├── .gitignore ├── Jamroot ├── README.md ├── algorithm.hpp ├── categorizer.cpp ├── categorizer.hpp ├── chunked_stream.hpp ├── download_factory.hpp ├── download_manager.cpp ├── download_manager.hpp ├── downloader.cpp ├── downloader.hpp ├── environment.cpp ├── environment.hpp ├── extractor.cpp ├── extractor.hpp ├── file_download_factory.cpp ├── file_download_factory.hpp ├── file_downloader.cpp ├── file_downloader.hpp ├── header.cpp ├── header.hpp ├── http_request.cpp ├── http_request.hpp ├── http_response.cpp ├── http_response.hpp ├── main.cpp ├── page_download_factory.cpp ├── page_download_factory.hpp ├── page_downloader.cpp ├── page_downloader.hpp ├── path.cpp ├── path.hpp ├── queue.hpp ├── spider.cpp ├── spider.hpp ├── stripper.cpp ├── stripper.hpp ├── task_pool.cpp ├── task_pool.hpp ├── tracker.cpp ├── tracker.hpp ├── url.cpp ├── url.hpp ├── url_finder.cpp └── url_finder.hpp /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/.gitignore -------------------------------------------------------------------------------- /Jamroot: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/Jamroot -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/README.md -------------------------------------------------------------------------------- /algorithm.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/algorithm.hpp -------------------------------------------------------------------------------- /categorizer.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/categorizer.cpp -------------------------------------------------------------------------------- /categorizer.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/categorizer.hpp -------------------------------------------------------------------------------- /chunked_stream.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/chunked_stream.hpp -------------------------------------------------------------------------------- /download_factory.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/download_factory.hpp -------------------------------------------------------------------------------- /download_manager.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/download_manager.cpp -------------------------------------------------------------------------------- /download_manager.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/download_manager.hpp -------------------------------------------------------------------------------- /downloader.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/downloader.cpp -------------------------------------------------------------------------------- /downloader.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/downloader.hpp -------------------------------------------------------------------------------- /environment.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/environment.cpp -------------------------------------------------------------------------------- /environment.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/environment.hpp -------------------------------------------------------------------------------- /extractor.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/extractor.cpp -------------------------------------------------------------------------------- /extractor.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/extractor.hpp -------------------------------------------------------------------------------- /file_download_factory.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/file_download_factory.cpp -------------------------------------------------------------------------------- /file_download_factory.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/file_download_factory.hpp -------------------------------------------------------------------------------- /file_downloader.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/file_downloader.cpp -------------------------------------------------------------------------------- /file_downloader.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/file_downloader.hpp -------------------------------------------------------------------------------- /header.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/header.cpp -------------------------------------------------------------------------------- /header.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/header.hpp -------------------------------------------------------------------------------- /http_request.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/http_request.cpp -------------------------------------------------------------------------------- /http_request.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/http_request.hpp -------------------------------------------------------------------------------- /http_response.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/http_response.cpp -------------------------------------------------------------------------------- /http_response.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/http_response.hpp -------------------------------------------------------------------------------- /main.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/main.cpp -------------------------------------------------------------------------------- /page_download_factory.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/page_download_factory.cpp -------------------------------------------------------------------------------- /page_download_factory.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/page_download_factory.hpp -------------------------------------------------------------------------------- /page_downloader.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/page_downloader.cpp -------------------------------------------------------------------------------- /page_downloader.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/page_downloader.hpp -------------------------------------------------------------------------------- /path.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/path.cpp -------------------------------------------------------------------------------- /path.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/path.hpp -------------------------------------------------------------------------------- /queue.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/queue.hpp -------------------------------------------------------------------------------- /spider.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/spider.cpp -------------------------------------------------------------------------------- /spider.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/spider.hpp -------------------------------------------------------------------------------- /stripper.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/stripper.cpp -------------------------------------------------------------------------------- /stripper.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/stripper.hpp -------------------------------------------------------------------------------- /task_pool.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/task_pool.cpp -------------------------------------------------------------------------------- /task_pool.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/task_pool.hpp -------------------------------------------------------------------------------- /tracker.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/tracker.cpp -------------------------------------------------------------------------------- /tracker.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/tracker.hpp -------------------------------------------------------------------------------- /url.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/url.cpp -------------------------------------------------------------------------------- /url.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/url.hpp -------------------------------------------------------------------------------- /url_finder.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/url_finder.cpp -------------------------------------------------------------------------------- /url_finder.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/jehugaleahsa/spider-cpp/HEAD/url_finder.hpp --------------------------------------------------------------------------------