├── .codespell-dictionary.txt ├── .gitattributes ├── .github ├── ISSUE_TEMPLATE │ ├── bug_report.md │ ├── feature_request.md │ ├── questions---help---documentation.md │ └── website---newssite-not-parsing-correctly.md ├── pull_request_template.md └── workflows │ ├── pipeline.yml │ └── python-publish.yml ├── .gitignore ├── .pre-commit-config.yaml ├── .python-version ├── .readthedocs.yaml ├── .travis.yml ├── CHANGELOG.md ├── CONTRIBUTING.md ├── GOOSE-LICENSE.txt ├── LANGUAGES.md ├── LICENSE ├── MANIFEST.in ├── README.md ├── docs ├── Makefile ├── _static │ ├── newspaper.jpg │ ├── recording-cli.gif │ └── recording-python.gif ├── conf.py ├── index.rst ├── make.bat ├── requirements.in ├── requirements.txt └── user_guide │ ├── advanced.rst │ ├── api_reference.rst │ ├── assets │ ├── chatgpt_chat200x75.png │ ├── chatgpt_chat75x75.png │ ├── edit_tutorials.png │ ├── logo_v1_150.png │ └── logo_v1_670.png │ ├── cli_reference.rst │ ├── examples.rst │ ├── faq.rst │ ├── installation.rst │ ├── known_issues.rst │ ├── known_newssites.rst │ ├── known_sites_not_working.csv │ ├── languages.rst │ └── quickstart.rst ├── evaluation ├── __init__.py ├── evaluate.py ├── evaluate_all └── helper.py ├── mypy.ini ├── newspaper ├── __init__.py ├── __main__.py ├── api.py ├── article.py ├── cleaners.py ├── cli.py ├── configuration.py ├── exceptions.py ├── extractors │ ├── __init__.py │ ├── articlebody_extractor.py │ ├── authors_extractor.py │ ├── categories_extractor.py │ ├── content_extractor.py │ ├── defines.py │ ├── image_extractor.py │ ├── metadata_extractor.py │ ├── pubdate_extractor.py │ ├── title_extractor.py │ └── videos_extractor.py ├── google_news.py ├── languages │ ├── __init__.py │ ├── ar.py │ ├── bn.py │ ├── hi.py │ ├── ja.py │ ├── ko.py │ ├── my.py │ ├── ne.py │ ├── ta.py │ ├── th.py │ └── zh.py ├── mthreading.py ├── network.py ├── nlp.py ├── outputformatters.py ├── parsers.py ├── resources │ ├── misc │ │ ├── google_sources.txt │ │ ├── popular_sources.txt │ │ └── useragents.txt │ └── text │ │ ├── stopwords-af.txt │ │ ├── stopwords-ar.txt │ │ ├── stopwords-as.txt │ │ ├── stopwords-be.txt │ │ ├── stopwords-bg.txt │ │ ├── stopwords-bn.txt │ │ ├── stopwords-br.txt │ │ ├── stopwords-ca.txt │ │ ├── stopwords-cs.txt │ │ ├── stopwords-cy.txt │ │ ├── stopwords-da.txt │ │ ├── stopwords-de.txt │ │ ├── stopwords-el.txt │ │ ├── stopwords-en.txt │ │ ├── stopwords-eo.txt │ │ ├── stopwords-es.txt │ │ ├── stopwords-et.txt │ │ ├── stopwords-eu.txt │ │ ├── stopwords-fa.txt │ │ ├── stopwords-fi.txt │ │ ├── stopwords-fr.txt │ │ ├── stopwords-ga.txt │ │ ├── stopwords-gl.txt │ │ ├── stopwords-gu.txt │ │ ├── stopwords-ha.txt │ │ ├── stopwords-he.txt │ │ ├── stopwords-hi.txt │ │ ├── stopwords-hr.txt │ │ ├── stopwords-hu.txt │ │ ├── stopwords-hy.txt │ │ ├── stopwords-id.txt │ │ ├── stopwords-is.txt │ │ ├── stopwords-it.txt │ │ ├── stopwords-ja.txt │ │ ├── stopwords-ka.txt │ │ ├── stopwords-kn.txt │ │ ├── stopwords-ko.txt │ │ ├── stopwords-ku.txt │ │ ├── stopwords-lb.txt │ │ ├── stopwords-lt.txt │ │ ├── stopwords-lv.txt │ │ ├── stopwords-mk.txt │ │ ├── stopwords-mn.txt │ │ ├── stopwords-mr.txt │ │ ├── stopwords-ms.txt │ │ ├── stopwords-my.txt │ │ ├── stopwords-nb.txt │ │ ├── stopwords-ne.txt │ │ ├── stopwords-nl.txt │ │ ├── stopwords-no.txt │ │ ├── stopwords-pa.txt │ │ ├── stopwords-pl.txt │ │ ├── stopwords-ps.txt │ │ ├── stopwords-pt.txt │ │ ├── stopwords-rn.txt │ │ ├── stopwords-ro.txt │ │ ├── stopwords-ru.txt │ │ ├── stopwords-rw.txt │ │ ├── stopwords-si.txt │ │ ├── stopwords-sk.txt │ │ ├── stopwords-sl.txt │ │ ├── stopwords-so.txt │ │ ├── stopwords-sr.txt │ │ ├── stopwords-st.txt │ │ ├── stopwords-sv.txt │ │ ├── stopwords-sw.txt │ │ ├── stopwords-ta.txt │ │ ├── stopwords-te.txt │ │ ├── stopwords-th.txt │ │ ├── stopwords-tl.txt │ │ ├── stopwords-tr.txt │ │ ├── stopwords-tt.txt │ │ ├── stopwords-uk.txt │ │ ├── stopwords-ur.txt │ │ ├── stopwords-uz.txt │ │ ├── stopwords-vi.txt │ │ ├── stopwords-yo.txt │ │ ├── stopwords-zh.txt │ │ └── stopwords-zu.txt ├── settings.py ├── source.py ├── text.py ├── urls.py ├── utils │ ├── __init__.py │ └── classes.py └── version.py ├── pyproject.toml ├── pytest.ini ├── requirements.txt ├── stubs ├── cloudscraper │ └── __init__.pyi ├── feedparser.pyi ├── gnews.pyi ├── gnews │ ├── __init__.pyi │ ├── gnews.pyi │ └── utils │ │ ├── constants.pyi │ │ └── utils.pyi ├── indicnlp │ └── tokenize │ │ └── indic_tokenize.pyi ├── jieba.pyi ├── nltk │ ├── __init__.pyi │ ├── data.pyi │ └── tokenize.pyi ├── pythainlp.pyi └── tinysegmenter.pyi └── tests ├── __init__.py ├── conftest.py ├── data ├── fulltext_domain_list.txt ├── fulltext_url_list.txt ├── html │ ├── ap_meta_refresh.html │ ├── arabic_article.html │ ├── article_with_br.html │ ├── article_with_divs.html │ ├── autoindustria.html │ ├── burmese_article.html │ ├── chinese_article.html │ ├── chinese_article_001.html │ ├── chinese_article_002.html │ ├── cleveland.com1.html │ ├── cnn_001.html │ ├── cnn_002.html │ ├── cnn_article.html │ ├── cnn_main_site.html │ ├── cnn_test_nlp.html │ ├── fox13now_001.html │ ├── google_meta_refresh.html │ ├── japanese_article.html │ ├── japanese_article2.html │ ├── latvian_article.html │ ├── sample_rss.html │ ├── spanish_article.html │ ├── thai_article.html │ ├── time_001.html │ ├── video_article_01.html │ ├── video_article_02.html │ ├── wired_001.html │ ├── wired_main_site.html │ ├── yahoo_main_site.html │ └── yna_co_kr.html ├── metadata │ ├── arabic_article.json │ ├── article_with_br.json │ ├── article_with_divs.json │ ├── chinese_article_001.json │ ├── chinese_article_002.json │ ├── cleveland.com1.json │ ├── cnn_001.json │ ├── cnn_002.json │ ├── cnn_article.json │ ├── cnn_test_nlp.json │ ├── fox13now_001.json │ ├── japanese_article.json │ ├── japanese_article2.json │ ├── spanish_article.json │ ├── thai_article.json │ ├── time_001.json │ ├── video_article_01.json │ ├── video_article_02.json │ ├── wired_001.json │ └── yna_co_kr.json ├── test_prepare_urls.txt ├── test_urls.txt ├── test_urls_pubdate.txt └── txt │ ├── arabic_article.txt │ ├── article_with_br.txt │ ├── article_with_divs.txt │ ├── bengali_article.txt │ ├── burmese_article.txt │ ├── chinese_article.txt │ ├── chinese_article_001.txt │ ├── chinese_article_002.txt │ ├── cleveland.com1.txt │ ├── cnn_001.txt │ ├── cnn_002.txt │ ├── cnn_article.txt │ ├── cnn_summary.txt │ ├── cnn_test_nlp.txt │ ├── fox13now_001.txt │ ├── hindi_article.txt │ ├── japanese_article.txt │ ├── japanese_article2.txt │ ├── korean_article.txt │ ├── latvian_article.txt │ ├── nepali_article.txt │ ├── spanish_article.txt │ ├── thai_article.txt │ ├── time_001.txt │ ├── video_article_01.txt │ ├── video_article_02.txt │ ├── wired_001.txt │ └── yna_co_kr.txt ├── e2e ├── __init__.py ├── conftest.py ├── test_article.py ├── test_cli.py └── test_source.py ├── helpers ├── create_test_data.py ├── create_test_data_duplicates └── get_many_articles.py ├── integration ├── __init__.py ├── conftest.py ├── test_article.py ├── test_cli.py ├── test_cookies.py ├── test_languages.py ├── test_misc.py ├── test_pdf.py ├── test_requests.py └── test_source.py ├── test_smoke.py └── unit ├── __init__.py ├── conftest.py ├── test_article.py ├── test_category_extractor.py ├── test_cleaners.py ├── test_cli.py ├── test_configuration.py ├── test_cookies.py ├── test_languages.py ├── test_misc.py ├── test_network.py ├── test_nlp.py ├── test_parsing.py ├── test_pdf.py ├── test_requests.py ├── test_source.py └── test_urls.py /.codespell-dictionary.txt: -------------------------------------------------------------------------------- 1 | doubleclick 2 | te 3 | shotcut 4 | annonces 5 | -------------------------------------------------------------------------------- /.gitattributes: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/.gitattributes -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/bug_report.