├── .coveragerc ├── .git-blame-ignore-revs ├── .gitattributes ├── .github ├── dependabot.yml └── workflows │ ├── python-package.yml │ └── python-publish.yml ├── .gitignore ├── .isort.cfg ├── .pre-commit-config.yaml ├── AUTHORS ├── HISTORY.rst ├── LICENSE ├── README.rst ├── extruct ├── VERSION ├── __init__.py ├── __main__.py ├── _extruct.py ├── dublincore.py ├── jsonld.py ├── microformat.py ├── opengraph.py ├── rdfa.py ├── tool.py ├── uniform.py ├── utils.py ├── w3cmicrodata.py └── xmldom.py ├── pyproject.toml ├── pytest.ini ├── requirements-dev.txt ├── requirements.txt ├── setup.cfg ├── setup.py ├── tests ├── __init__.py ├── samples │ ├── custom.invalid │ │ ├── AllocateAction.001.html │ │ ├── AllocateAction.001.jsonld │ │ ├── JSONLD_with_JS_comment.html │ │ ├── JSONLD_with_JS_comment.jsonld │ │ ├── JSONLD_with_control_characters.html │ │ ├── JSONLD_with_control_characters.jsonld │ │ ├── JSONLD_with_control_characters_comment.html │ │ ├── JSONLD_with_control_characters_comment.jsonld │ │ ├── JoinAction.001.html │ │ └── JoinAction.001.jsonld │ ├── misc │ │ ├── Portfolio_Niels_Lubberman.html │ │ ├── Portfolio_Niels_Lubberman.json │ │ ├── dublincore_test.html │ │ ├── dublincore_test.json │ │ ├── expanded_OG_support_test.html │ │ ├── expanded_OG_support_test.json │ │ ├── microformat_flat_test.json │ │ ├── microformat_test.html │ │ ├── microformat_test.json │ │ ├── null_ld_mock.html │ │ ├── null_ld_mock.jsonld │ │ ├── opengraph_flat_test.json │ │ ├── opengraph_ns_product_test.html │ │ ├── opengraph_ns_product_test.json │ │ ├── opengraph_test.html │ │ ├── opengraph_test.json │ │ └── product_microdata.html │ ├── schema.org.invalid │ │ ├── AllocateAction.001.html │ │ ├── AllocateAction.001.jsonld │ │ ├── JoinAction.001.html │ │ └── JoinAction.001.jsonld │ ├── schema.org │ │ ├── CreativeWork.001.html │ │ ├── CreativeWork.001.json │ │ ├── CreativeWork.001.jsonld │ │ ├── CreativeWork_flat.001.json │ │ ├── CreativeWork_flat_with_node_id.001.json │ │ ├── Event.001.html │ │ ├── Event.001.json │ │ ├── Event.002.html │ │ ├── Event.002.json │ │ ├── Event.003.html │ │ ├── Event.003.json │ │ ├── Event.004.html │ │ ├── Event.004.json │ │ ├── Event.008.html │ │ ├── Event.008.json │ │ ├── LocalBusiness.002.html │ │ ├── LocalBusiness.002.json │ │ ├── LocalBusiness.003.html │ │ ├── LocalBusiness.003.json │ │ ├── MusicRecording.001.html │ │ ├── MusicRecording.001.json │ │ ├── SearchAction.001.html │ │ ├── SearchAction.001.json │ │ ├── product-ref.html │ │ ├── product-ref.json │ │ ├── product.html │ │ ├── product.json │ │ ├── product_custom_url.json │ │ └── product_custom_url_and_node_id.json │ ├── songkick │ │ ├── Elysian Fields Brooklyn Tickets, The Owl Music Parlor, 31 Oct 2015.html │ │ ├── Elysian Fields Brooklyn Tickets, The Owl Music Parlor, 31 Oct 2015.jsonld │ │ ├── Maxïmo Park Gigography, Tour History & Past Concerts.html │ │ ├── Maxïmo Park Gigography, Tour History & Past Concerts.jsonld │ │ ├── Years & Years Tickets, Tour Dates 2015 & Concerts.html │ │ ├── Years & Years Tickets, Tour Dates 2015 & Concerts.jsonld │ │ ├── elysianfields.html │ │ ├── elysianfields.json │ │ ├── elysianfields_1.html │ │ ├── elysianfields_1.json │ │ ├── jsonld_empty_item_test.html │ │ ├── jsonld_empty_item_test.jsonld │ │ ├── tovestyrke.html │ │ └── tovestyrke.json │ ├── w3c │ │ ├── microdata.4.2.data.html │ │ ├── microdata.4.2.data.json │ │ ├── microdata.4.2.meter.html │ │ ├── microdata.4.2.meter.json │ │ ├── microdata.4.2.strings.html │ │ ├── microdata.4.2.strings.json │ │ ├── microdata.4.2.strings.unclean.html │ │ ├── microdata.4.2.strings.unclean.json │ │ ├── microdata.5.2.flat.json │ │ ├── microdata.5.2.html │ │ ├── microdata.5.2.json │ │ ├── microdata.5.2.withtext.json │ │ ├── microdata.5.3.html │ │ ├── microdata.5.3.json │ │ ├── microdata.5.5.html │ │ ├── microdata.5.5.json │ │ ├── microdata.7.1.flat.json │ │ ├── microdata.7.1.html │ │ ├── microdata.7.1.json │ │ ├── microdata.object.html │ │ └── microdata.object.json │ ├── w3crdfa │ │ ├── w3c.rdf11primer.example014.expanded.json │ │ ├── w3c.rdf11primer.example014.html │ │ ├── w3c.rdfalite.example003.expanded.json │ │ ├── w3c.rdfalite.example003.html │ │ ├── w3c.rdfalite.example004.expanded.json │ │ ├── w3c.rdfalite.example004.html │ │ ├── w3c.rdfalite.example005.expanded.json │ │ ├── w3c.rdfalite.example005.html │ │ ├── w3c.rdfaprimer.example005.expanded.json │ │ ├── w3c.rdfaprimer.example005.html │ │ ├── w3c.rdfaprimer.example006.expanded.json │ │ ├── w3c.rdfaprimer.example006.html │ │ ├── w3c.rdfaprimer.example007.expanded.json │ │ ├── w3c.rdfaprimer.example007.html │ │ ├── w3c.rdfaprimer.example008.expanded.json │ │ ├── w3c.rdfaprimer.example008.html │ │ ├── w3c.rdfaprimer.example009.expanded.json │ │ ├── w3c.rdfaprimer.example009.html │ │ ├── w3c.rdfaprimer.example010.expanded.json │ │ ├── w3c.rdfaprimer.example010.html │ │ ├── w3c.rdfaprimer.example011.expanded.json │ │ ├── w3c.rdfaprimer.example011.html │ │ ├── w3c.rdfaprimer.example015.expanded.json │ │ └── w3c.rdfaprimer.example015.html │ ├── websites │ │ ├── microdata-with-description.html │ │ └── microdata-with-description.json │ └── wikipedia │ │ ├── xhtml+rdfa.expanded.json │ │ └── xhtml+rdfa.html ├── test_dublincore.py ├── test_extruct.py ├── test_extruct_uniform.py ├── test_jsonld.py ├── test_microdata.py ├── test_microformat.py ├── test_opengraph.py ├── test_rdfa.py ├── test_tool.py └── test_uniform.py └── tox.ini /.coveragerc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/.coveragerc -------------------------------------------------------------------------------- /.git-blame-ignore-revs: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/.git-blame-ignore-revs -------------------------------------------------------------------------------- /.gitattributes: -------------------------------------------------------------------------------- 1 | tests/samples/** linguist-vendored 2 | -------------------------------------------------------------------------------- /.github/dependabot.