友情链接

main
tamguo 7 years ago
parent 1767f11901
commit 02f47ce1ac

@ -53,8 +53,8 @@ public class QuestionService extends ServiceImpl<QuestionMapper, QuestionEntity>
@Autowired
CacheService cacheService;
private static final String FILES_NO_FORMAT = "000000000";
private static final String FILES_PREFIX = "kyzz";
private static final String COURSE_ID = "kaoyanzhengzhi";
private static final String FILES_PREFIX = "qyglzs";
private static final String COURSE_ID = "qiyeguanlizhishi";
private RunData runData;

@ -30,9 +30,9 @@ import com.xuxueli.crawler.rundata.RunData;
@Service
public class SubjectService implements ISubjectService{
private final static String COURSE_ID = "kaoyanzhengzhi";
private final static String BOOK_ID = "1025976567395184651";
private final static String SUBJECT_ID = "kaoyan";
private final static String COURSE_ID = "qiyeguanlizhishi";
private final static String BOOK_ID = "1025976567395184652";
private final static String SUBJECT_ID = "qiyefalvguwen";
@Autowired
SubjectMapper subjectMapper;
@Autowired
@ -53,7 +53,7 @@ public class SubjectService implements ISubjectService{
@Override
public void crawlerSubject() {
XxlCrawler crawler = new XxlCrawler.Builder()
.setUrls("https://tiku.baidu.com/tikupc/chapterlist/f3eb19e8b8f67c1cfad6b805-342-knowpoint-11")
.setUrls("https://tiku.baidu.com/tikupc/chapterlist/ed6527d3240c844769eaee05-647-knowpoint-11")
.setAllowSpread(false)
.setFailRetryCount(5)
.setThreadCount(20)
@ -63,7 +63,7 @@ public class SubjectService implements ISubjectService{
public void parse(Document html, Element pageVoElement, SubjectVo subjectVo) {
// 解析封装 PageVo 对象
String pageUrl = html.baseUri();
if(pageUrl.contains("https://tiku.baidu.com/tikupc/chapterlist/f3eb19e8b8f67c1cfad6b805-342-knowpoint-11")) {
if(pageUrl.contains("https://tiku.baidu.com/tikupc/chapterlist/ed6527d3240c844769eaee05-647-knowpoint-11")) {
logger.info("开始解析书籍:{}" , pageUrl);
ChapterEntity chapterCondition = new ChapterEntity();
chapterCondition.setName(subjectVo.getChapterCurrName());

@ -34,13 +34,13 @@ public class PaperCrawler {
// 140000 山西 | 350000 福建 | 340000 安徽 | 220000 吉林 | 150000 内蒙古 | 640000 宁夏 | 650000 新疆 | 广西 450000 | 210000 辽宁
// 230000 黑龙江 | 610000 陕西 | 360000 江西 | 440000 广东 | 430000 湖南 | 460000 海南 | 530000 云南 | 510000 四川 | 630000 青海
// 620000 甘肃 | 130000 河北 | 540000 西藏 | 贵州 520000
private final String AREA_ID = "150000";
private final String AREA_ID = "440000";
// 年份
private final String YEAR = "2016";
// 真题试卷 类型(1:真题试卷,2:模拟试卷,3:押题预测,4:名校精品)
private final String PAPER_TYPE = "2";
private final String PAPER_TYPE = "4";
// 开始采集的URL
private final String START_URL = "https://tiku.baidu.com/tikupc/paperlist/1bfd700abb68a98271fefa04-18-4-2016-965-1-download";
private final String START_URL = "https://tiku.baidu.com/tikupc/paperlist/1bfd700abb68a98271fefa04-18-7-2016-1427-1-download";
private RunData runData;

@ -40,13 +40,6 @@
<li class="contain-li"><a class="contain-link"
href="http://www.chinadmoz.org/" style="color:#fff;" target="_blank" title="DMOZ目录收录各类优秀网站" rel="nofollow">DMOZ目录</a>
</li>
<li class="contain-li"><a class="contain-link"
href="http://www.cqcrgk.com/" style="color:#fff;" target="_blank" title="重庆成人高考">重庆高考</a>
</li>
<li class="contain-li"><a class="contain-link"
href="http://www.0791zikaow.com/" style="color:#fff;" target="_blank" title="江西自考网">江西自考网</a>
</li>
</ul>
</div>
</div>

Loading…
Cancel
Save