├── .gitattributes ├── .gitignore ├── .travis.yml ├── CHANGELOG.md ├── GOOSE-LICENSE.txt ├── LICENSE ├── MANIFEST.in ├── README.rst ├── docs ├── Makefile ├── _static │ └── newspaper.jpg ├── _templates │ ├── sidebarintro.html │ └── sidebarlogo.html ├── _themes │ ├── .gitignore │ ├── LICENSE │ ├── README.rst │ ├── flask_theme_support.py │ ├── kr │ │ ├── layout.html │ │ ├── relations.html │ │ ├── static │ │ │ └── flasky.css_t │ │ └── theme.conf │ └── kr_small │ │ ├── layout.html │ │ ├── static │ │ └── flasky.css_t │ │ └── theme.conf ├── conf.py ├── index.rst ├── make.bat └── user_guide │ ├── advanced.rst │ ├── api.rst │ ├── contributors.rst │ └── quickstart.rst ├── download_corpora.py ├── newspaper ├── __init__.py ├── api.py ├── article.py ├── cleaners.py ├── configuration.py ├── extractors.py ├── images.py ├── mthreading.py ├── network.py ├── nlp.py ├── outputformatters.py ├── parsers.py ├── resources │ ├── misc │ │ ├── google_sources.txt │ │ ├── popular_sources.txt │ │ ├── stopwords-nlp-en.txt │ │ └── useragents.txt │ └── text │ │ ├── stopwords-ar.txt │ │ ├── stopwords-be.txt │ │ ├── stopwords-bg.txt │ │ ├── stopwords-da.txt │ │ ├── stopwords-de.txt │ │ ├── stopwords-el.txt │ │ ├── stopwords-en.txt │ │ ├── stopwords-es.txt │ │ ├── stopwords-et.txt │ │ ├── stopwords-fa.txt │ │ ├── stopwords-fi.txt │ │ ├── stopwords-fr.txt │ │ ├── stopwords-he.txt │ │ ├── stopwords-hi.txt │ │ ├── stopwords-hr.txt │ │ ├── stopwords-hu.txt │ │ ├── stopwords-id.txt │ │ ├── stopwords-it.txt │ │ ├── stopwords-ja.txt │ │ ├── stopwords-ko.txt │ │ ├── stopwords-lt.txt │ │ ├── stopwords-mk.txt │ │ ├── stopwords-nb.txt │ │ ├── stopwords-nl.txt │ │ ├── stopwords-no.txt │ │ ├── stopwords-pl.txt │ │ ├── stopwords-pt.txt │ │ ├── stopwords-ro.txt │ │ ├── stopwords-ru.txt │ │ ├── stopwords-sl.txt │ │ ├── stopwords-sr.txt │ │ ├── stopwords-sv.txt │ │ ├── stopwords-sw.txt │ │ ├── stopwords-th.txt │ │ ├── stopwords-tr.txt │ │ ├── stopwords-uk.txt │ │ ├── stopwords-vi.txt │ │ └── stopwords-zh.txt ├── settings.py ├── source.py ├── text.py ├── urls.py ├── utils.py ├── version.py └── videos │ ├── __init__.py │ ├── extractors.py │ └── videos.py ├── requirements.txt ├── setup.py └── tests ├── __init__.py ├── benchmarks.py ├── data ├── fulltext_domain_list.txt ├── fulltext_url_list.txt ├── html │ ├── 247wallst.com1.html │ ├── 247wallst.com2.html │ ├── about.com1.html │ ├── about.com2.html │ ├── adoption.com1.html │ ├── al.com1.html │ ├── al.com2.html │ ├── ap_meta_refresh.html │ ├── apartmenttherapy.com1.html │ ├── apartmenttherapy.com2.html │ ├── arabic_article.html │ ├── architecturaldigest.com1.html │ ├── architecturaldigest.com2.html │ ├── avclub.com1.html │ ├── avclub.com2.html │ ├── backstage.com1.html │ ├── backstage.com2.html │ ├── bhg.com1.html │ ├── bhg.com2.html │ ├── bloomberg.com1.html │ ├── bostonherald.com1.html │ ├── bostonherald.com2.html │ ├── businessinsider.com1.html │ ├── businessinsider.com2.html │ ├── businessweek.com1.html │ ├── businessweek.com2.html │ ├── chinese_article.html │ ├── cleveland.com1.html │ ├── cleveland.com2.html │ ├── cnn_article.html │ ├── cnn_main_site.html │ ├── cntraveler.com1.html │ ├── cntraveler.com2.html │ ├── coolhunting.com1.html │ ├── coolhunting.com2.html │ ├── cricket.com.au1.html │ ├── cricket.com.au2.html │ ├── dailycaller.com1.html │ ├── dailycaller.com2.html │ ├── dailystar.co.uk1.html │ ├── dailystar.co.uk2.html │ ├── dallasnews.com1.html │ ├── dallasnews.com2.html │ ├── details.com1.html │ ├── details.com2.html │ ├── elle.com1.html │ ├── elle.com2.html │ ├── flavorwire.com1.html │ ├── flavorwire.com2.html │ ├── fool.com1.html │ ├── fool.com2.html │ ├── foxbusiness.com1.html │ ├── foxbusiness.com2.html │ ├── foxnews.com1.html │ ├── foxnews.com2.html │ ├── glamour.com1.html │ ├── glamour.com2.html │ ├── globalnews.ca1.html │ ├── globalnews.ca2.html │ ├── google_meta_refresh.html │ ├── gq.com1.html │ ├── gq.com2.html │ ├── graziadaily.co.uk1.html │ ├── graziadaily.co.uk2.html │ ├── gulflive.com1.html │ ├── gulflive.com2.html │ ├── huffingtonpost.com1.html │ ├── japanese_article.html │ ├── japanese_article2.html │ ├── lifebuzz.com1.html │ ├── lifebuzz.com2.html │ ├── livescience.com1.html │ ├── livescience.com2.html │ ├── mashable.com1.html │ ├── mashable.com2.html │ ├── mlive.com1.html │ ├── mlive.com2.html │ ├── newyorker.com1.html │ ├── nj.com1.html │ ├── nola.com1.html │ ├── nydailynews.com1.html │ ├── nypost.com1.html │ ├── nypost.com2.html │ ├── ok.co.uk1.html │ ├── ok.co.uk2.html │ ├── oregonlive.com1.html │ ├── oregonlive.com2.html │ ├── parsely.com1.html │ ├── parsely.com2.html │ ├── pe.com1.html │ ├── pewresearch.org1.html │ ├── pewresearch.org2.html │ ├── pixable.com1.html │ ├── pixable.com2.html │ ├── pixelmonkey.org1.html │ ├── pixelmonkey.org2.html │ ├── readwrite.com1.html │ ├── recipe.com1.html │ ├── recipe.com2.html │ ├── reuters.com1.html │ ├── reuters.com2.html │ ├── reuters.com3.html │ ├── reuters.com4.html │ ├── self.com1.html │ ├── self.com2.html │ ├── sitepoint.com1.html │ ├── sitepoint.com2.html │ ├── slate.com1.html │ ├── slate.com2.html │ ├── space.com1.html │ ├── space.com2.html │ ├── spanish_article.html │ ├── syracuse.com1.html │ ├── syracuse.com2.html │ ├── talkingpointsmemo.com1.html │ ├── technologyreview.com1.html │ ├── technologyreview.com2.html │ ├── teenvogue.com1.html │ ├── teenvogue.com2.html │ ├── telegraph.co.uk1.html │ ├── telegraph.co.uk2.html │ ├── thai_article.html │ ├── theatlantic.com1.html │ ├── theatlantic.com2.html │ ├── theatlanticcities.com1.html │ ├── theatlanticcities.com2.html │ ├── thedailybeast.com1.html │ ├── thedailybeast.com2.html │ ├── thedebrief.co.uk1.html │ ├── thedebrief.co.uk2.html │ ├── theglobeandmail.com1.html │ ├── theglobeandmail.com2.html │ ├── thekitchn.com1.html │ ├── thekitchn.com2.html │ ├── thenextweb.com1.html │ ├── theonion.com1.html │ ├── theroot.com1.html │ ├── tnr.com1.html │ ├── tnr.com2.html │ ├── uproxx.com1.html │ ├── uproxx.com2.html │ ├── upworthy.com1.html │ ├── upworthy.com2.html │ ├── usnews.com1.html │ ├── usnews.com2.html │ ├── vanityfair.com1.html │ ├── vogue.de1.html │ ├── vogue.de2.html │ ├── wetpaint.com1.html │ ├── wetpaint.com2.html │ ├── wired.com1.html │ ├── wired.com2.html │ ├── wnet.org1.html │ ├── wnet.org2.html │ ├── yahoo_main_site.html │ ├── youbeauty.com1.html │ └── youbeauty.com2.html ├── test_prepare_urls.txt ├── test_urls.txt ├── test_urls_pubdate.txt └── text │ ├── 247wallst.com1.txt │ ├── 247wallst.com2.txt │ ├── about.com1.txt │ ├── about.com2.txt │ ├── adoption.com1.txt │ ├── al.com1.txt │ ├── al.com2.txt │ ├── apartmenttherapy.com1.txt │ ├── apartmenttherapy.com2.txt │ ├── arabic.txt │ ├── architecturaldigest.com1.txt │ ├── architecturaldigest.com2.txt │ ├── avclub.com1.txt │ ├── avclub.com2.txt │ ├── backstage.com1.txt │ ├── backstage.com2.txt │ ├── bhg.com1.txt │ ├── bhg.com2.txt │ ├── bloomberg.com1.txt │ ├── bostonherald.com1.txt │ ├── bostonherald.com2.txt │ ├── businessinsider.com1.txt │ ├── businessinsider.com2.txt │ ├── businessweek.com1.txt │ ├── businessweek.com2.txt │ ├── chinese.txt │ ├── cleveland.com1.txt │ ├── cleveland.com2.txt │ ├── cnn.txt │ ├── cnn_summary.txt │ ├── cntraveler.com1.txt │ ├── cntraveler.com2.txt │ ├── coolhunting.com1.txt │ ├── cricket.com.au1.txt │ ├── cricket.com.au2.txt │ ├── dailycaller.com1.txt │ ├── dailycaller.com2.txt │ ├── dailystar.co.uk1.txt │ ├── dailystar.co.uk2.txt │ ├── dallasnews.com1.txt │ ├── dallasnews.com2.txt │ ├── details.com1.txt │ ├── details.com2.txt │ ├── elle.com1.txt │ ├── elle.com2.txt │ ├── flavorwire.com1.txt │ ├── flavorwire.com2.txt │ ├── fool.com1.txt │ ├── fool.com2.txt │ ├── foxbusiness.com1.txt │ ├── foxbusiness.com2.txt │ ├── foxnews.com1.txt │ ├── foxnews.com2.txt │ ├── foxnews.com3.txt │ ├── foxnews.com4.txt │ ├── glamour.com1.txt │ ├── glamour.com2.txt │ ├── globalnews.ca1.txt │ ├── globalnews.ca2.txt │ ├── gq.com1.txt │ ├── gq.com2.txt │ ├── graziadaily.co.uk1.txt │ ├── graziadaily.co.uk2.txt │ ├── gulflive.com1.txt │ ├── gulflive.com2.txt │ ├── huffingtonpost.com1.txt │ ├── japanese.txt │ ├── japanese2.txt │ ├── lifebuzz.com1.txt │ ├── lifebuzz.com2.txt │ ├── livescience.com1.txt │ ├── livescience.com2.txt │ ├── mashable.com1.txt │ ├── mashable.com2.txt │ ├── mlive.com1.txt │ ├── mlive.com2.txt │ ├── newyorker.com1.txt │ ├── nj.com1.txt │ ├── nola.com1.txt │ ├── nydailynews.com1.txt │ ├── nypost.com1.txt │ ├── nypost.com2.txt │ ├── ok.co.uk1.txt │ ├── ok.co.uk2.txt │ ├── oregonlive.com1.txt │ ├── oregonlive.com2.txt │ ├── parsely.com1.txt │ ├── parsely.com2.txt │ ├── pe.com1.txt │ ├── pewresearch.org1.txt │ ├── pewresearch.org2.txt │ ├── pixable.com1.txt │ ├── pixable.com2.txt │ ├── pixelmonkey.org1.txt │ ├── pixelmonkey.org2.txt │ ├── readwrite.com1.txt │ ├── recipe.com1.txt │ ├── recipe.com2.txt │ ├── reuters.com1.txt │ ├── reuters.com2.txt │ ├── reuters.com3.txt │ ├── reuters.com4.txt │ ├── reuters.com5.txt │ ├── reuters.com6.txt │ ├── self.com1.txt │ ├── self.com2.txt │ ├── sitepoint.com1.txt │ ├── sitepoint.com2.txt │ ├── slate.com1.txt │ ├── slate.com2.txt │ ├── space.com1.txt │ ├── space.com2.txt │ ├── spanish.txt │ ├── syracuse.com1.txt │ ├── syracuse.com2.txt │ ├── talkingpointsmemo.com1.txt │ ├── technologyreview.com1.txt │ ├── technologyreview.com2.txt │ ├── teenvogue.com1.txt │ ├── teenvogue.com2.txt │ ├── telegraph.co.uk1.txt │ ├── telegraph.co.uk2.txt │ ├── thai.txt │ ├── theatlantic.com1.txt │ ├── theatlantic.com2.txt │ ├── theatlanticcities.com1.txt │ ├── theatlanticcities.com2.txt │ ├── thedailybeast.com1.txt │ ├── thedailybeast.com2.txt │ ├── thedebrief.co.uk1.txt │ ├── thedebrief.co.uk2.txt │ ├── theglobeandmail.com1.txt │ ├── theglobeandmail.com2.txt │ ├── thekitchn.com1.txt │ ├── thekitchn.com2.txt │ ├── thenextweb.com1.txt │ ├── theonion.com1.txt │ ├── theroot.com1.txt │ ├── tnr.com1.txt │ ├── tnr.com2.txt │ ├── uproxx.com1.txt │ ├── uproxx.com2.txt │ ├── upworthy.com1.txt │ ├── upworthy.com2.txt │ ├── usnews.com1.txt │ ├── usnews.com2.txt │ ├── vanityfair.com1.txt │ ├── vogue.de1.txt │ ├── vogue.de2.txt │ ├── wetpaint.com1.txt │ ├── wetpaint.com2.txt │ ├── wired.com1.txt │ ├── wired.com2.txt │ ├── wnet.org1.txt │ ├── wnet.org2.txt │ ├── youbeauty.com1.txt │ └── youbeauty.com2.txt └── unit_tests.py /.gitattributes: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/.gitattributes -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/.gitignore -------------------------------------------------------------------------------- /.travis.