bib2xml.py

import bibtexparser
import argparse


class Bib2Xml:

    def __init__(self, _bibFile, _xmlFile):
        self.bibFile = _bibFile
        self.xmlFile = _xmlFile

    def get_bib_entries(self):
        tmpFile = open(self.bibFile, "r")
        return bibtexparser.load(tmpFile).entries

    def parse_bib_entries(self):
        tmpEntries = self.get_bib_entries()
        cleanedEntries = []
        for e in tmpEntries:
            tmpEntry = {}
            for key in e.keys():

                if key == "ENTRYTYPE" and e[key] == "inproceedings":
                    tmpEntry["source_type"] = "ConferenceProceedings"
                elif key == "ENTRYTYPE" and e[key] == "phdthesis":
                    tmpEntry["source_type"] = "Misc"
                elif key == "ENTRYTYPE" and e[key] == "article":
                    tmpEntry["source_type"] = "JournalArticle"
                elif key == "ENTRYTYPE" and e[key] == "book":
                    tmpEntry["source_type"] = "Book"
                elif key == "ENTRYTYPE" and e[key] == "misc":
                    tmpEntry["source_type"] = "InternetSite"

                if key == "title":
                    tmpEntry["title"] = e[key]

                if key == "author":
                    authors = [author for author in e[key].split(" and ")]
                    tmpEntry["authors"] = authors

                if key == "title":
                    tmpEntry["title"] = e[key]

                if key == "year":
                    tmpEntry["year"] = e[key]

                if key == "organization":
                    tmpEntry["publisher"] = e[key]

                if key == "pages":
                    tmpEntry["pages"] = e[key]

                if key == "journal":
                    tmpEntry["journal_name"] = e[key]
                elif key == "booktitle":
                    tmpEntry["conference_name"] = e[key]

                if key == "ID":
                    tmpEntry["tag"] = e[key]

                if key == "year":
                    tmpEntry["year"] = e[key]

                if key == "volume":
                    tmpEntry["volume"] = e[key]

                if key == "number":
                    tmpEntry["issue"] = e[key]

                if key == "address":
                    tmpEntry["city"] = e[key]

                if key == "url":
                    tmpEntry["url"] = e[key]

                if key == "ENTRYTYPE" and e[key] == "misc":
                    tmpEntry["source_type"] = "InternetSite"
                    tmpEntry["internet_site_title"] = e["organization"]
                    dates = e["urldate"].split("-")
                    tmpEntry["year_access"] = dates[0]
                    tmpEntry["month_access"] = dates[1]
                    tmpEntry["day_access"] = dates[2]

            cleanedEntries.append(tmpEntry)
        return cleanedEntries

    def export_xml(self, _entries):
        tmpFile = open(self.xmlFile, "w")
        tmpFile.write('<?xml version="1.0"?>')
        tmpFile.write(
            '<b:Sources SelectedStyle="" xmlns:b="http://schemas.openxmlformats.org/officeDocument/2006/bibliography" xmlns="http://schemas.openxmlformats.org/officeDocument/2006/bibliography">')
        for e in _entries:
            tmpFile.write('<b:Source>')
            for key in e.keys():

                if key == "tag":
                    tmpFile.write(f'<b:Tag>{e[key]}</b:Tag>')

                if key == "source_type":
                    tmpFile.write(f'<b:SourceType>{e[key]}</b:SourceType>')

                if key == "journal_name":
                    tmpFile.write(f'<b:JournalName>{e[key]}</b:JournalName>')
                elif key == "conference_name":
                    tmpFile.write(f'<b:ConferenceName>{e[key]}</b:ConferenceName>')

                if key == "authors":
                    tmpFile.write(f'<b:Author>')
                    tmpFile.write(f'<b:Author>')
                    tmpFile.write(f'<b:NameList>')
                    for author in e[key]:
                        tmpNames = author.split(", ")
                        tmpFile.write('<b:Person>')
                        tmpFile.write(f'<b:First>{tmpNames[1]}</b:First>')
                        tmpFile.write(f'<b:Last>{tmpNames[0]}</b:Last>')
                        tmpFile.write('</b:Person>')
                    tmpFile.write('</b:NameList>')
                    tmpFile.write('</b:Author>')
                    tmpFile.write('</b:Author>')

                if key == "title":
                    tmpFile.write(f'<b:Title>{e[key]}</b:Title>')

                if key == "year":
                    tmpFile.write(f'<b:Year>{e[key]}</b:Year>')

                if key == "volume":
                    tmpFile.write(f'<b:Volume>{e[key]}</b:Volume>')

                if key == "issue":
                    tmpFile.write(f'<b:Issue>{e[key]}</b:Issue>')

                if key == "city":
                    tmpFile.write(f'<b:City>{e[key]}</b:City>')

                if key == "url":
                    tmpFile.write(f'<b:URL>{e[key]}</b:URL>')

                if key == "year_access":
                    tmpFile.write(f'<b:YearAccessed>{e[key]}</b:YearAccessed>')

                if key == "month_access":
                    tmpFile.write(f'<b:MonthAccessed>{e[key]}</b:MonthAccessed>')

                if key == "day_access":
                    tmpFile.write(f'<b:DayAccessed>{e[key]}</b:DayAccessed>')

                if key == "internet_site_title":
                    tmpFile.write(f'<b:InternetSiteTitle>{e[key]}</b:InternetSiteTitle>')

            tmpFile.write('</b:Source>')
        tmpFile.write('</b:Sources>')


if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument("-i", "--input", "--bib", help="Provide the BibTex file for parsing.", type=str, required=True)
    parser.add_argument("-o", "--output", "--xml", help="Provide the name of an XML file for exporting.", type=str,
                        required=True)
    args = parser.parse_args()

    bib2xml = Bib2Xml(args.input, args.output)
    cleanedEntries = bib2xml.parse_bib_entries()
    bib2xml.export_xml(cleanedEntries)