import copy

import sys

import codecs

 

 

import bibtexparser

from   bibtexparser.bparser import BibTexParser

import bibtexparser.customization

 

 

import re

import random

from time import sleep

 

 

from bibliograph.parsing.parsers.bibtex import BibtexParser

from bs4 import BeautifulSoup

 

from urllib import FancyURLopener

class MyOpener(FancyURLopener):

    version = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/33.0.1750.152 Safari/537.36'

openurl = MyOpener().open

 

areas = { u'cv':(u'Computer Vision', u'Images/Vision-100.png'),

          u'ai':(u'Artificial Intelligence', u'Images/AI-100.png'),

          u'ml':(u'Machine Learning', u'Images/ML-80.png'),

          u'forensics':(u'Forensics', u'Images/Forensics-80.png'),

          u'access':(u'Accessibility', u'Images/Access-80.png'),

          u'cg':(u'Computer Graphics', u'Images/Graphics-80.png'),

          u'asl':(u'Sign Language', u'Images/ASL-100.png'),

          u'wavelets':(u'Wavelets', u'Images/Wavelet-100.png'),

          u'sport': (u'Sport', u'Images/Sport-80.png'),

          u'uncert': (u'Uncertanties', u'Images/Uncert-100.png'),

          u'virtcrd': (u'Virtual Crowds', u'Images/Crowd-80.png'),

          u'med': (u'Biomedical', u'Images/Med-64.png'),

          u'biblio': (u'Bibliometrics', u'Images/Book-80.png')

          }

 

areas_keys = areas.keys()

 

 

def parseBibtex( bibtex_fname ):

 

 

    with open(bibtex_fname) as bibtex_file:

        bibtex_database = bibtexparser.load(bibtex_file)

 

    # get list of dictionaries

    return bibtex_database.entries

 

 

def grabCitations(ref):

 

    #  test first if there is a gscholar page

 

    nref = copy.deepcopy(ref)

 

 

    nref[u'totalcites'] = '0'

    nref[u'citeshist'] = ''

 

    if 'gscholar' in nref:

 

        surl = ("https://scholar.google.com.br/"

                "citations?view_op=view_citation&hl=en&"

                "citation_for_view=%s") % nref['gscholar']

 

        nref[u'gscholarpage'] = openurl(surl).read()

   

        nref[u'soup'] =  BeautifulSoup(nref['gscholarpage'], 'html.parser')

        gb = nref[u'soup'].find('div', id = 'gsc_graph_bars')

 

        cithist = ""

        nref[u'totalcites'] = '0'

   

        if not gb is None:

            for link in gb.find_all('a'):

                year = int(link.get('href')[-4:])

                cites = int(link.span.contents[0])

                cithist = cithist + "%d,%d;" % (year,cites)

   

            cithist = cithist[:-1]

            m = re.search('Cited by ([0-9]*)', nref['gscholarpage'])

            nref[u'totalcites'] = m.group(1)

 

        nref[u'citeshist'] = cithist

 

   

    return nref

 

 

 

def grabAllCitations(bibs):

 

    nbibs = []

    i = 1

    for b in bibs:

        if i > 1:

            sleep(random.uniform(1.,6.))

 

 

 

        b2 = grabCitations(b)

 

        nbibs.append( b2 )

        i = i + 1

 

 

    return nbibs

 

 

def generateBiBTeX(refs,

            valid_fields=[u'title', u'editor', u'author', u'journal',

                          u'booktitle', u'publisher', u'school', u'issn',

                          u'volume', u'number', u'pages', u'year', u'doi',

                          u'totalcites' ,u'citeshist', u'gscholar'],

              omit_fields=[]):

 

    s = ""

       

   

    for bib in refs:

        s2 =    toBiBTeX(bib,valid_fields,omit_fields)            

        s  =    s + s2 + "\n"

 

    return s

 

 

def toBiBTeX (ref,

            valid_fields=[u'title', u'editor', u'author', u'journal', u'booktitle',

                          u'publisher', u'school', u'issn', u'volume', u'number',  

                          u'pages', u'year', u'doi', u'pdf'],

              omit_fields=[]):

 

 

 

    omit   = [each.lower() for each in omit_fields]

    fields = [each.lower() for each in valid_fields]

 

 

    bib_key = ref[u'ID']

    ref_type = ref[u'ENTRYTYPE'].replace(u'Reference','')

    bibtex = u'\n@' + ref_type + u'{' + bib_key + u',\n' # '%s{%s,\n" %  (ref_type, bib_key)

 

    ref_keys = ref.keys()

 

    for k in fields:

        if k in ref_keys and k not in omit:

            if type(ref[k]) == list:

                nv = ref[k][0]

            else:

                nv = ref[k]

 

 

            bibtex = bibtex + u'  %s = {%s},\n' % (k,nv)

           

    # remove trailing command

    bibtex = bibtex[0:-2] + u"}\n"

 

 

    return bibtex

 

 

if __name__ == "__main__":

    if len(sys.argv) != 3:

        print '\n typical usage:'

        print '  "%s" input output\n' % sys.argv[0]

        print '     input  - input bibtex file'

        print '     output - output bibtex file'

        sys.exit()

    fname = sys.argv[1]

    fnout  = sys.argv[2]

    bibs = parseBibtex( fname )

 

    nbibs = grabAllCitations(bibs)

 

    so  = generateBiBTeX(nbibs,[u'title', u'editor', u'author', u'journal',

                                u'booktitle', u'publisher', u'school', u'issn',

                                u'volume', u'number', u'pages', u'year',

                                u'doi', u'totalcites' ,u'citeshist',

                                u'gscholar', u'pdf', u'abstract'],

                                [])

   

    with open(fnout,'w') as fo:

        fo.write(so)