On 03.03.2017 11:43, Geoff Winkless
wrote:
As a side-note, it seems there are overlapping short months: Using this webpage http://web.library.yale.edu/cataloging/months.htm this JS(Firefox) JSON.stringify([for (x of document.querySelectorAll('table.grid tr td')) x.textContent]) this Python import pprint from collections import defaultdict def chunks(l, n): """Yield successive n-sized chunks from l.""" for i in range(0, len(l), n): yield l[i:i + n] a=<json output from Firefox> a=list(chunks(a, 13)) dd=defaultdict(list) for l in a: for i, m in enumerate(l): if i == 0: continue dd[m].append((i, l[0])) pprint.pprint(dict(dd)) {'\nmart\n': [(3, 'Serbian')], 'Ag.': [(8, 'Indonesian')], 'Agustos': [(8, 'Turkish')], 'Apr': [(4, 'Latin')], 'Apr.': [(4, 'English'), (4, 'German'), (4, 'Greek, Modern'), (4, 'Indonesian'), (4, 'Malaysian'), (4, 'Romanian')], 'Aralik': [(12, 'Turkish')], 'Aug.': [(8, 'English'), (8, 'German'), (8, 'Greek, Modern'), (8, 'Latin'), (8, 'Romanian')], 'Awst': [(8, 'Welsh')], 'Chwef.': [(2, 'Welsh')], 'Dec.': [(12, 'English'), (12, 'Latin'), (12, 'Romanian')], 'Dek.': [(12, 'Greek, Modern')], 'Des.': [(12, 'Indonesian')], 'Dez.': [(12, 'German')], 'Dis.': [(12, 'Malaysian')], 'Ebr.': [(4, 'Welsh')], 'Ekim': [(10, 'Turkish')], 'Eylul': [(9, 'Turkish')], 'Feb.': [(2, 'English'), (2, 'German'), (2, 'Malaysian'), (2, 'Romanian')], 'Febr.': [(2, 'Latin')], 'Gorff.': [(7, 'Welsh')], 'Haziran': [(6, 'Turkish')], 'Hyd.': [(10, 'Welsh')], 'Ian.': [(1, 'Greek, Modern'), (1, 'Latin'), (1, 'Romanian')], 'Ion.': [(1, 'Welsh')], 'Ioul.': [(7, 'Greek, Modern')], 'Ioun.': [(6, 'Greek, Modern')], 'Iul.': [(7, 'Latin')], 'Iulie': [(7, 'Romanian')], 'Iun.': [(6, 'Latin')], 'Iunie': [(6, 'Romanian')], 'Jan.': [(1, 'English'), (1, 'Malaysian')], 'Jan./Djan.\xc2\xa0': [(1, 'Indonesian')], 'Jan./J\xc3\xa4n.': [(1, 'German')], 'Julai': [(7, 'Malaysian')], 'Juli': [(7, 'German')], 'Juli/Djuli': [(7, 'Indonesian')], 'July': [(7, 'English')], 'Jun': [(6, 'Malaysian')], 'June': [(6, 'English')], 'Juni': [(6, 'German')], 'Juni/Djuni': [(6, 'Indonesian')], 'Kasim': [(11, 'Turkish')], 'Mac': [(3, 'Malaysian')], 'Mai': [(5, 'German'), (5, 'Romanian'), (5, 'Welsh')], 'Mai.': [(5, 'Latin')], 'Maios': [(5, 'Greek, Modern')], 'Mar.': [(3, 'English'), (3, 'Romanian')], 'Mart.': [(3, 'Greek, Modern'), (3, 'Latin')], 'Maw.': [(3, 'Welsh')], 'May': [(5, 'English')], 'Mayis': [(5, 'Turkish')], 'Medi': [(9, 'Welsh')], 'Meh.': [(6, 'Welsh')], 'Mei': [(5, 'Malaysian')], 'Mei/Mai': [(5, 