diff --git a/hal/create_xml2hal.py b/hal/create_xml2hal.py
index 0d19e2db4b66868d123393588051afb764fcdb7d..740f42804ee12ef838e3ef052abb01aee27ec4c0 100644
--- a/hal/create_xml2hal.py
+++ b/hal/create_xml2hal.py
@@ -17,7 +17,7 @@ from lxml import etree
#############################################################################################################################
#############################################################################################################################
-def createXml_sendHal(numero,listauthors, lang_title, title_publi, name_conf, nb_pages, date_pub, listdomains, type_pub, ville, pays, pays_acr, doi_value, editor_book, volume, name_user, labo_auth_final, id_hal_user, login_user, login_depot, passwd_depot, bool_depot_preprod, bool_depot_prod):
+def createXml_sendHal(numero,listauthors, lang_title, title_publi, name_conf, nb_pages, date_pub, listdomains, type_pub, ville, pays, pays_acr, doi_value, editor_book, volume, pubmed, name_user, labo_auth_final, id_hal_user, login_user, login_depot, passwd_depot, bool_depot_preprod, bool_depot_prod):
print ("method createXml_sendHal begin")
## VARIABLES CREATION XML
@@ -167,6 +167,11 @@ def createXml_sendHal(numero,listauthors, lang_title, title_publi, name_conf, nb
doi.set("type","doi")
doi.text = doi_value
+ if len(pubmed) > 0 :
+ pubm = etree.SubElement(biblStruct, "idno")
+ pubm.set("type","pubmed")
+ pubm.text = pubmed
+
# profileDesc
profileDesc = etree.SubElement(biblFull, "profileDesc")
langUsage = etree.SubElement(profileDesc, "langUsage")
@@ -258,7 +263,7 @@ def createXml_sendHal(numero,listauthors, lang_title, title_publi, name_conf, nb
####################################################################
-def create_single_xml(listauthors, lang_title, title_publi, name_conf, nb_pages, date_pub, listdomains, type_pub, ville, pays, pays_acr, doi_value, editor_book, volume, name_user, labo_auth_final, id_hal_user, login_user):
+def create_single_xml(listauthors, lang_title, title_publi, name_conf, nb_pages, date_pub, listdomains, type_pub, ville, pays, pays_acr, doi_value, editor_book, volume, pubmed, name_user, labo_auth_final, id_hal_user, login_user):
print ("method create_single_xml begin")
data = ""
@@ -401,6 +406,11 @@ def create_single_xml(listauthors, lang_title, title_publi, name_conf, nb_pages,
doi.set("type","doi")
doi.text = doi_value
+ if len(pubmed) > 0 :
+ pubm = etree.SubElement(biblStruct, "idno")
+ pubm.set("type","pubmed")
+ pubm.text = pubmed
+
# profileDesc
profileDesc = etree.SubElement(biblFull, "profileDesc")
langUsage = etree.SubElement(profileDesc, "langUsage")
diff --git a/hal/forms.py b/hal/forms.py
index 364d7879557ccb3758a16960f8c1fdea81ed939d..acd2e38c5e58e03d1bec1c2bf22ab069dad217a2 100644
--- a/hal/forms.py
+++ b/hal/forms.py
@@ -25,7 +25,8 @@ CHOICES_SOURCE_BIBTEX = (
)
CHOICES_SOURCE_CSV = (
-('KN','KeyNote'),
+('PUBMED','PUBMED'),
+#('SCOPUS','SCOPUS'),
)
CHOICES_SOURCE_TEXT = (
@@ -81,7 +82,7 @@ class Csv2halForm(forms.Form):
id_hal_user = forms.CharField(required=True, max_length=40, label="IdHal chercheur (*)")
login_user = forms.CharField(required=True, max_length=40, label="Login HAL chercheur (*)")
- choice_source = forms.ChoiceField(widget=forms.RadioSelect, choices=CHOICES_SOURCE_CSV, label="Choix de la source", initial='KN' )
