The fields available in the DBLP data

datasets.js

{
  "entity_id": "<UUID4>",
  "entity_type": "node",
  "entity_class": "",
  "@key": "conf\/www\/Ericsson07",
  "@cdate": "2021-01-01",
  "@mdate": "2022-08-31",
  "@publtype": NaN,
  "address": "",
  // Note: there is another form where author is just a string - must ETL
  // Note: sometimes this is a list of strings
  "authors": [{
    "#text": "Morgan Ericsson",
    "@orcid": "0000-0003-1173-5187"
  }],
  "booktitle": "OTM",
  "cdrom": NaN,
  "chapter": NaN,
  "cite": NaN,
  "crossref": "conf\/coopis\/2003",
  // Note: there is another form where author is just a string - must ETL
  // Note: sometimes this is a list of strings
  // Note: strings/dicts occur in same lists
  "editors": [{
    "#text": "Morgan Ericsson",
    "@orcid": "0000-0003-1173-5187"
  }],
  "ee": "https:\/\/doi.org\/10.1007\/s11280-007-0032-y",
  "isbn": "978-3-8244-2051-3",
  "journal": "World Wide Web",
  "month": NaN,
  "note": NaN,
  "number": "3",
  "pages": "279-307",
  "publisher": "Dt. Univ.-Verlag",
  "publnr": NaN,
  "school": NaN,
  "series_text": "Lecture Notes in Computer Science",
  "series_href": "db\/series\/lncs\/index.html",
  "title": "The Effects of XML Compression on SOAP Performance.",
  "url": "db\/journals\/www\/www10.html#Ericsson07",
  "volume": NaN,
  "year": "2007",
}

datasets.py

In [5]: for key, df in dfs.items():
   ...:     print(key, df.columns)
   ...:
article Index(['@mdate', '@key', '@publtype', 'title', 'author', 'pages', 'year',
       'journal', 'number', 'ee', 'url', 'volume', 'crossref', 'note', 'cdrom',
       'editor', 'cite', 'booktitle', 'publnr', 'month', '@cdate',
       'publisher'],
      dtype='object')
book Index(['@mdate', '@key', 'author', 'title', 'year', 'pages', 'publisher',
       'isbn', 'ee', 'school', '@publtype', 'series', 'volume', 'note',
       'editor', 'booktitle', 'url', 'crossref', 'month', 'cite', 'cdrom'],
      dtype='object')
incollection Index(['@mdate', '@key', 'author', 'title', 'pages', 'year', 'booktitle', 'ee',
       'crossref', 'url', '@publtype', 'cite', 'publisher', 'number', 'note',
       'cdrom', 'chapter'],
      dtype='object')
inproceedings Index(['@mdate', '@key', 'author', 'title', 'booktitle', 'year', 'url',
       'crossref', 'ee', 'pages', 'cite', 'cdrom', '@publtype', 'note',
       'editor', 'number', 'volume', 'month'],
      dtype='object')
mastersthesis Index(['@mdate', '@key', 'author', 'title', 'year', 'school', 'ee', 'note'], dtype='object')
phdthesis Index(['@mdate', '@key', 'author', 'title', 'year', 'school', 'publisher',
       'number', 'pages', 'isbn', 'ee', 'month', 'series', 'volume', 'note',
       '@publtype'],
      dtype='object')
proceedings Index(['@mdate', '@key', 'editor', 'title', 'publisher', 'year', 'isbn', 'ee',
       'url', 'booktitle', 'series', 'volume', 'note', 'number', 'pages',
       '@publtype', 'author', 'school', 'address', 'journal', 'cite'],
      dtype='object')
www Index(['@mdate', '@key', 'author', 'title', 'url', 'note', '@publtype',
       'crossref', 'cite', 'ee', 'year', 'editor'],
      dtype='object')