Files
TextNLPClassifierApp/graphify-out/cache/ast/v0.9.47-s2/a76fc087a959496bc2cf4767baaed89628bd945e1aaa8e981be840cf1240f1ba.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
70 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": "L34", "_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": "L43", "_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": "L54", "_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": "L77", "_callable": true}, {"id": "$graphify-root$_scripts_extract_article_contents_newspaperdata", "label": "NewspaperData", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L102", "_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": "L126", "_callable": true}, {"id": "$graphify-root$_scripts_extract_article_contents_readabilitydata", "label": "ReadabilityData", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L152", "_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": "L162", "_callable": true}, {"id": "$graphify-root$_scripts_extract_article_contents_extractedarticle", "label": "ExtractedArticle", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L174", "_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": "L187", "_callable": true}, {"id": "$graphify-root$_scripts_extract_article_contents_extractionbatchreport", "label": "ExtractionBatchReport", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L202", "_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": "L212", "_callable": true}, {"id": "$graphify-root$_scripts_extract_article_contents_trafilaturaextractor", "label": "TrafilaturaExtractor", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L228", "_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": "L232", "_callable": true}, {"id": "$graphify-root$_scripts_extract_article_contents_newspaperextractor", "label": "NewspaperExtractor", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L332", "_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": "L336", "_callable": true}, {"id": "$graphify-root$_scripts_extract_article_contents_readabilityextractor", "label": "ReadabilityExtractor", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L395", "_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": "L399", "_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": "L427", "_callable": true}, {"id": "$graphify-root$_scripts_extract_article_contents_articlecrawler", "label": "ArticleCrawler", "file_type": "code", "source_file": "scripts/extract_article_contents.py", "source_location": "L482", "_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": "L485", "_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": "L490", "_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": "L496", "_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": "L504", "_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": "L508", "_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": "L511", "_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": "L533", "_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": "L540", "_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": "L568", "_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": "L575", "_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": "L688", "_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": "L742", "_callable": true}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_35", "label": "Metadados originais da not\u00edcia contida no JSON de entrada.", "file_type": "rationale", "source_file": "scripts/extract_article_contents.py", "source_location": "L35"}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_55", "label": "Dados completos extra\u00eddos pelo motor Trafilatura.", "file_type": "rationale", "source_file": "scripts/extract_article_contents.py", "source_location": "L55"}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_103", "label": "Dados completos extra\u00eddos e enriquecidos com NLP pelo motor Newspaper4k.", "file_type": "rationale", "source_file": "scripts/extract_article_contents.py", "source_location": "L103"}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_153", "label": "Dados completos higienizados pelo algoritmo Readability.", "file_type": "rationale", "source_file": "scripts/extract_article_contents.py", "source_location": "L153"}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_175", "label": "Resultado consolidado da extra\u00e7\u00e3o de um artigo.", "file_type": "rationale", "source_file": "scripts/extract_article_contents.py", "source_location": "L175"}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_203", "label": "Relat\u00f3rio consolidado de sa\u00edda do processamento de um lote.", "file_type": "rationale", "source_file": "scripts/extract_article_contents.py", "source_location": "L203"}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_229", "label": "Motor de extra\u00e7\u00e3o baseado na biblioteca Trafilatura.", "file_type": "rationale", "source_file": "scripts/extract_article_contents.py", "source_location": "L229"}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_333", "label": "Motor de extra\u00e7\u00e3o baseado no Newspaper4k com NLP.", "file_type": "rationale", "source_file": "scripts/extract_article_contents.py", "source_location": "L333"}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_396", "label": "Motor de extra\u00e7\u00e3o baseado no algoritmo Readability (readability-lxml).", "file_type": "rationale", "source_file": "scripts/extract_article_contents.py", "source_location": "L396"}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_430", "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": "L430"}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_483", "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": "L483"}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_512", "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": "L512"}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_534", "label": "Escreve mensagem informativa no stderr.", "file_type": "rationale", "source_file": "scripts/extract_article_contents.py", "source_location": "L534"}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_541", "label": "Carrega o arquivo JSON gerado pelo extrator de not\u00edcias.", "file_type": "rationale", "source_file": "scripts/extract_article_contents.py", "source_location": "L541"}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_569", "label": "Salva o relat\u00f3rio consolidado em formato JSON com UTF-8.", "file_type": "rationale", "source_file": "scripts/extract_article_contents.py", "source_location": "L569"}, {"id": "$graphify-root$_scripts_extract_article_contents_rationale_583", "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": "L583"}], "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": "sys", "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": "time", "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": "dataclasses", "relation": "imports_from", "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": "datetime", "relation": "imports_from", "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": "pathlib", "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": "typing", "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": "trafilatura", "relation": "imports", "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": "L23", "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": "L24", "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": "L25", "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": "L26", "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": "L34", "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": "L43", "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": "L43", "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": "L54", "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": "L77", "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": "L77", "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": "L102", "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": "L126", "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": "L126", "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": "L152", "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": "L162", "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": "L162", "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": "L174", "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": "L187", "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": "L187", "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": "L202", "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": "L212", "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": "L212", "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": "L228", "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": "L232", "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": "L232", "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": "L332", "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": "L336", "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": "L336", "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": "L395", "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": "L399", "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": "L399", "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": "L427", "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": "L427", "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": "L427", "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": "L427", "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": "L482", "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": "L485", "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": "L490", "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": "L496", "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": "L504", "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": "L504", "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": "L508", "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": "L508", "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": "L508", "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": "L508", "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": "L511", "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": "L533", "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": "L540", "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": "L540", "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": "L540", "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": "L568", "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": "L568", "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": "L568", "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": "L575", "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": "L575", "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": "L575", "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": "L575", "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": "L688", "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": "L688", "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": "L742", "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": "L274", "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": "L369", "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": "L415", "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": "L434", "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": "L450", "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": "L466", "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": "L505", "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": "L509", "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": "L516", "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": "L556", "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": "L586", "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": "L