'Indonesian')], 'Mrt.': [(3, 'Indonesian')], 'M\xc3\xa4rz': [(3, 'German')], 'Nisan': [(4, 'Turkish')], 'Noem.': [(11, 'Greek, Modern')], 'Noiem.': [(11, 'Romanian')], 'Nop.': [(11, 'Indonesian')], 'Nov.': [(11, 'English'), (11, 'German'), (11, 'Latin'), (11, 'Malaysian')], 'Ocak': [(1, 'Turkish')], 'Oct.': [(10, 'English'), (10, 'Latin'), (10, 'Romanian')], 'Og': [(8, 'Malaysian')], 'Okt.': [(10, 'German'), (10, 'Greek, Modern'), (10, 'Indonesian'), (10, 'Malaysian')], 'Peb.': [(2, 'Indonesian')], 'Phevr.': [(2, 'Greek, Modern')], 'Rhag.': [(12, 'Welsh')], 'Saus.': [(1, 'Lithuanian')], 'Sept.': [(9, 'English'), (9, 'German'), (9, 'Greek, Modern'), (9, 'Indonesian'), (9, 'Latin'), (9, 'Malaysian'), (9, 'Romanian')], 'Subat': [(2, 'Turkish')], 'Tach.': [(11, 'Welsh')], 'Temmuz': [(7, 'Turkish')], 'abr.': [(4, 'Spanish')], 'abril': [(4, 'Portuguese')], 'ag.': [(8, 'Italian')], 'agosto': [(8, 'Portuguese'), (8, 'Spanish')], 'ao\xc3\xbbt': [(8, 'French')], 'apr.': [(4, 'Dutch'), (4, 'Estonian'), (4, 'Italian'), (4, 'Latvian'), (4, 'Russian')], 'apr./mali traven': [(4, 'Slovenian')], 'april': [(4, 'Bosnian'), (4, 'Bulgarian'), (4, 'Danish'), (4, 'Norwegian'), (4, 'Serbian'), (4, 'Swedish')], 'aug.': [(8, 'Bosnian'), (8, 'Danish'), (8, 'Dutch'), (8, 'Estonian'), (8, 'Hungarian'), (8, 'Latvian'), (8, 'Norwegian'), (8, 'Swedish')], 'avg.': [(8, 'Bulgarian'), (8, 'Russian'), (8, 'Serbian')], 'avg./veliki\xc2\xa0srpan': [(8, 'Slovenian')], 'avril': [(4, 'French')], 'bal.': [(4, 'Lithuanian')], 'ber.': [(3, 'Ukranian')], 'birz': [(6, 'Lithuanian')], 'brez.': [(3, 'Czech')], 'brez./mar.': [(3, 'Slovak')], 'cerv.': [(6, 'Czech')], 'cerv./j\xc3\xban': [(6, 'Slovak')], 'cerven.': [(7, 'Czech')], 'cerven./j\xc3\xbal': [(7, 'Slovak')], 'cher.': [(6, 'Ukranian')], 'cherv.': [(6, 'Belorusian')], 'czerw.': [(6, 'Polish')], 'dec.': [(12, 'Danish'), (12, 'Dutch'), (12, 'Hungarian'), (12, 'Latvian'), (12, 'Serbian'), (12, 'Swedish')], 'dec./gr.': [(12, 'Slovenian')], 'dec.\xc2\xa0': [(12, 'Bosnian')], 'dek.': [(12, 'Bulgarian'), (12, 'Russian')], 'des.': [(12, 'Norwegian')], 'dets.': [(12, 'Estonian')], 'dez.': [(12, 'Portuguese')], 'dic.': [(12, 'Italian'), (12, 'Spanish')], 'dub.': [(4, 'Czech')], 'dub./apr.': [(4, 'Slovak')], 'd\xc3\xa9c.': [(12, 'French')], 'enero': [(1, 'Spanish')], 'feb.': [(2, 'Bosnian'), (2, 'Dutch'), (2, 'Hungarian'), (2, 'Latvian'), (2, 'Spanish')], 'feb./svec.': [(2, 'Slovenian')], 'febbr.': [(2, 'Italian')], 'febr.': [(2, 'Danish'), (2, 'Norwegian'), (2, 