Files
TextNLPClassifierApp/graphify-out/cache/ast/v0.9.47-s2/4d249dbb980bff1f0034b80785cf0e68bfce185bd99bbbf2456480bdc7ac7606.json
andreferraro 6a45368cb0 feat(extractor): implement multi-engine article content extractor
- Added scripts/extract_article_contents.py for batch scraping with stealth Foxcape and triple extraction (Trafilatura, Newspaper4k, Readability)
- Created unit, integration, and E2E test suite in tests/test_extract_article_contents.py (90/90 passing)
- Updated specs/003-article-content-extractor and README.md with usage documentation and CLI contracts
- Passed ruff linting/formatting and mypy type checking cleanly
2026-08-20 19:22:20 -03:00

1 line
66 KiB
JSON

{"nodes": [{"id": "$graphify-root$_scripts_extract_article_contents_py", "label": "extract_article_contents.py", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L1"}, {"id": "$graphify-root$_scripts_extract_article_contents_inputarticle", "label": "InputArticle", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L37", "_callable": true, "_callable_class": true}, {"id": "$graphify-root$_scripts_extract_article_contents_inputarticle_to_dict", "label": ".to_dict()", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L46", "_callable": true}, {"id": "any", "label": "Any", "file_type": "code", "source_file": "", "source_location": "", "origin_file": "$graphify-root$/scripts/extract_article_contents.py"}, {"id": "$graphify-root$_scripts_extract_article_contents_trafilaturadata", "label": "TrafilaturaData", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L57", "_callable": true, "_callable_class": true}, {"id": "$graphify-root$_scripts_extract_article_contents_trafilaturadata_to_dict", "label": ".to_dict()", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L80", "_callable": true}, {"id": "$graphify-root$_scripts_extract_article_contents_newspaperdata", "label": "NewspaperData", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L105", "_callable": true, "_callable_class": true}, {"id": "$graphify-root$_scripts_extract_article_contents_newspaperdata_to_dict", "label": ".to_dict()", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L129", "_callable": true}, {"id": "$graphify-root$_scripts_extract_article_contents_readabilitydata", "label": "ReadabilityData", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L155", "_callable": true, "_callable_class": true}, {"id": "$graphify-root$_scripts_extract_article_contents_readabilitydata_to_dict", "label": ".to_dict()", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L165", "_callable": true}, {"id": "$graphify-root$_scripts_extract_article_contents_extractedarticle", "label": "ExtractedArticle", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L177", "_callable": true, "_callable_class": true}, {"id": "$graphify-root$_scripts_extract_article_contents_extractedarticle_to_dict", "label": ".to_dict()", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L190", "_callable": true}, {"id": "$graphify-root$_scripts_extract_article_contents_extractionbatchreport", "label": "ExtractionBatchReport", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L205", "_callable": true, "_callable_class": true}, {"id": "$graphify-root$_scripts_extract_article_contents_extractionbatchreport_to_dict", "label": ".to_dict()", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L215", "_callable": true}, {"id": "$graphify-root$_scripts_extract_article_contents_trafilaturaextractor", "label": "TrafilaturaExtractor", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L231", "_callable": true, "_callable_class": true}, {"id": "$graphify-root$_scripts_extract_article_contents_trafilaturaextractor_extract", "label": ".extract()", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L235", "_callable": true}, {"id": "$graphify-root$_scripts_extract_article_contents_newspaperextractor", "label": "NewspaperExtractor", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L310", "_callable": true, "_callable_class": true}, {"id": "$graphify-root$_scripts_extract_article_contents_newspaperextractor_extract", "label": ".extract()", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L314", "_callable": true}, {"id": "$graphify-root$_scripts_extract_article_contents_readabilityextractor", "label": "ReadabilityExtractor", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L371", "_callable": true, "_callable_class": true}, {"id": "$graphify-root$_scripts_extract_article_contents_readabilityextractor_extract", "label": ".extract()", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L375", "_callable": true}, {"id": "$graphify-root$_scripts_extract_article_contents_extract_all_engines", "label": "extract_all_engines()", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L403", "_callable": true}, {"id": "$graphify-root$_scripts_extract_article_contents_articlecrawler", "label": "ArticleCrawler", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L458", "_callable": true, "_callable_class": true}, {"id": "$graphify-root$_scripts_extract_article_contents_articlecrawler_init", "label": ".__init__()", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L461", "_callable": true}, {"id": "$graphify-root$_scripts_extract_article_contents_articlecrawler_start", "label": ".start()", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L466", "_callable": true}, {"id": "$graphify-root$_scripts_extract_article_contents_articlecrawler_close", "label": ".close()", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L472", "_callable": true}, {"id": "$graphify-root$_scripts_extract_article_contents_articlecrawler_enter", "label": ".__enter__()", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L480", "_callable": true}, {"id": "$graphify-root$_scripts_extract_article_contents_articlecrawler_exit", "label": ".