万网皆可爬-爬虫实战系列之-爬取高分电影拯救无聊的你

Pattern pattern = Pattern.compile("^[-\\+]?[\\d]*$");
Elements page = document.select(".paginator a");
for (Element p : page) {
  String href = p.attr("href");
  String text = p.text();
  if (pattern.matcher(text).matches()) {
    System.out.println(href + " " + text);

  }
}

Element videoItem = item.select(".doulist-video-items").first();
if (videoItem != null) {
  Elements videoAtags = videoItem.getElementsByTag("a");
  for (Element e : videoAtags) {
    String href = e.attr("href");
    String text = e.text();
    if (Objects.equals("更多", text)) {
      continue;
    }
    if (href.contains("www.douban.com/link2")) {
      String urlDecode = URLDecoder.decode(href);

      href = urlDecode.split("=")[1];
    }
    System.out.println(text + "  " + href);
  }

}

Elements itemElements = document.select(".article .doulist-item");
int size = itemElements.size();
for (int i = 0; i < size; i++) {
  Element item = itemElements.get(i);
  Element title = item.selectFirst("div.title");
  Element ratingNums = item.selectFirst(".rating_nums");
  Element rating = item.select(".rating").get(0).getElementsByTag("span").last();

  String titleText = title.text();
  String ratingNumsText = ratingNums.text();
  String ratingText = rating.text().replaceAll("\\(", "").replaceAll("人评价\\)", "");
  System.out.println(titleText);
  System.out.println(ratingNumsText);
  System.out.println(ratingText);
}