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/.github/dependabot.yml -------------------------------------------------------------------------------- /.github/workflows/python-package.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/.github/workflows/python-package.yml -------------------------------------------------------------------------------- /.github/workflows/python-publish.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/.github/workflows/python-publish.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/.gitignore -------------------------------------------------------------------------------- /.isort.cfg: -------------------------------------------------------------------------------- 1 | [settings] 2 | profile=black 3 | -------------------------------------------------------------------------------- /.pre-commit-config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/.pre-commit-config.yaml -------------------------------------------------------------------------------- /AUTHORS: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/AUTHORS -------------------------------------------------------------------------------- /HISTORY.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/HISTORY.rst -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/LICENSE -------------------------------------------------------------------------------- /README.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/README.rst -------------------------------------------------------------------------------- /extruct/VERSION: -------------------------------------------------------------------------------- 1 | 0.18.0 2 | -------------------------------------------------------------------------------- /extruct/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/extruct/__init__.py -------------------------------------------------------------------------------- /extruct/__main__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/extruct/__main__.py -------------------------------------------------------------------------------- /extruct/_extruct.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/extruct/_extruct.py -------------------------------------------------------------------------------- /extruct/dublincore.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/extruct/dublincore.py -------------------------------------------------------------------------------- /extruct/jsonld.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/extruct/jsonld.py -------------------------------------------------------------------------------- /extruct/microformat.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/extruct/microformat.py -------------------------------------------------------------------------------- /extruct/opengraph.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/extruct/opengraph.py -------------------------------------------------------------------------------- /extruct/rdfa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/extruct/rdfa.py -------------------------------------------------------------------------------- /extruct/tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/extruct/tool.py -------------------------------------------------------------------------------- /extruct/uniform.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/extruct/uniform.py -------------------------------------------------------------------------------- /extruct/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/extruct/utils.py -------------------------------------------------------------------------------- /extruct/w3cmicrodata.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/extruct/w3cmicrodata.py -------------------------------------------------------------------------------- /extruct/xmldom.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/extruct/xmldom.py -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/pyproject.toml -------------------------------------------------------------------------------- /pytest.ini: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/pytest.ini -------------------------------------------------------------------------------- /requirements-dev.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/requirements-dev.txt -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/requirements.txt -------------------------------------------------------------------------------- /setup.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/setup.cfg -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/setup.py -------------------------------------------------------------------------------- /tests/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/__init__.py -------------------------------------------------------------------------------- /tests/samples/custom.invalid/AllocateAction.001.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/custom.invalid/AllocateAction.001.html -------------------------------------------------------------------------------- /tests/samples/custom.invalid/AllocateAction.001.jsonld: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/custom.invalid/AllocateAction.001.jsonld -------------------------------------------------------------------------------- /tests/samples/custom.invalid/JSONLD_with_JS_comment.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/custom.invalid/JSONLD_with_JS_comment.html -------------------------------------------------------------------------------- /tests/samples/custom.invalid/JSONLD_with_JS_comment.jsonld: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/custom.invalid/JSONLD_with_JS_comment.jsonld -------------------------------------------------------------------------------- /tests/samples/custom.invalid/JSONLD_with_control_characters.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/custom.invalid/JSONLD_with_control_characters.html -------------------------------------------------------------------------------- /tests/samples/custom.invalid/JSONLD_with_control_characters.jsonld: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/custom.invalid/JSONLD_with_control_characters.jsonld -------------------------------------------------------------------------------- /tests/samples/custom.invalid/JSONLD_with_control_characters_comment.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/custom.invalid/JSONLD_with_control_characters_comment.html -------------------------------------------------------------------------------- /tests/samples/custom.invalid/JSONLD_with_control_characters_comment.jsonld: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/custom.invalid/JSONLD_with_control_characters_comment.jsonld -------------------------------------------------------------------------------- /tests/samples/custom.invalid/JoinAction.001.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/custom.invalid/JoinAction.001.html -------------------------------------------------------------------------------- /tests/samples/custom.invalid/JoinAction.001.jsonld: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/custom.invalid/JoinAction.001.jsonld -------------------------------------------------------------------------------- /tests/samples/misc/Portfolio_Niels_Lubberman.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/misc/Portfolio_Niels_Lubberman.html -------------------------------------------------------------------------------- /tests/samples/misc/Portfolio_Niels_Lubberman.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/misc/Portfolio_Niels_Lubberman.json -------------------------------------------------------------------------------- /tests/samples/misc/dublincore_test.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/misc/dublincore_test.html -------------------------------------------------------------------------------- /tests/samples/misc/dublincore_test.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/misc/dublincore_test.json -------------------------------------------------------------------------------- /tests/samples/misc/expanded_OG_support_test.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/misc/expanded_OG_support_test.html -------------------------------------------------------------------------------- /tests/samples/misc/expanded_OG_support_test.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/misc/expanded_OG_support_test.json -------------------------------------------------------------------------------- /tests/samples/misc/microformat_flat_test.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/misc/microformat_flat_test.json -------------------------------------------------------------------------------- /tests/samples/misc/microformat_test.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/misc/microformat_test.html -------------------------------------------------------------------------------- /tests/samples/misc/microformat_test.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/misc/microformat_test.json -------------------------------------------------------------------------------- /tests/samples/misc/null_ld_mock.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/misc/null_ld_mock.html -------------------------------------------------------------------------------- /tests/samples/misc/null_ld_mock.jsonld: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/misc/null_ld_mock.jsonld -------------------------------------------------------------------------------- /tests/samples/misc/opengraph_flat_test.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/misc/opengraph_flat_test.json -------------------------------------------------------------------------------- /tests/samples/misc/opengraph_ns_product_test.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/misc/opengraph_ns_product_test.html -------------------------------------------------------------------------------- /tests/samples/misc/opengraph_ns_product_test.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/misc/opengraph_ns_product_test.json -------------------------------------------------------------------------------- /tests/samples/misc/opengraph_test.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/misc/opengraph_test.html -------------------------------------------------------------------------------- /tests/samples/misc/opengraph_test.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/misc/opengraph_test.json -------------------------------------------------------------------------------- /tests/samples/misc/product_microdata.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/misc/product_microdata.html -------------------------------------------------------------------------------- /tests/samples/schema.org.invalid/AllocateAction.001.