I followed user13348's suggestion, and using his request function, I wrote a python3 script that takes a bib file and outputs a new bibfile with the DOIs it finds. I'm not using bibtool or taking any aux files.
The requirements are bibtexparser and unidecode.
#!/usr/bin/env python
import sys, re
from unidecode import unidecode
import bibtexparser
from bibtexparser.bwriter import BibTexWriter
import http.client as httplib
import urllib
# Search for the DOI given a title; e.g. "computation in Noisy Radio Networks"
# Credit to user13348, slight modifications
# http://tex.stackexchange.com/questions/6810/automatically-adding-doi-fields-to-a-hand-made-bibliography
def searchdoi(title, author):
params = urllib.parse.urlencode({"titlesearch":"titlesearch", "auth2" : author, "atitle2" : title, "multi_hit" : "on", "article_title_search" : "Search", "queryType" : "author-title"})
headers = {"User-Agent": "Mozilla/5.0" , "Accept": "text/html", "Content-Type" : "application/x-www-form-urlencoded", "Host" : "www.crossref.org"}
# conn = httplib.HTTPConnection("www.crossref.org:80") # Not working any more, HTTPS required
conn = httplib.HTTPSConnection("www.crossref.org")
conn.request("POST", "/guestquery/", params, headers)
response = conn.getresponse()
#print(response.status, response.reason)
data = response.read()
conn.close()
return re.search(r'doi\.org/([^"^<^>]+)', str(data))
def normalize(string):
"""Normalize strings to ascii, without latex."""
string = re.sub(r'[{}\\\'"^]',"", string)
string = re.sub(r"\$.*?\$","",string) # better remove all math expressions
return unidecode(string)
def get_authors(entry):
"""Get a list of authors' or editors' last names."""
def get_last_name(authors):
for author in authors :
author = author.strip(" ")
if "," in author:
yield author.split(",")[0]
elif " " in author:
yield author.split(" ")[-1]
else:
yield author
try:
authors = entry["author"]
except KeyError:
authors = entry["editor"]
authors = normalize(authors).split("and")
return list(get_last_name(authors))
print("Reading Bibliography...")
with open(sys.argv[1]) as bibtex_file:
bibliography = bibtexparser.load(bibtex_file)
print("Looking for Dois...")
before = 0
new = 0
total = len(bibliography.entries)
for i,entry in enumerate(bibliography.entries):
print("\r{i}/{total} entries processed, please wait...".format(i=i,total=total),flush=True,end="")
try:
if "doi" not in entry or entry["doi"].isspace():
title = entry["title"]
authors = get_authors(entry)
for author in authors:
doi_match = searchdoi(title,author)
if doi_match:
doi = doi_match.groups()[0]
entry["doi"] = doi
new += 1
else:
before += 1
except:
pass
print("")
template="We added {new} DOIs !\nBefore: {before}/{total} entries had DOI\nNow: {after}/{total} entries have DOI"
print(template.format(new=new,before=before,after=before+new,total=total))
outfile = sys.argv[1]+"_doi.bib"
print("Writing result to ",outfile)
writer = BibTexWriter()
writer.indent = ' ' # indent entries with 4 spaces instead of one
with open(outfile, 'w') as bibfile:
bibfile.write(writer.write(bibliography))
You can use it as such :
python3 searchdoi.py test.bib
And it will look like this :
Reading Bibliography...
Looking for Dois...
161/162 entries processed, please wait...
We added 49 DOIs !
Before: 42/162 entries had DOI
Now: 91/162 entries have DOI
Writing result to test.bib_doi.bib
You can now just check test.bib_doi.bib.
Here you are: patching journal+issuetitle:
\begin{filecontents}{my-bib.bib}
@article{Lubbers.2002,
author = {Lubbers, Marcel and Gijsberts, M{\'e}rove and Scheepers, Peer},
year = {2002},
title = {{E}xtreme {R}ight-{W}ing {V}oting in {W}estern {E}urope},
pages = {345--378},
volume = {41},
number = {3},
issn = {03044130},
journal = {European Journal of Political Research}
}
\end{filecontents}
\documentclass[11pt]{scrartcl}
\usepackage[margin= 1in]{geometry}
\usepackage[backend=bibtex, style=verbose-trad3, isbn=false, doi=false, firstinits=true, citepages=suppress]{biblatex}
\usepackage[style=british]{csquotes}
% Commas as separators
\renewcommand*{\newunitpunct}{\addcomma\space}
\usepackage{xpatch}
% Comma before issue + date
\xpatchbibmacro{journal+issuetitle}{%
\setunit{\addspace}%
\usebibmacro{issue+date}}%
{\setunit{\addcomma\addspace}%
\usebibmacro{issue+date}}%
{}{}
% No dot before number of articles
\xpatchbibmacro{volume+number+eid}{%
\setunit*{\adddot}%
}{%
}{}{}
% Number of articles in parentheses
\DeclareFieldFormat[article]{number}{\mkbibparens{#1}}
% Comma before and after journal volume
\renewbibmacro*{volume+number+eid}{%
\setunit*{\addcomma\space}% NEW
\printfield{volume}%
% \setunit*{\adddot}% DELETED
\setunit*{\addcomma\space}% NEW
\printfield{number}%
\setunit{\addcomma\space}%
\printfield{eid}}
% Prefixes for journal volume and number
\DeclareFieldFormat[article]{volume}{\bibstring{volume}~#1}% volume of a journal
\DeclareFieldFormat[article]{number}{\bibstring{number}~#1}% number of a journal
% Comma before date; date not in parentheses
\renewbibmacro*{issue+date}{%
\setunit*{\addcomma\space}% NEW
% \printtext[parens]{% DELETED
\iffieldundef{issue}
{\usebibmacro{date}}
{\printfield{issue}%
\setunit*{\addspace}%
% \usebibmacro{date}}}% DELETED
\usebibmacro{date}}% NEW
\newunit}
\bibliography{my-bib}
\begin{document}
\vspace*{6in}
Test\autocite{Lubbers.2002}.
\printbibliography
\end{document}
Best Answer
In the linked question is used another bibliography driver.
EDIT 2: Comment by maetra:
Solution:
In the version 1.6 of biblatex is a small bug in the file
authoryear.bbx. The style redefine the macroissue+date. The redefinition of the macro depends on the optionmergedate. If the option is set totrueorcompactthe redefinition is as follows:Before the last
\newunitwork there is a none escaped space which results in the extra space. So you have to do this:This fixes the problem.
EDIT 1: Changed Code.