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/.travis.yml -------------------------------------------------------------------------------- /CHANGELOG.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/CHANGELOG.md -------------------------------------------------------------------------------- /GOOSE-LICENSE.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/GOOSE-LICENSE.txt -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/LICENSE -------------------------------------------------------------------------------- /MANIFEST.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/MANIFEST.in -------------------------------------------------------------------------------- /README.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/README.rst -------------------------------------------------------------------------------- /docs/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/docs/Makefile -------------------------------------------------------------------------------- /docs/_static/newspaper.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/docs/_static/newspaper.jpg -------------------------------------------------------------------------------- /docs/_templates/sidebarintro.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/docs/_templates/sidebarintro.html -------------------------------------------------------------------------------- /docs/_templates/sidebarlogo.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/docs/_templates/sidebarlogo.html -------------------------------------------------------------------------------- /docs/_themes/.gitignore: -------------------------------------------------------------------------------- 1 | *.pyc 2 | *.pyo 3 | .DS_Store 4 | -------------------------------------------------------------------------------- /docs/_themes/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/docs/_themes/LICENSE -------------------------------------------------------------------------------- /docs/_themes/README.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/docs/_themes/README.rst -------------------------------------------------------------------------------- /docs/_themes/flask_theme_support.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/docs/_themes/flask_theme_support.py -------------------------------------------------------------------------------- /docs/_themes/kr/layout.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/docs/_themes/kr/layout.html -------------------------------------------------------------------------------- /docs/_themes/kr/relations.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/docs/_themes/kr/relations.html -------------------------------------------------------------------------------- /docs/_themes/kr/static/flasky.css_t: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/docs/_themes/kr/static/flasky.css_t -------------------------------------------------------------------------------- /docs/_themes/kr/theme.conf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/docs/_themes/kr/theme.conf -------------------------------------------------------------------------------- /docs/_themes/kr_small/layout.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/docs/_themes/kr_small/layout.html -------------------------------------------------------------------------------- /docs/_themes/kr_small/static/flasky.css_t: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/docs/_themes/kr_small/static/flasky.css_t -------------------------------------------------------------------------------- /docs/_themes/kr_small/theme.conf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/docs/_themes/kr_small/theme.conf -------------------------------------------------------------------------------- /docs/conf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/docs/conf.py -------------------------------------------------------------------------------- /docs/index.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/docs/index.rst -------------------------------------------------------------------------------- /docs/make.bat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/docs/make.bat -------------------------------------------------------------------------------- /docs/user_guide/advanced.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/docs/user_guide/advanced.rst -------------------------------------------------------------------------------- /docs/user_guide/api.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/docs/user_guide/api.rst -------------------------------------------------------------------------------- /docs/user_guide/contributors.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/docs/user_guide/contributors.rst -------------------------------------------------------------------------------- /docs/user_guide/quickstart.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/docs/user_guide/quickstart.rst -------------------------------------------------------------------------------- /download_corpora.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/download_corpora.py -------------------------------------------------------------------------------- /newspaper/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/__init__.py -------------------------------------------------------------------------------- /newspaper/api.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/api.py -------------------------------------------------------------------------------- /newspaper/article.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/article.py -------------------------------------------------------------------------------- /newspaper/cleaners.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/cleaners.py -------------------------------------------------------------------------------- /newspaper/configuration.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/configuration.py -------------------------------------------------------------------------------- /newspaper/extractors.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/extractors.py -------------------------------------------------------------------------------- /newspaper/images.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/images.py -------------------------------------------------------------------------------- /newspaper/mthreading.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/mthreading.py -------------------------------------------------------------------------------- /newspaper/network.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/network.py -------------------------------------------------------------------------------- /newspaper/nlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/nlp.py -------------------------------------------------------------------------------- /newspaper/outputformatters.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/outputformatters.py -------------------------------------------------------------------------------- /newspaper/parsers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/parsers.py -------------------------------------------------------------------------------- /newspaper/resources/misc/google_sources.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/misc/google_sources.txt -------------------------------------------------------------------------------- /newspaper/resources/misc/popular_sources.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/misc/popular_sources.txt -------------------------------------------------------------------------------- /newspaper/resources/misc/stopwords-nlp-en.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/misc/stopwords-nlp-en.txt -------------------------------------------------------------------------------- /newspaper/resources/misc/useragents.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/misc/useragents.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-ar.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-ar.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-be.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-be.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-bg.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-bg.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-da.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-da.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-de.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-de.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-el.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-el.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-en.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-en.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-es.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-es.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-et.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-et.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-fa.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-fa.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-fi.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-fi.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-fr.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-fr.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-he.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-he.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-hi.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-hi.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-hr.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-hr.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-hu.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-hu.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-id.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-id.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-it.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-it.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-ja.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-ja.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-ko.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-ko.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-lt.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-lt.