+ choice_source = forms.ChoiceField(widget=forms.RadioSelect, choices=CHOICES_SOURCE_CSV, label="Choix de la source", initial='PUBMED' )
login_depot = forms.CharField(required=True, max_length=40, label="Login HAL référent (*)")
passwd_depot = forms.CharField(required=True, max_length=40, label=("Password HAL référent (*)"), widget=forms.PasswordInput())
diff --git a/hal/scripts_bibtex.py b/hal/scripts_bibtex.py
index 9524fb4c563d905a7ce1cfda119cb173034b9d86..86efae02c7c014e09f105e8f76929908012131bd 100644
--- a/hal/scripts_bibtex.py
+++ b/hal/scripts_bibtex.py
@@ -139,6 +139,7 @@ def script_bibtex_2_hal (bibtex_file, bib_name_user, name_user, firstname_user,
doi_value = ""
publisher_book = ""
editor_book = ""
+ pubmed = ""
# Recup type publi, numero, language
if entry['ENTRYTYPE']=='article' :
@@ -360,7 +361,7 @@ def script_bibtex_2_hal (bibtex_file, bib_name_user, name_user, firstname_user,
if accept_depot == True :
print ("bool_depot_prod ",bool_depot_prod )
- result = createXml_sendHal(numero, listauthors, language, title, conf, nb_pages, year, listdomains, type_publi, town, country, country_acr,doi_value, editor_book, volume, name_user, labo_auth_final, id_hal_user, login_user, login_depot, passwd_depot, bool_depot_preprod, bool_depot_prod)
+ result = createXml_sendHal(numero, listauthors, language, title, conf, nb_pages, year, listdomains, type_publi, town, country, country_acr,doi_value, editor_book, volume, pubmed, name_user, labo_auth_final, id_hal_user, login_user, login_depot, passwd_depot, bool_depot_preprod, bool_depot_prod)
# methode createXml_sendHal renvoie true -> depot HAL ou preprod OK
if result == True :
@@ -388,7 +389,7 @@ def script_bibtex_2_hal (bibtex_file, bib_name_user, name_user, firstname_user,
town = town.encode("utf-8")
editor_book = editor_book.encode("utf-8")
login_user = login_depot
- reponse_single_xml = create_single_xml(listauthors, language, title, conf, nb_pages, year, listdomains, type_publi, town, country, country_acr, doi_value, editor_book, volume, name_user, labo_auth_final, id_hal_user, login_user)
+ reponse_single_xml = create_single_xml(listauthors, language, title, conf, nb_pages, year, listdomains, type_publi, town, country, country_acr, doi_value, editor_book, volume, pubmed, name_user, labo_auth_final, id_hal_user, login_user)
# ------------------END LOOP -----------------
cnt_total+=1
diff --git a/hal/scripts_csv.py b/hal/scripts_csv.py
index acd61b243afd277d7006c78381216f26de3662cd..f526c0b449ad32950f59d8b7482bddf81e4c1e41 100644
--- a/hal/scripts_csv.py
+++ b/hal/scripts_csv.py
@@ -1,16 +1,23 @@
#!/usr/bin/python
#-*- coding: utf-8 -*-
+# coding: utf-8
from __future__ import unicode_literals
import requests
-import csv
+
# lib XML
from lxml import etree
# lib csv
-
-
+#try:
+ # for Python 2.x
+from StringIO import StringIO
+#except ImportError:
+ # for Python 3.x
+# from io import StringIO
+import csv
+import unicodecsv
from create_xml2hal import createXml_sendHal, create_single_xml
@@ -23,6 +30,13 @@ from create_xml2hal import createXml_sendHal, create_single_xml
file_publis_csv = "all_csv.csv"
+"""
+def unicode_csv_reader(utf8_data, dialect=csv.excel, **kwargs):
+ csv_reader = csv.reader(utf8_data, dialect=dialect, **kwargs)
+ for row in csv_reader:
+ yield [unicode(cell, 'utf-8') for cell in row]