'Serbian'), (2, 'Swedish')], 'fev.': [(2, 'Portuguese')], 'fevr.': [(2, 'Bulgarian'), (2, 'Russian')], 'f\xc3\xa9vr.': [(2, 'French')], 'geg.': [(5, 'Lithuanian')], 'genn.': [(1, 'Italian')], 'giugno': [(6, 'Italian')], 'gr.': [(12, 'Lithuanian')], 'grudz.': [(12, 'Polish')], 'hrud.': [(12, 'Ukranian')], 'ian.': [(1, 'Bulgarian')], 'ianv.': [(1, 'Russian')], "iiul'": [(7, 'Russian')], "iiun'": [(6, 'Russian')], 'iuli': [(7, 'Bulgarian')], 'iuni': [(6, 'Bulgarian')], 'jaan.': [(1, 'Estonian')], 'jan.': [(1, 'Bosnian'), (1, 'Danish'), (1, 'Dutch'), (1, 'Hungarian'), (1, 'Latvian'), (1, 'Norwegian'), (1, 'Portuguese'), (1, 'Serbian'), (1, 'Swedish')], 'jan./pros.': [(1, 'Slovenian')], 'janv.': [(1, 'French')], 'juil.': [(7, 'French')], 'juin': [(6, 'French')], 'jul.': [(7, 'Hungarian'), (7, 'Spanish')], 'jul./mali srpan': [(7, 'Slovenian')], 'julho': [(7, 'Portuguese')], 'juli': [(7, 'Bosnian'), (7, 'Danish'), (7, 'Dutch'), (7, 'Norwegian'), (7, 'Serbian'), (7, 'Swedish')], 'julijs': [(7, 'Latvian')], 'jun.': [(6, 'Hungarian'), (6, 'Spanish')], 'jun./roz.': [(6, 'Slovenian')], 'junho': [(6, 'Portuguese')], 'juni': [(6, 'Bosnian'), (6, 'Danish'), (6, 'Dutch'), (6, 'Norwegian'), (6, 'Serbian'), (6, 'Swedish')], 'junijs': [(6, 'Latvian')], 'juuli': [(7, 'Estonian')], 'juuni': [(6, 'Estonian')], 'kastr.': [(10, 'Belorusian')], 'kol.': [(8, 'Croatian')], 'kovas': [(3, 'Lithuanian')], 'kras.': [(4, 'Belorusian')], 'kvet.': [(5, 'Czech')], 'kvet/m\xc3\xa1j': [(5, 'Slovak')], 'kvit.': [(4, 'Ukranian')], 'kwiec.': [(4, 'Polish')], "l'ad./jan.": [(1, 'Slovak')], 'lapkr.': [(11, 'Lithuanian')], 'led.': [(1, 'Czech')], 'liepa': [(7, 'Lithuanian')], 'lip.': [(7, 'Belorusian'), (6, 'Croatian'), (7, 'Polish')], 'list.': [(11, 'Belorusian'), (10, 'Croatian'), (11, 'Czech')], 'list./nov.': [(11, 'Slovak')], 'listop.': [(11, 'Polish')], 'liut.': [(2, 'Belorusian'), (2, 'Ukranian')], 'luglio': [(7, 'Italian')], 'luty': [(2, 'Polish')], 'lyp.': [(7, 'Ukranian')], 'lyst.': [(11, 'Ukranian')], 'maart': [(3, 'Dutch')], 'magg.': [(5, 'Italian')], 'mai': [(5, 'Bulgarian'), (5, 'Estonian'), (5, 'French'), (5, 'Norwegian'), (5, 'Russian')], 'maijs': [(5, 'Latvian')], 'maio': [(5, 'Portuguese')], 'maj': [(5, 'Bosnian'), (5, 'Danish'), (5, 'Polish'), (5, 'Serbian'), (5, 'Swedish')], 'maj./veliki traven': [(5, 'Slovenian')], 'mar.': [(3, 'Italian'), (3, 'Polish')], 'mar./sus.': [(3, 'Slovenian')], 'mars': [(3, 'French'), (3, 'Norwegian'), (3, 'Swedish')], 'mart': [(3, 'Bosnian'), (3, 'Bulgarian'), (3, 'Russian'), (3, 'Turkish')], 'marts': [(3, 'Danish'), (3, 'Latvian')], 'marzo': [(3, 'Spanish')], 'mar\xc3\xa7o': [(3, 'Portuguese')], 'mayo': [(5, 'Spanish')], 'mei': [(5, 'Dutch')], 'm\xc3\xa1j.': [(5, 'Hungarian')], 'm\xc3\xa1rc.': [(3, 'Hungarian')], 'm\xc3\xa4rts': [(3, 'Estonian')], 'noem.': [(11, 'Bulgarian')], "noiabr'": [(11, 'Russian')], 'nov.': [(11, 'Bosnian'), (11, 'Danish'), (11, 'Dutch'), (11, 'Estonian'), (11, 'French'), (11, 'Hungarian'), (11, 'Italian'), (11, 'Latvian'), (11, 'Norwegian'), (11, 'Portuguese'), (11, 'Serbian'), (11, 'Spanish'), (11, 'Swedish')], 'nov./list.': [(11, 'Slovenian')], 'oct.': [(10, 'French'), (10, 'Spanish')], 'oct./okt.': [(10, 'Dutch')], 'okt.': [(10, 'Bosnian'), (10, 'Bulgarian'), (10, 'Danish'), (10, 'Estonian'), (10, 'Hungarian'), (10, 'Latvian'), (10, 'Norwegian'), (10, 'Russian'), (10, 'Serbian'), (10, 'Swedish')], 'okt./vino.': [(10, 'Slovenian')], 'ott.': [(10, 'Italian')], 'out.': [(10, 'Portuguese')], 'ozuj.': [(3, 'Croatian')], 'pazdz.': [(10, 'Polish')], 'pros.': [(12, 'Croatian'), (12, 'Czech')], 'pros./dec.': [(12, 'Slovak')], 'rugp.': [(8, 'Lithuanian')], 'rugs.': [(9, 'Lithuanian')], 'ruj.': [(9, 'Croatian')], 'ruj./okt.': [(10, 'Slovak')], 'r\xc3\xadj.': [(10, 'Czech')], 'sak./mar.': [(3, 'Belorusian')], 'sent.': [(9, 'Russian')], 'sept.': [(9, 'Bosnian'), (9, 'Bulgarian'), (9, 'Danish'), (9, 'Dutch'), (9, 'Estonian'), (9, 'French'), (9, 'Latvian'), (9, 'Norwegian'), (9, 'Serbian'), (9, 'Swedish')], 'sept./kim.': [(9, 'Slovenian')], 'sept./set.': [(9, 'Spanish')], 'serp.': [(8, 'Ukranian')], 'set.': [(9, 'Portuguese')], 'sett.': [(9, 'Italian')], 'sich.': [(1, 'Ukranian')], 'sierp.': [(8, 'Polish')], 'sijec.': [(1, 'Croatian')], 'snezh.': [(12, 'Belorusian')], 'spalis': [(10, 'Lithuanian')], 'srp.': [(7, 'Croatian'), (8, 'Czech')], 'srp./aug.': [(8, 'Slovak')], 'stud.': [(11, 'Croatian')], 'studz.': [(1, 'Belorusian')], 'stycz.': [(1, 'Polish')], 'svib.': [(5, 'Croatian')], 'szept.': [(9, 'Hungarian')], 'trav.': [(5, 'Belorusian'), (4, 'Croatian'), (5, 'Ukranian')], 'vas.': [(2, 'Lithuanian')], 'veebr.': [(2, 'Estonian')], 'velj.': [(2, 'Croatian')], 'ver.': [(9, 'Ukranian')], 'veras.': [(9, 'Belorusian')], 'wrzes.': [(9, 'Polish')], "zhniven'": [(8, 'Belorusian')], 'zhovt.': [(10, 'Ukranian')], 'z\xc3\xa1r.': [(9, 'Czech')], 'z\xc3\xa1ri./sept.': [(9, 'Slovak')], '\xc3\xa1pr.': [(4, 'Hungarian')], '\xc3\xban.': [(2, 'Czech')], '\xc3\xban./feb.': [(2, 'Slovak')]} Sven |