__exit__()", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L484", "_callable": true}, {"id": "$graphify-root$_scripts_extract_article_contents_articlecrawler_crawl", "label": ".crawl()", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L487", "_callable": true}, {"id": "$graphify-root$_scripts_extract_article_contents_log_info", "label": "log_info()", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L509", "_callable": true}, {"id": "$graphify-root$_scripts_extract_article_contents_load_search_json", "label": "load_search_json()", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L516", "_callable": true}, {"id": "path", "label": "Path", "file_type": "code", "source_file": "", "source_location": "", "origin_file": "$graphify-root$/scripts/extract_article_contents.py"}, {"id": "$graphify-root$_scripts_extract_article_contents_save_extracted_json", "label": "save_extracted_json()", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L544", "_callable": true}, {"id": "$graphify-root$_scripts_extract_article_contents_process_batch", "label": "process_batch()", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L551", "_callable": true}, {"id": "$graphify-root$_scripts_extract_article_contents_parse_arguments", "label": "parse_arguments()", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L664", "_callable": true}, {"id": "namespace", "label": "Namespace", "file_type": "code", "source_file": "", "source_location": "", "origin_file": "$graphify-root$/scripts/extract_article_contents.py"}, {"id": "$graphify-root$_scripts_extract_article_contents_main", "label": "main()", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L718", "_callable": true}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_38", "label": "Metadados originais da not\u00edcia contida no JSON de entrada.", "file_type": "rationale", "source_file": "scripts/extract_article_contents.py", "source_location": "L38"}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_58", "label": "Dados completos extra\u00eddos pelo motor Trafilatura.", "file_type": "rationale", "source_file": "scripts/extract_article_contents.py", "source_location": "L58"}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_106", "label": "Dados completos extra\u00eddos e enriquecidos com NLP pelo motor Newspaper4k.", "file_type": "rationale", "source_file": "scripts/extract_article_contents.py", "source_location": "L106"}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_156", "label": "Dados completos higienizados pelo algoritmo Readability.", "file_type": "rationale", "source_file": "scripts/extract_article_contents.py", "source_location": "L156"}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_178", "label": "Resultado consolidado da extra\u00e7\u00e3o de um artigo.", "file_type": "rationale", "source_file": "scripts/extract_article_contents.py", "source_location": "L178"}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_206", "label": "Relat\u00f3rio consolidado de sa\u00edda do processamento de um lote.", "file_type": "rationale", "source_file": "scripts/extract_article_contents.py", "source_location": "L206"}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_232", "label": "Motor de extra\u00e7\u00e3o baseado na biblioteca Trafilatura.", "file_type": "rationale", "source_file": "scripts/extract_article_contents.py", "source_location": "L232"}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_311", "label": "Motor de extra\u00e7\u00e3o baseado no Newspaper4k com NLP.", "file_type": "rationale", "source_file": "scripts/extract_article_contents.py", "source_location": "L311"}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_372", "label": "Motor de extra\u00e7\u00e3o baseado no algoritmo Readability (readability-lxml).", "file_type": "rationale", "source_file": "scripts/extract_article_contents.py", "source_location": "L372"}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_406", "label": "Executa a extra\u00e7\u00e3o simult\u00e2nea pelos tr\u00eas motores de conte\u00fado com isolamento\u2026", "file_type": "rationale", "source_file": "scripts/extract_article_contents.py", "source_location": "L406"}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_459", "label": "Gerenciador de ciclo de vida e requisi\u00e7\u00f5es via Foxcape Headless.", "file_type": "rationale", "source_file": "scripts/extract_article_contents.py", "source_location": "L459"}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_488", "label": "Navega at\u00e9 a URL, aguarda o carregamento do DOM e retorna (html, page_title,\u2026", "file_type": "rationale", "source_file": "scripts/extract_article_contents.py", "source_location": "L488"}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_510", "label": "Escreve mensagem informativa no stderr.", "file_type": "rationale", "source_file": "scripts/extract_article_contents.py", "source_location": "L510"}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_517", "label": "Carrega o arquivo JSON gerado pelo extrator de not\u00edcias.", "file_type": "rationale", "source_file": "scripts/extract_article_contents.py", "source_location": "L517"}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_545", "label": "Salva o relat\u00f3rio consolidado em formato JSON com UTF-8.", "file_type": "rationale", "source_file": "scripts/extract_article_contents.py", "source_location": "L545"}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_559", "label": "Executa o pipeline completo de extra\u00e7\u00e3o em lote para o arquivo de entrada.", "file_type": "rationale", "source_file": "scripts/extract_article_contents.py", "source_location": "L559"}], "edges": [{"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "argparse", "relation": "imports", "context": "import", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L13", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "json", "relation": "imports", "context": "import", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L14", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "logging", "relation": "imports", "context": "import", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L15", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "os", "relation": "imports", "context": "import", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L16", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "sys", "relation": "imports", "context": "import", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L17", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "time", "relation": "imports", "context": "import", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L18", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "dataclasses", "relation": "imports_from", "context": "import", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L19", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "datetime", "relation": "imports_from", "context": "import", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L20", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "pathlib", "relation": "imports_from", "context": "import", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L21", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "typing", "relation": "imports_from", "context": "import", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L22", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "bs4", "relation": "imports_from", "context": "import", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L24", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "foxcape", "relation": "imports_from", "context": "import", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L25", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "newspaper", "relation": "imports_from", "context": "import", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L26", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "readability", "relation": "imports_from", "context": "import", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L27", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "trafilatura", "relation": "imports", "context": "import", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L28", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "$graphify-root$_scripts_extract_article_contents_inputarticle", "relation": "contains", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L37", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_inputarticle", "target": "$graphify-root$_scripts_extract_article_contents_inputarticle_to_dict", "relation": "method", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L46", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_inputarticle_to_dict", "target": "any", "relation": "references", "context": "generic_arg", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L46", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "$graphify-root$_scripts_extract_article_contents_trafilaturadata", "relation": "contains", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L57", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_trafilaturadata", "target": "$graphify-root$_scripts_extract_article_contents_trafilaturadata_to_dict", "relation": "method", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L80", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_trafilaturadata_to_dict", "target": "any", "relation": "references", "context": "generic_arg", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L80", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "$graphify-root$_scripts_extract_article_contents_newspaperdata", "relation": "contains", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L105", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_newspaperdata", "target": "$graphify-root$_scripts_extract_article_contents_newspaperdata_to_dict", "relation": "method", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L129", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_newspaperdata_to_dict", "target": "any", "relation": "references", "context": "generic_arg", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L129", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "$graphify-root$_scripts_extract_article_contents_readabilitydata", "relation": "contains", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L155", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_readabilitydata", "target": "$graphify-root$_scripts_extract_article_contents_readabilitydata_to_dict", "relation": "method", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L165", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_readabilitydata_to_dict", "target": "any", "relation": "references", "context": "generic_arg", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L165", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "$graphify-root$_scripts_extract_article_contents_extractedarticle", "relation": "contains", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L177", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_extractedarticle", "target": "$graphify-root$_scripts_extract_article_contents_extractedarticle_to_dict", "relation": "method", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L190", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_extractedarticle_to_dict", "target": "any", "relation": "references", "context": "generic_arg", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L190", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "$graphify-root$_scripts_extract_article_contents_extractionbatchreport", "relation": "contains", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L205", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_extractionbatchreport", "target": "$graphify-root$_scripts_extract_article_contents_extractionbatchreport_to_dict", "relation": "method", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L215", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_extractionbatchreport_to_dict", "target": "any", "relation": "references", "context": "generic_arg", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L215", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "$graphify-root$_scripts_extract_article_contents_trafilaturaextractor", "relation": "contains", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L231", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_trafilaturaextractor", "target": "$graphify-root$_scripts_extract_article_contents_trafilaturaextractor_extract", "relation": "method", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L235", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_trafilaturaextractor_extract", "target": "$graphify-root$_scripts_extract_article_contents_trafilaturadata", "relation": "references", "context": "return_type", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L235", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "$graphify-root$_scripts_extract_article_contents_newspaperextractor", "relation": "contains", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L310", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_newspaperextractor", "target": "$graphify-root$_scripts_extract_article_contents_newspaperextractor_extract", "relation": "method", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L314", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_newspaperextractor_extract", "target": "$graphify-root$_scripts_extract_article_contents_newspaperdata", "relation": "references", "context": "return_type", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L314", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "$graphify-root$_scripts_extract_article_contents_readabilityextractor", "relation": "contains", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L371", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_readabilityextractor", "target": "$graphify-root$_scripts_extract_article_contents_readabilityextractor_extract", "relation": "method", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L375", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_readabilityextractor_extract", "target": "$graphify-root$_scripts_extract_article_contents_readabilitydata", "relation": "references", "context": "return_type", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L375", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "$graphify-root$_scripts_extract_article_contents_extract_all_engines", "relation": "contains", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L403", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_extract_all_engines", "target": "$graphify-root$_scripts_extract_article_contents_trafilaturadata", "relation": "references", "context": "generic_arg", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L403", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_extract_all_engines", "target": "$graphify-root$_scripts_extract_article_contents_newspaperdata", "relation": "references", "context": "generic_arg", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L403", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_extract_all_engines", "target": "$graphify-root$_scripts_extract_article_contents_readabilitydata", "relation": "references", "context": "generic_arg", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L403", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "$graphify-root$_scripts_extract_article_contents_articlecrawler", "relation": "contains", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L458", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_articlecrawler", "target": "$graphify-root$_scripts_extract_article_contents_articlecrawler_init", "relation": "method", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L461", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_articlecrawler", "target": "$graphify-root$_scripts_extract_article_contents_articlecrawler_start", "relation": "method", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L466", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_articlecrawler", "target": "$graphify-root$_scripts_extract_article_contents_articlecrawler_close", "relation": "method", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L472", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_articlecrawler", "target": "$graphify-root$_scripts_extract_article_contents_articlecrawler_enter", "relation": "method", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L480", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_articlecrawler_enter", "target": "$graphify-root$_scripts_extract_article_contents_articlecrawler", "relation": "references", "context": "return_type", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L480", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_articlecrawler", "target": "$graphify-root$_scripts_extract_article_contents_articlecrawler_exit", "relation": "method", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L484", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_articlecrawler_exit", "target": "any", "relation": "references", "context": "parameter_type", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L484", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_articlecrawler_exit", "target": "any", "relation": "references", "context": "parameter_type", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L484", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_articlecrawler_exit", "target": "any", "relation": "references", "context": "parameter_type", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L484", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_articlecrawler", "target": "$graphify-root$_scripts_extract_article_contents_articlecrawler_crawl", "relation": "method", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L487", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "$graphify-root$_scripts_extract_article_contents_log_info", "relation": "contains", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L509", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "$graphify-root$_scripts_extract_article_contents_load_search_json", "relation": "contains", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L516", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_load_search_json", "target": "path", "relation": "references", "context": "parameter_type", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L516", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_load_search_json", "target": "$graphify-root$_scripts_extract_article_contents_inputarticle", "relation": "references", "context": "generic_arg", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L516", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "$graphify-root$_scripts_extract_article_contents_save_extracted_json", "relation": "contains", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L544", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_save_extracted_json", "target": "$graphify-root$_scripts_extract_article_contents_extractionbatchreport", "relation": "references", "context": "parameter_type", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L544", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_save_extracted_json", "target": "path", "relation": "references", "context": "parameter_type", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L544", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "$graphify-root$_scripts_extract_article_contents_process_batch", "relation": "contains", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L551", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_process_batch", "target": "path", "relation": "references", "context": "parameter_type", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L551", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_process_batch", "target": "path", "relation": "references", "context": "parameter_type", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L551", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_process_batch", "target": "$graphify-root$_scripts_extract_article_contents_extractionbatchreport", "relation": "references", "context": "return_type", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L551", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "$graphify-root$_scripts_extract_article_contents_parse_arguments", "relation": "contains", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L664", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_parse_arguments", "target": "namespace", "relation": "references", "context": "return_type", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L664", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_py", "target": "$graphify-root$_scripts_extract_article_contents_main", "relation": "contains", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L718", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_trafilaturaextractor_extract", "target": "$graphify-root$_scripts_extract_article_contents_trafilaturadata", "relation": "calls", "context": "call", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L276", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_newspaperextractor_extract", "target": "$graphify-root$_scripts_extract_article_contents_newspaperdata", "relation": "calls", "context": "call", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L345", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_readabilityextractor_extract", "target": "$graphify-root$_scripts_extract_article_contents_readabilitydata", "relation": "calls", "context": "call", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L391", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_extract_all_engines", "target": "$graphify-root$_scripts_extract_article_contents_trafilaturadata", "relation": "calls", "context": "call", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L410", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_extract_all_engines", "target": "$graphify-root$_scripts_extract_article_contents_newspaperdata", "relation": "calls", "context": "call", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L426", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_extract_all_engines", "target": "$graphify-root$_scripts_extract_article_contents_readabilitydata", "relation": "calls", "context": "call", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L442", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_articlecrawler_enter", "target": "$graphify-root$_scripts_extract_article_contents_articlecrawler_start", "relation": "calls", "context": "call", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L481", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_articlecrawler_exit", "target": "$graphify-root$_scripts_extract_article_contents_articlecrawler_close", "relation": "calls", "context": "call", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L485", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_articlecrawler_crawl", "target": "$graphify-root$_scripts_extract_article_contents_articlecrawler_start", "relation": "calls", "context": "call", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L492", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_load_search_json", "target": "$graphify-root$_scripts_extract_article_contents_inputarticle", "relation": "calls", "context": "call", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L532", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_process_batch", "target": "$graphify-root$_scripts_extract_article_contents_load_search_json", "relation": "calls", "context": "call", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L562", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_process_batch", "target": "$graphify-root$_scripts_extract_article_contents_log_info", "relation": "calls", "context": "call", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L569", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_process_batch", "target": "$graphify-root$_scripts_extract_article_contents_articlecrawler", "relation": "calls", "context": "call", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L583", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_process_batch", "target": "$graphify-root$_scripts_extract_article_contents_extract_all_engines", "relation": "calls", "context": "call", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L595", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_process_batch", "target": "$graphify-root$_scripts_extract_article_contents_extractedarticle", "relation": "calls", "context": "call", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L599", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_process_batch", "target": "$graphify-root$_scripts_extract_article_contents_extractionbatchreport", "relation": "calls", "context": "call", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L640", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_process_batch", "target": "$graphify-root$_scripts_extract_article_contents_save_extracted_json", "relation": "calls", "context": "call", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L649", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_main", "target": "$graphify-root$_scripts_extract_article_contents_parse_arguments", "relation": "calls", "context": "call", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L720", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_main", "target": "path", "relation": "calls", "context": "call", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L721", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_main", "target": "$graphify-root$_scripts_extract_article_contents_process_batch", "relation": "calls", "context": "call", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L728", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_38", "target": "$graphify-root$_scripts_extract_article_contents_inputarticle", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L38", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_58", "target": "$graphify-root$_scripts_extract_article_contents_trafilaturadata", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L58", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_106", "target": "$graphify-root$_scripts_extract_article_contents_newspaperdata", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L106", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_156", "target": "$graphify-root$_scripts_extract_article_contents_readabilitydata", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L156", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_178", "target": "$graphify-root$_scripts_extract_article_contents_extractedarticle", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L178", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_206", "target": "$graphify-root$_scripts_extract_article_contents_extractionbatchreport", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L206", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_232", "target": "$graphify-root$_scripts_extract_article_contents_trafilaturaextractor", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L232", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_311", "target": "$graphify-root$_scripts_extract_article_contents_newspaperextractor", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L311", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_372", "target": "$graphify-root$_scripts_extract_article_contents_readabilityextractor", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L372", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_406", "target": "$graphify-root$_scripts_extract_article_contents_extract_all_engines", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L406", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_459", "target": "$graphify-root$_scripts_extract_article_contents_articlecrawler", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L459", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_488", "target": "$graphify-root$_scripts_extract_article_contents_articlecrawler_crawl", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L488", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_510", "target": "$graphify-root$_scripts_extract_article_contents_log_info", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L510", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_517", "target": "$graphify-root$_scripts_extract_article_contents_load_search_json", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L517", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_545", "target": "$graphify-root$_scripts_extract_article_contents_save_extracted_json", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L545", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_559", "target": "$graphify-root$_scripts_extract_article_contents_process_batch", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L559", "weight": 1.0}], "raw_calls": [{"caller_nid": "$graphify-root$_scripts_extract_article_contents_extractedarticle_to_dict", "callee": "to_dict", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L192", "receiver": null}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_extractedarticle_to_dict", "callee": "to_dict", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L198", "receiver": null}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_extractedarticle_to_dict", "callee": "to_dict", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L199", "receiver": null}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_extractedarticle_to_dict", "callee": "to_dict", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L200", "receiver": null}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_extractionbatchreport_to_dict", "callee": "to_dict", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L222", "receiver": "a"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_trafilaturaextractor_extract", "callee": "bare_extraction", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L238", "receiver": "trafilatura"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_trafilaturaextractor_extract", "callee": "extract", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L250", "receiver": "trafilatura"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_trafilaturaextractor_extract", "callee": "extract", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L262", "receiver": "trafilatura"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_trafilaturaextractor_extract", "callee": "loads", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L271", "receiver": "json"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_trafilaturaextractor_extract", "callee": "strip", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L292", "receiver": null}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_trafilaturaextractor_extract", "callee": "strip", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L293", "receiver": null}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_trafilaturaextractor_extract", "callee": "extract", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L298", "receiver": "trafilatura"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_trafilaturaextractor_extract", "callee": "get", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L300", "receiver": "raw_json"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_trafilaturaextractor_extract", "callee": "strip", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L301", "receiver": "raw_text"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_trafilaturaextractor_extract", "callee": "strip", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L302", "receiver": "markdown_text"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_trafilaturaextractor_extract", "callee": "e", "is_member_call": false, "indirect": true, "context": "argument", "source_file": "scripts/extract_article_contents.py", "source_location": "L307"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_newspaperextractor_extract", "callee": "lower", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L316", "receiver": null}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_newspaperextractor_extract", "callee": "split", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L316", "receiver": "language"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_newspaperextractor_extract", "callee": "Article", "is_member_call": false, "source_file": "scripts/extract_article_contents.py", "source_location": "L318", "receiver": null}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_newspaperextractor_extract", "callee": "download", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L319", "receiver": "article"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_newspaperextractor_extract", "callee": "parse", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L320", "receiver": "article"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_newspaperextractor_extract", "callee": "nlp", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L324", "receiver": "article"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_newspaperextractor_extract", "callee": "keyword_scores", "is_member_call": false, "indirect": true, "context": "getattr", "source_file": "scripts/extract_article_contents.py", "source_location": "L327"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_newspaperextractor_extract", "callee": "isoformat", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L334", "receiver": null}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_newspaperextractor_extract", "callee": "tags", "is_member_call": false, "indirect": true, "context": "getattr", "source_file": "scripts/extract_article_contents.py", "source_location": "L341"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_newspaperextractor_extract", "callee": "movies", "is_member_call": false, "indirect": true, "context": "getattr", "source_file": "scripts/extract_article_contents.py", "source_location": "L342"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_newspaperextractor_extract", "callee": "meta_img", "is_member_call": false, "indirect": true, "context": "getattr", "source_file": "scripts/extract_article_contents.py", "source_location": "L353"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_newspaperextractor_extract