+"""
+
########################################################################################################################################
########################################################################################################################################
########## SCRIPT PRINCIPAL
@@ -30,9 +44,9 @@ file_publis_csv = "all_csv.csv"
########################################################################################################################################
-def script_csv_2_hal (csv_file, bib_name_user, name_user, firstname_user, labo_auth_final, id_hal_user, login_user, listdomains, login_depot, passwd_depot, bool_depot_preprod, bool_depot_prod, single, source_csv):
+def script_csv_2_hal (csv_file, form_author, name_user, firstname_user, labo_auth_final, id_hal_user, login_user, listdomains, login_depot, passwd_depot, bool_depot_preprod, bool_depot_prod, single, source_csv):
'''
- take bibtex file and some values in entry and parse the bibtex to get info upon publications
+ take csv file and some values in entry and parse the bibtex to get info upon publications
if the bool 'single' == False -> bibtex file has many publications, call createXml_sendHal (create XML and deposit) return a lis of results
if the bool 'single' == True -> bibtex file has one publication, call create_single_xml (post single XML no deposit) return the XML in string
@@ -45,16 +59,19 @@ def script_csv_2_hal (csv_file, bib_name_user, name_user, firstname_user, labo_a
depots = ""
reponse_single_xml = ""
+ list_pub_csv=[]
+
+ print ("source CSV "+source_csv)
+
###################################
###### COMPTEURS
###################################
cnt_article = 0
- cnt_inproceeding = 0
- cnt_proceeding = 0
- cnt_incollection = 0
+ cnt_conf = 0
cnt_book = 0
cnt_total = 0
+ cnt_reel = 0
cnt_phdthesis = 0
# errors bibtex
@@ -76,29 +93,8 @@ def script_csv_2_hal (csv_file, bib_name_user, name_user, firstname_user, labo_a
cnt_error_publisher_p = 0
cnt_error_editor_p = 0
- list_pub_csv = []
-
- # une participation a une conf (inproceeding) peut avoir une crossref reliee a une proceeding qui est une conf, celle ci
- # se trouve en fin du doc bibtex donc ->
- # on cherche crossref dans inproceeding, si on le trouve aller le chercher en bas, sinon chercher editor et publier directement dans inproceeding
- # car certains chercheurs peuvent creer leur bibtex comme ceci
-
- #bibtex_file = bibtex_file.encode("utf-8")
- print (csv_file)
-
- parser = BibTexParser()
- parser.ignore_nonstandard_types = False
- parser.homogenize_fields = False
- parser.common_strings = False
- parser.customization = convert_to_unicode
- bib_database = bibtexparser.loads(bibtex_file, parser = parser)
- '''
- parser = BibTexParser()
- parser.customization = convert_to_unicode
- bib_database = bibtexparser.load(bibtex_file, parser=parser)
- '''
- # list_acronym_country -> nom du pays en anglais majuscule , acronyme du pays
+ # read CSV contries
list_acronym_country = []
with open('hal/countries.csv', 'rb') as csvfile:
delim = str(':')
@@ -106,15 +102,24 @@ def script_csv_2_hal (csv_file, bib_name_user, name_user, firstname_user, labo_a
list_countries = csv.reader(csvfile, delimiter=delim, quotechar=quotech)
for row in list_countries:
list_acronym_country.append((row[1],row[0]))
