def bibtex_reader(self, bibtextdata):
"""
Parse the bibtex data
Arguments:
bibtextdata {str} -- bibtexdata
Returns:
list -- list of all entries of the bibtex
"""
parser = BibTexParser()
parser.ignore_nonstandard_types = False
parser.homogenise_fields = False
parser.common_strings = False
bib_database = bibtexparser.loads(bibtextdata, parser)
return bib_database.entries[0]
def main():
args = _args()
bibfile = args.input_bib
with open(bibfile) as bibtex_file:
parser = BibTexParser()
parser.ignore_nonstandard_types = False
parser.homogenize_fields = True
parser.common_strings = True
parser.customization = keep_uppercase
bib_database = bibtexparser.load(bibtex_file, parser=parser)
if args.clean:
for entry in bib_database.entries:
for k in ('file', 'annote', 'abstract', 'url', 'file', 'link'):
entry.pop(k, None)
for entry in bib_database.entries:
entry['title'] = '{{{}}}'.format(entry['title'])
bibwriter = BibTexWriter()
with open(args.output_bib, 'w') as outbib:
bibtexparser.dump(bib_database, outbib, bibwriter)
""" Draft zero of code to read Dave's Refs.bib file and allow search
and pdf viewing """
import bibtexparser
import subprocess
import sys
from bibtexparser.bparser import BibTexParser
from bibtexparser.bwriter import BibTexWriter
from bibtexparser.bibdatabase import BibDatabase
# Failed
#import bibtexparser.bibtexexpression.BibtexExpression as be
#be.set_string_name_parse_action(None)
parser = BibTexParser(interpolate_strings=False)
parser.ignore_nonstandard_types = False # ?
parser.common_strings = True
#parser.interpolate_strings = False # None
homedir = '/home/davids/'
texdir = homedir + 'Documents/D_Articles/'
testr = 'Documents/TeX/testr.bib'
testr = 'Documents/TeX/fixed.testr.bib' # fixtext2
testr = homedir + 'Documents/TeX/Refs.bib'
test_export = False # True
def query_user():
search_terms = input('Give search terms:') # eg QQDEP, 2014
search_terms = search_terms.split()
from habanero import Crossref
import pandas as pd
import bibtexparser
from bibtexparser.bparser import BibTexParser
import datetime
work = Crossref()
parser = BibTexParser()
parser.ignore_nonstandard_types = False
parser.homogenise_fields = False
parser.common_strings = False
# This list contains words that are not decisive to identify the publications,
# such as articles and adverbs. They must be removed because the Crossref
# API retrieves all the publications whose titles that have at least a word
# in common with the publication under analysis
common_words = ['a','the','on','an','for','of','at','with', 'without', 'toward',
'towards', 'not', 'but', 'in', 'is', 'are', 'that', 'and', 'or',
'learning','into','to','its','which','do','does','using','via',
'from']
def doisearcher(origtitle, inauthor):
"""
This function calls the Crossref API and returns the most relevant publications
whose title has at least one word in common with the input title (origtitle).
This list is limited to the first 1000 entries.
It is possible to run the search on the list of authors. In this version, this
option is commented out.
:param origtitle: title of the input publication
:param inauthor: list of authors of the input publication
:return: the list of the matched publications (w2) and the title of the
@STRING{ apr = "apr"}
@STRING{ may = "may"}
@STRING{ jun = "jun"}
@STRING{ jul = "jul"}
@STRING{ aug = "aug"}
@STRING{ sep = "sep"}
@STRING{ oct = "oct"}
@STRING{ nov = "nov"}
@STRING{ dec = "dec"}
"""
print 'Parsing files in '+folder+'/'
for file in os.listdir(folder):
if file.endswith(".bib"):
print(os.path.join(folder, file))
with open(os.path.join(folder, file)) as bibtex_file:
content = Months + bibtex_file.read()
parser = BibTexParser()
parser.common_strings = True
bib_database = bibtexparser.loads(content, parser)
for entry in bib_database.entries:
#print(entry['ID'])
entry['keywords'] = entry.get('keywords', '')
if(entry['keywords'] != ''):
entry['keywords'] = 'cleBib/' + entry['ID'] + ', article/' + os.path.splitext(file)[0] + ', ' + entry['keywords']
else:
entry['keywords'] = 'cleBib/' + entry['ID'] + ', article/' + os.path.splitext(file)[0]
with open(os.path.join(folder+'-clean', file), 'w') as bibtex_export:
bibtex_export_str = bibtexparser.dumps(bib_database, writer)
bibtex_export.write(bibtex_export_str.encode('utf8'))