Polityka and Newsweek Polska by Mateusz Kielar

resources/recipes/newsweek_polska.recipe

@@ -0,0 +1,68 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2010, Mateusz Kielar, matek09@gmail.com'
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Newsweek(BasicNewsRecipe):
+	EDITION = 0
+
+	title = u'Newsweek Polska'
+	__author__ = 'Mateusz Kielar'
+	description = 'Weekly magazine'
+	encoding = 'utf-8'
+	no_stylesheets = True
+	language = 'en'
+	remove_javascript = True
+
+	keep_only_tags =[]
+	keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'article'}))
+
+	remove_tags =[]
+	remove_tags.append(dict(name = 'div', attrs = {'class' : 'copy'}))
+	remove_tags.append(dict(name = 'div', attrs = {'class' : 'url'}))
+
+	extra_css = '''
+					.body {font-size: small}
+					.author {font-size: x-small}
+					.lead {font-size: x-small}
+					.title{font-size: x-large; font-weight: bold}
+					'''
+
+	def print_version(self, url):
+		return url.replace("http://www.newsweek.pl/artykuly/wydanie/" + str(self.EDITION), "http://www.newsweek.pl/artykuly") + '/print'
+
+	def find_last_full_issue(self):
+		page = self.index_to_soup('http://www.newsweek.pl/Frames/IssueCover.aspx')
+		issue = 'http://www.newsweek.pl/Frames/' + page.find(lambda tag: tag.name == 'span' and not tag.attrs).a['href']
+		page = self.index_to_soup(issue)
+		issue = 'http://www.newsweek.pl/Frames/' + page.find(lambda tag: tag.name == 'span' and not tag.attrs).a['href']
+		page = self.index_to_soup(issue)
+		self.EDITION = page.find('a', attrs={'target' : '_parent'})['href'].replace('/wydania/','')
+
+	def parse_index(self):
+		self.find_last_full_issue()
+		soup = self.index_to_soup('http://www.newsweek.pl/wydania/' + str(self.EDITION))
+		img = soup.find('img', id="ctl00_C1_PaperIsssueView_IssueImage", src=True)
+		self.cover_url = img['src']
+		feeds = []
+		parent = soup.find(id='content-left-big')
+		for txt in parent.findAll(attrs={'class':'txt_normal_red strong'}):
+			section = self.tag_to_string(txt).capitalize()
+			articles = list(self.find_articles(txt))
+			feeds.append((section, articles))
+		return feeds
+
+	def find_articles(self, txt):
+		for a in txt.findAllNext( attrs={'class':['strong','hr']}):
+			if a.name in "div":
+				break
+			yield {
+				'title' : self.tag_to_string(a),
+				'url'   : 'http://www.newsweek.pl'+a['href'],
+				'date'  : '',
+				'description' : ''
+				}
+
+

resources/recipes/polityka.recipe

@@ -0,0 +1,68 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2010, Mateusz Kielar, matek09@gmail.com'
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Polityka(BasicNewsRecipe):
+
+	title = u'Polityka'
+	__author__ = 'Mateusz Kielar'
+	description = 'Weekly magazine. Last archive issue'
+	encoding = 'utf-8'
+	no_stylesheets = True
+	language = 'en'
+	remove_javascript = True
+
+	remove_tags_before = dict(dict(name = 'h2', attrs = {'class' : 'box_nag'}))
+	remove_tags_after = dict(dict(name = 'div', attrs = {'class' : 'box_footer'}))
+
+	remove_tags =[]
+	remove_tags.append(dict(name = 'h2', attrs = {'class' : 'box_nag'}))
+	remove_tags.append(dict(name = 'div', attrs = {'class' : 'box_footer'}))
+
+
+	extra_css = '''
+					h1 {font-size: x-large; font-weight: bold}
+					'''
+
+	def parse_index(self):
+		soup = self.index_to_soup('http://archiwum.polityka.pl/')
+		box_img3 = soup.findAll(attrs={'class' : 'box_img3'})
+		feeds = []
+		last = 0
+		self.cover_url = 'http://archiwum.polityka.pl' + box_img3[-1].find('img')['src']
+		last_edition = 'http://archiwum.polityka.pl' + box_img3[-1].find('a')['href']
+
+		while True:
+			index = self.index_to_soup(last_edition)
+
+
+			box_list = index.findAll('div', attrs={'class' : 'box_list'})
+			if len(box_list) == 0:
+				break
+
+			articles = {}
+			for box in box_list:
+				for div in box.findAll('div', attrs={'class': 'list_tresc'}):
+					article_page = self.index_to_soup('http://archiwum.polityka.pl' + div.a['href'],)
+					section = self.tag_to_string(article_page.find('h2', attrs = {'class' : 'box_nag'})).split('/')[0].lstrip().rstrip()
+					print section
+					if not articles.has_key(section):
+						articles[section] = []
+					articles[section].append( {
+						'title' : self.tag_to_string(div.a),
+						'url'   : 'http://archiwum.polityka.pl' + div.a['href'],
+						'date'  : '',
+						'description' : ''
+						})
+
+			for section in articles:
+				feeds.append((section, articles[section]))
+
+			last_edition = last_edition.replace('http://archiwum.polityka.pl/wydanie/' + str(last), 'http://archiwum.polityka.pl/wydanie/' + str(last + 1))
+			last = last + 1
+
+		return feeds
+