{"id":"W4285540454","doi":"10.52458/978-93-91842-08-6-38","title":"Web Scraping Techniques and Applications: A Literature Review","year":2021,"lang":"en","type":"review","venue":"Soft Computing Research Society eBooks","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"Cégep de Chicoutimi; Université du Québec à Chicoutimi","funders":"","keywords":"Computer science; World Wide Web; Web intelligence; Big data; Data science; Web mining; Web analytics; Web application; Analytics; Social media; Web standards; Web development; Web engineering; Web modeling; The Internet; Web page; Data mining","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002049687,0.00107107,0.001560047,0.01008933,0.0007076002,0.002079927,0.001390041,0.001316542,0.00397356],"category_scores_gemma":[0.006809024,0.0006805962,0.001316573,0.01237519,0.0007800526,0.003373937,0.000975812,0.001318444,0.001701263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009278256,"about_ca_system_score_gemma":0.003572143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003310082,"about_ca_topic_score_gemma":0.004924365,"domain_scores_codex":[0.9987337,0.0002478078,0.000248946,0.00016816,0.0005303852,0.00007093301],"domain_scores_gemma":[0.9933404,0.004302704,0.0005651999,0.000137198,0.001515771,0.0001386954],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004473941,0.00009931128,0.0005179359,0.05352835,0.0001120058,0.0001905323,0.0002150855,0.0003964326,0.0006128149,0.00251033,0.01480396,0.9269685],"study_design_scores_gemma":[0.00001855064,0.0002047485,0.003800734,0.07926469,0.0007579902,0.002645392,0.0006714191,0.0006114329,0.001398381,0.004310669,0.9062393,0.00007657528],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0003033988,0.9976619,0.0004918237,0.0003452962,0.0001181985,0.00001807219,0.00002722492,0.00001658808,0.001017369],"genre_scores_gemma":[0.00135018,0.9972824,0.0007395396,0.0001826957,0.0001020533,0.00001915751,0.00003818344,0.000005478057,0.0002803302],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.01008933,"threshold_uncertainty_score":0.01329291,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0854457235976239,"score_gpt":0.4236613379830667,"score_spread":0.3382156143854428,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}