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org.invalid/AllocateAction.001.html -------------------------------------------------------------------------------- /tests/samples/schema.org.invalid/AllocateAction.001.jsonld: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org.invalid/AllocateAction.001.jsonld -------------------------------------------------------------------------------- /tests/samples/schema.org.invalid/JoinAction.001.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org.invalid/JoinAction.001.html -------------------------------------------------------------------------------- /tests/samples/schema.org.invalid/JoinAction.001.jsonld: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org.invalid/JoinAction.001.jsonld -------------------------------------------------------------------------------- /tests/samples/schema.org/CreativeWork.001.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org/CreativeWork.001.html -------------------------------------------------------------------------------- /tests/samples/schema.org/CreativeWork.001.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org/CreativeWork.001.json -------------------------------------------------------------------------------- /tests/samples/schema.org/CreativeWork.001.jsonld: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org/CreativeWork.001.jsonld -------------------------------------------------------------------------------- /tests/samples/schema.org/CreativeWork_flat.001.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org/CreativeWork_flat.001.json -------------------------------------------------------------------------------- /tests/samples/schema.org/CreativeWork_flat_with_node_id.001.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org/CreativeWork_flat_with_node_id.001.json -------------------------------------------------------------------------------- /tests/samples/schema.org/Event.001.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org/Event.001.html -------------------------------------------------------------------------------- /tests/samples/schema.org/Event.001.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org/Event.001.json -------------------------------------------------------------------------------- /tests/samples/schema.org/Event.002.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org/Event.002.html -------------------------------------------------------------------------------- /tests/samples/schema.org/Event.002.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org/Event.002.json -------------------------------------------------------------------------------- /tests/samples/schema.org/Event.003.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org/Event.003.html -------------------------------------------------------------------------------- /tests/samples/schema.org/Event.003.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org/Event.003.json -------------------------------------------------------------------------------- /tests/samples/schema.org/Event.004.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org/Event.004.html -------------------------------------------------------------------------------- /tests/samples/schema.org/Event.004.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org/Event.004.json -------------------------------------------------------------------------------- /tests/samples/schema.org/Event.008.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org/Event.008.html -------------------------------------------------------------------------------- /tests/samples/schema.org/Event.008.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org/Event.008.json -------------------------------------------------------------------------------- /tests/samples/schema.org/LocalBusiness.002.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org/LocalBusiness.002.html -------------------------------------------------------------------------------- /tests/samples/schema.org/LocalBusiness.002.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org/LocalBusiness.002.json -------------------------------------------------------------------------------- /tests/samples/schema.org/LocalBusiness.003.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org/LocalBusiness.003.html -------------------------------------------------------------------------------- /tests/samples/schema.org/LocalBusiness.003.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org/LocalBusiness.003.json -------------------------------------------------------------------------------- /tests/samples/schema.org/MusicRecording.001.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org/MusicRecording.001.html -------------------------------------------------------------------------------- /tests/samples/schema.org/MusicRecording.001.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org/MusicRecording.001.json -------------------------------------------------------------------------------- /tests/samples/schema.org/SearchAction.001.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org/SearchAction.001.html -------------------------------------------------------------------------------- /tests/samples/schema.org/SearchAction.001.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org/SearchAction.001.json -------------------------------------------------------------------------------- /tests/samples/schema.org/product-ref.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org/product-ref.html -------------------------------------------------------------------------------- /tests/samples/schema.org/product-ref.