Java爬虫实践：Jsoup+HttpUnit爬取今日头条、网易、搜狐、凤凰新闻
0x0 背景
最近学习爬虫，分析了几种主流的爬虫框架，决定使用最原始的两大框架进行练手：
Jsoup&HttpUnit
其中jsoup可以获取静态页面，并解析页面标签，最主要的是，可以采用类似于jquery的语法获取想要的标签元素，例如：
//1.获取url地址的网页html
html = Jsoup.connect(url).get();
// 2.jsoup获取新闻标签
Elements newsATags = html.select("div#headLineDefault")
.select("ul.FNewMTopLis")
.select("li")
.select("a");
但是，有些网页（例如今日头条）并非是静态页面，而是在首页加载后通过ajax获取新闻内容然后用js渲染到页面上的。对于这种页面，我们需要使用htmlunit来模拟一个浏览器访问该url，即可获取该页面的html字符串。代码如下：
WebClient webClient = new WebClient(BrowserVersion.CHROME);
webClient.getOptions().setJavaScriptEnabled(true);
webClient.getOptions().setCssEnabled(false);
webClient.getOptions().setActiveXNative(false);
webClient.getOptions().setCssEnabled(false);
webClient.getOptions().setThrowExceptionOnScriptError(false);
webClient.getOptions().setThrowExceptionOnFailingStatusCode(false);
webClient.getOptions().setTimeout(10000);
HtmlPage htmlPage = null;
try {
htmlPage = webClient.getPage(url);
webClient.waitForBackgroundJavaScript(10000);
String htmlString = htmlPage.asXml();
return Jsoup.parse(htmlString);
} finally {
webClient.close();
}
0x1 搜狐、凤凰、网易爬虫
这三家的页面都是静态的，因此代码都差不多，只要分析页面标签找到对应的元素，提取出想要的内容即可。
爬虫基本步骤为以下四步：
（1）获取首页
（2）使用jsoup获取新闻
（3）从
（4）根据新闻url访问新闻页面，获取新闻内容、图片等
1.爬虫接口
一个接口，接口有一个抽象方法pullNews用于拉新闻，有一个默认方法用于获取新闻首页：
public interface NewsPuller {
void pullNews();
// url:即新闻首页url
// useHtmlUnit:是否使用htmlunit
default Document getHtmlFromUrl(String url, boolean useHtmlUnit) throws Exception {
if (!useHtmlUnit) {
return Jsoup.connect(url)
//模拟火狐浏览器
.userAgent("Mozilla/4.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)")
.get();
} else {
WebClient webClient = new WebClient(BrowserVersion.CHROME);
webClient.getOptions().setJavaScriptEnabled(true);
webClient.getOptions().setCssEnabled(false);
webClient.getOptions().setActiveXNative(false);
webClient.getOptions().setCssEnabled(false);
webClient.getOptions().setThrowExceptionOnScriptError(false);
webClient.getOptions().setThrowExceptionOnFailingStatusCode(false);
webClient.getOptions().setTimeout(10000);
HtmlPage htmlPage = null;
try {
htmlPage = webClient.getPage(url);
webClient.waitForBackgroundJavaScript(10000);
String htmlString = htmlPage.asXml();
return Jsoup.parse(htmlString);
} finally {
webClient.close();
}
}
}
}
2.搜狐爬虫
@Component("sohuNewsPuller")
public class SohuNewsPuller implements NewsPuller {
private static final Logger logger = LoggerFactory.getLogger(SohuNewsPuller.class);
@Value("${news.sohu.url}")
private String url;
@Autowired
private NewsService newsService;
@Override
public void pullNews() {
logger.info("开始拉取搜狐新闻！");
// 1.获取首页
Document html= null;
try {
html = getHtmlFromUrl(url, false);
} catch (Exception e) {
logger.error("==============获取搜狐首页失败: {}=============", url);
e.printStackTrace();
return;
}
// 2.jsoup获取新闻标签
Elements newsATags = html.select("div.focus-news")
.select("div.list16")
.select("li")
.select("a");
// 3.从标签中抽取基本信息，封装成news
HashSet newsSet = new HashSet<>();
for (Element a : newsATags) {
String url = a.attr("href");
String title = a.attr("title");
News n = new News();
n.setSource("搜狐");
n.setUrl(url);
n.setTitle(title);
n.setCreateDate(new Date());
newsSet.add(n);
}
// 4.根据新闻url访问新闻，获取新闻内容
newsSet.forEach(news -> {