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/.github/ISSUE_TEMPLATE/bug_report.md -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/feature_request.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/.github/ISSUE_TEMPLATE/feature_request.md -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/questions---help---documentation.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/.github/ISSUE_TEMPLATE/questions---help---documentation.md -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/website---newssite-not-parsing-correctly.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/.github/ISSUE_TEMPLATE/website---newssite-not-parsing-correctly.md -------------------------------------------------------------------------------- /.github/pull_request_template.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/.github/pull_request_template.md -------------------------------------------------------------------------------- /.github/workflows/pipeline.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/.github/workflows/pipeline.yml -------------------------------------------------------------------------------- /.github/workflows/python-publish.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/.github/workflows/python-publish.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/.gitignore -------------------------------------------------------------------------------- /.pre-commit-config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/.pre-commit-config.yaml -------------------------------------------------------------------------------- /.python-version: -------------------------------------------------------------------------------- 1 | 3.12 2 | -------------------------------------------------------------------------------- /.readthedocs.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/.readthedocs.yaml -------------------------------------------------------------------------------- /.travis.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/.travis.yml -------------------------------------------------------------------------------- /CHANGELOG.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/CHANGELOG.md -------------------------------------------------------------------------------- /CONTRIBUTING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/CONTRIBUTING.md -------------------------------------------------------------------------------- /GOOSE-LICENSE.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/GOOSE-LICENSE.txt -------------------------------------------------------------------------------- /LANGUAGES.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/LANGUAGES.md -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/LICENSE -------------------------------------------------------------------------------- /MANIFEST.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/MANIFEST.in -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/README.md -------------------------------------------------------------------------------- /docs/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/docs/Makefile -------------------------------------------------------------------------------- /docs/_static/newspaper.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/docs/_static/newspaper.jpg -------------------------------------------------------------------------------- /docs/_static/recording-cli.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/docs/_static/recording-cli.gif -------------------------------------------------------------------------------- /docs/_static/recording-python.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/docs/_static/recording-python.gif -------------------------------------------------------------------------------- /docs/conf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/docs/conf.py -------------------------------------------------------------------------------- /docs/index.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/docs/index.rst -------------------------------------------------------------------------------- /docs/make.bat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/docs/make.bat -------------------------------------------------------------------------------- /docs/requirements.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/docs/requirements.in -------------------------------------------------------------------------------- /docs/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/docs/requirements.txt -------------------------------------------------------------------------------- /docs/user_guide/advanced.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/docs/user_guide/advanced.rst -------------------------------------------------------------------------------- /docs/user_guide/api_reference.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/docs/user_guide/api_reference.rst -------------------------------------------------------------------------------- /docs/user_guide/assets/chatgpt_chat200x75.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/docs/user_guide/assets/chatgpt_chat200x75.png -------------------------------------------------------------------------------- /docs/user_guide/assets/chatgpt_chat75x75.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/docs/user_guide/assets/chatgpt_chat75x75.png -------------------------------------------------------------------------------- /docs/user_guide/assets/edit_tutorials.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/docs/user_guide/assets/edit_tutorials.png -------------------------------------------------------------------------------- /docs/user_guide/assets/logo_v1_150.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/docs/user_guide/assets/logo_v1_150.png -------------------------------------------------------------------------------- /docs/user_guide/assets/logo_v1_670.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/docs/user_guide/assets/logo_v1_670.png -------------------------------------------------------------------------------- /docs/user_guide/cli_reference.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/docs/user_guide/cli_reference.rst -------------------------------------------------------------------------------- /docs/user_guide/examples.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/docs/user_guide/examples.rst -------------------------------------------------------------------------------- /docs/user_guide/faq.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/docs/user_guide/faq.rst -------------------------------------------------------------------------------- /docs/user_guide/installation.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/docs/user_guide/installation.rst -------------------------------------------------------------------------------- /docs/user_guide/known_issues.