-
- for entry in bib_database.entries :
+
+
+ # Split CSV
+ list_all_pub = []
+ list_all_pub = csv_file.split("\r\n")
+
+ #del list_pub_csv[0]
+ for row_pub in list_all_pub :
+ cnt_total+=1
+
# initialize entries
type_publi =""
+ pubmed = ""
numero = ""
language = "en"
title = ""
- conf=""
+ confjournal=""
nb_pages=""
volume = ""
town=""
@@ -122,234 +127,214 @@ def script_csv_2_hal (csv_file, bib_name_user, name_user, firstname_user, labo_a
country_acr="XX"
year = 0
doi_value = ""
+ pubmed = ""
publisher_book = ""
editor_book = ""
- # Recup type publi, numero, language
- if entry['ENTRYTYPE']=='article' :
- cnt_article +=1
- type_publi = "ART"
- numero = "RI"+str(cnt_article)
- language = "en"
-
- if entry['ENTRYTYPE']=='inproceedings' :
- cnt_inproceeding +=1
- type_publi = "COMM"
- numero = "CI"+str(cnt_inproceeding)
- language = "en"
-
- if entry['ENTRYTYPE']=='book' :
- cnt_book +=1
- type_publi = "OUV"
- numero = "O"+str(cnt_book)
- language = "en"
-
- # Recup title and format
- title = entry['title']
- title = title.replace("\n"," ")
- title = title.replace("\\emph","")
-
- # get authors according to source_bibtex
- listauthors = []
- if source_bibtex == "DBLP" :
- try :
- #print ("AUTHOR:"+entry['author'])
- authors = entry['author']
- list_authors_mix = authors.split("\n")
- for auth in list_authors_mix :
- lab_struct = ""
- #print ("TEST name_user "+name_user+" - auth "+auth)
-
- if name_user in auth :
- print ("Script_DBLP Match form_author DBLP")
- auth = firstname_user+" "+name_user
- lab_struct = labo_auth_final
- if auth[-4:] == " and" :
- auth = auth[:-4]
- auth_full = auth.split(" ")
- prenom = auth_full[0]
- prenom = prenom.encode('utf-8')
- nom = auth_full[-1]
- nom = nom.encode('utf-8')
- #print ("Script_dblp "+"author "+auth.encode('utf-8')+ " - prenom "+ prenom.encode('utf-8')+ " - nom "+nom.encode('utf-8')+ str(type(auth.encode('utf-8'))))
- listauthors.append((nom,prenom,lab_struct))
- except KeyError :
- cnt_error_auth+=1
-
- # if source_bibtex == "..." :
-
- # Get journal for ARTICLES
- if type_publi == "ART" :
- try :
- conf = entry['journal']
- conf = conf.replace("\n"," ")
- except KeyError :
- cnt_error_jrn+=1
-
- # Get conf for COMM, split entry with ',' , first occurence is conf name
- # then search country from CSV in other occurences and if found, get previous occurence to get town (except USA previuous previous occurence)
- if type_publi == "COMM" :
- try :
- booktitle = entry['booktitle']
- conf_all = booktitle.split(",")
- conf = conf_all[0]
- conf = conf.replace("\n"," ")
- conf = conf.replace("\\(^\\mboxth\\)","th")
- conf = conf.replace("\\(^\\mboxe\\)","e")
- prev_conf_elmt = ""
- prev_prev_conf_elmt = ""
- for conf_elmt in conf_all :
- conf_elmt = conf_elmt.strip()
- for csv_country in list_acronym_country :
- if conf_elmt.upper() == csv_country[0] :
- if csv_country[0] == "USA" :
- prev_prev_conf_elmt = prev_prev_conf_elmt.replace("\n"," ")
- town = prev_prev_conf_elmt
- country_acr = csv_country[1]
- country = csv_country[0]
-
- else :
- prev_conf_elmt = prev_conf_elmt.replace("\n"," ")
- town = prev_conf_elmt
- country_acr = csv_country[1]
- country = csv_country[0]
-
- prev_prev_conf_elmt = prev_conf_elmt
- prev_conf_elmt = conf_elmt
-
- except KeyError :
- cnt_error_booktitle+=1
-
- # get volume