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-mk.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-mk.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-nb.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-nb.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-nl.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-nl.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-no.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-no.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-pl.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-pl.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-pt.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-pt.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-ro.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-ro.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-ru.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-ru.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-sl.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-sl.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-sr.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-sr.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-sv.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-sv.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-sw.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-sw.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-th.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-th.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-tr.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-tr.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-uk.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-uk.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-vi.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-vi.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-zh.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/resources/text/stopwords-zh.txt -------------------------------------------------------------------------------- /newspaper/settings.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/settings.py -------------------------------------------------------------------------------- /newspaper/source.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/source.py -------------------------------------------------------------------------------- /newspaper/text.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/text.py -------------------------------------------------------------------------------- /newspaper/urls.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/urls.py -------------------------------------------------------------------------------- /newspaper/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/utils.py -------------------------------------------------------------------------------- /newspaper/version.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/version.py -------------------------------------------------------------------------------- /newspaper/videos/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /newspaper/videos/extractors.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/videos/extractors.py -------------------------------------------------------------------------------- /newspaper/videos/videos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/newspaper/videos/videos.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/requirements.txt -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/setup.py -------------------------------------------------------------------------------- /tests/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/benchmarks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/benchmarks.py -------------------------------------------------------------------------------- /tests/data/fulltext_domain_list.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/fulltext_domain_list.txt -------------------------------------------------------------------------------- /tests/data/fulltext_url_list.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/fulltext_url_list.txt -------------------------------------------------------------------------------- /tests/data/html/247wallst.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/247wallst.com1.html -------------------------------------------------------------------------------- /tests/data/html/247wallst.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/247wallst.com2.html -------------------------------------------------------------------------------- /tests/data/html/about.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/about.com1.html -------------------------------------------------------------------------------- /tests/data/html/about.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/about.com2.html -------------------------------------------------------------------------------- /tests/data/html/adoption.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/adoption.com1.html -------------------------------------------------------------------------------- /tests/data/html/al.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/al.com1.html -------------------------------------------------------------------------------- /tests/data/html/al.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/al.com2.html -------------------------------------------------------------------------------- /tests/data/html/ap_meta_refresh.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/ap_meta_refresh.html -------------------------------------------------------------------------------- /tests/data/html/apartmenttherapy.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/apartmenttherapy.com1.html -------------------------------------------------------------------------------- /tests/data/html/apartmenttherapy.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/apartmenttherapy.com2.html -------------------------------------------------------------------------------- /tests/data/html/arabic_article.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/arabic_article.html -------------------------------------------------------------------------------- /tests/data/html/architecturaldigest.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/architecturaldigest.com1.html -------------------------------------------------------------------------------- /tests/data/html/architecturaldigest.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/architecturaldigest.com2.html -------------------------------------------------------------------------------- /tests/data/html/avclub.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/avclub.com1.html -------------------------------------------------------------------------------- /tests/data/html/avclub.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/avclub.com2.html -------------------------------------------------------------------------------- /tests/data/html/backstage.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/backstage.com1.html -------------------------------------------------------------------------------- /tests/data/html/backstage.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/backstage.com2.html -------------------------------------------------------------------------------- /tests/data/html/bhg.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/bhg.com1.html -------------------------------------------------------------------------------- /tests/data/html/bhg.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/bhg.com2.html -------------------------------------------------------------------------------- /tests/data/html/bloomberg.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/bloomberg.com1.html -------------------------------------------------------------------------------- /tests/data/html/bostonherald.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/bostonherald.com1.html -------------------------------------------------------------------------------- /tests/data/html/bostonherald.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/bostonherald.com2.html -------------------------------------------------------------------------------- /tests/data/html/businessinsider.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/businessinsider.com1.html -------------------------------------------------------------------------------- /tests/data/html/businessinsider.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/businessinsider.com2.html -------------------------------------------------------------------------------- /tests/data/html/businessweek.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/businessweek.com1.html -------------------------------------------------------------------------------- /tests/data/html/businessweek.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/businessweek.com2.html -------------------------------------------------------------------------------- /tests/data/html/chinese_article.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/chinese_article.html -------------------------------------------------------------------------------- /tests/data/html/cleveland.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/cleveland.com1.html -------------------------------------------------------------------------------- /tests/data/html/cleveland.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/cleveland.com2.html -------------------------------------------------------------------------------- /tests/data/html/cnn_article.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/cnn_article.html -------------------------------------------------------------------------------- /tests/data/html/cnn_main_site.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/cnn_main_site.html -------------------------------------------------------------------------------- /tests/data/html/cntraveler.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/cntraveler.com1.html -------------------------------------------------------------------------------- /tests/data/html/cntraveler.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/cntraveler.com2.html -------------------------------------------------------------------------------- /tests/data/html/coolhunting.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/coolhunting.com1.html -------------------------------------------------------------------------------- /tests/data/html/coolhunting.