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/docs/user_guide/known_issues.rst -------------------------------------------------------------------------------- /docs/user_guide/known_newssites.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/docs/user_guide/known_newssites.rst -------------------------------------------------------------------------------- /docs/user_guide/known_sites_not_working.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/docs/user_guide/known_sites_not_working.csv -------------------------------------------------------------------------------- /docs/user_guide/languages.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/docs/user_guide/languages.rst -------------------------------------------------------------------------------- /docs/user_guide/quickstart.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/docs/user_guide/quickstart.rst -------------------------------------------------------------------------------- /evaluation/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation/evaluate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/evaluation/evaluate.py -------------------------------------------------------------------------------- /evaluation/evaluate_all: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/evaluation/evaluate_all -------------------------------------------------------------------------------- /evaluation/helper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/evaluation/helper.py -------------------------------------------------------------------------------- /mypy.ini: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/mypy.ini -------------------------------------------------------------------------------- /newspaper/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/__init__.py -------------------------------------------------------------------------------- /newspaper/__main__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/__main__.py -------------------------------------------------------------------------------- /newspaper/api.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/api.py -------------------------------------------------------------------------------- /newspaper/article.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/article.py -------------------------------------------------------------------------------- /newspaper/cleaners.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/cleaners.py -------------------------------------------------------------------------------- /newspaper/cli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/cli.py -------------------------------------------------------------------------------- /newspaper/configuration.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/configuration.py -------------------------------------------------------------------------------- /newspaper/exceptions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/exceptions.py -------------------------------------------------------------------------------- /newspaper/extractors/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/extractors/__init__.py -------------------------------------------------------------------------------- /newspaper/extractors/articlebody_extractor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/extractors/articlebody_extractor.py -------------------------------------------------------------------------------- /newspaper/extractors/authors_extractor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/extractors/authors_extractor.py -------------------------------------------------------------------------------- /newspaper/extractors/categories_extractor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/extractors/categories_extractor.py -------------------------------------------------------------------------------- /newspaper/extractors/content_extractor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/extractors/content_extractor.py -------------------------------------------------------------------------------- /newspaper/extractors/defines.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/extractors/defines.py -------------------------------------------------------------------------------- /newspaper/extractors/image_extractor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/extractors/image_extractor.py -------------------------------------------------------------------------------- /newspaper/extractors/metadata_extractor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/extractors/metadata_extractor.py -------------------------------------------------------------------------------- /newspaper/extractors/pubdate_extractor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/extractors/pubdate_extractor.py -------------------------------------------------------------------------------- /newspaper/extractors/title_extractor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/extractors/title_extractor.py -------------------------------------------------------------------------------- /newspaper/extractors/videos_extractor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/extractors/videos_extractor.py -------------------------------------------------------------------------------- /newspaper/google_news.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/google_news.py -------------------------------------------------------------------------------- /newspaper/languages/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/languages/__init__.py -------------------------------------------------------------------------------- /newspaper/languages/ar.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/languages/ar.py -------------------------------------------------------------------------------- /newspaper/languages/bn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/languages/bn.py -------------------------------------------------------------------------------- /newspaper/languages/hi.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/languages/hi.py -------------------------------------------------------------------------------- /newspaper/languages/ja.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/languages/ja.py -------------------------------------------------------------------------------- /newspaper/languages/ko.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/languages/ko.py -------------------------------------------------------------------------------- /newspaper/languages/my.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/languages/my.py -------------------------------------------------------------------------------- /newspaper/languages/ne.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/languages/ne.py -------------------------------------------------------------------------------- /newspaper/languages/ta.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/languages/ta.py -------------------------------------------------------------------------------- /newspaper/languages/th.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/languages/th.py -------------------------------------------------------------------------------- /newspaper/languages/zh.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/languages/zh.py -------------------------------------------------------------------------------- /newspaper/mthreading.