Mobai
/
magic-Dependency
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

resolve issue #226

master
Qiannan Lu 2015-09-18 09:30:01 +08:00
parent 21f81bb8c1
commit 155215290f
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
webmagic-samples/src/main/java/us/codecraft/webmagic/samples/GithubRepoPageProcessor.java
View File

@ -19,7 +19,7 @@ public class GithubRepoPageProcessor implements PageProcessor {
page.addTargetRequests(page.getHtml().links().regex("(https://github\\.com/\\w+)").all()); page.addTargetRequests(page.getHtml().links().regex("(https://github\\.com/\\w+)").all());
GithubRepo githubRepo = new GithubRepo(); GithubRepo githubRepo = new GithubRepo();
githubRepo.setAuthor(page.getUrl().regex("https://github\\.com/(\\w+)/.*").toString()); githubRepo.setAuthor(page.getUrl().regex("https://github\\.com/(\\w+)/.*").toString());
githubRepo.setName(page.getHtml().xpath("//h1[@class='entry-title public']/strong/a/text()").toString()); githubRepo.setName(page.getHtml().xpath("//h1[contains(@class, 'entry-title') and contains(@class, 'public')]/strong/a/text()").toString());
githubRepo.setReadme(page.getHtml().xpath("//div[@id='readme']/tidyText()").toString()); githubRepo.setReadme(page.getHtml().xpath("//div[@id='readme']/tidyText()").toString());
if (githubRepo.getName() == null) { if (githubRepo.getName() == null) {
//skip this page //skip this page