From: Dylan Lloyd <dylan@psu.edu>
Date: Tue, 25 Jan 2011 02:24:06 +0000 (-0500)
Subject: Rewriting the parsing code to use HTMLParser
X-Git-Url: https://disinclined.org/git/?a=commitdiff_plain;h=f365c39a36f222266a8140d702dcd4c6549a6431;p=i_like_pandora.git

Rewriting the parsing code to use HTMLParser

HTMLParser is a standard library and should be faster too, although I'd imagine the biggest bottleneck is fetching the files with urllib.

To keep things simple, I just made a new file for now called htmlparse.py to work on it, I'll probably put them together later.
---

diff --git a/htmlparse.py b/htmlparse.py
new file mode 100755
index 0000000..3447cd8
--- /dev/null
+++ b/htmlparse.py
@@ -0,0 +1,41 @@
+#!/usr/bin/env python
+from HTMLParser import HTMLParser
+import urllib
+
+USER = 'alphabethos'
+
+class parse(HTMLParser):
+
+    def __init__(self, data, mode):
+        HTMLParser.__init__(self)
+        print mode
+        self.__in_row = False
+        self.station_tokens = []
+        self.feed(data)
+
+    def handle_starttag(self, tag, attrs):
+        if tag == 'div':
+            for attr, value in attrs:
+                if attr == 'class' and value == 'station_table_row':
+                    self.__in_row = True
+                    continue
+        if tag == 'a':
+            for attr, value in attrs:
+                if attr == 'href' and self.__in_row:
+                    self.station_tokens.append(value[10:])
+                    continue
+
+    def handle_data(self, text):
+        pass
+
+    def handle_endtag(self, tag):
+        self.__in_row = False
+        pass
+
+
+page = urllib.urlopen('http://www.pandora.com/favorites/profile_tablerows_station.vm?webname=' + USER).read()
+#page = urllib.urlopen('http://www.pandora.com/favorites/station_tablerows_thumb_up.vm?token=' + station + '&sort_col=thumbsUpDate')
+#page = urllib.urlopen(search_url)
+p = parse(page, 'stations')
+p = parse(page, 'tracks')
+print p.station_tokens