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/mthreading.py -------------------------------------------------------------------------------- /newspaper/network.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/network.py -------------------------------------------------------------------------------- /newspaper/nlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/nlp.py -------------------------------------------------------------------------------- /newspaper/outputformatters.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/outputformatters.py -------------------------------------------------------------------------------- /newspaper/parsers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/parsers.py -------------------------------------------------------------------------------- /newspaper/resources/misc/google_sources.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/misc/google_sources.txt -------------------------------------------------------------------------------- /newspaper/resources/misc/popular_sources.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/misc/popular_sources.txt -------------------------------------------------------------------------------- /newspaper/resources/misc/useragents.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/misc/useragents.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-af.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-af.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-ar.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-ar.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-as.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-as.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-be.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-be.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-bg.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-bg.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-bn.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-bn.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-br.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-br.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-ca.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-ca.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-cs.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-cs.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-cy.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-cy.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-da.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-da.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-de.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-de.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-el.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-el.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-en.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-en.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-eo.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-eo.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-es.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-es.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-et.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-et.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-eu.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-eu.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-fa.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-fa.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-fi.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-fi.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-fr.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-fr.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-ga.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-ga.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-gl.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-gl.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-gu.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-gu.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-ha.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-ha.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-he.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-he.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-hi.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-hi.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-hr.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-hr.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-hu.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-hu.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-hy.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-hy.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-id.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-id.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-is.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-is.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-it.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-it.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-ja.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-ja.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-ka.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-ka.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-kn.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-kn.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-ko.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-ko.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-ku.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-ku.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-lb.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-lb.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-lt.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-lt.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-lv.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-lv.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-mk.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-mk.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-mn.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-mn.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-mr.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-mr.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-ms.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-ms.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-my.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-my.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-nb.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-nb.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-ne.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-ne.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-nl.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-nl.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-no.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-no.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-pa.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-pa.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-pl.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-pl.