1 /* 2 * Copyright (C) 2009 Google Inc. All rights reserved. 3 * 4 * Redistribution and use in source and binary forms, with or without 5 * modification, are permitted provided that the following conditions are 6 * met: 7 * 8 * * Redistributions of source code must retain the above copyright 9 * notice, this list of conditions and the following disclaimer. 10 * * Redistributions in binary form must reproduce the above 11 * copyright notice, this list of conditions and the following disclaimer 12 * in the documentation and/or other materials provided with the 13 * distribution. 14 * * Neither the name of Google Inc. nor the names of its 15 * contributors may be used to endorse or promote products derived from 16 * this software without specific prior written permission. 17 * 18 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 19 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT 20 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR 21 * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT 22 * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, 23 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT 24 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, 25 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY 26 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT 27 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE 28 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 29 */ 30 31 #ifndef WebPageSerializer_h 32 #define WebPageSerializer_h 33 34 #include "../platform/WebCString.h" 35 #include "../platform/WebCommon.h" 36 #include "../platform/WebURL.h" 37 #include "WebFrame.h" 38 39 namespace blink { 40 class WebPageSerializerClient; 41 class WebString; 42 class WebView; 43 template <typename T> class WebVector; 44 45 // Get html data by serializing all frames of current page with lists 46 // which contain all resource links that have local copy. 47 class WebPageSerializer { 48 public: 49 struct Resource { 50 WebURL url; 51 WebCString mimeType; 52 WebCString data; 53 }; 54 55 // Serializes all the frames from the WebView, retrieves the page's 56 // resources (such as images and CSS) and adds them to the passed vector. 57 // The first resource in that vector is the top frame contents. 58 // Note that this also strips-out any script tag or link to JavaScript. 59 BLINK_EXPORT static void serialize(WebView*, WebVector<Resource>*); 60 61 // Serializes the WebView contents to a MHTML representation. 62 BLINK_EXPORT static WebCString serializeToMHTML(WebView*); 63 64 // Similar to serializeToMHTML but uses binary encoding for the MHTML parts. 65 // This results in a smaller MHTML file but it might not be supported by other browsers. 66 BLINK_EXPORT static WebCString serializeToMHTMLUsingBinaryEncoding(WebView*); 67 68 // IMPORTANT: 69 // The API below is an older implementation of a pageserialization that 70 // will be removed soon. 71 72 73 // This function will find out all frames and serialize them to HTML data. 74 // We have a data buffer to temporary saving generated html data. We will 75 // sequentially call WebPageSeriazlierClient once the data buffer is full. 76 // 77 // Return false means no available frame has been serialized, otherwise 78 // return true. 79 // 80 // The parameter frame specifies which frame need to be serialized. 81 // The parameter recursive specifies whether we need to 82 // serialize all sub frames of the specified frame or not. 83 // The parameter client specifies the pointer of interface 84 // WebPageSerializerClient providing a sink interface to receive the 85 // individual chunks of data to be saved. 86 // The parameter links contain original URLs of all saved links. 87 // The parameter localPaths contain corresponding local file paths of all 88 // saved links, which matched with vector:links one by one. 89 // The parameter localDirectoryName is relative path of directory which 90 // contain all saved auxiliary files included all sub frames and resources. 91 BLINK_EXPORT static bool serialize( 92 WebLocalFrame*, 93 bool recursive, 94 WebPageSerializerClient*, 95 const WebVector<WebURL>& links, 96 const WebVector<WebString>& localPaths, 97 const WebString& localDirectoryName); 98 99 // Retrieve all the resource for the passed view, including the main frame 100 // and sub-frames. Returns true if all resources were retrieved 101 // successfully. 102 BLINK_EXPORT static bool retrieveAllResources(WebView*, 103 const WebVector<WebCString>& supportedSchemes, 104 WebVector<WebURL>* resources, 105 WebVector<WebURL>* frames); 106 107 // FIXME: The following are here for unit testing purposes. Consider 108 // changing the unit tests instead. 109 110 // Generate the META for charset declaration. 111 BLINK_EXPORT static WebString generateMetaCharsetDeclaration(const WebString& charset); 112 // Generate the MOTW declaration. 113 BLINK_EXPORT static WebString generateMarkOfTheWebDeclaration(const WebURL&); 114 // Generate the default base tag declaration. 115 BLINK_EXPORT static WebString generateBaseTagDeclaration(const WebString& baseTarget); 116 }; 117 118 } // namespace blink 119 120 #endif 121