A script to extract title from hand-written bib items and download the bibtex item from Google Scholar with the help of scholar.py (https://github.com/hildensia/scholar).

bib_downloader.py

# -*- coding: utf-8 -*-
"""
Created on Mon Mar 23 21:13:21 2015

@author: Qing

A script to extract title from hand-written bib items and download the bibtex item
from Google Scholar with the help of scholar.py (https://github.com/hildensia/scholar).
"""
from subprocess import Popen, PIPE
import time

def extract_title(texFile, output='title.txt'):
    lines = ''.join(open(texFile).readlines())
    papers = lines.split('\\bibitem')
    titles = []
    for p in papers:
        if p.strip() == '':
            continue
        tokens = p.replace(',', '.').split('.')
        tlen = [len(t) for t in tokens]
        # pick the longest phrase as title
        title = tokens[tlen.index(max(tlen))].replace('\n', ' ')
        # remove latex command
        latex = ['\\newblock', '\it', '{', '}']
        for cmd in latex:
            title = title.replace(cmd, '').strip()
        titles.append(title)
    with open(output, 'w') as fout:
        fout.write('\n'.join(titles))

def batch_cmd(fname='title.txt', output='bibtext.txt', seconds=0.5):
    cnt = 1
    with open(fname) as fin, open(output, 'w') as fout:
        for line in fin:
            title = line.strip()
            print cnt,
            bibtex = Popen('scholar.py -c 1 -p "%s" --citation bt' % title, stdout=PIPE, shell=True).stdout.read()
            cnt += 1
            fout.write('%s\n' % bibtex)
            time.sleep(seconds)

if __name__ == "__main__":
    '''
    The input file is the hand-written bib items. For example:
    \bibitem{i}M.T. Barlow, Diffusions on fractals, Lectures on Probability Theory and Statistics, Lect. Notes Math., Springer, 1690(1998),1-121
    \bibitem{k}M.T. Barlow, Heat kernels and sets with fractal structure, in Heat kernels and analysis on manifolds graphs, and metric spaces, Contemporary Math. 338(2003), 11-40
    \bibitem{l}M.T. Barlow, T.Coulhon and T.Kumagai, Characterization of sub-Gaussian heat kernel estimates on strongly recurrent graphs, Comm. Pure Appl. Math. 58(200)
    '''
    extract_title('bibitem.tex')
    batch_cmd()