tobib.py

#!/home/abhijit/anaconda/bin/python

import re

def getauthor(x):
	authlist = x.split('.')[0]
	bl = authlist.split(',')
	bl = [u.lstrip().replace(' ',', ') for u in bl]
	bl = [u.replace('et al','"et al"') for u in bl]
	out = 'author = {'+' and '.join(bl)+'}'
	return out

def getvol(x,pos=2):	
	a = x.split('.')[pos]
	out = a[a.find(';'):a.find(':')].lstrip(';')
	return out


f = open('Bibliography_ToddArnedtGrant.txt','r')
x = f.readlines()
f.close()

x = [u.rstrip('\r\n') for u in x]
x = [u for u in x if re.search('^[0-9]',u) is not None]
x = [u.split('\t')[1] for u in x]

y = [u.split('.')[:-1] for u in x]

outliers = [x[i] for i in range(len(x)) if len(y[i]) != 3]
goodx = list(set(x).difference(set(outliers)))

books = [u for u in goodx if re.search('\d{4}\.$', u) is not None]
articles = list(set(goodx).difference(set(books)))



g = file('Todd.bib','w')
# Articles first
authors = [getauthor(u) for u in articles]
title = ['title = {'+u.split('.')[1].lstrip()+'}' for u in articles]
journal = ['journal = {' + re.split('\d{4}',u.split('.')[2])[0].strip()+'}' for u in articles]
pages = ['pages = {'+u.split('.')[2].split(':')[-1].rstrip('.')+'}' for u in articles]
vols = ['volume = {'+getvol(u)+'}' for u in articles]
year = ['year = {'+ re.findall('\d{4}',u.split('.')[2])[0]+'}' for u in articles]
kw = [u[0][u[0].find('{'):u[0].find(',')].lstrip('{')+re.findall('\d{4}',u[1])[0] for u in zip(authors, year)]

bibs = [',\n\t'.join(u) for u in zip(kw, authors, title, journal, pages, vols,year)]
bibs = ['@article{'+u+'}\n\n' for u in bibs]
g.writelines(bibs)

#Books next
authors = [getauthor(u) for u in books]
title = ['title = {'+u.split('.')[1].lstrip()+'}' for u in books]
year = ['year = {'+ re.findall('\d{4}',u.split('.')[2])[0]+'}' for u in books]
publisher = [re.split(' \d{4}',u.split('.')[2])[0] for u in books]
publisher = ['publisher = {'+ u.lstrip().rstrip(',')+'}' for u in publisher]
kw = [u[0][u[0].find('{'):u[0].find(',')].lstrip('{')+re.findall('\d{4}',u[1])[0] for u in zip(authors, year)]

bibs = [',\n\t'.join(u) for u in zip(kw, authors, title, publisher, year)]
bibs = ['@book{'+u+'}\n\n' for u in bibs]
g.writelines(bibs)

g.close()

g = open('ToddOutliers.txt','w')
g.writelines([u+'\n\n' for u in outliers])
g.close()

#---------------------

f = open('Bibliography_SoniaDuffyGrant.txt','r')
x = f.readlines()
f.close()

x = [u.rstrip('\r\n') for u in x]
x = [u for u in x if re.search('^\t[0-9]',u) is not None]
x = [u.split('\t')[2] for u in x]

y = [u.split('.')[:-1] for u in x]

outliers = [x[i] for i in range(len(x)) if len(y[i]) != 4]
goodx = list(set(x).difference(set(outliers)))

books = [u for u in goodx if re.search('\d{4}\.$', u) is not None and re.search('-',u.split('.')[-2]) is None]
articles = list(set(goodx).difference(set(books)))
outliers.append(articles[59])
articles.remove(articles[59])
outliers.append(books[1])
books.remove(books[1])


g = file('Sonia.bib','w')
# Articles first
authors = [getauthor(u) for u in articles]
title = ['title = {'+u.split('.')[1].lstrip()+'}' for u in articles]
journal = ['journal = {' + u.split('.')[2].strip()+'}' for u in articles]
pages = ['pages = {'+u.split('.')[3].split(':')[-1].rstrip('.')+'}' for u in articles]
vols = ['volume = {'+getvol(u,3)+'}' for u in articles]
yr = [re.findall('\d{4}', u.split('.')[3]) for u in articles]
yr[[len(u) for u in yr].index(0)] = ['']
year = ['year = {'+ u[0]+'}' for u in yr]
kw = [u[0][u[0].find('{'):u[0].find(',')].lstrip('{')+u[1][0] for u in zip(authors, yr)]

bibs = [',\n\t'.join(u) for u in zip(kw, authors, title, journal, pages, vols,year)]
bibs = ['@article{'+u+'}\n\n' for u in bibs]
g.writelines(bibs)

#Books next
authors = [getauthor(u) for u in books]
title = ['title = {'+u.split('.')[1].lstrip()+'}' for u in books]
year = ['year = {'+ re.findall('\d{4}',u.split('.')[-2])[0]+'}' for u in books]
publisher = [re.split(' \d{4}',u.split('.')[2])[0] for u in books]
publisher = ['publisher = {'+ u.lstrip().rstrip(',')+'}' for u in publisher]
kw = [u[0][u[0].find('{'):u[0].find(',')].lstrip('{')+re.findall('\d{4}',u[1])[0] for u in zip(authors, year)]

bibs = [',\n\t'.join(u) for u in zip(kw, authors, title, publisher, year)]
bibs = ['@book{'+u+'}\n\n' for u in bibs]
g.writelines(bibs)

g.close()

g = open('SoniaOutliers.txt','w')
g.writelines([u+'\n\n' for u in outliers])
g.close()

This is a Python script to convert Word-based bibliographies to bibtex, for loading into Papers. This script is very rudimentary.