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org/product-ref.json -------------------------------------------------------------------------------- /tests/samples/schema.org/product.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org/product.html -------------------------------------------------------------------------------- /tests/samples/schema.org/product.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org/product.json -------------------------------------------------------------------------------- /tests/samples/schema.org/product_custom_url.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org/product_custom_url.json -------------------------------------------------------------------------------- /tests/samples/schema.org/product_custom_url_and_node_id.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/schema.org/product_custom_url_and_node_id.json -------------------------------------------------------------------------------- /tests/samples/songkick/Elysian Fields Brooklyn Tickets, The Owl Music Parlor, 31 Oct 2015.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/songkick/Elysian Fields Brooklyn Tickets, The Owl Music Parlor, 31 Oct 2015.html -------------------------------------------------------------------------------- /tests/samples/songkick/Elysian Fields Brooklyn Tickets, The Owl Music Parlor, 31 Oct 2015.jsonld: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/songkick/Elysian Fields Brooklyn Tickets, The Owl Music Parlor, 31 Oct 2015.jsonld -------------------------------------------------------------------------------- /tests/samples/songkick/Maxïmo Park Gigography, Tour History & Past Concerts.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/songkick/Maxïmo Park Gigography, Tour History & Past Concerts.html -------------------------------------------------------------------------------- /tests/samples/songkick/Maxïmo Park Gigography, Tour History & Past Concerts.jsonld: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/songkick/Maxïmo Park Gigography, Tour History & Past Concerts.jsonld -------------------------------------------------------------------------------- /tests/samples/songkick/Years & Years Tickets, Tour Dates 2015 & Concerts.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/songkick/Years & Years Tickets, Tour Dates 2015 & Concerts.html -------------------------------------------------------------------------------- /tests/samples/songkick/Years & Years Tickets, Tour Dates 2015 & Concerts.jsonld: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/songkick/Years & Years Tickets, Tour Dates 2015 & Concerts.jsonld -------------------------------------------------------------------------------- /tests/samples/songkick/elysianfields.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/songkick/elysianfields.html -------------------------------------------------------------------------------- /tests/samples/songkick/elysianfields.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/songkick/elysianfields.json -------------------------------------------------------------------------------- /tests/samples/songkick/elysianfields_1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/songkick/elysianfields_1.html -------------------------------------------------------------------------------- /tests/samples/songkick/elysianfields_1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/songkick/elysianfields_1.json -------------------------------------------------------------------------------- /tests/samples/songkick/jsonld_empty_item_test.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/songkick/jsonld_empty_item_test.html -------------------------------------------------------------------------------- /tests/samples/songkick/jsonld_empty_item_test.jsonld: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/songkick/jsonld_empty_item_test.jsonld -------------------------------------------------------------------------------- /tests/samples/songkick/tovestyrke.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/songkick/tovestyrke.html -------------------------------------------------------------------------------- /tests/samples/songkick/tovestyrke.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/songkick/tovestyrke.json -------------------------------------------------------------------------------- /tests/samples/w3c/microdata.4.2.data.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3c/microdata.4.2.data.html -------------------------------------------------------------------------------- /tests/samples/w3c/microdata.4.2.data.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3c/microdata.4.2.data.json -------------------------------------------------------------------------------- /tests/samples/w3c/microdata.4.2.meter.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3c/microdata.4.2.meter.html -------------------------------------------------------------------------------- /tests/samples/w3c/microdata.4.2.meter.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3c/microdata.4.2.meter.json -------------------------------------------------------------------------------- /tests/samples/w3c/microdata.4.2.strings.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3c/microdata.4.2.strings.html -------------------------------------------------------------------------------- /tests/samples/w3c/microdata.4.2.strings.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3c/microdata.4.2.strings.json -------------------------------------------------------------------------------- /tests/samples/w3c/microdata.4.2.strings.unclean.