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-ps.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-ps.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-pt.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-pt.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-rn.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-rn.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-ro.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-ro.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-ru.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-ru.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-rw.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-rw.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-si.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-si.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-sk.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-sk.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-sl.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-sl.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-so.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-so.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-sr.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-sr.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-st.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-st.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-sv.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-sv.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-sw.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-sw.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-ta.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-ta.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-te.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-te.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-th.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-th.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-tl.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-tl.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-tr.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-tr.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-tt.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-tt.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-uk.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-uk.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-ur.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-ur.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-uz.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-uz.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-vi.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-vi.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-yo.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-yo.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-zh.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-zh.txt -------------------------------------------------------------------------------- /newspaper/resources/text/stopwords-zu.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/resources/text/stopwords-zu.txt -------------------------------------------------------------------------------- /newspaper/settings.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/settings.py -------------------------------------------------------------------------------- /newspaper/source.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/source.py -------------------------------------------------------------------------------- /newspaper/text.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/text.py -------------------------------------------------------------------------------- /newspaper/urls.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/urls.py -------------------------------------------------------------------------------- /newspaper/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/utils/__init__.py -------------------------------------------------------------------------------- /newspaper/utils/classes.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/utils/classes.py -------------------------------------------------------------------------------- /newspaper/version.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/newspaper/version.py -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/pyproject.toml -------------------------------------------------------------------------------- /pytest.ini: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/pytest.ini -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/requirements.txt -------------------------------------------------------------------------------- /stubs/cloudscraper/__init__.pyi: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/stubs/cloudscraper/__init__.pyi -------------------------------------------------------------------------------- /stubs/feedparser.pyi: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /stubs/gnews.pyi: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /stubs/gnews/__init__.pyi: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/stubs/gnews/__init__.pyi -------------------------------------------------------------------------------- /stubs/gnews/gnews.pyi: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/stubs/gnews/gnews.pyi -------------------------------------------------------------------------------- /stubs/gnews/utils/constants.pyi: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/stubs/gnews/utils/constants.pyi -------------------------------------------------------------------------------- /stubs/gnews/utils/utils.pyi: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/stubs/gnews/utils/utils.pyi -------------------------------------------------------------------------------- /stubs/indicnlp/tokenize/indic_tokenize.pyi: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/stubs/indicnlp/tokenize/indic_tokenize.pyi -------------------------------------------------------------------------------- /stubs/jieba.pyi: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/stubs/jieba.pyi -------------------------------------------------------------------------------- /stubs/nltk/__init__.pyi: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/stubs/nltk/__init__.pyi -------------------------------------------------------------------------------- /stubs/nltk/data.pyi: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/stubs/nltk/data.pyi -------------------------------------------------------------------------------- /stubs/nltk/tokenize.pyi: -------------------------------------------------------------------------------- 1 | class WhitespaceTokenizer: ... 2 | -------------------------------------------------------------------------------- /stubs/pythainlp.pyi: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/stubs/pythainlp.pyi -------------------------------------------------------------------------------- /stubs/tinysegmenter.pyi: -------------------------------------------------------------------------------- 1 | class TinySegmenter: 2 | def tokenize(self, text: str): ... 3 | -------------------------------------------------------------------------------- /tests/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/conftest.py -------------------------------------------------------------------------------- /tests/data/fulltext_domain_list.