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/coolhunting.com2.html -------------------------------------------------------------------------------- /tests/data/html/cricket.com.au1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/cricket.com.au1.html -------------------------------------------------------------------------------- /tests/data/html/cricket.com.au2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/cricket.com.au2.html -------------------------------------------------------------------------------- /tests/data/html/dailycaller.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/dailycaller.com1.html -------------------------------------------------------------------------------- /tests/data/html/dailycaller.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/dailycaller.com2.html -------------------------------------------------------------------------------- /tests/data/html/dailystar.co.uk1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/dailystar.co.uk1.html -------------------------------------------------------------------------------- /tests/data/html/dailystar.co.uk2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/dailystar.co.uk2.html -------------------------------------------------------------------------------- /tests/data/html/dallasnews.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/dallasnews.com1.html -------------------------------------------------------------------------------- /tests/data/html/dallasnews.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/dallasnews.com2.html -------------------------------------------------------------------------------- /tests/data/html/details.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/details.com1.html -------------------------------------------------------------------------------- /tests/data/html/details.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/details.com2.html -------------------------------------------------------------------------------- /tests/data/html/elle.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/elle.com1.html -------------------------------------------------------------------------------- /tests/data/html/elle.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/elle.com2.html -------------------------------------------------------------------------------- /tests/data/html/flavorwire.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/flavorwire.com1.html -------------------------------------------------------------------------------- /tests/data/html/flavorwire.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/flavorwire.com2.html -------------------------------------------------------------------------------- /tests/data/html/fool.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/fool.com1.html -------------------------------------------------------------------------------- /tests/data/html/fool.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/fool.com2.html -------------------------------------------------------------------------------- /tests/data/html/foxbusiness.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/foxbusiness.com1.html -------------------------------------------------------------------------------- /tests/data/html/foxbusiness.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/foxbusiness.com2.html -------------------------------------------------------------------------------- /tests/data/html/foxnews.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/foxnews.com1.html -------------------------------------------------------------------------------- /tests/data/html/foxnews.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/foxnews.com2.html -------------------------------------------------------------------------------- /tests/data/html/glamour.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/glamour.com1.html -------------------------------------------------------------------------------- /tests/data/html/glamour.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/glamour.com2.html -------------------------------------------------------------------------------- /tests/data/html/globalnews.ca1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/globalnews.ca1.html -------------------------------------------------------------------------------- /tests/data/html/globalnews.ca2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/globalnews.ca2.html -------------------------------------------------------------------------------- /tests/data/html/google_meta_refresh.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/google_meta_refresh.html -------------------------------------------------------------------------------- /tests/data/html/gq.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/gq.com1.html -------------------------------------------------------------------------------- /tests/data/html/gq.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/gq.com2.html -------------------------------------------------------------------------------- /tests/data/html/graziadaily.co.uk1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/graziadaily.co.uk1.html -------------------------------------------------------------------------------- /tests/data/html/graziadaily.co.uk2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/graziadaily.co.uk2.html -------------------------------------------------------------------------------- /tests/data/html/gulflive.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/gulflive.com1.html -------------------------------------------------------------------------------- /tests/data/html/gulflive.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/gulflive.com2.html -------------------------------------------------------------------------------- /tests/data/html/huffingtonpost.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/huffingtonpost.com1.html -------------------------------------------------------------------------------- /tests/data/html/japanese_article.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/japanese_article.html -------------------------------------------------------------------------------- /tests/data/html/japanese_article2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/japanese_article2.html -------------------------------------------------------------------------------- /tests/data/html/lifebuzz.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/lifebuzz.com1.html -------------------------------------------------------------------------------- /tests/data/html/lifebuzz.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/lifebuzz.com2.html -------------------------------------------------------------------------------- /tests/data/html/livescience.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/livescience.com1.html -------------------------------------------------------------------------------- /tests/data/html/livescience.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/livescience.com2.html -------------------------------------------------------------------------------- /tests/data/html/mashable.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/mashable.com1.html -------------------------------------------------------------------------------- /tests/data/html/mashable.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/mashable.com2.html -------------------------------------------------------------------------------- /tests/data/html/mlive.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/mlive.com1.html -------------------------------------------------------------------------------- /tests/data/html/mlive.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/mlive.com2.html -------------------------------------------------------------------------------- /tests/data/html/newyorker.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/newyorker.com1.html -------------------------------------------------------------------------------- /tests/data/html/nj.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/nj.com1.html -------------------------------------------------------------------------------- /tests/data/html/nola.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/nola.com1.html -------------------------------------------------------------------------------- /tests/data/html/nydailynews.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/nydailynews.com1.html -------------------------------------------------------------------------------- /tests/data/html/nypost.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/nypost.com1.html -------------------------------------------------------------------------------- /tests/data/html/nypost.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/nypost.com2.html -------------------------------------------------------------------------------- /tests/data/html/ok.co.uk1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/ok.co.uk1.html -------------------------------------------------------------------------------- /tests/data/html/ok.co.uk2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/ok.co.uk2.html -------------------------------------------------------------------------------- /tests/data/html/oregonlive.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/oregonlive.com1.html -------------------------------------------------------------------------------- /tests/data/html/oregonlive.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/oregonlive.com2.html -------------------------------------------------------------------------------- /tests/data/html/parsely.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/parsely.com1.html -------------------------------------------------------------------------------- /tests/data/html/parsely.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/parsely.com2.html -------------------------------------------------------------------------------- /tests/data/html/pe.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/pe.com1.html -------------------------------------------------------------------------------- /tests/data/html/pewresearch.org1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/pewresearch.org1.html -------------------------------------------------------------------------------- /tests/data/html/pewresearch.org2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/pewresearch.org2.html -------------------------------------------------------------------------------- /tests/data/html/pixable.