def frbnfBib2arkAut(NumNot, frbnf, nom, prenom, date_debut):
"""Recherche de l'identifiant d'auteur à partir d'une recherche N° BIB + nom d'auteur :
on cherche le n° BIB comme NNB, comme FRBNF ou comme ancien numéro"""
listeArk = []
systemid_full = frbnf.lower().replace("f", "").replace("r", "").replace(
"b", "").replace("n", "")
nnb_possible = systemid_full[0:8]
url = funcs.url_requete_sru('bib.recordid all "' + nnb_possible + '"')
(test, page) = funcs.testURLetreeParse(url)
if (test == True):
for record in page.xpath("//srw:recordData", namespaces=main.ns):
listeArk.extend(
extractARKautfromBIB(record, nom, prenom, date_debut))
if (listeArk == []):
url = funcs.url_requete_sru('bib.otherid all "' + frbnf +
'" and bib.author all "' + nom + '"')
(test, page) = funcs.testURLetreeParse(url)
if (test == True):
for record in page.xpath("//srw:recordData", namespaces=main.ns):
listeArk.extend(
extractARKautfromBIB(record, nom, prenom, date_debut))
if (listeArk == []):
systemid1 = systemid_full[0:9]
systemid2 = systemid_full[0:8]
url = funcs.url_requete_sru('bib.otherid any "' + systemid1 + " " +
systemid2 + '" and bib.author all "' +
nom + '"')
(test, page) = funcs.testURLetreeParse(url)
if (test == True):
for record in page.xpath("//srw:recordData", namespaces=main.ns):
listeArk.extend(
extractARKautfromBIB(record, nom, prenom, date_debut))
listeArk = ",".join(set(listeArk))
return listeArk
def comparerAutBnf(NumNot, ark_current, nna, nom, origineComparaison):
ark = ""
url = funcs.url_requete_sru('aut.persistentid all "' + ark_current + '"')
(test, recordBNF) = funcs.testURLetreeParse(url)
if (test == True):
ark = compareAccessPoint(NumNot, ark_current, nna, nom, recordBNF)
return ark
def nna2ark(nna):
url = funcs.url_requete_sru('aut.recordid any ' + nna +
'and aut.status any "sparse validated"')
ark = ""
(test, record) = funcs.testURLetreeParse(url)
if (test):
if (record.find("//srw:recordIdentifier", namespaces=main.ns)
is not None):
ark = record.find("//srw:recordIdentifier",
namespaces=main.ns).text
return ark
def arkBib2arkAut(NumNot, arkBib, nom, prenom, date_debut):
"""Identifier un ARK de notice d'autorité à partir d'un ARK de notice BIB + contrôle sur le nom"""
url = funcs.url_requete_sru('bib.persistentid all "' + arkBib + '"')
(test, page) = funcs.testURLetreeParse(url)
listeArk = ""
if (test == True):
for record in page.xpath("//srw:recordData/mxc:record",
namespaces=main.ns):
listeArk.extend(
extractARKautfromBIB(record, nom, prenom, date_debut))
NumNotices2methode[NumNot].append(
"ARK notice BIB + contrôle accesspoint")
return listeArk
def arkAut2arkAut(NumNot, ark):
"""Actualisation d'un ARK de notice d'autorité"""
url = funcs.url_requete_sru('aut.persistentid all "' + ark + '"')
(test, page) = funcs.testURLetreeParse(url)
nv_ark = ""
if (test == True):
if (page.find("//srw:recordIdentifier", namespaces=main.ns)
is not None):
nv_ark = page.find("//srw:recordIdentifier",
namespaces=main.ns).text
NumNotices2methode[NumNot].append("Actualisation ARK")
return nv_ark
def isni2ark(NumNot, isni, origine="isni"):
url = funcs.url_requete_sru('aut.isni all "' + isni +
'" and aut.status any "sparse validated"')
(test, page) = funcs.testURLetreeParse(url)
nv_ark = ""
if (test == True):
if (page.find("//srw:recordIdentifier", namespaces=main.ns)
is not None):
nv_ark = page.find("//srw:recordIdentifier",
namespaces=main.ns).text
if (origine == "isni"):
NumNotices2methode[NumNot].append("ISNI")
