/ Published in: Python
Expand |
Embed | Plain Text
Copy this code and paste it in your HTML
from urllib import urlopen def most_prolific_authors(): """ Return the list of most prolific DBLP authors http://www.informatik.uni-trier.de/~ley/db/about/prolific.html The number of publications listed in DBLP for an author is no indication for the quality or importance of her/his work. """ url = 'http://www.informatik.uni-trier.de/~ley/db/indices/a-tree/prolific/index.html' doc = urlopen(url).read() start = doc.find('number of publications / names') end_of_cloud = doc.find('DBLP lists',start) authors = [] while(True): start = doc.find('html">',start) if start == -1 or start>end_of_cloud: return authors end = doc.find('</a>',start) name = doc[start+6:end] if not isNumber(name): authors.append(name) start = end+14 # </a></td></tr> return authors
URL: http://www.informatik.uni-trier.de/~ley/db/indices/a-tree/prolific/index.html