logger.info("开始抽取搜狐新闻内容：{}", news.getUrl());
Document newsHtml = null;
try {
newsHtml = getHtmlFromUrl(news.getUrl(), false);
Element newsContent = newsHtml.select("div#article-container")
.select("div.main")
.select("div.text")
.first();
String title = newsContent.select("div.text-title").select("h1").text();
String content = newsContent.select("article.article").first().toString();
String image = NewsUtils.getImageFromContent(content);
news.setTitle(title);
news.setContent(content);
news.setImage(image);
newsService.saveNews(news);
logger.info("抽取搜狐新闻《{}》成功！", news.getTitle());
} catch (Exception e) {
logger.error("新闻抽取失败:{}", news.getUrl());
e.printStackTrace();
}
});
}
}
2.凤凰新闻爬虫
@Component("ifengNewsPuller")
public class IfengNewsPuller implements NewsPuller {
private static final Logger logger = LoggerFactory.getLogger(IfengNewsPuller.class);
@Value("${news.ifeng.url}")
private String url;
@Autowired
private NewsService newsService;
@Override
public void pullNews() {
logger.info("开始拉取凤凰新闻！");
// 1.获取首页
Document html= null;
try {
html = getHtmlFromUrl(url, false);
} catch (Exception e) {
logger.error("==============获取凤凰首页失败: {} =============", url);
e.printStackTrace();
return;
}
// 2.jsoup获取新闻标签
Elements newsATags = html.select("div#headLineDefault")
.select("ul.FNewMTopLis")
.select("li")
.select("a");
// 3.从标签中抽取基本信息，封装成news
HashSet newsSet = new HashSet<>();
for (Element a : newsATags) {
String url = a.attr("href");
String title = a.text();
News n = new News();
n.setSource("凤凰");
n.setUrl(url);
n.setTitle(title);
n.setCreateDate(new Date());
newsSet.add(n);
}
// 4.根据新闻url访问新闻，获取新闻内容
newsSet.parallelStream().forEach(news -> {
logger.info("开始抽取凤凰新闻《{}》内容：{}", news.getTitle(), news.getUrl());
Document newsHtml = null;
try {
newsHtml = getHtmlFromUrl(news.getUrl(), false);
Elements contentElement = newsHtml.select("div#main_content");
if (contentElement.isEmpty()) {
contentElement = newsHtml.select("div#yc_con_txt");
}
if (contentElement.isEmpty())
return;
String content = contentElement.toString();
String image = NewsUtils.getImageFromContent(content);
news.setContent(content);
news.setImage(image);
newsService.saveNews(news);
logger.info("抽取凤凰新闻《{}》成功！", news.getTitle());
} catch (Exception e) {
logger.error("凤凰新闻抽取失败:{}", news.getUrl());
e.printStackTrace();
}
});
logger.info("凤凰新闻抽取完成！");
}
}
3.网易爬虫
@Component("netEasyNewsPuller")
public class NetEasyNewsPuller implements NewsPuller {
private static final Logger logger = LoggerFactory.getLogger(NetEasyNewsPuller.class);
@Value("${news.neteasy.url}")
private String url;
@Autowired
private NewsService newsService;
@Override
public void pullNews() {
logger.info("开始拉取网易热门新闻！");
// 1.获取首页
Document html= null;
try {
html = getHtmlFromUrl(url, false);
} catch (Exception e) {
logger.error("==============获取网易新闻首页失败: {}=============", url);
e.printStackTrace();
return;
}
// 2.jsoup获取指定标签
Elements newsA = html.select("div#whole")
.next("div.area-half.left")
.select("div.tabContents")
.first()
.select("tbody > tr")
.select("a[href~=^http://news.163.com.*]");
// 3.从标签中抽取信息，封装成news
HashSet newsSet = new HashSet<>();
newsA.forEach(a -> {
String url = a.attr("href");
News n = new News();
n.setSource("网易");