return nv_ark
def accesspoint2arkAut(NumNot, nom_nett, prenom_nett, date_debut, date_fin):
listeArk = []
url = funcs.url_requete_sru('aut.accesspoint adj "' +
" ".join([nom_nett, prenom_nett, date_debut]) +
'"')
testdatefin = False
if (date_debut == "" and date_fin != ""):
url = funcs.url_requete_sru('aut.accesspoint adj "' +
" ".join([nom_nett, prenom_nett]) +
'" and aut.accesspoint all "' + date_fin +
'"')
testdatefin = True
#print(url)
(test, results) = funcs.testURLetreeParse(url)
if (test):
for record in results.xpath("//srw:records/srw:record",
namespaces=main.ns):
ark = record.find("srw:recordIdentifier", namespaces=main.ns).text
if (testdatefin == True):
if (record.find(
"srw:recordData/mxc:record/mxc:datafield[@tag='103']/mxc:subfield[@code='a']",
namespaces=main.ns) is not None):
f103a_datefin = record.find(
"srw:recordData/mxc:record/mxc:datafield[@tag='103']/mxc:subfield[@code='a']",
namespaces=main.ns).text[11:15]
if (date_fin == f103a_datefin):
listeArk.append(ark)
NumNotices2methode[NumNot].append(
"Point d'accès avec date de fin")
elif (date_debut != ""):
listeArk.append(ark)
NumNotices2methode[NumNot].append(
"Point d'accès avec date de début")
else:
listeArk.append(ark)
NumNotices2methode[NumNot].append("Point d'accès")
listeArk = ",".join(listeArk)
return listeArk
def bib2arkAUT(NumNot, titre, pubDate, nom, prenom, date_debut):
listeArk = []
if (pubDate == ""):
pubDate = "-"
url = funcs.url_requete_sru("".join([
'bib.title all "', titre, '" and bib.author all "', nom, " ", prenom,
'" and bib.publicationdate all "', pubDate, '"'
]))
(test, results) = funcs.testURLetreeParse(url)
if (test):
for record in results.xpath("//srw:recordData/mxc:record",
namespaces=main.ns):
listeArk.extend(
extractARKautfromBIB(record, nom, prenom, date_debut))
listeArk = ",".join(set(listeArk))
return listeArk
def relancerNNA_nomAuteur(NumNot, systemid, nom):
listeArk = []
if (nom != "" and nom is not None):
urlSRU = funcs.url_requete_sru('aut.accesspoint all "' + nom +
'" and aut.otherid all "' + systemid +
'"')
(test, pageSRU) = funcs.testURLetreeParse(urlSRU)
if (test == True):
for record in pageSRU.xpath("//srw:records/srw:record",
namespaces=main.ns):
ark = record.find("srw:recordIdentifier",
namespaces=main.ns).text
NumNotices2methode[NumNot].append("N° sys FRBNF + Nom")
listeArk.append(ark)
listeArk = ",".join(listeArk)
return listeArk
def rechercheNNA(NumNot, nna, nom):
ark = ""
if (nna.isdigit() is False):
#pb_frbnf_source.write("\t".join[NumNot,nnb] + "\n")
ark = "Pb FRBNF"
elif (10000000 < int(nna) < 25000000):
url = funcs.url_requete_sru('aut.recordid any "' + nna + '"')
(test, page) = funcs.testURLetreeParse(url)
if (test == True):
for record in page.xpath("//srw:records/srw:record",
namespaces=main.ns):
ark_current = record.find("srw:recordIdentifier",
namespaces=main.ns).text
ark = comparerAutBnf(NumNot, ark_current, nna, nom,
"Numéro de notice")
return ark
def frbnfAut2arkAut(NumNot, frbnf, nom, prenom, date_debut):
ark = ""
frbnf = nettoyageFRBNF(frbnf)
url = funcs.url_requete_sru('aut.otherid all "' + frbnf + '"')
(test, page) = funcs.testURLetreeParse(url)
if (test == True):
nb_resultats = int(
page.find("//srw:numberOfRecords", namespaces=main.ns).text)
if (nb_resultats == 0):
ark = oldfrbnf2ark(NumNot, frbnf, nom)
elif (nb_resultats == 1):
ark = page.find("//srw:recordIdentifier", namespaces=main.ns).text
NumNotices2methode[NumNot].append("FRBNF")
else:
