回答編集履歴
2
XMLAgilityPackの例を追加しました.
answer
CHANGED
@@ -86,4 +86,42 @@
|
|
86
86
|
</tempDataRoot>
|
87
87
|
```
|
88
88
|
|
89
|
-
入力はたまたまXHTMLでした.他のダーティーなのでも試した方が良いのでしょうけれども、私の家は冷房なしでこれ以上気力が持ちません... あと普段まずVisual Studioを立ち上げる機会はゼロです.おかしな点があるかもしれません、ご容赦ください.
|
89
|
+
入力はたまたまXHTMLでした.他のダーティーなのでも試した方が良いのでしょうけれども、私の家は冷房なしでこれ以上気力が持ちません... あと普段まずVisual Studioを立ち上げる機会はゼロです.おかしな点があるかもしれません、ご容赦ください.
|
90
|
+
|
91
|
+
[追記]
|
92
|
+
> HtmlAgilityPackを使ってみましたが結果は散々でした.
|
93
|
+
|
94
|
+
HtmlAgilityPackでもいろいろやった末、以下のコードで動きました.エンコーディングの指定が要るようです.
|
95
|
+
|
96
|
+
```vb
|
97
|
+
Imports System.Text.Encoding
|
98
|
+
Imports System.Net
|
99
|
+
Imports HtmlAgilityPack
|
100
|
+
|
101
|
+
...
|
102
|
+
|
103
|
+
Sub Main()
|
104
|
+
Dim xw As XmlWriter = CreateXmlWriter("maxTemp.xml")
|
105
|
+
xw.WriteStartElement("tempDataRoot", "")
|
106
|
+
Dim wc As WebClient = New WebClient()
|
107
|
+
wc.Encoding = UTF8
|
108
|
+
Dim htmlSource As String = wc.DownloadString("http://www.data.jma.go.jp/obd/stats/data/mdrr/synopday/data1s.html")
|
109
|
+
Dim doc As HtmlDocument = New HtmlDocument()
|
110
|
+
doc.LoadHtml(htmlSource)
|
111
|
+
Dim trs = doc.DocumentNode.SelectNodes("//table[@class = 'o1']//tr[@class != 'o1h']")
|
112
|
+
For Each tr In trs
|
113
|
+
Dim tds As IEnumerable(Of HtmlNode) = tr.Elements("td")
|
114
|
+
Dim tdArray As HtmlNode() = tds.ToArray
|
115
|
+
Dim regionTd As HtmlNode = tdArray(0)
|
116
|
+
Dim maxTempTd As HtmlNode = tdArray(6)
|
117
|
+
xw.WriteStartElement("tempData")
|
118
|
+
xw.WriteAttributeString("region", regionTd.InnerText)
|
119
|
+
xw.WriteAttributeString("maxTemp", maxTempTd.InnerText)
|
120
|
+
Debug.WriteLine("region={0} max-temp={1}", regionTd.InnerText, maxTempTd.InnerText)
|
121
|
+
xw.WriteEndElement()
|
122
|
+
Next
|
123
|
+
xw.WriteEndElement()
|
124
|
+
xw.Close()
|
125
|
+
End Sub
|
126
|
+
|
127
|
+
```
|
1
サンプルプログラムを追加しました.
answer
CHANGED
@@ -15,4 +15,75 @@
|
|
15
15
|
|
16
16
|
という訳でMSXMLは入力がXHTMLでない限りあきらめられた方が良いと思います.
|
17
17
|
|
18
|
-
以上 少しでもお役にたてば.
|
18
|
+
以上 少しでもお役にたてば.
|
19
|
+
|
20
|
+
[追記]
|
21
|
+
コメントに書きましたプログラムです.