n.setUrl(url);
n.setCreateDate(new Date());
newsSet.add(n);
});
// 4.根据url访问新闻，获取新闻内容
newsSet.forEach(news -> {
logger.info("开始抽取新闻内容：{}", news.getUrl());
Document newsHtml = null;
try {
newsHtml = getHtmlFromUrl(news.getUrl(), false);
Elements newsContent = newsHtml.select("div#endText");
Elements titleP = newsContent.select("p.otitle");
String title = titleP.text();
title = title.substring(5, title.length() - 1);
String image = NewsUtils.getImageFromContent(newsContent.toString());
news.setTitle(title);
news.setContent(newsContent.toString());
news.setImage(image);
newsService.saveNews(news);
logger.info("抽取网易新闻《{}》成功！", news.getTitle());
} catch (Exception e) {
logger.error("新闻抽取失败:{}", news.getUrl());
e.printStackTrace();
}
});
logger.info("网易新闻拉取完成！");
}
}
0x2 今日头条爬虫
由于今日头条页面中的新闻是通过ajax获取后加载的，因此需要使用httpunit进行抓取。
主要代码如下：
@Component("toutiaoNewsPuller")
public class ToutiaoNewsPuller implements NewsPuller {
private static final Logger logger = LoggerFactory.getLogger(ToutiaoNewsPuller.class);
private static final String TOUTIAO_URL = "https://www.toutiao.com";
@Autowired
private NewsService newsService;
@Value("${news.toutiao.url}")
private String url;
@Override
public void pullNews() {
logger.info("开始拉取今日头条热门新闻！");
// 1.load html from url
Document html = null;
try {
html = getHtmlFromUrl(url, true);
} catch (Exception e) {
logger.error("获取今日头条主页失败！");
e.printStackTrace();
return;
}
// 2.parse the html to news information and load into POJO
Map newsMap = new HashMap<>();
for (Element a : html.select("a[href~=/group/.*]:not(.comment)")) {
logger.info("标签a: \n{}", a);
String href = TOUTIAO_URL + a.attr("href");
String title = StringUtils.isNotBlank(a.select("p").text()) ?
a.select("p").text() : a.text();
String image = a.select("img").attr("src");
News news = newsMap.get(href);
if (news == null) {
News n = new News();
n.setSource("今日头条");
n.setUrl(href);
n.setCreateDate(new Date());
n.setImage(image);
n.setTitle(title);
newsMap.put(href, n);
} else {
if (a.hasClass("img-wrap")) {
news.setImage(image);
} else if (a.hasClass("title")) {
news.setTitle(title);
}
}
}
logger.info("今日头条新闻标题拉取完成!");
logger.info("开始拉取新闻内容...");
newsMap.values().parallelStream().forEach(news -> {
logger.info("===================={}====================", news.getTitle());
Document contentHtml = null;
try {
contentHtml = getHtmlFromUrl(news.getUrl(), true);
} catch (Exception e) {
logger.error("获取新闻《{}》内容失败！", news.getTitle());
return;
}
Elements scripts = contentHtml.getElementsByTag("script");
scripts.forEach(script -> {
String regex = "articleInfo: \\{\\s*[\\n\\r]*\\s*title: '.*',\\s*[\\n\\r]*\\s*content: '(.*)',";
Pattern pattern = Pattern.compile(regex);
Matcher matcher = pattern.matcher(script.toString());
if (matcher.find()) {
String content = matcher.group(1)
.replace("<", "<")
.replace(">", ">")
.replace(""", "\"")
.replace("=", "=");
logger.info("content: {}", content);
news.setContent(content);
}
});
});
newsMap.values()
.stream()
.filter(news -> StringUtils.isNotBlank(news.getContent()) && !news.getContent().equals("null"))
.forEach(newsService::saveNews);
logger.info("今日头条新闻内容拉取完成!");
}
}
拉取结果：
不好意思各位，好久没上csdn，现在吧github地址发一下：https://github.com/gx304419380/NewsCrawler