593", "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": "L607", "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": "L619", "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": "L623", "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": "L664", "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": "L673", "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": "L744", "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": "L745", "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": "L752", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_35", "target": "$graphify-root$_scripts_extract_article_contents_inputarticle", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L35", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_55", "target": "$graphify-root$_scripts_extract_article_contents_trafilaturadata", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L55", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_103", "target": "$graphify-root$_scripts_extract_article_contents_newspaperdata", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L103", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_153", "target": "$graphify-root$_scripts_extract_article_contents_readabilitydata", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L153", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_175", "target": "$graphify-root$_scripts_extract_article_contents_extractedarticle", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L175", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_203", "target": "$graphify-root$_scripts_extract_article_contents_extractionbatchreport", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L203", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_229", "target": "$graphify-root$_scripts_extract_article_contents_trafilaturaextractor", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L229", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_333", "target": "$graphify-root$_scripts_extract_article_contents_newspaperextractor", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L333", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_396", "target": "$graphify-root$_scripts_extract_article_contents_readabilityextractor", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L396", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_430", "target": "$graphify-root$_scripts_extract_article_contents_extract_all_engines", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L430", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_483", "target": "$graphify-root$_scripts_extract_article_contents_articlecrawler", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L483", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_512", "target": "$graphify-root$_scripts_extract_article_contents_articlecrawler_crawl", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L512", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_534", "target": "$graphify-root$_scripts_extract_article_contents_log_info", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L534", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_541", "target": "$graphify-root$_scripts_extract_article_contents_load_search_json", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L541", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_569", "target": "$graphify-root$_scripts_extract_article_contents_save_extracted_json", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L569", "weight": 1.0}, {"source": "$graphify-root$_scripts_extract_article_contents_rationale_583", "target": "$graphify-root$_scripts_extract_article_contents_process_batch", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "scripts/extract_article_contents.py", "source_location": "L583", "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": "L189", "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": "L195", "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": "L196", "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": "L197", "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": "L219", "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": "L235", "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": "L247", "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": "L259", "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": "L268", "receiver": "json"}, {"caller_nid": "$graphify-root$_scripts_extract_article_contents_trafilaturaextractor_extract", "callee": "dict", "is_member_call": false, "indirect": true, "context": "argument", "source_file": "scripts/extract_article_contents.py", "source_location": "L271"}, {"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": "L272", "receiver": "doc"}, {"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": "L272", "receiver": "doc"}, {"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": "L273", "receiver": "doc"}, {"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": "L273", "receiver": "doc"}, {"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": "L275", "receiver": "doc"}, {"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": "L276", "receiver": "doc"}, {"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": "L277", "receiver": "doc"}, {"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": "L278", "receiver": "doc"}, {"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": "L279", "receiver": "doc"}, {"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": "L280", "receiver": "doc"}, {"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": "L281", "receiver": "doc"}, {"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": "L284", "receiver": "doc"}, {"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": "L285", "receiver": "doc"}, {"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": "L286", "receiver": "doc"}, {"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": "L287", "receiver": "doc"}, {"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": "L288", "receiver": "doc"}, {"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": "L289", "receiver": "doc"}, {"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": "L290", "receiver": null}, {"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": "L290", "receiver": "doc"}, {"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": "L291", "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": "L314", "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": "L315", "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": "L320", "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": "L322", "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": "L323", "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": "L324", "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": "L329"}, {"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": "L338", "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": "L338", "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": "L340", "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": "L341", "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": "L342", "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": "L346", "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": "L349"}, {"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": "L356", "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": "L365"}, {"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": "L366"}, {"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": "L377"}, {"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": "L381"}, {"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": "L382"}, {"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": "L383"}, {"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": "L385"}, {"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": "L386"}, {"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": "L387"}, {"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": "L392"}, {"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": "L401", "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": "L402", "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": "L403", "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": "L404", "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": "L407", "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": "L412", "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": "L413", "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": "L424"}, {"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": "L432", "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": "L444"}, {"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": "L448", "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": "L460"}, {"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": "L464", "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": "L471"}, {"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": "L492", "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": "L493", "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": "L494", "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": "L499", "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": "L519", "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": "L536", "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": "L537", "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": "L542", "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": "L543", "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": "L546", "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": "L546"}, {"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": "L548", "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": "L549", "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": "L550", "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": "L554"}, {"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": "L555", "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": "L559", "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": "L560", "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": "L561", "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": "L570", "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": "L572", "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": "L572"}, {"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": "L572", "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": "L605", "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": "L613", "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": "L642"}, {"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": "L659", "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": "L661", "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": "L662", "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": "L662", "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": "L689", "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": "L693", "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": "L700", "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": "L704"}, {"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": "L708", "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": "L712"}, {"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": "L716", "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": "L721"}, {"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": "L725", "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": "L729"}, {"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": "L733", "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": "L739", "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": "L748", "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": "L749", "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": "L762", "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": "L765", "receiver": null}]}