Files

• .drone.yml
• .perlcriticrc
• Build.PL
• Changes
• LICENSE
• MANIFEST
• META.json
• META.yml
• README
• cpanfile
• dev-bin/test-recall.pl
• dev-bin/try-htmlextract.pl
• lib/NewsExtractor.pm
• lib/NewsExtractor/Article.pm
• lib/NewsExtractor/CSSExtractor.pm
• lib/NewsExtractor/CSSRuleSet.pm
• lib/NewsExtractor/Constants.pm
• lib/NewsExtractor/Download.pm
• lib/NewsExtractor/Error.pm
• lib/NewsExtractor/Extractor.pm
• lib/NewsExtractor/GenericExtractor.pm
• lib/NewsExtractor/JSONLDExtractor.pm
• lib/NewsExtractor/Role/ContentTextExtractor.pm
• lib/NewsExtractor/SiteSpecificExtractor.pm
• lib/NewsExtractor/SiteSpecificExtractor/ChinaTimes.pm
• lib/NewsExtractor/SiteSpecificExtractor/ETtoday.pm
• lib/NewsExtractor/SiteSpecificExtractor/UDN.pm
• lib/NewsExtractor/SiteSpecificExtractor/ctee_com_tw.pm
• lib/NewsExtractor/SiteSpecificExtractor/estate_ltn_com_tw.pm
• lib/NewsExtractor/SiteSpecificExtractor/focustaiwan_tw.pm
• lib/NewsExtractor/SiteSpecificExtractor/hk_crntt_com.pm
• lib/NewsExtractor/SiteSpecificExtractor/hk_on_cc.pm
• lib/NewsExtractor/SiteSpecificExtractor/m_news_cctv_com.pm
• lib/NewsExtractor/SiteSpecificExtractor/money_udn_com.pm
• lib/NewsExtractor/SiteSpecificExtractor/new_ctv_com_tw.pm
• lib/NewsExtractor/SiteSpecificExtractor/newnet_tw.pm
• lib/NewsExtractor/SiteSpecificExtractor/news_cctv_com.pm
• lib/NewsExtractor/SiteSpecificExtractor/news_cts_com_tw.pm
• lib/NewsExtractor/SiteSpecificExtractor/news_ebc_net_tw.pm
• lib/NewsExtractor/SiteSpecificExtractor/news_pts_org_tw.pm
• lib/NewsExtractor/SiteSpecificExtractor/news_tnn_tw.pm
• lib/NewsExtractor/SiteSpecificExtractor/news_ttv_com_tw.pm
• lib/NewsExtractor/SiteSpecificExtractor/news_tvbs_com_tw.pm
• lib/NewsExtractor/SiteSpecificExtractor/newtalk_tw.pm
• lib/NewsExtractor/SiteSpecificExtractor/talk_ltn_com_tw.pm
• lib/NewsExtractor/SiteSpecificExtractor/turnnewsapp_com.pm
• lib/NewsExtractor/SiteSpecificExtractor/www_aljazeera_com.pm
• lib/NewsExtractor/SiteSpecificExtractor/www_allnews_tw.pm
• lib/NewsExtractor/SiteSpecificExtractor/www_bbc_com.pm
• lib/NewsExtractor/SiteSpecificExtractor/www_bcc_com_tw.pm
• lib/NewsExtractor/SiteSpecificExtractor/www_digitimes_com_tw.pm
• lib/NewsExtractor/SiteSpecificExtractor/www_epochtimes_com.pm
• lib/NewsExtractor/SiteSpecificExtractor/www_fountmedia_io.pm
• lib/NewsExtractor/SiteSpecificExtractor/www_hkcna_hk.pm
• lib/NewsExtractor/SiteSpecificExtractor/www_hkcnews_com.pm
• lib/NewsExtractor/SiteSpecificExtractor/www_idn_com_tw.pm
• lib/NewsExtractor/SiteSpecificExtractor/www_ksnews_com_tw.pm
• lib/NewsExtractor/SiteSpecificExtractor/www_mdnkids_com.pm
• lib/NewsExtractor/SiteSpecificExtractor/www_nownews_com.pm
• lib/NewsExtractor/SiteSpecificExtractor/www_ntdtv_com.pm
• lib/NewsExtractor/SiteSpecificExtractor/www_penghutimes_com.pm
• lib/NewsExtractor/SiteSpecificExtractor/www_peopo_org.pm
• lib/NewsExtractor/SiteSpecificExtractor/www_rti_org_tw.pm
• lib/NewsExtractor/SiteSpecificExtractor/www_rvn_com_tw.pm
• lib/NewsExtractor/SiteSpecificExtractor/www_setn_com.pm
• lib/NewsExtractor/SiteSpecificExtractor/www_taipeitimes_com.pm
• lib/NewsExtractor/SiteSpecificExtractor/www_thestandnews_com.pm
• lib/NewsExtractor/SiteSpecificExtractor/www_ttv_com_tw.pm
• lib/NewsExtractor/SiteSpecificExtractor/www_twreporter_org.pm
• lib/NewsExtractor/SiteSpecificExtractor/www_upmedia_mg.pm
• lib/NewsExtractor/SiteSpecificExtractor/www_ustv_com_tw.pm
• lib/NewsExtractor/SiteSpecificExtractor/www_xinhuanet_com.pm
• lib/NewsExtractor/SiteSpecificExtractor/yimedia_com_tw.pm
• lib/NewsExtractor/TXExtractor.pm
• lib/NewsExtractor/TextUtil.pm
• lib/NewsExtractor/Types.pm
• metamerge.json
• t/data/strs.txt
• t/data/urls
• t/live-extract-1.t
• t/type-NewspaperName.t
• t/type-Text.t
• t/util-normalize-whitespace.t
• t/util-parse-dateline-ymdhms.t
• t/util-reformat-dateline.t
• t/util-u.t