{"_buckets": {"deposit": "dd6d7b82-9e49-47a9-857e-225d23fe0cc1"}, "_deposit": {"id": "4270", "owners": [], "pid": {"revision_id": 0, "type": "recid", "value": "4270"}, "status": "published"}, "_oai": {"id": "oai:meral.edu.mm:recid/4270", "sets": ["user-ucsy"]}, "communities": ["ucsy"], "item_1583103067471": {"attribute_name": "Title", "attribute_value_mlt": [{"subitem_1551255647225": "Boilerplate removal and Content Extraction from Dynamic Web Pages", "subitem_1551255648112": "en"}]}, "item_1583103085720": {"attribute_name": "Description", "attribute_value_mlt": [{"interim": "Web pages not only contain main content, but also other elements such as navigation panels,advertisements and links to related documents. To ensure the high quality of web page, a goodboilerplate removal algorithm is needed to extract only the relevant contents from web page. Maintextual contents are just included in HTML source code which makes up the files. The goal of contentextraction or boilerplate detection is to separate the main content from navigation chrome,advertising blocks, and copyright notices in web pages. The system removes boilerplate and extractsmain content. In this system, there are two phases: Feature Extraction phase and Clustering phase. Thesystem classifies the noise or content from HTML web page. Content Extraction algorithm describes toget high performance without parsing DOM trees. After observation the HTML tags, one line may notcontain a piece of complete information and long texts are distributed in close lines, this system uses Line-Block concept to determine the distance of any two neighbor lines with text and Feature Extraction such as text-to-tag ratio (TTR), anchor text-to-text ratio (ATTR) and new content feature as Title Keywords Density (TKD) classifies noise or content. After extracting the features, the system uses these features as parameters in threshold method to classify the block are content or noncontent."}]}, "item_1583103108160": {"attribute_name": "Keywords", "attribute_value_mlt": [{"interim": "content extraction"}, {"interim": "line-block"}, {"interim": "TKD"}, {"interim": "TTR"}, {"interim": "ATTR"}]}, "item_1583103120197": {"attribute_name": "Files", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_access", "date": [{"dateType": "Available", "dateValue": "2019-08-13"}], "displaytype": "preview", "download_preview_message": "", "file_order": 0, "filename": "Boilerplate removal and content extraction(ijren).pdf", "filesize": [{"value": "596 Kb"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 596000.0, "url": {"url": "https://meral.edu.mm/record/4270/files/Boilerplate removal and content extraction(ijren).pdf"}, "version_id": "889304ab-4d33-46d3-8ea3-e7155e9a13e3"}]}, "item_1583103131163": {"attribute_name": "Journal articles", "attribute_value_mlt": [{"subitem_issue": "", "subitem_journal_title": "International Journal of Computer Science, Engineering and Applications (IJCSEA)", "subitem_pages": "", "subitem_volume": ""}]}, "item_1583103147082": {"attribute_name": "Conference papers", "attribute_value_mlt": [{"subitem_acronym": "", "subitem_c_date": "", "subitem_conference_title": "", "subitem_part": "", "subitem_place": "", "subitem_session": "", "subitem_website": ""}]}, "item_1583103211336": {"attribute_name": "Books/reports/chapters", "attribute_value_mlt": [{"subitem_book_title": "", "subitem_isbn": "", "subitem_pages": "", "subitem_place": "", "subitem_publisher": ""}]}, "item_1583103233624": {"attribute_name": "Thesis/dissertations", "attribute_value_mlt": [{"subitem_awarding_university": "", "subitem_supervisor(s)": [{"subitem_supervisor": ""}]}]}, "item_1583105942107": {"attribute_name": "Authors", "attribute_value_mlt": [{"subitem_authors": [{"subitem_authors_fullname": "San, Pan Ei"}]}]}, "item_1583108359239": {"attribute_name": "Upload type", "attribute_value_mlt": [{"interim": "Publication"}]}, "item_1583108428133": {"attribute_name": "Publication type", "attribute_value_mlt": [{"interim": "Article"}]}, "item_1583159729339": {"attribute_name": "Publication date", "attribute_value": "2014-12"}, "item_1583159847033": {"attribute_name": "Identifier", "attribute_value": "http://onlineresource.ucsy.edu.mm/handle/123456789/2127"}, "item_title": "Boilerplate removal and Content Extraction from Dynamic Web Pages", "item_type_id": "21", "owner": "1", "path": ["1597824175385"], "permalink_uri": "http://hdl.handle.net/20.500.12678/0000004270", "pubdate": {"attribute_name": "Deposited date", "attribute_value": "2019-08-13"}, "publish_date": "2019-08-13", "publish_status": "0", "recid": "4270", "relation": {}, "relation_version_is_last": true, "title": ["Boilerplate removal and Content Extraction from Dynamic Web Pages"], "weko_shared_id": -1}