Let's not talk about anything else. Code , The code is very simple, do not understand the message. Code
1 Using System;
2 Using System. Collections. Generic;
3 Using System. LINQ;
4 Using System. text;
5 Using System. runtime. interopservices;
6 Using Mshtml;
7 Using System. Threading;
8 Using System. runtime. interopservices. comtypes;
9 Using System. IO;
10
11 Namespace Eric. Utilities. html
12 {
13 Public Enum Hresult
14 {
15 E_fail = - 2147467259 ,
16 E_invalidarg = - 2147024809 ,
17 E_nointerface = - 2147467262 ,
18 E_notimpl = - 2147467263 ,
19 E_unexpected = - 2147418113 ,
20 S_false = 1 ,
21 S_ OK = 0
22 }
23
24 [Comimport, GUID ( " 0000010c-0000-0000-c000-000000000046 " ), Interfacetype (cominterfacetype. interfaceisiunknown), comvisible ( True )]
25 Public Interface Ipersist
26 {
27VoidGetclassid (RefGuid pclassid );
28}
29
30 [Comimport, interfacetype (cominterfacetype. interfaceisiunknown), comvisible ( True ), GUID ( " 7fd52380-4e07-101b-ae2d-08002b2ec713 " )]
31 Public Interface Ipersiststreaminit: ipersist
32 {
33 New Void Getclassid ( Ref Guid pclassid );
34 [Preservesig]
35 Int Isdirty ();
36 [Preservesig]
37 Hresult load (istream PSTM );
38 [Preservesig]
39 Hresult save (istream PSTM, [financialas (unmanagedtype. bool)] Bool Fcleardirty );
40 [Preservesig]
41 Hresult getsizemax ([In, out, financialas (unmanagedtype. u8)] Ref Long Pcbsize );
42 [Preservesig]
43 Hresult initnew ();
44 }
45
46 Public Class Htmlparser
47 {
48 Public Ihtmldocument3 parse ( String URL)
49 {
50 Htmldocument objmshtml = New Htmldocument ();
51 Ihtmldocument2 objmshtml2;
52 Ihtmldocument3 objmshtml3;
53
54 Ipersiststreaminit objips;
55 Objips = Objmshtml As Ipersiststreaminit;
56 Objips. initnew ();
57 Objips = Null ;
58
59 Objmshtml2 = Objmshtml. createdocumentfromurl (URL, " Null " );
60 While (Objmshtml2.readystate ! = " Complete " )
61 {
62Thread. Sleep (1000);
63}
64 Objmshtml3 = Objmshtml2 As Ihtmldocument3;
65 Return Objmshtml3;
66 }
67
68 Public Ihtmldocument3 parsehtml ( String HTML, encoding)
69 {
70 String Tmpfile = Path. gettempfilename ();
71 File. writealltext (tmpfile, HTML, encoding );
72 Return Parse (tmpfile );
73 }
74 }
75 }
76
To solve this problem, we first created a temporary file for parsehtml. If we wanted to create a temporary file, we could not do it directly, but we had to use the makup service on the Internet, but I found it unavailable. I wonder if you have any good solutions.
