From 6166cb8249e08a1388abcb4406fa4b607fbabe85 Mon Sep 17 00:00:00 2001 From: Craig Macdonald Date: Wed, 8 Sep 2021 14:59:31 +0100 Subject: [PATCH] record citations per year in scraped data --- scrape.js | 23 +++++++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-) diff --git a/scrape.js b/scrape.js index 48c48fa..5475500 100644 --- a/scrape.js +++ b/scrape.js @@ -29,6 +29,22 @@ var scrapeEntry = function(person, doneCallback) { } var rawStats = $('#gsc_rsb_st'); + var rawYear = $('.gsc_md_hist_b'); + + var spanArray = rawYear.find('span'); + var years = new Array(); + for(var s=0;s cites_by_year[key] = citeyears[i]); var stats = { 'citations' : [ rawStats[0].children[1].children[0].children[1].children[0].data, @@ -36,11 +52,10 @@ var scrapeEntry = function(person, doneCallback) { 'hindex' : [ rawStats[0].children[1].children[1].children[1].children[0].data, rawStats[0].children[1].children[1].children[2].children[0].data ], 'i10index' : [ rawStats[0].children[1].children[2].children[1].children[0].data, - rawStats[0].children[1].children[2].children[2].children[0].data ] + rawStats[0].children[1].children[2].children[2].children[0].data ], + 'citations_by_year' : cites_by_year }; - var rawYear = $('.gsc_md_hist_b'); - data = { 'name' : person, 'url': url, @@ -48,7 +63,7 @@ var scrapeEntry = function(person, doneCallback) { 'affiliation' : affiliation, 'keywords' : keywords, 'stats' : stats, - 'year' : rawYear[0].children[0].children[0].data + 'year' : rawYear[0].children[0].children[0].data, }; } catch (ex) {