Skip to content

record citations per year in scraped data #8

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
cmacdonald wants to merge 1 commit into
base: master
Choose a base branch
from
Open

record citations per year in scraped data #8

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
23 changes: 19 additions & 4 deletions scrape.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,26 +29,41 @@ 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<spanArray.length;s++){
years[s] = spanArray[s].children[0].data;
}

var citeyears = new Array();
var aArray = rawYear.find('a');
for(var s=0;s<aArray.length;s++){
citeyears[s] = parseInt(aArray[s].children[0].children[0].data);
}

var cites_by_year = {};
years.forEach((key, i) => cites_by_year[key] = citeyears[i]);

var stats = {
'citations' : [ rawStats[0].children[1].children[0].children[1].children[0].data,
rawStats[0].children[1].children[0].children[2].children[0].data ],
'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,
'photo' : 'http://scholar.google.com' + photo,
'affiliation' : affiliation,
'keywords' : keywords,
'stats' : stats,
'year' : rawYear[0].children[0].children[0].data
'year' : rawYear[0].children[0].children[0].data,
};

} catch (ex) {
Expand Down