OLD | NEW |
---|---|
(Empty) | |
1 // Copyright 2017 The Chromium Authors. All rights reserved. | |
2 // Use of this source code is governed by a BSD-style license that can be | |
3 // found in the LICENSE file. | |
4 | |
5 #include "chrome/browser/page_load_metrics/ads_detection.h" | |
6 | |
7 #include <memory> | |
8 #include <string> | |
9 #include <utility> | |
10 | |
11 #include "base/logging.h" | |
12 #include "base/macros.h" | |
13 #include "base/memory/ptr_util.h" | |
14 #include "base/strings/string_util.h" | |
15 #include "base/supports_user_data.h" | |
16 #include "content/public/browser/navigation_handle.h" | |
17 #include "content/public/browser/render_frame_host.h" | |
18 #include "content/public/browser/web_contents.h" | |
19 #include "url/gurl.h" | |
20 | |
jkarlin
2017/07/19 13:32:36
page_load_metrics namespace
Łukasz Anforowicz
2017/07/19 18:11:29
Done.
| |
21 namespace { | |
22 | |
23 bool IsGoogleAd(content::NavigationHandle* navigation_handle) { | |
24 // Because sub-resource filtering isn't always enabled, and doesn't work | |
25 // well in monitoring mode (no CSS enforcement), it's difficult to identify | |
26 // ads. Google ads are prevalent and easy to track, so we'll start by | |
27 // tracking those. Note that the frame name can be very large, so be careful | |
28 // to avoid full string searches if possible. | |
29 // TODO(jkarlin): Track other ad networks that are easy to identify. | |
30 | |
31 // In case the navigation aborted, look up the RFH by the Frame Tree Node | |
32 // ID. It returns the committed frame host or the initial frame host for the | |
33 // frame if no committed host exists. Using a previous host is fine because | |
34 // once a frame has an ad we always consider it to have an ad. | |
35 // We use the unsafe method of FindFrameByFrameTreeNodeId because we're not | |
36 // concerned with which process the frame lives on (we're just measuring | |
37 // bytes and not granting security priveleges). | |
38 content::RenderFrameHost* current_frame_host = | |
39 navigation_handle->GetWebContents()->UnsafeFindFrameByFrameTreeNodeId( | |
40 navigation_handle->GetFrameTreeNodeId()); | |
41 if (current_frame_host) { | |
42 const std::string& frame_name = current_frame_host->GetFrameName(); | |
43 if (base::StartsWith(frame_name, "google_ads_iframe", | |
44 base::CompareCase::SENSITIVE) || | |
45 base::StartsWith(frame_name, "google_ads_frame", | |
46 base::CompareCase::SENSITIVE)) { | |
47 return true; | |
48 } | |
49 } | |
50 | |
51 const GURL& frame_url = navigation_handle->GetURL(); | |
52 if (frame_url.host_piece() == "tpc.googlesyndication.com" && | |
53 base::StartsWith(frame_url.path_piece(), "/safeframe", | |
54 base::CompareCase::SENSITIVE)) { | |
55 return true; | |
56 } | |
57 | |
58 return false; | |
59 } | |
60 | |
61 class NavigationHandleAdsData : public base::SupportsUserData::Data { | |
62 public: | |
63 static NavigationHandleAdsData* GetOrCreate( | |
64 content::NavigationHandle* navigation_handle) { | |
65 DCHECK(navigation_handle); | |
66 NavigationHandleAdsData* ads_data = static_cast<NavigationHandleAdsData*>( | |
67 navigation_handle->GetUserData(kUserDataKey)); | |
68 if (!ads_data) { | |
69 std::unique_ptr<NavigationHandleAdsData> new_ads_data = | |
70 base::MakeUnique<NavigationHandleAdsData>(); | |
71 if (IsGoogleAd(navigation_handle)) | |
jkarlin
2017/07/19 13:32:36
The NavigationHandleAdsData might be created earli
Łukasz Anforowicz
2017/07/19 18:11:29
Good point (and sort of "done"), but:
1. Repeated
jkarlin
2017/07/20 16:51:51
The calculation cost isn't terrible, but I'd prefe
Łukasz Anforowicz
2017/07/20 17:33:51
Done.
| |
72 new_ads_data->ad_types().set(AD_TYPE_GOOGLE); | |
73 | |
74 // It is safe to retain |ads_data| raw pointer, despite passing an | |
75 // ownership of |new_ads_data| to SetUserData, because |navigation_handle| | |
76 // will keep the NavigationHandleAdsData instance alive until the | |
77 // |navigation_handle| is destroyed. | |
78 ads_data = new_ads_data.get(); | |
79 | |
80 navigation_handle->SetUserData(kUserDataKey, std::move(new_ads_data)); | |
81 } | |
82 | |
83 return ads_data; | |
84 } | |
85 | |
86 NavigationHandleAdsData() = default; | |
87 ~NavigationHandleAdsData() override {} | |
88 | |
89 AdTypes& ad_types() { return ad_types_; } | |
90 const AdTypes& ad_types() const { return ad_types_; } | |
91 | |
92 private: | |
93 AdTypes ad_types_; | |
94 | |
95 static const char kUserDataKey[]; | |
96 | |
97 DISALLOW_COPY_AND_ASSIGN(NavigationHandleAdsData); | |
98 }; | |
99 | |
100 const char NavigationHandleAdsData::kUserDataKey[] = "AdsData"; | |
101 | |
102 } // namespace | |
103 | |
104 const AdTypes& GetDetectedAdTypes( | |
105 content::NavigationHandle* navigation_handle) { | |
106 DCHECK(navigation_handle); | |
jkarlin
2017/07/19 13:32:35
An indirect (but better than nothing) way to verif
Łukasz Anforowicz
2017/07/19 18:11:29
Done, although this is somewhat tricky in case the
Łukasz Anforowicz
2017/07/19 22:44:26
Actually this didn't quite work with PlzNavigate:
jkarlin
2017/07/20 16:51:51
Sorry, I should have realized that it wouldn't wor
Łukasz Anforowicz
2017/07/20 17:33:51
I've added a TODO here.
| |
107 return NavigationHandleAdsData::GetOrCreate(navigation_handle)->ad_types(); | |
108 } | |
109 | |
110 void SetDetectedAdTypes(content::NavigationHandle* navigation_handle, | |
111 AdType type) { | |
112 DCHECK(navigation_handle); | |
113 NavigationHandleAdsData::GetOrCreate(navigation_handle)->ad_types().set(type); | |
114 } | |
OLD | NEW |