From e9dbaad0d71ab580d4303ba622d9690ce8e3471f Mon Sep 17 00:00:00 2001
From: Felix Van der Jeugt <felix.vanderjeugt@gmail.com>
Date: Mon, 26 Jan 2015 14:14:39 +0100
Subject: [PATCH] newsbeuter - scrape mangahere latest to rss

---
 local/bin/mangahere_rss.py | 44 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)
 create mode 100755 local/bin/mangahere_rss.py

diff --git a/local/bin/mangahere_rss.py b/local/bin/mangahere_rss.py
new file mode 100755
index 0000000..edb9c80
--- /dev/null
+++ b/local/bin/mangahere_rss.py
@@ -0,0 +1,44 @@
+#!/usr/bin/python
+
+from pyquery import PyQuery as pq
+from pprint import pprint
+import sys
+
+ITEM = """
+<item>
+    <title>{title}</title>
+    <description>{description}</description>
+    <link>{link}</link>
+</item>"""
+
+class Release(object):
+
+    def __init__(self, title, link):
+        self.title = title
+        self.link = link
+
+    def __str__(self):
+        return ITEM.format(
+            title=self.title,
+            description="New release: {}".format(self.title),
+            link=self.link)
+
+    def __contains__(self, string):
+        return string in self.title or string in self.link
+
+latest = pq(url="http://www.mangahere.co/latest/")
+
+print("""\
+<?xml version="1.0" encoding="UTF-8" ?>
+<rss version="2.0">
+<channel>""")
+
+for item in map(pq, latest("dd > a")):
+    release = Release(item.attr("title"), item.attr("href"))
+    if any(word in release for word in sys.argv):
+        print(str(release))
+
+print("""
+</channel>
+</rss>
+""")