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3c/microdata.4.2.strings.unclean.html -------------------------------------------------------------------------------- /tests/samples/w3c/microdata.4.2.strings.unclean.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3c/microdata.4.2.strings.unclean.json -------------------------------------------------------------------------------- /tests/samples/w3c/microdata.5.2.flat.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3c/microdata.5.2.flat.json -------------------------------------------------------------------------------- /tests/samples/w3c/microdata.5.2.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3c/microdata.5.2.html -------------------------------------------------------------------------------- /tests/samples/w3c/microdata.5.2.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3c/microdata.5.2.json -------------------------------------------------------------------------------- /tests/samples/w3c/microdata.5.2.withtext.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3c/microdata.5.2.withtext.json -------------------------------------------------------------------------------- /tests/samples/w3c/microdata.5.3.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3c/microdata.5.3.html -------------------------------------------------------------------------------- /tests/samples/w3c/microdata.5.3.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3c/microdata.5.3.json -------------------------------------------------------------------------------- /tests/samples/w3c/microdata.5.5.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3c/microdata.5.5.html -------------------------------------------------------------------------------- /tests/samples/w3c/microdata.5.5.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3c/microdata.5.5.json -------------------------------------------------------------------------------- /tests/samples/w3c/microdata.7.1.flat.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3c/microdata.7.1.flat.json -------------------------------------------------------------------------------- /tests/samples/w3c/microdata.7.1.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3c/microdata.7.1.html -------------------------------------------------------------------------------- /tests/samples/w3c/microdata.7.1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3c/microdata.7.1.json -------------------------------------------------------------------------------- /tests/samples/w3c/microdata.object.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3c/microdata.object.html -------------------------------------------------------------------------------- /tests/samples/w3c/microdata.object.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3c/microdata.object.json -------------------------------------------------------------------------------- /tests/samples/w3crdfa/w3c.rdf11primer.example014.expanded.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3crdfa/w3c.rdf11primer.example014.expanded.json -------------------------------------------------------------------------------- /tests/samples/w3crdfa/w3c.rdf11primer.example014.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3crdfa/w3c.rdf11primer.example014.html -------------------------------------------------------------------------------- /tests/samples/w3crdfa/w3c.rdfalite.example003.expanded.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3crdfa/w3c.rdfalite.example003.expanded.json -------------------------------------------------------------------------------- /tests/samples/w3crdfa/w3c.rdfalite.example003.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3crdfa/w3c.rdfalite.example003.html -------------------------------------------------------------------------------- /tests/samples/w3crdfa/w3c.rdfalite.example004.expanded.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3crdfa/w3c.rdfalite.example004.expanded.json -------------------------------------------------------------------------------- /tests/samples/w3crdfa/w3c.rdfalite.example004.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3crdfa/w3c.rdfalite.example004.html -------------------------------------------------------------------------------- /tests/samples/w3crdfa/w3c.rdfalite.example005.expanded.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3crdfa/w3c.rdfalite.example005.expanded.json -------------------------------------------------------------------------------- /tests/samples/w3crdfa/w3c.rdfalite.example005.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3crdfa/w3c.rdfalite.example005.html -------------------------------------------------------------------------------- /tests/samples/w3crdfa/w3c.rdfaprimer.example005.expanded.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3crdfa/w3c.rdfaprimer.example005.expanded.json -------------------------------------------------------------------------------- /tests/samples/w3crdfa/w3c.rdfaprimer.example005.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3crdfa/w3c.rdfaprimer.example005.html -------------------------------------------------------------------------------- /tests/samples/w3crdfa/w3c.rdfaprimer.example006.expanded.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3crdfa/w3c.rdfaprimer.example006.expanded.json -------------------------------------------------------------------------------- /tests/samples/w3crdfa/w3c.rdfaprimer.example006.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3crdfa/w3c.rdfaprimer.example006.html -------------------------------------------------------------------------------- /tests/samples/w3crdfa/w3c.rdfaprimer.example007.expanded.