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/fulltext_domain_list.txt -------------------------------------------------------------------------------- /tests/data/fulltext_url_list.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/fulltext_url_list.txt -------------------------------------------------------------------------------- /tests/data/html/ap_meta_refresh.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/html/ap_meta_refresh.html -------------------------------------------------------------------------------- /tests/data/html/arabic_article.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/html/arabic_article.html -------------------------------------------------------------------------------- /tests/data/html/article_with_br.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/html/article_with_br.html -------------------------------------------------------------------------------- /tests/data/html/article_with_divs.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/html/article_with_divs.html -------------------------------------------------------------------------------- /tests/data/html/autoindustria.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/html/autoindustria.html -------------------------------------------------------------------------------- /tests/data/html/burmese_article.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/html/burmese_article.html -------------------------------------------------------------------------------- /tests/data/html/chinese_article.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/html/chinese_article.html -------------------------------------------------------------------------------- /tests/data/html/chinese_article_001.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/html/chinese_article_001.html -------------------------------------------------------------------------------- /tests/data/html/chinese_article_002.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/html/chinese_article_002.html -------------------------------------------------------------------------------- /tests/data/html/cleveland.com1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/html/cleveland.com1.html -------------------------------------------------------------------------------- /tests/data/html/cnn_001.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/html/cnn_001.html -------------------------------------------------------------------------------- /tests/data/html/cnn_002.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/html/cnn_002.html -------------------------------------------------------------------------------- /tests/data/html/cnn_article.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/html/cnn_article.html -------------------------------------------------------------------------------- /tests/data/html/cnn_main_site.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/html/cnn_main_site.html -------------------------------------------------------------------------------- /tests/data/html/cnn_test_nlp.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/html/cnn_test_nlp.html -------------------------------------------------------------------------------- /tests/data/html/fox13now_001.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/html/fox13now_001.html -------------------------------------------------------------------------------- /tests/data/html/google_meta_refresh.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/html/google_meta_refresh.html -------------------------------------------------------------------------------- /tests/data/html/japanese_article.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/html/japanese_article.html -------------------------------------------------------------------------------- /tests/data/html/japanese_article2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/html/japanese_article2.html -------------------------------------------------------------------------------- /tests/data/html/latvian_article.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/html/latvian_article.html -------------------------------------------------------------------------------- /tests/data/html/sample_rss.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/html/sample_rss.html -------------------------------------------------------------------------------- /tests/data/html/spanish_article.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/html/spanish_article.html -------------------------------------------------------------------------------- /tests/data/html/thai_article.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/html/thai_article.html -------------------------------------------------------------------------------- /tests/data/html/time_001.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/html/time_001.html -------------------------------------------------------------------------------- /tests/data/html/video_article_01.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/html/video_article_01.html -------------------------------------------------------------------------------- /tests/data/html/video_article_02.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/html/video_article_02.html -------------------------------------------------------------------------------- /tests/data/html/wired_001.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/html/wired_001.html -------------------------------------------------------------------------------- /tests/data/html/wired_main_site.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/html/wired_main_site.html -------------------------------------------------------------------------------- /tests/data/html/yahoo_main_site.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/html/yahoo_main_site.html -------------------------------------------------------------------------------- /tests/data/html/yna_co_kr.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/html/yna_co_kr.html -------------------------------------------------------------------------------- /tests/data/metadata/arabic_article.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/metadata/arabic_article.json -------------------------------------------------------------------------------- /tests/data/metadata/article_with_br.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/metadata/article_with_br.json -------------------------------------------------------------------------------- /tests/data/metadata/article_with_divs.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/metadata/article_with_divs.json -------------------------------------------------------------------------------- /tests/data/metadata/chinese_article_001.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/metadata/chinese_article_001.json -------------------------------------------------------------------------------- /tests/data/metadata/chinese_article_002.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/metadata/chinese_article_002.json -------------------------------------------------------------------------------- /tests/data/metadata/cleveland.com1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/metadata/cleveland.com1.json -------------------------------------------------------------------------------- /tests/data/metadata/cnn_001.