Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Utrinski Vesnik

Browse Source
This commit is contained in:
Kovid Goyal 2011-09-22 13:37:28 -06:00
parent 19581b8806
commit cdca8936e2
1 changed files with 19 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
recipes/utrinski.recipe
View File

@ -1,5 +1,6 @@
#!/usr/bin/env python
__author__ = 'Darko Spasovski'
__license__ = 'GPL v3'
__copyright__ = '2011, Darko Spasovski <darko.spasovski at gmail.com>'
'''
@ -9,10 +10,11 @@ utrinski.com.mk
import re
import datetime
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup
from calibre import browser
class UtrinskiVesnik(BasicNewsRecipe):
__author__ = 'Darko Spasovski'
INDEX = 'http://www.utrinski.com.mk/'
title = 'Utrinski Vesnik'
description = 'Daily Macedonian newspaper'
@ -21,7 +23,6 @@ class UtrinskiVesnik(BasicNewsRecipe):
remove_javascript = True
publication_type = 'newspaper'
category = 'news, Macedonia'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
@ -47,25 +48,29 @@ class UtrinskiVesnik(BasicNewsRecipe):
}
def parse_index(self):
soup = self.index_to_soup(self.INDEX)
feeds = []
for section in soup.findAll('a', attrs={'class':'WB_UTRINSKIVESNIK_TOCTitleBig'}):
# open main page
soup = self.index_to_soup(self.INDEX)
# find all anchors with class attribute equal to 'WB_UTRINSKIVESNIK_MainMenu'
for section in soup.findAll('a', attrs={'class':'WB_UTRINSKIVESNIK_MainMenu'}):
sectionTitle = section.contents[0].string
tocItemTable = section.findAllPrevious('table')[1]
if tocItemTable is None: continue
sectionUrl = self.INDEX + section['href'].strip()
# open the anchor link
raw = browser().open_novisit(sectionUrl).read()
sectionSoup = BeautifulSoup(raw)
# find all anchors with class attribute equal to 'WB_UTRINSKIVESNIK_ONLINEArticleTitle'
sectionArticles = sectionSoup.findAll('a', attrs={'class':'WB_UTRINSKIVESNIK_ONLINEArticleTitle'})
articles = []
while True:
tocItemTable = tocItemTable.nextSibling
if tocItemTable is None: break
article = tocItemTable.findAll('a', attrs={'class': 'WB_UTRINSKIVESNIK_TocItem'})
if len(article)==0: break
title = self.tag_to_string(article[0], use_alt=True).strip()
articles.append({'title': title, 'url':'http://www.utrinski.com.mk/' + article[0]['href'], 'description':'', 'date':''})
for sectionArticle in sectionArticles:
# article title = anchor's contents, article url = anchor's href
articleTitle = sectionArticle.contents[0].string.strip()
articleUrl = self.INDEX + sectionArticle['href'].strip()
articleDate = datetime.datetime.today().strftime('%d.%m.%Y')
articles.append({'title': articleTitle, 'url':articleUrl, 'description':'', 'date': articleDate})
if articles:
feeds.append((sectionTitle, articles))
return feeds
def get_cover_url(self):
datum = datetime.datetime.today().strftime('%d_%m_%Y')
return 'http://www.utrinski.com.mk/WBStorage/Files/' + datum + '.jpg'