|
22
|
+
|
23
|
+
```vb
|
24
|
+
Imports System.Xml
|
25
|
+
Imports System.Xml.XPath
|
26
|
+
Imports System.Text.Encoding
|
27
|
+
Imports Sgml
|
28
|
+
Module HtmlXPathModule
|
29
|
+
Sub Main()
|
30
|
+
Dim xw As XmlWriter = CreateXmlWriter("maxTemp.xml")
|
31
|
+
xw.WriteStartElement("tempDataRoot", "")
|
32
|
+
Dim sgml As SgmlReader = New SgmlReader()
|
33
|
+
sgml.DocType = "HTML"
|
34
|
+
sgml.Href = "http://www.data.jma.go.jp/obd/stats/data/mdrr/synopday/data1s.html"
|
35
|
+
sgml.IgnoreDtd = True
|
36
|
+
Dim htmlDoc As XDocument = XDocument.Load(sgml)
|
37
|
+
Dim nsTable As NameTable = New NameTable
|
38
|
+
Dim nsMgr As XmlNamespaceManager = New XmlNamespaceManager(nsTable)
|
39
|
+
nsMgr.AddNamespace("xhtml", "http://www.w3.org/1999/xhtml")
|
40
|
+
Dim targetTrs As IEnumerable(Of XElement) = htmlDoc.XPathSelectElements("//xhtml:table[@class = 'o1']//xhtml:tr[@class != 'o1h']", nsMgr)
|
41
|
+
For Each tr As XElement In targetTrs
|
42
|
+
Dim targetTds As IEnumerable(Of XElement) = tr.Elements
|
43
|
+
Dim tdArray As XElement() = targetTds.ToArray
|
44
|
+
Dim region As XElement = tdArray(0)
|
45
|
+
Dim maxTemp As XElement = tdArray(6)
|
46
|
+
xw.WriteStartElement("tempData")
|
47
|
+
xw.WriteAttributeString("region", "", region.Value)
|
48
|
+
xw.WriteAttributeString("maxTemp", "", maxTemp.Value)
|
49
|
+
xw.WriteEndElement()
|
50
|
+
Next
|
51
|
+
xw.WriteEndElement()
|
52
|
+
xw.Close()
|
53
|
+
End Sub
|
54
|
+
|
55
|
+
Function CreateXmlWriter(outputPath As String) As XmlWriter
|
56
|
+
Dim settings As XmlWriterSettings = New XmlWriterSettings()
|
57
|
+
settings.CloseOutput = True
|
58
|
+
settings.ConformanceLevel = ConformanceLevel.Document
|
59
|
+
settings.Encoding = UTF8
|
60
|
+
settings.Indent = False
|
61
|
+
settings.NewLineChars = vbCrLf
|
62
|
+
settings.NewLineHandling = NewLineHandling.None
|
63
|
+
settings.OmitXmlDeclaration = False
|
64
|
+
settings.WriteEndDocumentOnClose = False
|
65
|
+
Dim xw As XmlWriter = XmlWriter.Create(outputPath, settings)
|
66
|
+
Return xw
|
67
|
+
End Function
|
68
|
+
|
69
|
+
End Module
|
70
|
+
```
|
71
|
+
|
72
|
+
こんなXMLが出ます.(maxTemp.xml)今日は日本列島暑いです.37℃越え(!)のところもあります.
|
73
|
+
|
74
|
+
```XML
|
75
|
+
<?xml version="1.0" encoding="UTF-8"?>
|
76
|
+
<tempDataRoot>
|
77
|
+
<tempData maxTemp="27.1]" region="札幌"/>
|
78
|
+
<tempData maxTemp="26.9]" region="稚内"/>
|
79
|
+
<tempData maxTemp="26.0]" region="北見枝幸"/>
|
80
|
+
...
|
81
|
+
<tempData maxTemp="37.1]" region="鹿児島"/>
|
82
|
+
...
|
83
|
+
<tempData maxTemp="31.3]" region="西表島"/>
|
84
|
+
<tempData maxTemp="33.1]" region="石垣島"/>
|
85
|
+
<tempData maxTemp="" region="昭和"/>
|
86
|
+
</tempDataRoot>
|
87
|
+
```
|
88
|
+
|
89
|
+
入力はたまたまXHTMLでした.他のダーティーなのでも試した方が良いのでしょうけれども、私の家は冷房なしでこれ以上気力が持ちません... あと普段まずVisual Studioを立ち上げる機会はゼロです.おかしな点があるかもしれません、ご容赦ください.
|