crawler-master
.gitignore
42B
CHANGELOG
1KB
src
main
resources
crawler.properties
454B
java
com
soulgalore
crawler
core
Crawler.java
1KB
HTMLPageResponseCallable.java
2KB
HTMLPageResponse.java
5KB
HTMLPageResponseFetcher.java
2KB
assets
AssetFetcher.java
1KB
AssetsVerifier.java
1KB
AssetsVerificationResult.java
1KB
AssetResponseCallable.java
2KB
AssetsParser.java
1KB
impl
HTTPClientAssetFetcher.java
3KB
DefaultAssetsParser.java
2KB
DefaultAssetsVerifier.java
4KB
AssetResponse.java
2KB
PageURLParser.java
1KB
CrawlerURL.java
4KB
impl
AhrefPageURLParser.java
3KB
DefaultCrawler.java
11KB
HTTPClientResponseFetcher.java
7KB
CrawlerConfiguration.java
5KB
CrawlerResult.java
3KB
run
CrawlToCsv.java
4KB
CrawlToFile.java
6KB
AbstractCrawl.java
5KB
CrawlToSystemOut.java
2KB
CrawlAndVerifyAssets.java
3KB
AbstractRunner.java
2KB
CrawlToPlainTxtOnlyMatching.java
3KB
CrawlAndVerifyAssetsToCsv.java
4KB
guice
AbstractPropertiesModule.java
3KB
ExecutorServiceProvider.java
2KB
HttpClientProvider.java
6KB
CrawlModule.java
2KB
util
StatusCode.java
2KB
AuthUtil.java
2KB
HTTPSFaker.java
3KB
HeaderUtil.java
2KB
Auth.java
2KB
test
resources
crawler
pageWithMailToLinks.html
267B
crawler1.html
100B
crawler4.html
150B
crawler2.html
231B
crawler5.html
71B
crawler3.html
129B
pageToParse.html
480B
java
com
soulgalore
crawler
core
impl
WhenACrawlIsDone.java
6KB
WhenAhrefsIsParsedFromResponse.java
1KB
run
WhenCrawlToPlainTxtRun.java
1KB
AbstractRun.java
569B
util
WhenAHeaderIsParsed.java
1KB
WhenAnAuthObjectIsCreated.java
2KB
WhenACrawlerResultIsCreated.java
2KB
WhenAStatusCodeIsChecked.java
541B
test
TestFileHelper.java
1KB
WhenAPageURLIsCreated.java
3KB
.travis.yml
14B
LICENSE
10KB
pom.xml
6KB
README.md
8KB
暂无评论