使用XPATH和HTMLCleaner解析HTML/XML（UsingXPATHandHTMLCleanertoparseHTML/XML）_html/css_WEB-ITnose

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

23

24

25

26

27

28

29

30

31

32

33

34

35

36

37

38

39

40

41

42

43

44

45

46

47

48

49

50

51

52

53

54

55

56

57

58

59

60

61

62

63

64

65

66

public class OptionScraper {

// EXAMPLE XPATH QUERIES IN THE FORM OF STRINGS - WILL BE USED LATER

private static final String NAME_XPATH = "//div[@class='yfi_quote']/div[@class='hd']/h2" ;

private static final String TIME_XPATH = "//table[@id='time_table']/tbody/tr/td[@class='yfnc_tabledata1']" ;

private static final String PRICE_XPATH = "//table[@id='price_table']//tr//span" ;

// TAGNODE OBJECT, ITS USE WILL COME IN LATER

private static TagNode node;

// A METHOD THAT HELPS ME RETRIEVE THE STOCK OPTION'S DATA BASED OFF THE NAME (I.E. GOUAA IS ONE OF GOOGLE'S STOCK OPTIONS)

public static Option getOptionFromName(String name) throws XPatherException, ParserConfigurationException,SAXException, IOException, XPatherException {

// THE URL WHOSE HTML I WANT TO RETRIEVE AND PARSE

String option_url = " http://finance.yahoo.com/q?s=" + name.toUpperCase();

// THIS IS WHERE THE HTMLCLEANER COMES IN, I INITIALIZE IT HERE

HtmlCleaner cleaner = new HtmlCleaner();

CleanerProperties props = cleaner.getProperties();

props.setAllowHtmlInsideAttributes( true );

props.setAllowMultiWordAttributes( true );

props.setRecognizeUnicodeChars( true );

props.setOmitComments( true );

// OPEN A CONNECTION TO THE DESIRED URL

URL url = new URL(option_url);

URLConnection conn = url.openConnection();

//USE THE CLEANER TO "CLEAN" THE HTML AND RETURN IT AS A TAGNODE OBJECT

node = cleaner.clean( new InputStreamReader(conn.getInputStream()));

// ONCE THE HTML IS CLEANED, THEN YOU CAN RUN YOUR XPATH EXPRESSIONS ON THE NODE, WHICH WILL THEN RETURN AN ARRAY OF TAGNODE OBJECTS (THESE ARE RETURNED AS OBJECTS BUT GET CASTED BELOW)

Object[] info_nodes = node.evaluateXPath(NAME_XPATH);

Object[] time_nodes = node.evaluateXPath(TIME_XPATH);

Object[] price_nodes = node.evaluateXPath(PRICE_XPATH);

// HERE I JUST DO A SIMPLE CHECK TO MAKE SURE THAT MY XPATH WAS CORRECT AND THAT AN ACTUAL NODE(S) WAS RETURNED

if (info_nodes.length > 0 ) {

// CASTED TO A TAGNODE

TagNode info_node = (TagNode) info_nodes[ 0 ];

// HOW TO RETRIEVE THE CONTENTS AS A STRING

String info = info_node.getChildren().iterator().next().toString().trim();

// SOME METHOD THAT PROCESSES THE STRING OF INFORMATION (IN MY CASE, THIS WAS THE STOCK QUOTE, ETC)

processInfoNode(o, info);

}

if (time_nodes.length > 0 ) {

TagNode time_node = (TagNode) time_nodes[ 0 ];

String date = time_node.getChildren().iterator().next().toString().trim();

// DATE RETURNED IN 15-JAN-10 FORMAT, SO THIS IS SOME METHOD I WROTE TO JUST PARSE THAT STRING INTO THE FORMAT THAT I USE

processDateNode(o, date);

}

if (price_nodes.length > 0 ) {

TagNode price_node = (TagNode) price_nodes[ 0 ];

double price = Double.parseDouble(price_node.getChildren().iterator().next().toString().trim());

o.setPremium(price);

}

return o;

}

}