extract authors of research papers from all editions of the IEEE ICDM so far

ieee_icdm_authors.py

#!/usr/bin/python3
import requests
from collections import Counter

from bs4 import BeautifulSoup

top_k = 10
authors = list()
for year in range(2001, 2019):
    print(year)
    res = requests.get("https://dblp.org/db/conf/icdm/icdm%d.html" % year)
    soup = BeautifulSoup(res.text, features="html.parser")
    entries = soup.find_all("li", {"class": "entry inproceedings"})
    for entry in entries:
        name_tags = entry.find_all("span", {"itemprop": "author"})
        authors.extend(name_tag.text for name_tag in name_tags)

for author, npub in Counter(authors).most_common(top_k):
    print("%s -> %d" % (author, npub))