ark = ",".join([
ark.text for ark in page.xpath("//srw:recordIdentifier",
namespaces=main.ns)
])
return ark
def ark2metas(ark, unidec=True):
recordBNF_url = funcs.url_requete_sru('bib.persistentid any "' + ark + '"')
(test, record) = funcs.testURLetreeParse(recordBNF_url)
accesspoint = ""
accesspoint_compl = ""
dates = ""
if (test == True):
if (record.find("//mxc:datafield[@tag='200']/mxc:subfield[@code='a']",
namespaces=main.ns) is not None):
accesspoint = record.find(
"//mxc:datafield[@tag='200']/mxc:subfield[@code='a']",
namespaces=main.ns).text
if (record.find("//mxc:datafield[@tag='210']/mxc:subfield[@code='a']",
namespaces=main.ns) is not None):
accesspoint = record.find(
"//mxc:datafield[@tag='210']/mxc:subfield[@code='a']",
namespaces=main.ns).text
if (record.find("//mxc:datafield[@tag='200']/mxc:subfield[@code='b']",
namespaces=main.ns) is not None):
accesspoint_compl = record.find(
"//mxc:datafield[@tag='200']/mxc:subfield[@code='b']",
namespaces=main.ns).text
if (record.find("//mxc:datafield[@tag='210']/mxc:subfield[@code='b']",
namespaces=main.ns) is not None):
accesspoint_compl = record.find(
"//mxc:datafield[@tag='210']/mxc:subfield[@code='b']",
namespaces=main.ns).text
if (record.find("//mxc:datafield[@tag='200']/mxc:subfield[@code='f']",
namespaces=main.ns) is not None):
dates = record.find(
"//mxc:datafield[@tag='200']/mxc:subfield[@code='f']",
namespaces=main.ns).text
if (record.find("//mxc:datafield[@tag='210']/mxc:subfield[@code='f']",
namespaces=main.ns) is not None):
dates = record.find(
"//mxc:datafield[@tag='210']/mxc:subfield[@code='f']",
namespaces=main.ns).text
metas = [accesspoint, accesspoint_compl, dates]
if (unidec == True):
metas = [unidecode(meta) for meta in metas]
return metas
def systemid2ark(NumNot, systemid, tronque, nom):
url = funcs.url_requete_sru('aut.otherid all "' + systemid + '"')
#url = "http://catalogueservice.bnf.fr/SRU?version=1.2&operation=searchRetrieve&query=NumNotice%20any%20%22" + systemid + "%22&recordSchema=InterXMarc_Complet&maximumRecords=1000&startRecord=1"
listeARK = []
(test, page) = funcs.testURLetreeParse(url)
if (test):
for record in page.xpath("//srw:records/srw:record",
namespaces=main.ns):
ark_current = record.find("srw:recordIdentifier",
namespaces=main.ns).text
for zone9XX in record.xpath(
"srw:recordData/mxc:record/mxc:datafield",
namespaces=main.ns):
#print(ark_current)
tag = zone9XX.get("tag")
if (tag[0:1] == "9"):
if (zone9XX.find("mxc:subfield[@code='a']",
namespaces=main.ns) is not None):
if (zone9XX.find("mxc:subfield[@code='a']",
namespaces=main.ns).text is not None):
if (zone9XX.find(
"mxc:subfield[@code='a']",
namespaces=main.ns).text == systemid):
#print(zone9XX.get("tag"))
listeARK.append(
comparerAutBnf(NumNot, ark_current,
systemid, nom,
"Ancien n° notice"))
listeARK = ",".join([ark1 for ark1 in listeARK if ark1 != ''])
#Si pas de réponse, on fait la recherche SystemID + Nom auteur
if (listeARK == ""):
listeARK = relancerNNA_nomAuteur(NumNot, systemid, nom)
listeARK = ",".join([ark1 for ark1 in listeARK.split(",") if ark1 != ''])
#Si à l'issue d'une première requête sur le numéro système dont on a conservé la clé ne donne rien -> on recherche sur le numéro tronqué comme numéro système
if (listeARK == "" and tronque == False):
systemid_tronque = systemid[0:len(systemid) - 1]
systemid2ark(NumNot, systemid_tronque, True, nom)
listeARK = ",".join([ark1 for ark1 in listeARK.split(",") if ark1 != ''])
return listeARK