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/metadata/cnn_001.json -------------------------------------------------------------------------------- /tests/data/metadata/cnn_002.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/metadata/cnn_002.json -------------------------------------------------------------------------------- /tests/data/metadata/cnn_article.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/metadata/cnn_article.json -------------------------------------------------------------------------------- /tests/data/metadata/cnn_test_nlp.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/metadata/cnn_test_nlp.json -------------------------------------------------------------------------------- /tests/data/metadata/fox13now_001.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/metadata/fox13now_001.json -------------------------------------------------------------------------------- /tests/data/metadata/japanese_article.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/metadata/japanese_article.json -------------------------------------------------------------------------------- /tests/data/metadata/japanese_article2.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/metadata/japanese_article2.json -------------------------------------------------------------------------------- /tests/data/metadata/spanish_article.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/metadata/spanish_article.json -------------------------------------------------------------------------------- /tests/data/metadata/thai_article.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/metadata/thai_article.json -------------------------------------------------------------------------------- /tests/data/metadata/time_001.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/metadata/time_001.json -------------------------------------------------------------------------------- /tests/data/metadata/video_article_01.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/metadata/video_article_01.json -------------------------------------------------------------------------------- /tests/data/metadata/video_article_02.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/metadata/video_article_02.json -------------------------------------------------------------------------------- /tests/data/metadata/wired_001.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/metadata/wired_001.json -------------------------------------------------------------------------------- /tests/data/metadata/yna_co_kr.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/metadata/yna_co_kr.json -------------------------------------------------------------------------------- /tests/data/test_prepare_urls.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/test_prepare_urls.txt -------------------------------------------------------------------------------- /tests/data/test_urls.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/test_urls.txt -------------------------------------------------------------------------------- /tests/data/test_urls_pubdate.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/test_urls_pubdate.txt -------------------------------------------------------------------------------- /tests/data/txt/arabic_article.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/txt/arabic_article.txt -------------------------------------------------------------------------------- /tests/data/txt/article_with_br.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/txt/article_with_br.txt -------------------------------------------------------------------------------- /tests/data/txt/article_with_divs.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/txt/article_with_divs.txt -------------------------------------------------------------------------------- /tests/data/txt/bengali_article.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/txt/bengali_article.txt -------------------------------------------------------------------------------- /tests/data/txt/burmese_article.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/txt/burmese_article.txt -------------------------------------------------------------------------------- /tests/data/txt/chinese_article.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/txt/chinese_article.txt -------------------------------------------------------------------------------- /tests/data/txt/chinese_article_001.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/txt/chinese_article_001.txt -------------------------------------------------------------------------------- /tests/data/txt/chinese_article_002.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/txt/chinese_article_002.txt -------------------------------------------------------------------------------- /tests/data/txt/cleveland.com1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/txt/cleveland.com1.txt -------------------------------------------------------------------------------- /tests/data/txt/cnn_001.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/txt/cnn_001.txt -------------------------------------------------------------------------------- /tests/data/txt/cnn_002.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/txt/cnn_002.txt -------------------------------------------------------------------------------- /tests/data/txt/cnn_article.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/txt/cnn_article.txt -------------------------------------------------------------------------------- /tests/data/txt/cnn_summary.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/txt/cnn_summary.txt -------------------------------------------------------------------------------- /tests/data/txt/cnn_test_nlp.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/txt/cnn_test_nlp.txt -------------------------------------------------------------------------------- /tests/data/txt/fox13now_001.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/txt/fox13now_001.txt -------------------------------------------------------------------------------- /tests/data/txt/hindi_article.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/txt/hindi_article.txt -------------------------------------------------------------------------------- /tests/data/txt/japanese_article.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/txt/japanese_article.txt -------------------------------------------------------------------------------- /tests/data/txt/japanese_article2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/txt/japanese_article2.txt -------------------------------------------------------------------------------- /tests/data/txt/korean_article.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/txt/korean_article.txt -------------------------------------------------------------------------------- /tests/data/txt/latvian_article.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/txt/latvian_article.txt -------------------------------------------------------------------------------- /tests/data/txt/nepali_article.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/txt/nepali_article.txt -------------------------------------------------------------------------------- /tests/data/txt/spanish_article.