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/pixable.com1.html -------------------------------------------------------------------------------- /tests/data/html/pixable.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/pixable.com2.html -------------------------------------------------------------------------------- /tests/data/html/pixelmonkey.org1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/pixelmonkey.org1.html -------------------------------------------------------------------------------- /tests/data/html/pixelmonkey.org2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/pixelmonkey.org2.html -------------------------------------------------------------------------------- /tests/data/html/readwrite.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/readwrite.com1.html -------------------------------------------------------------------------------- /tests/data/html/recipe.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/recipe.com1.html -------------------------------------------------------------------------------- /tests/data/html/recipe.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/recipe.com2.html -------------------------------------------------------------------------------- /tests/data/html/reuters.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/reuters.com1.html -------------------------------------------------------------------------------- /tests/data/html/reuters.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/reuters.com2.html -------------------------------------------------------------------------------- /tests/data/html/reuters.com3.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/reuters.com3.html -------------------------------------------------------------------------------- /tests/data/html/reuters.com4.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/reuters.com4.html -------------------------------------------------------------------------------- /tests/data/html/self.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/self.com1.html -------------------------------------------------------------------------------- /tests/data/html/self.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/self.com2.html -------------------------------------------------------------------------------- /tests/data/html/sitepoint.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/sitepoint.com1.html -------------------------------------------------------------------------------- /tests/data/html/sitepoint.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/sitepoint.com2.html -------------------------------------------------------------------------------- /tests/data/html/slate.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/slate.com1.html -------------------------------------------------------------------------------- /tests/data/html/slate.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/slate.com2.html -------------------------------------------------------------------------------- /tests/data/html/space.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/space.com1.html -------------------------------------------------------------------------------- /tests/data/html/space.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/space.com2.html -------------------------------------------------------------------------------- /tests/data/html/spanish_article.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/spanish_article.html -------------------------------------------------------------------------------- /tests/data/html/syracuse.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/syracuse.com1.html -------------------------------------------------------------------------------- /tests/data/html/syracuse.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/syracuse.com2.html -------------------------------------------------------------------------------- /tests/data/html/talkingpointsmemo.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/talkingpointsmemo.com1.html -------------------------------------------------------------------------------- /tests/data/html/technologyreview.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/technologyreview.com1.html -------------------------------------------------------------------------------- /tests/data/html/technologyreview.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/technologyreview.com2.html -------------------------------------------------------------------------------- /tests/data/html/teenvogue.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/teenvogue.com1.html -------------------------------------------------------------------------------- /tests/data/html/teenvogue.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/teenvogue.com2.html -------------------------------------------------------------------------------- /tests/data/html/telegraph.co.uk1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/telegraph.co.uk1.html -------------------------------------------------------------------------------- /tests/data/html/telegraph.co.uk2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/telegraph.co.uk2.html -------------------------------------------------------------------------------- /tests/data/html/thai_article.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/thai_article.html -------------------------------------------------------------------------------- /tests/data/html/theatlantic.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/theatlantic.com1.html -------------------------------------------------------------------------------- /tests/data/html/theatlantic.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/theatlantic.com2.html -------------------------------------------------------------------------------- /tests/data/html/theatlanticcities.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/theatlanticcities.com1.html -------------------------------------------------------------------------------- /tests/data/html/theatlanticcities.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/theatlanticcities.com2.html -------------------------------------------------------------------------------- /tests/data/html/thedailybeast.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/thedailybeast.com1.html -------------------------------------------------------------------------------- /tests/data/html/thedailybeast.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/thedailybeast.com2.html -------------------------------------------------------------------------------- /tests/data/html/thedebrief.co.uk1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/thedebrief.co.uk1.html -------------------------------------------------------------------------------- /tests/data/html/thedebrief.co.uk2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/thedebrief.co.uk2.html -------------------------------------------------------------------------------- /tests/data/html/theglobeandmail.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/theglobeandmail.com1.html -------------------------------------------------------------------------------- /tests/data/html/theglobeandmail.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/theglobeandmail.com2.html -------------------------------------------------------------------------------- /tests/data/html/thekitchn.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/thekitchn.com1.html -------------------------------------------------------------------------------- /tests/data/html/thekitchn.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/thekitchn.com2.html -------------------------------------------------------------------------------- /tests/data/html/thenextweb.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/thenextweb.com1.html -------------------------------------------------------------------------------- /tests/data/html/theonion.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/theonion.com1.html -------------------------------------------------------------------------------- /tests/data/html/theroot.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/theroot.com1.html -------------------------------------------------------------------------------- /tests/data/html/tnr.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/tnr.com1.html -------------------------------------------------------------------------------- /tests/data/html/tnr.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/tnr.com2.html -------------------------------------------------------------------------------- /tests/data/html/uproxx.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/uproxx.com1.html -------------------------------------------------------------------------------- /tests/data/html/uproxx.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/uproxx.com2.html -------------------------------------------------------------------------------- /tests/data/html/upworthy.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/upworthy.com1.html -------------------------------------------------------------------------------- /tests/data/html/upworthy.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/upworthy.com2.html -------------------------------------------------------------------------------- /tests/data/html/usnews.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/usnews.com1.html -------------------------------------------------------------------------------- /tests/data/html/usnews.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/usnews.com2.html -------------------------------------------------------------------------------- /tests/data/html/vanityfair.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/vanityfair.com1.html -------------------------------------------------------------------------------- /tests/data/html/vogue.de1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/vogue.de1.html -------------------------------------------------------------------------------- /tests/data/html/vogue.de2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/vogue.de2.html -------------------------------------------------------------------------------- /tests/data/html/wetpaint.