Skip to content

W
webmagic
Commit 15521529 authored by Qiannan Lu's avatar Qiannan Lu
Browse files
Options

resolve issue #226

parent 21f81bb8
Show whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
webmagic-samples/src/main/java/us/codecraft/webmagic/samples/GithubRepoPageProcessor.java
View file @ 15521529
...@@ -19,7 +19,7 @@ public class GithubRepoPageProcessor implements PageProcessor { ...@@ -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
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment