From 481d6638fd0ecf0a92b26c11d06620ba5b5017f6 Mon Sep 17 00:00:00 2001
From: Jan Hoek <github@uncommonsense.nl>
Date: Wed, 29 Mar 2017 20:44:51 +0200
Subject: [PATCH] Testing with regexes for npo.nl episodes

---
 testregex.py | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)
 create mode 100644 testregex.py

diff --git a/testregex.py b/testregex.py
new file mode 100644
index 000000000..5d90ff876
--- /dev/null
+++ b/testregex.py
@@ -0,0 +1,21 @@
+#!/usr/bin/python
+
+import re
+
+npo12files = ['./jinek.htm', './midsomer.htm']
+npo3files = ['./keuringsdienst.htm', './pownews.htm']
+
+npo12regex = r"""<div class='span4'>\s*<div class='image-container'>\s*<a href="(.*?)">\s*(<div class="program-not-available">)?"""
+npo3regex = r"""<div class='span4 image'>\s*<a href="(.*?)">\s*<div class="meta-container">\s*<div class="meta first">\s*<div class="md-label"><span class="npo-glyph triangle-right"></span></div>\s*<div class="md-value">.*?</div>\s*</div>\s*</div>\s*(<div class="program-not-available">)?"""
+
+for filename in npo12files:
+	with open(filename) as f:
+		for match in re.finditer(npo12regex, f.read()):
+			print(match.group(1), match.group(2) is None)
+		print('')
+		
+for filename in npo3files:
+	with open(filename) as f:
+		for match in re.finditer(npo3regex, f.read()):
+			print(match.group(1), match.group(2) is None)
+		print('')
\ No newline at end of file