From 2822623f7e154eaa17f386157d3f5f69b4a6fa98 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Tomasz=20D=C5=82ugosz?= <tomek3d@gmail.com>
Date: Sun, 18 Nov 2012 18:47:45 +0100
Subject: [PATCH] telepolis

---
 recipes/icons/telepolis_pl.png | Bin 0 -> 1179 bytes
 recipes/telepolis_pl.recipe    |  67 +++++++++++++++++++++++++++++++++
 2 files changed, 67 insertions(+)
 create mode 100644 recipes/icons/telepolis_pl.png
 create mode 100644 recipes/telepolis_pl.recipe

diff --git a/recipes/icons/telepolis_pl.png b/recipes/icons/telepolis_pl.png
new file mode 100644
index 0000000000000000000000000000000000000000..0b94658d947f4785ef1618f478fcad335ceeb748
GIT binary patch
literal 1179
zcmeAS@N?(olHy`uVBq!ia0vp^0wB!61|;P_|4#%`jKx9jP7LeL$-D$|*pj^6T^Rm@
z;DWu&Cj&(|3p^r=85p>QL70(Y)*K0-AbW|YuPgf<4mn|Y=H#{UQy3Unq&;06Lo5Ut
z1z6ty2CAS8Fp{EumWE0@Q2h_69*(pdcPd%1830ts0F=ZgRe>gm-2jkgpdtT}6$8bv
zx)$sLY)(Vg3}d4kvZkb%5#|L9rvWu}05ROZAVc;aIP{-^5#bO=ds{{(kOa{Hr1?LJ
z&lp%h&Isx0MHq`P4ZEut8Btut0@VC}|G~p3#)6!NFb6*i76urq&;tyr0K-)<126)N
zq-eyj9)|$B*MMGUfVlv}X+SeDT!n5f&_K8W=yIT>T!|rwO#tK!bbw6^T@BUvA8$Gt
T<nMcV9b}-VtDnm{r-UW|t!QPU

literal 0
HcmV?d00001

diff --git a/recipes/telepolis_pl.recipe b/recipes/telepolis_pl.recipe
new file mode 100644
index 0000000000..ff4803697f
--- /dev/null
+++ b/recipes/telepolis_pl.recipe
@@ -0,0 +1,67 @@
+#!/usr/bin/env  python
+
+__license__ = 'GPL v3'
+
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+
+
+class telepolis(BasicNewsRecipe):
+    title = u'Telepolis.pl'
+    __author__ = 'Artur Stachecki <artur.stachecki@gmail.com>'
+    language = 'pl'
+    description = u'Twój telekomunikacyjny serwis informacyjny.\
+                  Codzienne informacje, testy i artykuły,\
+                  promocje, baza telefonów oraz centrum rozrywki'
+    oldest_article = 7
+    masthead_url = 'http://telepolis.pl/i/telepolis-logo2.gif'
+    max_articles_per_feed = 100
+    simultaneous_downloads = 5
+    remove_javascript = True
+    no_stylesheets = True
+    use_embedded_content = False
+
+    remove_tags = []
+    remove_tags.append(dict(attrs={'alt': 'TELEPOLIS.pl'}))
+
+    preprocess_regexps = [(re.compile(r'<: .*? :>'),
+                           lambda match: ''),
+                          (re.compile(r'<b>Zobacz:</b>.*?</a>', re.DOTALL),
+                           lambda match: ''),
+                          (re.compile(r'<-ankieta.*?>'),
+                           lambda match: ''),
+                          (re.compile(r'\(Q\!\)'),
+                           lambda match: ''),
+                          (re.compile(r'\(plik.*?\)'),
+                           lambda match: ''),
+                          (re.compile(r'<br.*?><br.*?>', re.DOTALL),
+                           lambda match: '')
+                          ]
+
+    extra_css = '''.tb { font-weight: bold; font-size: 20px;}'''
+
+    feeds = [
+        (u'Wiadomości', u'http://www.telepolis.pl/rss/news.php'),
+        (u'Artykuły', u'http://www.telepolis.pl/rss/artykuly.php')
+    ]
+
+    def print_version(self, url):
+        if 'news.php' in url:
+            print_url = url.replace('news.php', 'news_print.php')
+        else:
+            print_url = url.replace('artykuly.php', 'art_print.php')
+        return print_url
+
+    def preprocess_html(self, soup):
+        for image in soup.findAll('img'):
+            if 'm.jpg' in image['src']:
+                image_big = image['src']
+                image_big = image_big.replace('m.jpg', '.jpg')
+                image['src'] = image_big
+        logo = soup.find('tr')
+        logo.extract()
+        for tag in soup.findAll('tr'):
+            for strings in ['Wiadomość wydrukowana', 'copyright']:
+                if strings in self.tag_to_string(tag):
+                    tag.extract()
+        return self.adeify_images(soup)