[DoNotCommit] telemetry: Retrieve per-allocator memory usage

tools/perf/page_sets/alexa_top_500.py

+# Copyright 2015 The Chromium Authors. All rights reserved.
+# Use of this source code is governed by a BSD-style license that can be
+# found in the LICENSE file.
+import json
+import os
+
+from telemetry.page import page as page_module
+from telemetry.page import shared_page_state
+from telemetry import story
+
+
+_ALEXA_TOP500_JSON = os.path.join(
+    os.path.abspath(os.path.dirname(__file__)), 'alexa_top_500.json')
+_ALEXA_TOP500_JSON_BLACKLIST = os.path.join(
+    os.path.abspath(os.path.dirname(__file__)), 'alexa_top_500_blacklist.json')
+
+class AlexaTop500Page(page_module.Page):
+
+  def __init__(self, url, page_set):
+    super(AlexaTop500Page, self).__init__(
+        url=url, page_set=page_set,
+        shared_page_state_class=shared_page_state.SharedDesktopPageState)
+
+  def RunPageInteractions(self, action_runner):
+    with action_runner.CreateGestureInteraction('ScrollAction'):
+      action_runner.ScrollPage()
+
+
+class AlexaTop500PageSet(story.StorySet):
+  def __init__(self):
+    super(AlexaTop500PageSet, self).__init__(
+      archive_data_file='data/alexa_top_500.json',
+    )
+
+    excludes = set([
+      'qq.com',
+      'telegraph.co.uk',
+      'googleusercontent.com',
+      'nba.com',
+      'seznam.cz',
+      'sina.com.cn',
+      'youku.com',
+      'zhihu.com',
+      'huffingtonpost.com',
+      't-online.de',
+    ])
+
+    # with open(_ALEXA_TOP500_JSON_BLACKLIST) as f:
+    #   excludes = set(json.load(f))
+
+    sites = []
+    with open(_ALEXA_TOP500_JSON) as f:
+      site_entries = json.load(f)
+      for entry in site_entries:
+        if entry['url'] in excludes:
+          continue
+        sites.append(entry['url'])
+
+    MAX_PAGES = 300
+    for i, site in enumerate(sites):
+      if i < MAX_PAGES:
+        self.AddStory(AlexaTop500Page('http://' + site, self))