質問編集履歴
1
ソースコード追加
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -1,32 +1,140 @@
|
|
|
1
1
|
HTMLページの<p><p></p></p>で囲まれた文章をC++で表示したいのですが、うまくいきません。
|
|
2
2
|
|
|
3
|
-
なに
|
|
3
|
+
なにか良い方法はありませんか？？
|
|
4
4
|
|
|
5
|
-
現在こんな感じのプログラムでやってます
|
|
5
|
+
現在こんな感じのプログラムでやってます
|
|
6
6
|
|
|
7
7
|
|
|
8
8
|
|
|
9
9
|
---------------------------------------------------
|
|
10
10
|
|
|
11
|
-
/
|
|
11
|
+
#include <libxml/HTMLparser.h>
|
|
12
12
|
|
|
13
|
-
i
|
|
13
|
+
#include <iostream>
|
|
14
14
|
|
|
15
|
-
|
|
15
|
+
#include <string>
|
|
16
16
|
|
|
17
|
-
|
|
17
|
+
#include <fstream>
|
|
18
18
|
|
|
19
|
-
|
|
19
|
+
#include <stdio.h>
|
|
20
20
|
|
|
21
|
-
|
|
21
|
+
#include <string.h>
|
|
22
22
|
|
|
23
|
-
|
|
23
|
+
#include <stdlib.h>
|
|
24
24
|
|
|
25
|
-
}
|
|
26
25
|
|
|
26
|
+
|
|
27
|
+
using namespace std;
|
|
28
|
+
|
|
29
|
+
|
|
30
|
+
|
|
31
|
+
void FindInfo(xmlNode*& element);
|
|
32
|
+
|
|
33
|
+
|
|
34
|
+
|
|
35
|
+
int main() {
|
|
36
|
+
|
|
37
|
+
//HTML用の構造体
|
|
38
|
+
|
|
39
|
+
htmlDocPtr m_doc;
|
|
40
|
+
|
|
41
|
+
|
|
42
|
+
|
|
43
|
+
// ファイル名とエンコードの設定
|
|
44
|
+
|
|
45
|
+
char* file = "http://www.visit-hokkaido.jp/article/detail/2";
|
|
46
|
+
|
|
47
|
+
char* enc = "utf-8";
|
|
48
|
+
|
|
49
|
+
// xmlの読み込み
|
|
50
|
+
|
|
51
|
+
if (m_doc = htmlReadFile(file, enc, HTML_PARSE_RECOVER)) {
|
|
52
|
+
|
|
53
|
+
htmlNodePtr root = xmlDocGetRootElement(m_doc);
|
|
54
|
+
|
|
55
|
+
if (root != NULL) {
|
|
56
|
+
|
|
57
|
+
FindInfo(root);
|
|
58
|
+
|
|
27
|
-
|
|
59
|
+
}
|
|
60
|
+
|
|
61
|
+
xmlFreeDoc(m_doc);
|
|
62
|
+
|
|
63
|
+
m_doc = NULL;
|
|
64
|
+
|
|
65
|
+
}
|
|
66
|
+
|
|
67
|
+
|
|
68
|
+
|
|
69
|
+
xmlCleanupParser();
|
|
70
|
+
|
|
71
|
+
xmlCleanupCharEncodingHandlers();
|
|
72
|
+
|
|
73
|
+
return;
|
|
28
74
|
|
|
29
75
|
}
|
|
76
|
+
|
|
77
|
+
|
|
78
|
+
|
|
79
|
+
//地域
|
|
80
|
+
|
|
81
|
+
void FindInfo(xmlNode*& element){
|
|
82
|
+
|
|
83
|
+
char* count;
|
|
84
|
+
|
|
85
|
+
for (htmlNodePtr node = element; node != NULL; node = node->next){
|
|
86
|
+
|
|
87
|
+
//<p><p>
|
|
88
|
+
|
|
89
|
+
count = (char *)node->next->next->children->content;
|
|
90
|
+
|
|
91
|
+
string a = count;
|
|
92
|
+
|
|
93
|
+
printf("%s\n",count);
|
|
94
|
+
|
|
95
|
+
if(xmlStrcasecmp(node->name, (const xmlChar*)"p") == 0){
|
|
96
|
+
|
|
97
|
+
for(xmlAttrPtr attr = node->properties; attr != NULL; attr = attr->next){
|
|
98
|
+
|
|
99
|
+
if(xmlStrcasecmp(node->name, (const xmlChar*)"p") == 0){
|
|
100
|
+
|
|
101
|
+
count = (char *)node->next->next->children->content;
|
|
102
|
+
|
|
103
|
+
string a = count;
|
|
104
|
+
|
|
105
|
+
printf("%s\n",count);
|
|
106
|
+
|
|
107
|
+
}
|
|
108
|
+
|
|
109
|
+
}
|
|
110
|
+
|
|
111
|
+
}
|
|
112
|
+
|
|
113
|
+
|
|
114
|
+
|
|
115
|
+
|
|
116
|
+
|
|
117
|
+
|
|
118
|
+
|
|
119
|
+
|
|
120
|
+
|
|
121
|
+
|
|
122
|
+
|
|
123
|
+
//再起読み込み
|
|
124
|
+
|
|
125
|
+
if(node->children != NULL)
|
|
126
|
+
|
|
127
|
+
{
|
|
128
|
+
|
|
129
|
+
FindInfo(node->children);
|
|
130
|
+
|
|
131
|
+
}
|
|
132
|
+
|
|
133
|
+
}
|
|
134
|
+
|
|
135
|
+
}
|
|
136
|
+
|
|
137
|
+
|
|
30
138
|
|
|
31
139
|
|
|
32
140
|
|