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/wetpaint.com1.html -------------------------------------------------------------------------------- /tests/data/html/wetpaint.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/wetpaint.com2.html -------------------------------------------------------------------------------- /tests/data/html/wired.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/wired.com1.html -------------------------------------------------------------------------------- /tests/data/html/wired.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/wired.com2.html -------------------------------------------------------------------------------- /tests/data/html/wnet.org1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/wnet.org1.html -------------------------------------------------------------------------------- /tests/data/html/wnet.org2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/wnet.org2.html -------------------------------------------------------------------------------- /tests/data/html/yahoo_main_site.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/yahoo_main_site.html -------------------------------------------------------------------------------- /tests/data/html/youbeauty.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/youbeauty.com1.html -------------------------------------------------------------------------------- /tests/data/html/youbeauty.com2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/html/youbeauty.com2.html -------------------------------------------------------------------------------- /tests/data/test_prepare_urls.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/test_prepare_urls.txt -------------------------------------------------------------------------------- /tests/data/test_urls.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/test_urls.txt -------------------------------------------------------------------------------- /tests/data/test_urls_pubdate.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/test_urls_pubdate.txt -------------------------------------------------------------------------------- /tests/data/text/247wallst.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/247wallst.com1.txt -------------------------------------------------------------------------------- /tests/data/text/247wallst.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/247wallst.com2.txt -------------------------------------------------------------------------------- /tests/data/text/about.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/about.com1.txt -------------------------------------------------------------------------------- /tests/data/text/about.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/about.com2.txt -------------------------------------------------------------------------------- /tests/data/text/adoption.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/adoption.com1.txt -------------------------------------------------------------------------------- /tests/data/text/al.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/al.com1.txt -------------------------------------------------------------------------------- /tests/data/text/al.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/al.com2.txt -------------------------------------------------------------------------------- /tests/data/text/apartmenttherapy.com1.txt: -------------------------------------------------------------------------------- 1 | ONLY EXTRACTED AUTHOR BLURB AFTER THE ACTUAL ARTICLE -------------------------------------------------------------------------------- /tests/data/text/apartmenttherapy.com2.txt: -------------------------------------------------------------------------------- 1 | EXTRACTED NOTHING 2 | -------------------------------------------------------------------------------- /tests/data/text/arabic.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/arabic.txt -------------------------------------------------------------------------------- /tests/data/text/architecturaldigest.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/architecturaldigest.com1.txt -------------------------------------------------------------------------------- /tests/data/text/architecturaldigest.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/architecturaldigest.com2.txt -------------------------------------------------------------------------------- /tests/data/text/avclub.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/avclub.com1.txt -------------------------------------------------------------------------------- /tests/data/text/avclub.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/avclub.com2.txt -------------------------------------------------------------------------------- /tests/data/text/backstage.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/backstage.com1.txt -------------------------------------------------------------------------------- /tests/data/text/backstage.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/backstage.com2.txt -------------------------------------------------------------------------------- /tests/data/text/bhg.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/bhg.com1.txt -------------------------------------------------------------------------------- /tests/data/text/bhg.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/bhg.com2.txt -------------------------------------------------------------------------------- /tests/data/text/bloomberg.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/bloomberg.com1.txt -------------------------------------------------------------------------------- /tests/data/text/bostonherald.com1.txt: -------------------------------------------------------------------------------- 1 | MISSED TINY PARAGRAPH AT THE VERY END 2 | -------------------------------------------------------------------------------- /tests/data/text/bostonherald.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/bostonherald.com2.txt -------------------------------------------------------------------------------- /tests/data/text/businessinsider.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/businessinsider.com1.txt -------------------------------------------------------------------------------- /tests/data/text/businessinsider.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/businessinsider.com2.txt -------------------------------------------------------------------------------- /tests/data/text/businessweek.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/businessweek.com1.txt -------------------------------------------------------------------------------- /tests/data/text/businessweek.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/businessweek.com2.txt -------------------------------------------------------------------------------- /tests/data/text/chinese.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/chinese.txt -------------------------------------------------------------------------------- /tests/data/text/cleveland.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/cleveland.com1.txt -------------------------------------------------------------------------------- /tests/data/text/cleveland.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/cleveland.com2.txt -------------------------------------------------------------------------------- /tests/data/text/cnn.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/cnn.txt -------------------------------------------------------------------------------- /tests/data/text/cnn_summary.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/cnn_summary.txt -------------------------------------------------------------------------------- /tests/data/text/cntraveler.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/cntraveler.com1.txt -------------------------------------------------------------------------------- /tests/data/text/cntraveler.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/cntraveler.com2.txt -------------------------------------------------------------------------------- /tests/data/text/coolhunting.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/coolhunting.com1.txt -------------------------------------------------------------------------------- /tests/data/text/cricket.com.au1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/cricket.com.au1.txt -------------------------------------------------------------------------------- /tests/data/text/cricket.com.au2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/cricket.com.au2.txt -------------------------------------------------------------------------------- /tests/data/text/dailycaller.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/dailycaller.com1.txt -------------------------------------------------------------------------------- /tests/data/text/dailycaller.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/dailycaller.com2.txt -------------------------------------------------------------------------------- /tests/data/text/dailystar.co.uk1.txt: -------------------------------------------------------------------------------- 1 | ONLY EXTRACTS ARTICLE UP UNTIL THE FIRST IMAGE 2 | -------------------------------------------------------------------------------- /tests/data/text/dailystar.co.uk2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/dailystar.co.uk2.txt -------------------------------------------------------------------------------- /tests/data/text/dallasnews.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/dallasnews.com1.txt -------------------------------------------------------------------------------- /tests/data/text/dallasnews.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/dallasnews.com2.txt -------------------------------------------------------------------------------- /tests/data/text/details.com1.txt: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/data/text/details.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/details.com2.txt -------------------------------------------------------------------------------- /tests/data/text/elle.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/elle.com1.txt -------------------------------------------------------------------------------- /tests/data/text/elle.