Last active
October 10, 2015 12:37
-
-
Save rgiot/3690666 to your computer and use it in GitHub Desktop.
Python script allowing to extract some metrics from a google citation page
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# -*- coding: utf-8 -*- | |
"""Python script to extract citations numbers from google citation pages | |
Extract informations from google citation (number of citations, h-index, i10 index). | |
The main program outputs LaTeX definition in order to automatically use the result | |
in a LaTeX document (ie. academic cv) | |
""" | |
# imports | |
from bs4 import BeautifulSoup | |
import httplib, sys | |
HEADERS = {'User-Agent': 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'} | |
def extract_information_for(user): | |
"""Extract the information for the required user. | |
Parameters | |
========== | |
- user: str | |
Code of the user of google citation | |
""" | |
conn = httplib.HTTPConnection('scholar.google.co.uk' ) | |
conn.request("GET", '/citations?user=%s' % user, {}, HEADERS) | |
resp = conn.getresponse() | |
if resp.status == 200: | |
# Dowload stuff | |
html = resp.read() | |
html = html.decode( 'ascii', 'ignore' ) | |
soup = BeautifulSoup( html, 'html5lib' ) | |
# Search interesting part | |
for record in soup('table', {'id':'stats'}): | |
# TODO cleanup this part | |
pointer = record.next_element.next_element.next_sibling.next_element.next_sibling | |
nb_citations = pointer.text | |
pointer = record.next_element.next_element.next_sibling.next_sibling.next_element.next_sibling | |
h_index = pointer.text | |
pointer = record.next_element.next_element.next_sibling.next_sibling.next_sibling.next_element.next_sibling | |
i10_index = pointer.text | |
break | |
return int(nb_citations), int(h_index), int(i10_index) | |
else: | |
print 'Error: ' | |
print resp.status, resp.reason | |
exit(-1) | |
if __name__ == '__main__': | |
if len(sys.argv) < 2: | |
user = 'bwwARrQAAAAJ' | |
else: | |
user = sys.argv[1] | |
# Build a latex content | |
nb_citations, h_index, i10_index = extract_information_for(user) | |
print "\def\scholarnbcitations{%d}" % nb_citations | |
print "\def\scholarhindex{%d}" % h_index | |
print "\def\scholaritenindex{%d}" % i10_index | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment