Let's get some profiling going.

3 files changed, 33 insertions, 13 deletions

diff --git a/bs4/__init__.py b/bs4/__init__.py
index 0dded3a..4e268ef 100644
--- a/bs4/__init__.py
+++ b/bs4/__init__.py
@@ -208,7 +208,7 @@ class BeautifulSoup(Tag):
         Tag.__init__(self, self, self.builder, self.ROOT_TAG_NAME)
         self.hidden = 1
         self.builder.reset()
-        self.currentData = []
+        self.current_data = []
         self.currentTag = None
         self.tagStack = []
         self.pushTag(self)
@@ -244,21 +244,21 @@ class BeautifulSoup(Tag):
         self.currentTag = self.tagStack[-1]
 
     def endData(self, containerClass=NavigableString):
-        if self.currentData:
-            currentData = u''.join(self.currentData)
-            if (currentData.translate(self.STRIP_ASCII_SPACES) == '' and
+        if self.current_data:
+            current_data = u''.join(self.current_data)
+            if (current_data.translate(self.STRIP_ASCII_SPACES) == '' and
                 not set([tag.name for tag in self.tagStack]).intersection(
                     self.builder.preserve_whitespace_tags)):
-                if '\n' in currentData:
-                    currentData = '\n'
+                if '\n' in current_data:
+                    current_data = '\n'
                 else:
-                    currentData = ' '
-            self.currentData = []
+                    current_data = ' '
+            self.current_data = []
             if self.parse_only and len(self.tagStack) <= 1 and \
                    (not self.parse_only.text or \
-                    not self.parse_only.search(currentData)):
+                    not self.parse_only.search(current_data)):
                 return
-            o = containerClass(currentData)
+            o = containerClass(current_data)
             self.object_was_parsed(o)
 
     def object_was_parsed(self, o, parent=None, most_recent_element=None):
@@ -328,7 +328,7 @@ class BeautifulSoup(Tag):
         self._popToTag(name, nsprefix)
 
     def handle_data(self, data):
-        self.currentData.append(data)
+        self.current_data.append(data)
 
     def decode(self, pretty_print=False,
                eventual_encoding=DEFAULT_OUTPUT_ENCODING,
diff --git a/bs4/diagnose.py b/bs4/diagnose.py
index f9bff28..b6eaa8d 100644
--- a/bs4/diagnose.py
+++ b/bs4/diagnose.py
@@ -1,10 +1,15 @@
 """Diagnostic functions, mainly for use when doing tech support."""
+import cProfile
 from StringIO import StringIO
 from HTMLParser import HTMLParser
+import bs4
 from bs4 import BeautifulSoup, __version__
 from bs4.builder import builder_registry
+
 import os
+import pstats
 import random
+import tempfile
 import time
 import traceback
 import sys
@@ -174,5 +179,21 @@ def benchmark_parsers(num_elements=100000):
     b = time.time()
     print "Raw lxml parsed the markup in %.2fs." % (b-a)
 
+def profile(num_elements=100000, parser="lxml"):
+
+    filehandle = tempfile.NamedTemporaryFile()
+    filename = filehandle.name
+
+    data = rdoc(num_elements)
+    vars = dict(bs4=bs4, data=data, parser=parser)
+    cProfile.runctx('bs4.BeautifulSoup(data, parser)' , vars, vars, filename)
+
+    stats = pstats.Stats(filename)
+    stats.strip_dirs()
+    cumulative = stats.sort_stats("cumulative")
+    total = stats.sort_stats("time")
+    import pdb; pdb.set_trace()
+
 if __name__ == '__main__':
-    diagnose(sys.stdin.read())
+    #diagnose(sys.stdin.read())
+    profile()
diff --git a/bs4/tests/test_soup.py b/bs4/tests/test_soup.py
index 6219b89..910b37e 100644
--- a/bs4/tests/test_soup.py
+++ b/bs4/tests/test_soup.py
@@ -96,7 +96,6 @@ class TestWarnings(SoupTest):
             soup = self.soup("http://www.crummy.com/ is great")
         self.assertEqual(0, len(w))
 
-
 class TestSelectiveParsing(SoupTest):
 
     def test_parse_with_soupstrainer(self):