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/elle.com2.txt -------------------------------------------------------------------------------- /tests/data/text/flavorwire.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/flavorwire.com1.txt -------------------------------------------------------------------------------- /tests/data/text/flavorwire.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/flavorwire.com2.txt -------------------------------------------------------------------------------- /tests/data/text/fool.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/fool.com1.txt -------------------------------------------------------------------------------- /tests/data/text/fool.com2.txt: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/data/text/foxbusiness.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/foxbusiness.com1.txt -------------------------------------------------------------------------------- /tests/data/text/foxbusiness.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/foxbusiness.com2.txt -------------------------------------------------------------------------------- /tests/data/text/foxnews.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/foxnews.com1.txt -------------------------------------------------------------------------------- /tests/data/text/foxnews.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/foxnews.com2.txt -------------------------------------------------------------------------------- /tests/data/text/foxnews.com3.txt: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/data/text/foxnews.com4.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/foxnews.com4.txt -------------------------------------------------------------------------------- /tests/data/text/glamour.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/glamour.com1.txt -------------------------------------------------------------------------------- /tests/data/text/glamour.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/glamour.com2.txt -------------------------------------------------------------------------------- /tests/data/text/globalnews.ca1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/globalnews.ca1.txt -------------------------------------------------------------------------------- /tests/data/text/globalnews.ca2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/globalnews.ca2.txt -------------------------------------------------------------------------------- /tests/data/text/gq.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/gq.com1.txt -------------------------------------------------------------------------------- /tests/data/text/gq.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/gq.com2.txt -------------------------------------------------------------------------------- /tests/data/text/graziadaily.co.uk1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/graziadaily.co.uk1.txt -------------------------------------------------------------------------------- /tests/data/text/graziadaily.co.uk2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/graziadaily.co.uk2.txt -------------------------------------------------------------------------------- /tests/data/text/gulflive.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/gulflive.com1.txt -------------------------------------------------------------------------------- /tests/data/text/gulflive.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/gulflive.com2.txt -------------------------------------------------------------------------------- /tests/data/text/huffingtonpost.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/huffingtonpost.com1.txt -------------------------------------------------------------------------------- /tests/data/text/japanese.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/japanese.txt -------------------------------------------------------------------------------- /tests/data/text/japanese2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/japanese2.txt -------------------------------------------------------------------------------- /tests/data/text/lifebuzz.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/lifebuzz.com1.txt -------------------------------------------------------------------------------- /tests/data/text/lifebuzz.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/lifebuzz.com2.txt -------------------------------------------------------------------------------- /tests/data/text/livescience.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/livescience.com1.txt -------------------------------------------------------------------------------- /tests/data/text/livescience.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/livescience.com2.txt -------------------------------------------------------------------------------- /tests/data/text/mashable.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/mashable.com1.txt -------------------------------------------------------------------------------- /tests/data/text/mashable.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/mashable.com2.txt -------------------------------------------------------------------------------- /tests/data/text/mlive.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/mlive.com1.txt -------------------------------------------------------------------------------- /tests/data/text/mlive.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/mlive.com2.txt -------------------------------------------------------------------------------- /tests/data/text/newyorker.com1.txt: -------------------------------------------------------------------------------- 1 | VERY LAST LINE IN THE POEM IS MISSED 2 | -------------------------------------------------------------------------------- /tests/data/text/nj.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/nj.com1.txt -------------------------------------------------------------------------------- /tests/data/text/nola.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/nola.com1.txt -------------------------------------------------------------------------------- /tests/data/text/nydailynews.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/nydailynews.com1.txt -------------------------------------------------------------------------------- /tests/data/text/nypost.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/nypost.com1.txt -------------------------------------------------------------------------------- /tests/data/text/nypost.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/nypost.com2.txt -------------------------------------------------------------------------------- /tests/data/text/ok.co.uk1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/ok.co.uk1.txt -------------------------------------------------------------------------------- /tests/data/text/ok.co.uk2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/ok.co.uk2.txt -------------------------------------------------------------------------------- /tests/data/text/oregonlive.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/oregonlive.com1.txt -------------------------------------------------------------------------------- /tests/data/text/oregonlive.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/oregonlive.com2.txt -------------------------------------------------------------------------------- /tests/data/text/parsely.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/parsely.com1.txt -------------------------------------------------------------------------------- /tests/data/text/parsely.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/parsely.com2.txt -------------------------------------------------------------------------------- /tests/data/text/pe.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/pe.com1.txt -------------------------------------------------------------------------------- /tests/data/text/pewresearch.org1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/pewresearch.org1.txt -------------------------------------------------------------------------------- /tests/data/text/pewresearch.org2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/pewresearch.org2.txt -------------------------------------------------------------------------------- /tests/data/text/pixable.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/pixable.com1.txt -------------------------------------------------------------------------------- /tests/data/text/pixable.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/pixable.com2.txt -------------------------------------------------------------------------------- /tests/data/text/pixelmonkey.org1.txt: -------------------------------------------------------------------------------- 1 | MISSED LAST SENTENCE IN THE ARTICLE 2 | -------------------------------------------------------------------------------- /tests/data/text/pixelmonkey.org2.txt: -------------------------------------------------------------------------------- 1 | ONLY "More coming soon!" AT END OF ARTICLE WAS EXTRACTED 2 | -------------------------------------------------------------------------------- /tests/data/text/readwrite.com1.txt: -------------------------------------------------------------------------------- 1 | FAILED, ENTIRE ARTICLE LOADED VIA JS 2 | -------------------------------------------------------------------------------- /tests/data/text/recipe.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/recipe.com1.txt -------------------------------------------------------------------------------- /tests/data/text/recipe.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/recipe.com2.txt -------------------------------------------------------------------------------- /tests/data/text/reuters.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/reuters.com1.txt -------------------------------------------------------------------------------- /tests/data/text/reuters.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/reuters.com2.txt -------------------------------------------------------------------------------- /tests/data/text/reuters.com3.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/reuters.com3.txt -------------------------------------------------------------------------------- /tests/data/text/reuters.com4.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/reuters.com4.txt -------------------------------------------------------------------------------- /tests/data/text/reuters.com5.