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/txt/spanish_article.txt -------------------------------------------------------------------------------- /tests/data/txt/thai_article.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/txt/thai_article.txt -------------------------------------------------------------------------------- /tests/data/txt/time_001.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/txt/time_001.txt -------------------------------------------------------------------------------- /tests/data/txt/video_article_01.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/txt/video_article_01.txt -------------------------------------------------------------------------------- /tests/data/txt/video_article_02.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/txt/video_article_02.txt -------------------------------------------------------------------------------- /tests/data/txt/wired_001.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/txt/wired_001.txt -------------------------------------------------------------------------------- /tests/data/txt/yna_co_kr.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/data/txt/yna_co_kr.txt -------------------------------------------------------------------------------- /tests/e2e/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/e2e/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/e2e/conftest.py -------------------------------------------------------------------------------- /tests/e2e/test_article.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/e2e/test_article.py -------------------------------------------------------------------------------- /tests/e2e/test_cli.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/e2e/test_source.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/e2e/test_source.py -------------------------------------------------------------------------------- /tests/helpers/create_test_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/helpers/create_test_data.py -------------------------------------------------------------------------------- /tests/helpers/create_test_data_duplicates: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/helpers/create_test_data_duplicates -------------------------------------------------------------------------------- /tests/helpers/get_many_articles.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/helpers/get_many_articles.py -------------------------------------------------------------------------------- /tests/integration/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/integration/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/integration/conftest.py -------------------------------------------------------------------------------- /tests/integration/test_article.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/integration/test_article.py -------------------------------------------------------------------------------- /tests/integration/test_cli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/integration/test_cli.py -------------------------------------------------------------------------------- /tests/integration/test_cookies.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/integration/test_cookies.py -------------------------------------------------------------------------------- /tests/integration/test_languages.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/integration/test_languages.py -------------------------------------------------------------------------------- /tests/integration/test_misc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/integration/test_misc.py -------------------------------------------------------------------------------- /tests/integration/test_pdf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/integration/test_pdf.py -------------------------------------------------------------------------------- /tests/integration/test_requests.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/integration/test_requests.py -------------------------------------------------------------------------------- /tests/integration/test_source.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/integration/test_source.py -------------------------------------------------------------------------------- /tests/test_smoke.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/test_smoke.py -------------------------------------------------------------------------------- /tests/unit/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/unit/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/unit/conftest.py -------------------------------------------------------------------------------- /tests/unit/test_article.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/unit/test_article.py -------------------------------------------------------------------------------- /tests/unit/test_category_extractor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/unit/test_category_extractor.py -------------------------------------------------------------------------------- /tests/unit/test_cleaners.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/unit/test_cleaners.py -------------------------------------------------------------------------------- /tests/unit/test_cli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/unit/test_cli.py -------------------------------------------------------------------------------- /tests/unit/test_configuration.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/unit/test_configuration.py -------------------------------------------------------------------------------- /tests/unit/test_cookies.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/unit/test_cookies.py -------------------------------------------------------------------------------- /tests/unit/test_languages.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/unit/test_languages.py -------------------------------------------------------------------------------- /tests/unit/test_misc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/unit/test_misc.py -------------------------------------------------------------------------------- /tests/unit/test_network.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/unit/test_network.py -------------------------------------------------------------------------------- /tests/unit/test_nlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/unit/test_nlp.py -------------------------------------------------------------------------------- /tests/unit/test_parsing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/unit/test_parsing.py -------------------------------------------------------------------------------- /tests/unit/test_pdf.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/unit/test_requests.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/unit/test_requests.py -------------------------------------------------------------------------------- /tests/unit/test_source.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/unit/test_source.py -------------------------------------------------------------------------------- /tests/unit/test_urls.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/AndyTheFactory/newspaper4k/HEAD/tests/unit/test_urls.py --------------------------------------------------------------------------------