From: lottaviano <lottaviano@38d2e660-2303-0410-9eaa-f027e97ec537>
Date: Wed, 1 Jul 2009 10:46:44 +0000 (+0000)
Subject: First version of dev status page downloader.
X-Git-Tag: 2.2.0~245
X-Git-Url: https://codewiz.org/gitweb?a=commitdiff_plain;h=7253a8a7aac939250ab75bf05a0a6f34c045c6d3;p=bertos.git

First version of dev status page downloader.

git-svn-id: https://src.develer.com/svnoss/bertos/trunk@2723 38d2e660-2303-0410-9eaa-f027e97ec537
---

diff --git a/doc/dev-status-page.py b/doc/dev-status-page.py
new file mode 100644
index 00000000..9c81cd5c
--- /dev/null
+++ b/doc/dev-status-page.py
@@ -0,0 +1,67 @@
+#!/usr/bin/env python
+from __future__ import with_statement
+import urllib, HTMLParser, os
+
+class PageParser(HTMLParser.HTMLParser):
+	def __init__(self, output_file):
+		HTMLParser.HTMLParser.__init__(self, )
+		self.out_file = open(output_file, "w")
+		self.ignore = 0
+	
+	def __del__(self):
+		self.out_file.close()
+
+	def handle_starttag(self, tag, attrs):
+		d = dict(attrs)
+		if tag == 'head':
+			self.ignore += 1
+		elif tag == 'div':
+			if 'id' in d and (d['id'] == 'banner' or d['id'] == 'mainnav' or d['id'] == 'ctxtnav' \
+					or d['id'] == 'footer' or d['id'] == 'altlinks'):
+				self.ignore += 1
+			elif self.ignore:
+				self.ignore += 1
+		elif tag == 'form':
+			self.ignore += 1
+		elif tag == 'script':
+			self.ignore += 1
+		if not self.ignore:
+			self.out_file.write(self.get_starttag_text())
+
+	def handle_endtag(self, tag):
+		if not self.ignore:
+			#self.out_file.write(self.get_starttag_text() + '\n')
+			self.out_file.write(r'</' + tag + r'>')
+
+		if tag == 'head':
+			self.ignore -= 1
+		elif tag == 'div' and self.ignore:
+			self.ignore -= 1
+		elif tag == 'form':
+			self.ignore -= 1
+		elif tag == 'script':
+			self.ignore -= 1
+
+	def handle_startendtag(self, tag, attrs):
+		if not self.ignore:
+			self.out_file.write(self.get_starttag_text())
+	
+	def handle_data(self, data):
+		if not self.ignore:
+			self.out_file.write(data)
+
+local_file = "dev_status.html"
+stripped_file = "stripped.html"
+urllib.urlretrieve("http://dev.bertos.org/wiki/DevelopmentStatus", local_file)
+development_status_parser = PageParser(stripped_file)
+with open(local_file, "r") as f:
+	for line in f:
+		if line.find('body>') != -1 or line.find('</html') != -1 or line.find('<html') != -1:
+			continue
+		development_status_parser.feed(line)
+	development_status_parser.close()
+
+# TODO: append tabs header
+# TODO: make internal links really internal
+# TODO: rename stripped file?
+os.unlink(local_file)