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/reuters.com5.txt -------------------------------------------------------------------------------- /tests/data/text/reuters.com6.txt: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/data/text/self.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/self.com1.txt -------------------------------------------------------------------------------- /tests/data/text/self.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/self.com2.txt -------------------------------------------------------------------------------- /tests/data/text/sitepoint.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/sitepoint.com1.txt -------------------------------------------------------------------------------- /tests/data/text/sitepoint.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/sitepoint.com2.txt -------------------------------------------------------------------------------- /tests/data/text/slate.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/slate.com1.txt -------------------------------------------------------------------------------- /tests/data/text/slate.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/slate.com2.txt -------------------------------------------------------------------------------- /tests/data/text/space.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/space.com1.txt -------------------------------------------------------------------------------- /tests/data/text/space.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/space.com2.txt -------------------------------------------------------------------------------- /tests/data/text/spanish.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/spanish.txt -------------------------------------------------------------------------------- /tests/data/text/syracuse.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/syracuse.com1.txt -------------------------------------------------------------------------------- /tests/data/text/syracuse.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/syracuse.com2.txt -------------------------------------------------------------------------------- /tests/data/text/talkingpointsmemo.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/talkingpointsmemo.com1.txt -------------------------------------------------------------------------------- /tests/data/text/technologyreview.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/technologyreview.com1.txt -------------------------------------------------------------------------------- /tests/data/text/technologyreview.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/technologyreview.com2.txt -------------------------------------------------------------------------------- /tests/data/text/teenvogue.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/teenvogue.com1.txt -------------------------------------------------------------------------------- /tests/data/text/teenvogue.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/teenvogue.com2.txt -------------------------------------------------------------------------------- /tests/data/text/telegraph.co.uk1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/telegraph.co.uk1.txt -------------------------------------------------------------------------------- /tests/data/text/telegraph.co.uk2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/telegraph.co.uk2.txt -------------------------------------------------------------------------------- /tests/data/text/thai.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/thai.txt -------------------------------------------------------------------------------- /tests/data/text/theatlantic.com1.txt: -------------------------------------------------------------------------------- 1 | MISSES SECOND HALF OF ARTICLE 2 | -------------------------------------------------------------------------------- /tests/data/text/theatlantic.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/theatlantic.com2.txt -------------------------------------------------------------------------------- /tests/data/text/theatlanticcities.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/theatlanticcities.com1.txt -------------------------------------------------------------------------------- /tests/data/text/theatlanticcities.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/theatlanticcities.com2.txt -------------------------------------------------------------------------------- /tests/data/text/thedailybeast.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/thedailybeast.com1.txt -------------------------------------------------------------------------------- /tests/data/text/thedailybeast.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/thedailybeast.com2.txt -------------------------------------------------------------------------------- /tests/data/text/thedebrief.co.uk1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/thedebrief.co.uk1.txt -------------------------------------------------------------------------------- /tests/data/text/thedebrief.co.uk2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/thedebrief.co.uk2.txt -------------------------------------------------------------------------------- /tests/data/text/theglobeandmail.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/theglobeandmail.com1.txt -------------------------------------------------------------------------------- /tests/data/text/theglobeandmail.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/theglobeandmail.com2.txt -------------------------------------------------------------------------------- /tests/data/text/thekitchn.com1.txt: -------------------------------------------------------------------------------- 1 | ONLY EXTRACTED AUTHOR BLURB -------------------------------------------------------------------------------- /tests/data/text/thekitchn.com2.txt: -------------------------------------------------------------------------------- 1 | ONLY EXTRACTED AUTHOR BLURB -------------------------------------------------------------------------------- /tests/data/text/thenextweb.com1.txt: -------------------------------------------------------------------------------- 1 | FAILED, MISSING ARTICLE AFTR FIRST PARAGRAPH 2 | -------------------------------------------------------------------------------- /tests/data/text/theonion.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/theonion.com1.txt -------------------------------------------------------------------------------- /tests/data/text/theroot.com1.txt: -------------------------------------------------------------------------------- 1 | MISSED LAST PARAGRAPH 2 | -------------------------------------------------------------------------------- /tests/data/text/tnr.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/tnr.com1.txt -------------------------------------------------------------------------------- /tests/data/text/tnr.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/tnr.com2.txt -------------------------------------------------------------------------------- /tests/data/text/uproxx.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/uproxx.com1.txt -------------------------------------------------------------------------------- /tests/data/text/uproxx.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/uproxx.com2.txt -------------------------------------------------------------------------------- /tests/data/text/upworthy.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/upworthy.com1.txt -------------------------------------------------------------------------------- /tests/data/text/upworthy.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/upworthy.com2.txt -------------------------------------------------------------------------------- /tests/data/text/usnews.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/usnews.com1.txt -------------------------------------------------------------------------------- /tests/data/text/usnews.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/usnews.com2.txt -------------------------------------------------------------------------------- /tests/data/text/vanityfair.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/vanityfair.com1.txt -------------------------------------------------------------------------------- /tests/data/text/vogue.de1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/vogue.de1.txt -------------------------------------------------------------------------------- /tests/data/text/vogue.de2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/vogue.de2.txt -------------------------------------------------------------------------------- /tests/data/text/wetpaint.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/wetpaint.com1.txt -------------------------------------------------------------------------------- /tests/data/text/wetpaint.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/wetpaint.com2.txt -------------------------------------------------------------------------------- /tests/data/text/wired.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/wired.com1.txt -------------------------------------------------------------------------------- /tests/data/text/wired.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/wired.com2.txt -------------------------------------------------------------------------------- /tests/data/text/wnet.org1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/wnet.org1.txt -------------------------------------------------------------------------------- /tests/data/text/wnet.org2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/wnet.org2.txt -------------------------------------------------------------------------------- /tests/data/text/youbeauty.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/youbeauty.com1.txt -------------------------------------------------------------------------------- /tests/data/text/youbeauty.com2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/data/text/youbeauty.com2.txt -------------------------------------------------------------------------------- /tests/unit_tests.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codelucas/newspaper/HEAD/tests/unit_tests.py --------------------------------------------------------------------------------