Examples with Request com.cv4j.netdiscovery.core.domain.Request used on opensource projects

Example 1 with Request

use of com.cv4j.netdiscovery.core.domain.Request in project NetDiscovery by fengzhizi715.

the class OkHttpDownloader method download.

@Override
public Maybe<Response> download(Request request) {
    okhttp3.Request.Builder requestBuilder = null;
    if (request.getHttpMethod() == HttpMethod.GET) {
        requestBuilder = new okhttp3.Request.Builder().url(request.getUrl());
    } else if (request.getHttpMethod() == HttpMethod.POST) {
        HttpRequestBody httpRequestBody = request.getHttpRequestBody();
        if (httpRequestBody != null) {
            MediaType mediaType = MediaType.parse(httpRequestBody.getContentType());
            // 创建RequestBody对象，将参数按照指定的MediaType封装
            RequestBody requestBody = RequestBody.create(mediaType, httpRequestBody.getBody());
            requestBuilder = new okhttp3.Request.Builder().url(request.getUrl()).post(requestBody);
        }
    }
    if (request.getHeader() != null) {
        for (Map.Entry<String, String> entry : request.getHeader().entrySet()) {
            requestBuilder.addHeader(entry.getKey(), entry.getValue());
        }
    }
    // 针对post请求，需要对header添加一些信息
    if (request.getHttpMethod() == HttpMethod.POST) {
        if (Preconditions.isNotBlank(request.getHttpRequestBody()) && Preconditions.isNotBlank(request.getHttpRequestBody().getContentType())) {
            requestBuilder.addHeader("Content-type", request.getHttpRequestBody().getContentType());
        }
    }
    okhttp3.Request okrequest = requestBuilder.build();
    return Maybe.create(new MaybeOnSubscribe<okhttp3.Response>() {

        @Override
        public void subscribe(MaybeEmitter emitter) throws Exception {
            emitter.onSuccess(client.newCall(okrequest).execute());
        }
    }).map(new Function<okhttp3.Response, Response>() {

        @Override
        public Response apply(okhttp3.Response resp) throws Exception {
            Response response = new Response();
            response.setContent(resp.body().bytes());
            response.setStatusCode(resp.code());
            response.setContentType(resp.header("Content-Type"));
            return response;
        }
    });
}

Example 2 with Request

use of com.cv4j.netdiscovery.core.domain.Request in project NetDiscovery by fengzhizi715.

the class Spider method run.

public void run() {
    checkRunningStat();
    initialDelay();
    try {
        while (getSpiderStatus() != SPIDER_STATUS_STOPPED) {
            // 暂停抓取
            if (pause) {
                try {
                    this.pauseCountDown.await();
                } catch (InterruptedException e) {
                    log.error("can't pause : ", e);
                }
                initialDelay();
            }
            final Request request = queue.poll(name);
            if (request != null) {
                if (request.getSleepTime() > 0) {
                    try {
                        Thread.sleep(request.getSleepTime());
                    } catch (InterruptedException e) {
                        e.printStackTrace();
                    }
                }
                if (autoProxy && request.getProxy() == null) {
                    Proxy proxy = ProxyPool.getProxy();
                    if (proxy != null && Utils.checkProxy(proxy)) {
                        request.proxy(proxy);
                    }
                }
                if (request.getBeforeRequest() != null) {
                    request.getBeforeRequest().process(request);
                }
                downloader.download(request).map(new Function<Response, Page>() {

                    @Override
                    public Page apply(Response response) throws Exception {
                        Page page = new Page();
                        page.setRequest(request);
                        page.setUrl(request.getUrl());
                        page.setStatusCode(response.getStatusCode());
                        if (Utils.isTextType(response.getContentType())) {
                            // text/html
                            page.setHtml(new Html(response.getContent()));
                            return page;
                        } else if (Utils.isApplicationJSONType(response.getContentType())) {
                            // application/json
                            // 将json字符串转化成Json对象，放入Page的"RESPONSE_JSON"字段。之所以转换成Json对象，是因为Json提供了toObject()，可以转换成具体的class。
                            page.putField(Constant.RESPONSE_JSON, new Json(new String(response.getContent())));
                            return page;
                        } else {
                            // 保存InputStream
                            page.putField(Constant.RESPONSE_RAW, response.getIs());
                            return page;
                        }
                    }
                }).map(new Function<Page, Page>() {

                    @Override
                    public Page apply(Page page) throws Exception {
                        if (parser != null) {
                            parser.process(page);
                        }
                        return page;
                    }
                }).map(new Function<Page, Page>() {

                    @Override
                    public Page apply(Page page) throws Exception {
                        if (Preconditions.isNotBlank(pipelines)) {
                            pipelines.stream().forEach(pipeline -> pipeline.process(page.getResultItems()));
                        }
                        return page;
                    }
                }).observeOn(Schedulers.io()).subscribe(new Consumer<Page>() {

                    @Override
                    public void accept(Page page) throws Exception {
                        log.info(page.getUrl());
                        if (request.getAfterRequest() != null) {
                            request.getAfterRequest().process(page);
                        }
                    }
                }, new Consumer<Throwable>() {

                    @Override
                    public void accept(Throwable throwable) throws Exception {
                        log.error(throwable.getMessage());
                    }
                });
            } else {
                break;
            }
        }
    } finally {
        // 爬虫停止
        stopSpider(downloader);
    }
}

Example 3 with Request

use of com.cv4j.netdiscovery.core.domain.Request in project NetDiscovery by fengzhizi715.

the class RequestDeserializer method deserialize.

@Override
public Request deserialize(String topic, byte[] data) {
    ObjectMapper mapper = new ObjectMapper();
    Request request = null;
    try {
        request = mapper.readValue(data, Request.class);
    } catch (Exception e) {
        e.printStackTrace();
    }
    return request;
}

Example 4 with Request

use of com.cv4j.netdiscovery.core.domain.Request in project NetDiscovery by fengzhizi715.

the class RedisQueue method poll.

@Override
public synchronized Request poll(String spiderName) {
    Jedis jedis = pool.getResource();
    try {
        String url = jedis.lpop(getQueueKey(spiderName));
        if (url == null) {
            return null;
        }
        String key = ITEM_PREFIX + url;
        String field = DigestUtils.shaHex(url);
        byte[] bytes = jedis.hget(key.getBytes(), field.getBytes());
        if (bytes != null) {
            Request o = JSON.parseObject(new String(bytes), Request.class);
            return o;
        }
        Request request = new Request(url);
        return request;
    } finally {
        pool.returnResource(jedis);
    }
}

Example 5 with Request

use of com.cv4j.netdiscovery.core.domain.Request in project NetDiscovery by fengzhizi715.

the class Spider method repeatRequest.

/**
 * 可以重复提交request，用于实现定时任务，使用该方法时需要跟initialDelay一起配合使用。
 * @param period 每隔一定的时间提交一次request
 * @param url
 * @return
 */
public Spider repeatRequest(long period, String url) {
    checkIfRunning();
    compositeDisposable.add(Flowable.interval(period, TimeUnit.MILLISECONDS).onBackpressureBuffer().subscribe(new Consumer<Long>() {

        @Override
        public void accept(Long aLong) throws Exception {
            if (!pause) {
                Request request = new Request(url);
                request.checkDuplicate(false);
                request.spiderName(name);
                request.sleep(period);
                queue.push(request);
            }
        }
    }));
    return this;
}