", "callee": "canonical_link", "is_member_call": false, "indirect": true, "context": "getattr", "source_file": "scripts/extract_article_contents.py", "source_location": "L357"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_newspaperextractor_extract", "callee": "article_html", "is_member_call": false, "indirect": true, "context": "getattr", "source_file": "scripts/extract_article_contents.py", "source_location": "L358"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_newspaperextractor_extract", "callee": "meta_description", "is_member_call": false, "indirect": true, "context": "getattr", "source_file": "scripts/extract_article_contents.py", "source_location": "L359"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_newspaperextractor_extract", "callee": "meta_favicon", "is_member_call": false, "indirect": true, "context": "getattr", "source_file": "scripts/extract_article_contents.py", "source_location": "L361"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_newspaperextractor_extract", "callee": "meta_site_name", "is_member_call": false, "indirect": true, "context": "getattr", "source_file": "scripts/extract_article_contents.py", "source_location": "L362"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_newspaperextractor_extract", "callee": "meta_lang", "is_member_call": false, "indirect": true, "context": "getattr", "source_file": "scripts/extract_article_contents.py", "source_location": "L363"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_newspaperextractor_extract", "callee": "e", "is_member_call": false, "indirect": true, "context": "argument", "source_file": "scripts/extract_article_contents.py", "source_location": "L368"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_readabilityextractor_extract", "callee": "Document", "is_member_call": false, "source_file": "scripts/extract_article_contents.py", "source_location": "L377", "receiver": null}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_readabilityextractor_extract", "callee": "title", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L378", "receiver": "doc"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_readabilityextractor_extract", "callee": "short_title", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L379", "receiver": "doc"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_readabilityextractor_extract", "callee": "summary", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L380", "receiver": "doc"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_readabilityextractor_extract", "callee": "author", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L383", "receiver": "doc"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_readabilityextractor_extract", "callee": "BeautifulSoup", "is_member_call": false, "source_file": "scripts/extract_article_contents.py", "source_location": "L388", "receiver": null}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_readabilityextractor_extract", "callee": "get_text", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L389", "receiver": "soup"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_readabilityextractor_extract", "callee": "e", "is_member_call": false, "indirect": true, "context": "argument", "source_file": "scripts/extract_article_contents.py", "source_location": "L400"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_extract_all_engines", "callee": "extract", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L408", "receiver": "TrafilaturaExtractor"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_extract_all_engines", "callee": "exc", "is_member_call": false, "indirect": true, "context": "argument", "source_file": "scripts/extract_article_contents.py", "source_location": "L420"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_extract_all_engines", "callee": "extract", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L424", "receiver": "NewspaperExtractor"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_extract_all_engines", "callee": "exc", "is_member_call": false, "indirect": true, "context": "argument", "source_file": "scripts/extract_article_contents.py", "source_location": "L436"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_extract_all_engines", "callee": "extract", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L440", "receiver": "ReadabilityExtractor"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_extract_all_engines", "callee": "exc", "is_member_call": false, "indirect": true, "context": "argument", "source_file": "scripts/extract_article_contents.py", "source_location": "L447"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_articlecrawler_start", "callee": "FoxcapeConfig", "is_member_call": false, "source_file": "scripts/extract_article_contents.py", "source_location": "L468", "receiver": null}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_articlecrawler_start", "callee": "Foxcape", "is_member_call": false, "source_file": "scripts/extract_article_contents.py", "source_location": "L469", "receiver": null}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_articlecrawler_start", "callee": "start", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L470", "receiver": null}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_articlecrawler_close", "callee": "close", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L475", "receiver": null}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_articlecrawler_crawl", "callee": "get", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L495", "receiver": null}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_log_info", "callee": "write", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L512", "receiver": null}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_log_info", "callee": "flush", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L513", "receiver": null}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_load_search_json", "callee": "exists", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L518", "receiver": "file_path"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_load_search_json", "callee": "FileNotFoundError", "is_member_call": false, "source_file": "scripts/extract_article_contents.py", "source_location": "L519", "receiver": null}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_load_search_json", "callee": "load", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L522", "receiver": "json"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_load_search_json", "callee": "f", "is_member_call": false, "indirect": true, "context": "argument", "source_file": "scripts/extract_article_contents.py", "source_location": "L522"