java动态爬虫jsoup以及正则表达式的运用

1  Document doc = Jsoup
2                     .connect(url)
3                     .userAgent(
4                             "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:37.0) Gecko/20100101 Firefox/37.0)") // 设置User-Agent
5                     .timeout(5000) // 设置连接超时时间
6                     .get();

 1 Elements elements = doc.getElementsByClass("desc");
 2 Elements subelements = elements.get(0).getElementsByTag("li");
 3  Elements dayElements = eachDayElement.getElementsByTag("tr");
 4  Elements firstSubElements = firstElement.getElementsByTag("td");
 5 String text = elements.get(0).text();
 6 private static String regEx_publishDate = "由中央气象台\\s*(\\d+):(\\d+)\\s*发布的";
 7     private static Pattern pattern_publishDate = Pattern
 8             .compile(regEx_publishDate);
 9 Matcher matcher = pattern_publishDate.matcher(text);
10 if (matcher.find()) {
11             int hour = Integer.parseInt(matcher.group(1));
12             int minute = Integer.parseInt(matcher.group(2));}

1 (\\d{4})-(\\d{2})-(\\d{2})\\s+(\\d{2}):(\\d{2})发布
2 (\\S+过敏\\S+)：\\s+(\\S+)\\s+(\\S+)
3 \\s+(感冒\\S+)：\\s+(\\S+)\\s+(\\S+)
4 \\s*(\\S+)\\s*
5 首要污染物：\\s*(\\S+)\\s*"