Java爬虫抓取B站视频信息

PXM的算法星球2025-03-19 18:30

依赖

xml 复制代码

<dependency>
            <groupId>org.jsoup</groupId>
            <artifactId>jsoup</artifactId>
            <version>1.17.2</version> <!-- 最新版可去官网查看 -->
        </dependency>

编码

java 复制代码

public static List<VideoDto> parseSearchPage(String keyword, int page,int lim) throws Exception {
        String url = "https://search.bilibili.com/all?keyword=" + keyword + "&page=" + page;
        Document doc = Jsoup.connect(url)
                .userAgent("Mozilla/5.0")
                .timeout(10000)
                .get();
        List<VideoDto> list = new ArrayList<>();
        Elements pictures = doc.select("picture");
        System.out.println("OK");
        int cnt=0;
        for (Element picture : pictures) {

            String pictureSrc = Objects.requireNonNull(picture.selectFirst("source")).attr("srcset");
            String title = Objects.requireNonNull(picture.selectFirst("img")).attr("alt");

            VideoDto videoDto = new VideoDto();
            videoDto.setPicture(pictureSrc);
            videoDto.setTitle(title);
            list.add(videoDto);
            cnt++;
            if(cnt==lim)break;


        }
        Elements divElements = doc.select("div.bili-video-card__info--right");
        cnt=0;
        for(Element divElement : divElements){
            Element firstLink = divElement.selectFirst("a");
            if(firstLink != null){
                String link= firstLink.attr("href");
                VideoDto videoDto=list.get(cnt);
                videoDto.setUrl(link);
                list.set(cnt,videoDto);
                cnt++;
                if(cnt==lim)break;
            }

        }
        return list;
    }