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_load_search_json", "callee": "get", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L524", "receiver": "data"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_load_search_json", "callee": "get", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L525", "receiver": "data"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_load_search_json", "callee": "get", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L526", "receiver": "data"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_load_search_json", "callee": "dict", "is_member_call": false, "indirect": true, "context": "argument", "source_file": "scripts/extract_article_contents.py", "source_location": "L530"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_load_search_json", "callee": "append", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L531", "receiver": "articles"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_load_search_json", "callee": "get", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L535", "receiver": "item"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_load_search_json", "callee": "get", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L536", "receiver": "item"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_load_search_json", "callee": "get", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L537", "receiver": "item"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_save_extracted_json", "callee": "mkdir", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L546", "receiver": null}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_save_extracted_json", "callee": "dump", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L548", "receiver": "json"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_save_extracted_json", "callee": "f", "is_member_call": false, "indirect": true, "context": "argument", "source_file": "scripts/extract_article_contents.py", "source_location": "L548"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_save_extracted_json", "callee": "to_dict", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L548", "receiver": "report"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_process_batch", "callee": "time", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L581", "receiver": "time"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_process_batch", "callee": "crawl", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L589", "receiver": "crawler"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_process_batch", "callee": "exc", "is_member_call": false, "indirect": true, "context": "argument", "source_file": "scripts/extract_article_contents.py", "source_location": "L618"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_process_batch", "callee": "append", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L635", "receiver": "extracted_list"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_process_batch", "callee": "time", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L637", "receiver": "time"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_process_batch", "callee": "isoformat", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L638", "receiver": null}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_process_batch", "callee": "now", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L638", "receiver": "datetime"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_parse_arguments", "callee": "ArgumentParser", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L665", "receiver": "argparse"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_parse_arguments", "callee": "add_argument", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L669", "receiver": "parser"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_parse_arguments", "callee": "str", "is_member_call": false, "indirect": true, "context": "argument", "source_file": "scripts/extract_article_contents.py", "source_location": "L673"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_parse_arguments", "callee": "add_argument", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L676", "receiver": "parser"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_parse_arguments", "callee": "str", "is_member_call": false, "indirect": true, "context": "argument", "source_file": "scripts/extract_article_contents.py", "source_location": "L680"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_parse_arguments", "callee": "add_argument", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L684", "receiver": "parser"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_parse_arguments", "callee": "int", "is_member_call": false, "indirect": true, "context": "argument", "source_file": "scripts/extract_article_contents.py", "source_location": "L688"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_parse_arguments", "callee": "add_argument", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L692", "receiver": "parser"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_parse_arguments", "callee": "str", "is_member_call": false, "indirect": true, "context": "argument", "source_file": "scripts/extract_article_contents.py", "source_location": "L697"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_parse_arguments", "callee": "add_argument", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L701", "receiver": "parser"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_parse_arguments", "callee": "int", "is_member_call": false, "indirect": true, "context": "argument", "source_file": "scripts/extract_article_contents.py", "source_location": "L705"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_parse_arguments", "callee": "add_argument", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L709", "receiver": "parser"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_parse_arguments", "callee": "parse_args", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L715", "receiver": "parser"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_main", "callee": "exists", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L724", "receiver": "input_path"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_main", "callee": "write", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L725", "receiver": null}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_main", "callee": "write", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L738", "receiver": null}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_main", "callee": "write", "is_member_call": true, "source_file": "scripts/extract_article_contents.py", "source_location": "L741", "receiver": null}]}