Create a bibliography from (R)markdown sorted by in-article citation frequency

count-and-sort.py

#!/usr/bin/env python3

# Create a bibliography from (R)markdown sorted by in-article citation frequency
#
# usage: pandoc -s --bibliography=refs.bib --citeproc foo.Rmd bar.Rmd ... | count-and-sort.py > refs_by_citation_frequency.html
#
# Author: emilianoeheyns
# Details: https://forums.zotero.org/discussion/comment/385929#Comment_385929

import xml.etree.ElementTree as ET
import sys

def citekey(key):
  if key.startswith('ref-'): key = key[4:]
  return key

tree = ET.parse(sys.stdin)
root = tree.getroot()

for node in root.findall('.//*'):
  node.tag = node.tag.split('}')[-1]

cited = {}
for node in root.findall('.//span'):
  if node.attrib.get('class') == 'citation':
    for key in node.attrib['data-cites'].split(' '):
      if not key in cited: cited[key] = 0
      cited[key] += 1

body = root.find('.//body')
body[:] = [node for node in body if node.tag == 'div' and node.attrib.get('role') == 'doc-bibliography']

bib = [node for node in root.findall('.//div') if node.attrib.get('role') == 'doc-bibliography'][0]
bib[:] = sorted(bib[:], reverse=True, key=lambda node: cited[citekey(node.attrib['id'])])

for node in root.findall('.//div'):
  if node.attrib.get('role') == 'doc-biblioentry':
    count = ET.SubElement(node, 'span')
    count.text = f': {cited[citekey(node.attrib["id"])]}'

tree.write(sys.stdout.buffer)