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3crdfa/w3c.rdfaprimer.example007.expanded.json -------------------------------------------------------------------------------- /tests/samples/w3crdfa/w3c.rdfaprimer.example007.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3crdfa/w3c.rdfaprimer.example007.html -------------------------------------------------------------------------------- /tests/samples/w3crdfa/w3c.rdfaprimer.example008.expanded.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3crdfa/w3c.rdfaprimer.example008.expanded.json -------------------------------------------------------------------------------- /tests/samples/w3crdfa/w3c.rdfaprimer.example008.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3crdfa/w3c.rdfaprimer.example008.html -------------------------------------------------------------------------------- /tests/samples/w3crdfa/w3c.rdfaprimer.example009.expanded.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3crdfa/w3c.rdfaprimer.example009.expanded.json -------------------------------------------------------------------------------- /tests/samples/w3crdfa/w3c.rdfaprimer.example009.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3crdfa/w3c.rdfaprimer.example009.html -------------------------------------------------------------------------------- /tests/samples/w3crdfa/w3c.rdfaprimer.example010.expanded.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3crdfa/w3c.rdfaprimer.example010.expanded.json -------------------------------------------------------------------------------- /tests/samples/w3crdfa/w3c.rdfaprimer.example010.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3crdfa/w3c.rdfaprimer.example010.html -------------------------------------------------------------------------------- /tests/samples/w3crdfa/w3c.rdfaprimer.example011.expanded.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3crdfa/w3c.rdfaprimer.example011.expanded.json -------------------------------------------------------------------------------- /tests/samples/w3crdfa/w3c.rdfaprimer.example011.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3crdfa/w3c.rdfaprimer.example011.html -------------------------------------------------------------------------------- /tests/samples/w3crdfa/w3c.rdfaprimer.example015.expanded.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3crdfa/w3c.rdfaprimer.example015.expanded.json -------------------------------------------------------------------------------- /tests/samples/w3crdfa/w3c.rdfaprimer.example015.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/w3crdfa/w3c.rdfaprimer.example015.html -------------------------------------------------------------------------------- /tests/samples/websites/microdata-with-description.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/websites/microdata-with-description.html -------------------------------------------------------------------------------- /tests/samples/websites/microdata-with-description.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/websites/microdata-with-description.json -------------------------------------------------------------------------------- /tests/samples/wikipedia/xhtml+rdfa.expanded.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/wikipedia/xhtml+rdfa.expanded.json -------------------------------------------------------------------------------- /tests/samples/wikipedia/xhtml+rdfa.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/samples/wikipedia/xhtml+rdfa.html -------------------------------------------------------------------------------- /tests/test_dublincore.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/test_dublincore.py -------------------------------------------------------------------------------- /tests/test_extruct.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/test_extruct.py -------------------------------------------------------------------------------- /tests/test_extruct_uniform.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/test_extruct_uniform.py -------------------------------------------------------------------------------- /tests/test_jsonld.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/test_jsonld.py -------------------------------------------------------------------------------- /tests/test_microdata.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/test_microdata.py -------------------------------------------------------------------------------- /tests/test_microformat.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/test_microformat.py -------------------------------------------------------------------------------- /tests/test_opengraph.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/test_opengraph.py -------------------------------------------------------------------------------- /tests/test_rdfa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/test_rdfa.py -------------------------------------------------------------------------------- /tests/test_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/test_tool.py -------------------------------------------------------------------------------- /tests/test_uniform.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tests/test_uniform.py -------------------------------------------------------------------------------- /tox.ini: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/scrapinghub/extruct/HEAD/tox.ini --------------------------------------------------------------------------------