import copy

import sys

import codecs

 

 

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

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

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

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

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

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

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

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

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

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

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

          }

 

areas_keys = areas.keys()

 

 

def parseBibtex( source ):

 

    # Bibtex parser

    parser = BibtexParser()

 

    # fix encoding

    #//    source = parser.checkEncoding(source)

 

    # fix latex special characters, among other things

    source = parser.preprocess(source) #.encode('utf-8'))

 

    # get list of dictionaries

    return parser.getEntries(source)

 

 

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

   

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

        gb = nref['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):

 

 

    # this should work, but I want the printout and random wait

    #  nbibs = [ grabCitations(b) for b in 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]

 

    ttable = [('&', r'\&'),

              ('~', r'\~'),

              ('—',r'---'),

              ('–', r'--'),

              ]

 

    bib_key = ref['pid']

    ref_type = ref['reference_type'].replace('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]

 

            for a,b in ttable:

                nv = nv.replace(a,b)

 

            bibtex = bibtex + u'  '

            bibtex = bibtex + k

            bibtex = bibtex + u' = {'  

            #            bibtex = bibtex + unicode(nv.encode('utf8'))

            #            bibtex = bibtex + unicode(nv, encoding='utf8')

            bibtex = bibtex +  unicode(nv, encoding='latin_1')

            bibtex = bibtex + u'},\n'

           

    # remove trailing command

    bibtex = bibtex[0:-2] + u"}\n"

 

 

    return bibtex

 

 

if __name__ == "__main__":

    if len(sys.argv) != 2:

        print '\n' +  sys.argv[0] + ': requires name of the bibtex file!\n'

        sys.exit()

    fname = sys.argv[1]

    bibfile = codecs.open(fname,encoding='latin_1').read()

    bibs = parseBibtex( bibfile )

 

    nbibs = grabAllCitations(bibs)

   

    print 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'],

                                []).encode('latin_1')