/dilema/theme/dilema_two/layouter/dilema_two_homepage/logo.png'
publication_type = 'magazine'
feeds = [
('Editoriale si opinii - Situatiunea', 'http://www.dilemaveche.ro/taxonomy/term/37/0/feed'),
('Editoriale si opinii - Pe ce lume traim', 'http://www.dilemaveche.ro/taxonomy/term/38/0/feed'),
('Editoriale si opinii - Bordeie si obiceie', 'http://www.dilemaveche.ro/taxonomy/term/44/0/feed'),
('Editoriale si opinii - Talc Show', 'http://www.dilemaveche.ro/taxonomy/term/44/0/feed'),
('Tema saptamanii', 'http://www.dilemaveche.ro/taxonomy/term/19/0/feed'),
('La zi in cultura - Dilema va recomanda', 'http://www.dilemaveche.ro/taxonomy/term/58/0/feed'),
('La zi in cultura - Carte', 'http://www.dilemaveche.ro/taxonomy/term/14/0/feed'),
('La zi in cultura - Film', 'http://www.dilemaveche.ro/taxonomy/term/13/0/feed'),
('La zi in cultura - Muzica', 'http://www.dilemaveche.ro/taxonomy/term/1341/0/feed'),
('La zi in cultura - Arte performative', 'http://www.dilemaveche.ro/taxonomy/term/1342/0/feed'),
('La zi in cultura - Arte vizuale', 'http://www.dilemaveche.ro/taxonomy/term/1512/0/feed'),
('Societate - Ieri cu vedere spre azi', 'http://www.dilemaveche.ro/taxonomy/term/15/0/feed'),
('Societate - Din polul opus', 'http://www.dilemaveche.ro/taxonomy/term/41/0/feed'),
('Societate - Mass comedia', 'http://www.dilemaveche.ro/taxonomy/term/43/0/feed'),
('Societate - La singular si la plural', 'http://www.dilemaveche.ro/taxonomy/term/42/0/feed'),
('Oameni si idei - Educatie', 'http://www.dilemaveche.ro/taxonomy/term/46/0/feed'),
('Oameni si idei - Polemici si dezbateri', 'http://www.dilemaveche.ro/taxonomy/term/48/0/feed'),
('Oameni si idei - Stiinta si tehnologie', 'http://www.dilemaveche.ro/taxonomy/term/46/0/feed'),
('Dileme on-line', 'http://www.dilemaveche.ro/taxonomy/term/005/0/feed')
]
remove_tags_before = dict(name='div',attrs={'class':'spacer_10'})
remove_tags = [
dict(name='div', attrs={'class':'art_related_left'}),
dict(name='div', attrs={'class':'controale'}),
dict(name='div', attrs={'class':'simple_overlay'}),
]
remove_tags_after = [dict(id='facebookLike')]
remove_javascript = True
no_stylesheets = True
remove_empty_feeds = True
extra_css = """
body{font-family: Georgia,Times,serif }
img{margin-bottom: 0.4em; display:block}
"""
def get_cover_url(self):
cover_url = None
soup = self.index_to_soup('http://dilemaveche.ro')
link_item = soup.find('div',attrs={'class':'box_dr_pdf_picture'})
if link_item and link_item.a:
cover_url = link_item.a['href']
br = BasicNewsRecipe.get_browser()
try:
br.open(cover_url)
except: #daca nu gaseste pdf-ul
self.log("\nPDF indisponibil")
link_item = soup.find('div',attrs={'class':'box_dr_pdf_picture'})
if link_item and link_item.img:
cover_url = link_item.img['src']
br = BasicNewsRecipe.get_browser()
try:
br.open(cover_url)
except: #daca nu gaseste nici imaginea mica mica
print('Mama lor de nenorociti! nu este nici pdf nici imagine')
cover_url ='http://www.dilemaveche.ro/sites/all/themes/dilema/theme/dilema_two/layouter/dilema_two_homepage/logo.png'
return cover_url
cover_margins = (10, 15, '#ffffff')
Observatorul Cultural:
Code:
import re
from calibre.web.feeds.news import BasicNewsRecipe
class ObservatorulCultural(BasicNewsRecipe):
title = u'Observatorul cultural'
__author__ = 'song2' #prelucrat dupa un script de http://www.thenowhereman.com
encoding = 'utf-8'
language = 'ro'
publication_type = 'magazine'
description = 'Spiritul critic in acţiune\n'
no_stylesheets = True
remove_javascript = True
masthead_url='http://www.observatorcultural.ro/userfiles/article/sigla%20Observator%20cultural_02231058.JPG'
keep_only_tags = [
dict(name='div', attrs={'class':'detaliuArticol'})]
remove_tags = [dict(name='div', attrs={'class':'comentariiArticol'}),
dict(name='div', attrs={'class':'postComment'}),
dict(name='div', attrs={'class':'utileArticol'}),
dict(name='p', attrs={'class':'butonComenteaza'}),
dict(name='h5'),
dict(name='div', attrs={'style':'margin-top: 0px; padding-top: 0px;'})
]
def parse_index(self):
soup = self.index_to_soup('http://www.observatorcultural.ro/Arhiva*-archive.html')
issueTag = soup.find('a', href=re.compile("observatorcultural.ro\/Numarul"))
issueURL = issueTag['href']
print issueURL;
issueSoup = self.index_to_soup(issueURL)
feeds = []
stories = []
for categorie in issueSoup.findAll('dl',attrs={'class':'continutArhive'}):
categ=self.tag_to_string(categorie.find('dt'))
for story in categorie.findAll('dd'):
title=[]
for bucatele in story.findAll('a'):
title.append(bucatele)
if len(title)==1: #daca articolul nu are autor
stories.append({
'title' : self.tag_to_string(title[0]),
'url' : title[0]['href'],
'date' : '',
'author' : ''})
else: # daca articolul are autor len(title)=2
stories.append({
'title' : self.tag_to_string(title[1]),
'url' :title[1]['href'],
'date' : '',
'author' : self.tag_to_string(title[0])})
print(self.tag_to_string(title[0]))
if 'Editorial' in categ:
global coverpage
coverpage=title[1]['href'] # am luat link-ul spre editorial
feeds.append((categ,stories))
stories = []
print feeds
return feeds
#procedura de luat coperta
def get_cover_url(self):
soup = self.index_to_soup(coverpage)
link_item = soup.find('a',attrs={'rel':'lightbox'}) # caut imaginea textului
a=''
cover_url = a.join(link_item.img['src'].split('_details_'))
return cover_url