你好!本方法为根据正则表达式获取文本内存在的日期。
由于网站中存在各种类型的日期格式,笔者根据实际匹配情况进行统计,编写方法以匹配大多数日期格式。
代码如下:
/**
*
* @param content 包含日期的原文本
* @return 文本中包含的日期,返回匹配列表
*/
public static List<String> getTime(String content) {
List<String> result = new ArrayList<String>();
// 网站内publish_time的正则表达式种类
// 备注:字符串的顺序不能改变!!!!!!!!!!!!!!!!
String[] regexList = {
"\\d{1,2}\\s*(January|February|March|April|May|June|July|August|September|October|November|December)(\\,)?\\s*\\d{4}",
"(Monday|Tuesday|Wednesday|Thursday|Friday|Saturday|Sunday)\\,\\s*(January|February|March|April|May|June|July|August|September|October|November|December)\\s*\\d{2}\\,\\s*\\d{4}",
"(Monday|Tuesday|Wednesday|Thursday|Friday|Saturday|Sunday)\\,\\d{2}\\s*(January|February|March|April|May|June|July|August|September|October|November|December),\\s*\\d{4}",
"(Monday|Tuesday|Wednesday|Thursday|Friday|Saturday|Sunday)\\,\\s*\\d{2}\\s*(January|February|March|April|May|June|July|August|September|October|November|December)\\s*\\d{4}",
"(Monday|Tuesday|Wednesday|Thursday|Friday|Saturday|Sunday)\\,\\s*\\d{1,2}(st|nd|rd|th)\\s+(Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)\\s*\\d{4}",
"(January|February|March|April|May|June|July|August|September|October|November|December)\\s*\\d{2}\\,\\s*\\d{4}",
"(January|February|March|April|May|June|July|August|September|October|November|December)(\\s*\\d{1,2},)?\\s*\\d{4}",
"(Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)\\s\\d{2}\\,\\s*\\d{4}",
"\\d{2}\\s*(Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)\\s*\\d{4}",
"\\d{1,2}\\s*(Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)\\s*\\d{4}",
"\\d{2}\\s*(Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)",
"\\d{2}\\s*\\d{2}\\s*\\d{4}",
"\\d{1,2}-\\d{2}-\\d{4}",
"\\d{4}-\\d{2}-\\d{2}",
"\\d{4}[\u4e00-\u9fa5]\\d{2}[\u4e00-\u9fa5]\\d{2}[\u4e00-\u9fa5]",
"\\d{2}[\u4e00-\u9fa5]\\d{2}[\u4e00-\u9fa5]\\d{4}[\u4e00-\u9fa5]",
"\\d{2}\\/\\d{2}\\/\\d{4}",
"\\d{4}\\/\\d{1,2}\\/\\d{1,2}",
"\\d{1,2}\\/\\d{4}",
"\\d{1,2}\\/\\d{1,2}",
"\\d{2}\\.\\d{2}\\.\\d{4}",
"\\d{1,2}\\.\\d{2}\\.\\d{4}",
"\\d{4}" };
//循环尝试每个正则表达式
for (String regex : regexList) {
Pattern pattern = Pattern.compile(regex, Pattern.CASE_INSENSITIVE | Pattern.DOTALL);
Matcher match = pattern.matcher(content);
if (match.find()) {
if (TimeRight(match.group(0)))
result.add(match.group(0));
while (match.find()) {
if (TimeRight(match.group(0)))
result.add(match.group(0));
}
break;
} else {
continue;
}
}
return result;
}
在获取匹配日期后,对日期的合法性进行判断,如 2100.9 便为无效日期
public static boolean TimeRight(String string) {
//标志输入的时间是否格式,日期正确
boolean flag = true;
Pattern year_pattern = Pattern.compile("\\d{4}", Pattern.CASE_INSENSITIVE | Pattern.DOTALL);
Matcher year_match = year_pattern.matcher(string);
if (year_match.find()) {
int year = Integer.parseInt(year_match.group(0));
if (1900<=year && year<2020) {
flag = true;
}else {
flag = false;
}
}
return flag;
}
完!