从网页中提取日期
|
我想从网页中提取不同格式的日期。我正在使用Selenium2 Java API与浏览器进行交互。我也使用jQuery进一步与文档进行交互。因此，欢迎为这两层提供解决方案。
日期在不同的区域中可以具有非常不同的格式。另外，月份名称可以写为文本或数字。我需要尽可能地匹配日期，并且我知道有很多组合的事实。
例如，如果我有这样的HTML元素：
<div class=\"tag_view\">
Last update: May,22,2011
View :40
</div>
May,22,2011
<span class=\"relativetime\" title=\"2011-05-13 14:45:06Z\">May 13 at 14:45</span>
没有找到相关结果
已邀请:
3 个回复
田眯衅
var datePatterns = new Array(); datePatterns.push(/\\d\\d\\/\\d\\d\\/\\d\\d\\d\\d/g); datePatterns.push(/\\d\\d\\d\\d\\/\\d\\d\\/\\d\\d/g); ... var stringToSearch = $(\'body\').html(); // change this to be more specific if at all possible var allMatches = new Array(); for (datePatternIndex in datePatterns){ allMatches.push(stringToSearch.match(datePatterns[datePatternIndex])); }盛虱
乏摩纶誊伟
/** * Extract date * * @return Date object * @throws ParseException */ public Date extractDate(String text) throws ParseException { Date date = null; boolean dateFound = false; String year = null; String month = null; String monthName = null; String day = null; String hour = null; String minute = null; String second = null; String ampm = null; String regexDelimiter = \"[-:\\\\/.,]\"; String regexDay = \"((?:[0-2]?\\\\d{1})|(?:[3][01]{1}))\"; String regexMonth = \"(?:([0]?[1-9]|[1][012])|(Jan(?:uary)?|Feb(?:ruary)?|Mar(?:ch)?|Apr(?:il)?|May|Jun(?:e)?|Jul(?:y)?|Aug(?:ust)?|Sep(?:tember)?|Sept|Oct(?:ober)?|Nov(?:ember)?|Dec(?:ember)?))\"; String regexYear = \"((?:[1]{1}\\\\d{1}\\\\d{1}\\\\d{1})|(?:[2]{1}\\\\d{3}))\"; String regexHourMinuteSecond = \"(?:(?:\\\\s)((?:[0-1][0-9])|(?:[2][0-3])|(?:[0-9])):([0-5][0-9])(?::([0-5][0-9]))?(?:\\\\s?(am|AM|pm|PM))?)?\"; String regexEndswith = \"(?![\\\\d])\"; // DD/MM/YYYY String regexDateEuropean = regexDay + regexDelimiter + regexMonth + regexDelimiter + regexYear + regexHourMinuteSecond + regexEndswith; // MM/DD/YYYY String regexDateAmerican = regexMonth + regexDelimiter + regexDay + regexDelimiter + regexYear + regexHourMinuteSecond + regexEndswith; // YYYY/MM/DD String regexDateTechnical = regexYear + regexDelimiter + regexMonth + regexDelimiter + regexDay + regexHourMinuteSecond + regexEndswith; // see if there are any matches Matcher m = checkDatePattern(regexDateEuropean, text); if (m.find()) { day = m.group(1); month = m.group(2); monthName = m.group(3); year = m.group(4); hour = m.group(5); minute = m.group(6); second = m.group(7); ampm = m.group(8); dateFound = true; } if(!dateFound) { m = checkDatePattern(regexDateAmerican, text); if (m.find()) { month = m.group(1); monthName = m.group(2); day = m.group(3); year = m.group(4); hour = m.group(5); minute = m.group(6); second = m.group(7); ampm = m.group(8); dateFound = true; } } if(!dateFound) { m = checkDatePattern(regexDateTechnical, text); if (m.find()) { year = m.group(1); month = m.group(2); monthName = m.group(3); day = m.group(3); hour = m.group(5); minute = m.group(6); second = m.group(7); ampm = m.group(8); dateFound = true; } } // construct date object if date was found if(dateFound) { String dateFormatPattern = \"\"; String dayPattern = \"\"; String dateString = \"\"; if(day != null) { dayPattern = \"d\" + (day.length() == 2 ? \"d\" : \"\"); } if(day != null && month != null && year != null) { dateFormatPattern = \"yyyy MM \" + dayPattern; dateString = year + \" \" + month + \" \" + day; } else if(monthName != null) { if(monthName.length() == 3) dateFormatPattern = \"yyyy MMM \" + dayPattern; else dateFormatPattern = \"yyyy MMMM \" + dayPattern; dateString = year + \" \" + monthName + \" \" + day; } if(hour != null && minute != null) { //TODO ampm dateFormatPattern += \" hh:mm\"; dateString += \" \" + hour + \":\" + minute; if(second != null) { dateFormatPattern += \":ss\"; dateString += \":\" + second; } } if(!dateFormatPattern.equals(\"\") && !dateString.equals(\"\")) { //TODO support different locales SimpleDateFormat dateFormat = new SimpleDateFormat(dateFormatPattern.trim(), Locale.US); date = dateFormat.parse(dateString.trim()); } } return date; } private Matcher checkDatePattern(String regex, String text) { Pattern p = Pattern.compile(regex, Pattern.CASE_INSENSITIVE | Pattern.DOTALL); return p.matcher(text); }