Un article de Rodovid FR.
[modifier] Version pour Rodovid.FR
# -*- coding: utf-8 -*-
import pywikibot
a_per = "Personne"
a_fam = "Famille"
# Récupération du numéro de la personne
num = raw_input ("Matricule : ")
# Création de l'adresse
urltyp = "http://fr.rodovid.org/wk/Special:Tree/"
urlnum = urltyp + num + "?showfulltree=yes"
# Récupération de la page ("arbre complet"):
import urllib
text = urllib.urlopen(urlnum)
htmlSource = text.read()
text.close()
# Découpage de la page :
listSource = htmlSource.split("'")
# Sélection des adresses :
list = []
n = 0
for elem in listSource:
if ":" in elem:
ind_el = elem.index(":")
if elem[0:ind_el] == a_per or elem[0:ind_el] == a_fam:
list.append(elem)
# Suppression des doublons :
listem = []
listen = []
listem_fm = []
listem_rp = []
listem_fd = []
listem_sr = []
for el in list:
if el not in listem:
listem.append(el)
listem_fm.append([])
listem_rp.append([])
listem_fd.append("")
listem_sr.append("")
else:
listen.append(el)
print listem
print len(listem), "fiches"
# Récupération des fiches et création des listes :
header_0 = "0 HEAD\n"
header_s1 = "1 SOUR RODOVID\n"
header_c1 = "1 CHAR UTF-8\n"
header_g1 = "1 GEDC\n"
header_g2 = "2 VERS 5.5\n"
header_g3 = "2 FORM LINEAGE-LINKED\n"
header_g = header_g1 + header_g2 + header_g3
header = header_0 + header_s1 + header_c1 + header_g
textpf = ""
nx = 0
ny = 0
nz = 0
listep = []
for s0 in listem:
site = pywikibot.getSite()
page = pywikibot.Page(site, s0)
textpn = page.get(get_redirect = True)
textpn = textpn.encode('utf-8') + "\n"
listep.append(textpn)
ind_es = s0.index(":")
if s0[:ind_es] == a_per:
nx = nx + 1
nz = nz + 1
print nz, ":", nx, "personne(s)"
if s0[:ind_es] == a_fam:
ny = ny + 1
nz = nz + 1
print nz, ":", ny, "famille(s)"
#Listage des parents (avec leurs enfants) de chaque famille :
while "\n1 HUSB @" in textpn:
ind_ta = textpn.index("\n1 HUSB @") + 1
ind_ty = textpn[ind_ta + 8:].index("@")
ind_tz = textpn[ind_ta:].index("\n") + 1
s_tn = a_per + ":" + textpn[ind_ta + 8:ind_ta + 8 + ind_ty]
ind_tn = listem.index(s_tn)
n_fm = listem_fm[ind_tn]
n_fm.append(s0[ind_es + 1:])
listem_fm[ind_tn] = n_fm
textpn = textpn[:ind_ta] + textpn[ind_ta + ind_tz:]
textps = textpn
while "\n1 CHIL @" in textps:
ind_ra = textps.index("\n1 CHIL @") + 1
ind_ry = textps[ind_ra + 8:].index("@")
ind_rz = textps[ind_ra:].index("\n") + 1
n_rp = listem_rp[ind_tn]
n_rp.append(textps[ind_ra + 8:ind_ra + 8 + ind_ry])
listem_rp[ind_tn] = n_rp
textps = textps[:ind_ra] + textps[ind_ra + ind_rz:]
while "\n1 WIFE @" in textpn:
ind_ma = textpn.index("\n1 WIFE @") + 1
ind_my = textpn[ind_ma + 8:].index("@")
ind_mz = textpn[ind_ma:].index("\n") + 1
s_mn = a_per + ":" + textpn[ind_ma + 8:ind_ma + 8 + ind_my]
ind_mn = listem.index(s_mn)
m_fm = listem_fm[ind_mn]
m_fm.append(s0[ind_es + 1:])
listem_fm[ind_mn] = m_fm
textpn = textpn[:ind_ma] + textpn[ind_ma + ind_mz:]
textps = textpn
while "\n1 CHIL @" in textps:
ind_ra = textps.index("\n1 CHIL @") + 1
ind_ry = textps[ind_ra + 8:].index("@")
ind_rz = textps[ind_ra:].index("\n") + 1
m_rp = listem_rp[ind_mn]
m_rp.append(textps[ind_ra + 8:ind_ra + 8 + ind_ry])
listem_rp[ind_mn] = m_rp
textps = textps[:ind_ra] + textps[ind_ra + ind_rz:]
# Conversion vers le Gedcom classique et compilation des fiches :
listed = []
lister = []
listeb = []
for s1 in listem:
listec = []
listef = []
ind_lim = listem.index(s1)
textpr = listep[ind_lim]
ind_db = s1.index(":")
nm = s1[ind_db + 1:]
#Adjonction des fiches-familles :
if s1[0:ind_db] == a_per:
textpx = ""
if "1 SEX M\n" in textpr:
sp = "m"
if "1 SEX F\n" in textpr:
sp = "f"
if "1 SEX \n" in textpr:
sp = "n"
#Inscription des numéros des fiches-familles existantes :
for elef in listem_fm[ind_lim]:
textpb = "1 FAMS " + "@" + elef + "@\n"
listep[ind_lim] = listep[ind_lim] + textpb
listef.append(elef)
#Inscription des numéros des fiches-familles absentes :
while "\n1 CHIL" in textpr:
ind_tec = textpr.index("\n1 CHIL") + 9
textpr = textpr[ind_tec:]
ind_tex = textpr.index("@")
nm_enf = textpr[:ind_tex]
elee = a_per + ":" + nm_enf
if nm_enf not in listem_rp[ind_lim]:
listec.append(nm_enf)
if elee not in listem:
if elee not in lister:
site = pywikibot.getSite()
page = pywikibot.Page(site, elee)
textpc = page.get(get_redirect = True)
textpc = textpc.encode('utf-8') + "\n"
lister.append(elee)
listeb.append(textpc)
for n_enf in listec:
if (a_per + ":" + n_enf) in listem:
ind_nem = listem.index(a_per + ":" + n_enf)
textpc = listep[ind_nem]
else:
ind_ner = lister.index(a_per + ":" + n_enf)
textpc = listeb[ind_ner]
ind_tef = textpc.index("\n1 FAMC ") + 1
textpc = textpc[ind_tef:]
ind_tev = textpc.index("\n")
textpp = "1 FAMS " + textpc[7:ind_tev + 1]
n_foy = textpc[8:ind_tev - 1]
if n_foy not in listef:
listef.append(n_foy)
listep[ind_lim] = listep[ind_lim] + textpp
#Incorporation de fiches-couples absentes de Rodovid :
if n_foy not in listed:
textpx = textpx + "0 @" + n_foy + "@ FAM\n"
listed.append(n_foy)
if "+" not in n_foy:
if sp == "m" or sp == "n":
textpx = textpx + "1 HUSB @" + nm + "@\n"
if sp == "f":
textpx = textpx + "1 WIFE @" + nm + "@\n"
else:
ind_sp = n_foy.index("+")
if n_foy.index(nm) == 1:
elep = n_foy[ind_sp + 1:]
else:
elep = n_foy[1:ind_sp]
if sp == "m" or sp == "n":
textpx = textpx + "1 HUSB @" + nm + "@\n"
textpx = textpx + "1 WIFE @" + elep + "@\n"
if sp == "f":
textpx = textpx + "1 HUSB @" + elep + "@\n"
textpx = textpx + "1 WIFE @" + nm + "@\n"
for elei in listem:
ind_nei = listem.index(elei)
textpy = listep[ind_nei]
eley = elei[len(a_per) + 1:]
if ("1 FAMC @" + n_foy + "@\n") in textpy:
textpx = textpx + "1 CHIL @" + eley + "@\n"
for elej in lister:
ind_nej = lister.index(elej)
textpj = listeb[ind_nej]
eler = elej[len(a_per) + 1:]
if ("1 FAMC @" + n_foy + "@\n") in textpj:
textpx = textpx + "1 CHIL @" + eler + "@\n"
print textpx
listem_fd[ind_lim] = listem_fd[ind_lim] + textpx
textpr = listep[ind_lim] + listem_fd[ind_lim]
#Transformation des sources en fiches indépendantes Gedcom :
ind_sr = 0
textpz = listep[ind_lim]
textpw = ""
textsr = ""
if s1[0:ind_db] == a_per:
texttp = "I"
if s1[0:ind_db] == a_fam:
texttp = "F"
nm_sr = 0
while "\n1 SOUR" in textpz[ind_sr:]:
nm_sr = nm_sr + 1
textpq = "1 SOUR @S" + texttp + nm + "." + repr(nm_sr) + "@\n"
ind_sy = ind_sr + textpz[ind_sr:].index("\n1 SOUR") + 1
if "\n1 " in textpz[ind_sy:]:
ind_sz = ind_sy + textpz[ind_sy:].index("\n1 ") + 1
textsc = textpz[ind_sy:ind_sz]
textpz = textpz[:ind_sy] + textpq + textpz[ind_sz:]
else:
textsc = textpz[ind_sy:]
textpz = textpz[:ind_sy] + textpq
textsa = "0 @S" + texttp + nm + "." + repr(nm_sr) + "@ SOUR\n"
textsc = textsa + "1 TITL"+ textsc[6:]
if "\n2 TEXT" in textsc:
ind_st = textsc.index("\n2 TEXT") + 1
textsc = textsc[:ind_st] + "1 TEXT" + textsc[ind_st + 6:]
while "\n3 CONC" in textsc:
ind_sc = textsc.index("\n3 CONC") + 1
textsc = textsc[:ind_sc] + "2 CONC" + textsc[ind_sc + 6:]
textsr = textsr + textsc
ind_sr = ind_sy
listep[ind_lim] = textpz
listem_sr[ind_lim] = textsr
# Compilation des fiches
textpr = listep[ind_lim] + listem_sr[ind_lim] + listem_fd[ind_lim]
textpf = textpf + textpr
textfi = header + textpf
trlr = "0 TRLR"
text0 = textfi + trlr
out_file = open("rgtest0.txt", "w")
out_file.write(text0)
out_file.close()
[modifier] Python et Pywikibot :
[modifier] GeRod, du Gedcom vers Rodovid :
[modifier] RoGer, de Rodovid vers un Gedcom :