- try :
- volume = entry['volume']
- except KeyError :
- cnt_error_vol+=1
-
- # get nb_pages
- try :
- nb_pages = entry['pages']
- except KeyError :
- cnt_error_pages+=1
-
- # get Year
+ # split row publi
+ list_field = []
try :
- year = entry['year']
- except KeyError :
- cnt_error_year_art+=1
-
- # get DOI
- try :
- doi_value = entry['doi']
- except KeyError :
- cnt_error_doi+=1
-
-
- if (type_publi == "COMM") or (type_publi == "BOOK") :
- # get Publisher
- try :
- publisher_book = entry['publisher']
- except KeyError :
- cnt_error_publisher+=1
-
- # get Editor
- try :
- editor_book = entry['editor']
- except KeyError :
- cnt_error_editor+=1
-
-
- # Test value "single"
- # if false -> call createXml_sendHal (create XML and deposit)
- # if true -> call create_single_xml (build XML without creation, no deposit)
- if (type_publi == "ART") or (type_publi == "COMM") or (type_publi == "OUV") :
- if single == False :
-
- action_todo=""
-
- # Verification que la publi n'existe pas deja dans HAL
- # pour un meilleur matching, titre en minuscule et recherche par le champ title_t (sans casse ni accent)
- title_low = title.lower()
- url_request = "https://api.archives-ouvertes.fr/search/?q=title_t:\"{0}\"&fl=uri_s,halId_s,authFullName_s,authIdHal_s,title_s&wt=json".format(title_low)
-
- req = requests.get(url_request)
- json = ""
+ list_field = row_pub.split("_")
+ except AttributeError :
+ list_field = []
+
+ if len(list_field) > 0 :
+ cnt_reel+=1
+
+ ################
+ ### IF PUBMED
+ if source_csv == "PUBMED":
+ title = list_field[0]
+ print ("title "+title)
+
+
+ authors = list_field[2]
+ details = list_field[3]
+ confjournalyear = list_field[4]
+ typepub = list_field[6]
+ pubmed = list_field[9]
+
+ ## TYPEPUB
+ if typepub == "citation" :
+ cnt_article+=1
+ type_publi = "ART"
+ numero = "RI"+str(cnt_article)
+ ## TODO -> mettre autres
+ print ("numero "+str(numero))
+ print ("pubmed "+str(pubmed))
+
+ ## AUTHORS
try :
- json = req.json()
- except ValueError :
- print ("PROBLEME VALUEERROR")
- try :
- if json is not "" :
- result = json['response']['docs']
-
- # si un resultat est trouve, recup authors et URI pour affichage dans 'resultat', action_todo = "E"
- if (len(result) == 1 ) :
- all_auth = ""
- try :
- tous_authors = result[0]["authFullName_s"]
- for auth in tous_authors:
- all_auth = all_auth + auth+"-"
- except KeyError, e :
- print ("error print authors existing publi")
- resultat = resultat + "num. "+numero+" - "+result[0]["uri_s"]+" - auteurs:"+all_auth+"<br/>"
- action_todo = "E"
-
- # si plusieurs resultats trouves, recup URI pour affichage dans 'problemes_doublon', action_todo = "2"
- if (len(result) >1 ) :
- problemes_doublon = problemes_doublon + "num. "+numero+" - URLS "+result[0]["uri_s"]+" "+result[1]["uri_s"]+"<br/>"
- action_todo = "2"
-
- # Si aucun resultat on peut deposer, action_todo = "D"
- if (len(result) == 0 ) :
- action_todo = "D"
- result = False
- accept_depot = True
-
- # Si caracteres incoherents (issus de DBLP) dans le titre -> pas de depot -> problemes_depot
- if ("\\(^\\mbox" in title) :
- print("-----------------> MBOX")
- accept_depot = False
- result = False
-
- title = title.encode("utf-8")
- conf = conf.encode("utf-8")
- town = town.encode("utf-8")
- editor_book = editor_book.encode("utf-8")
-
- if accept_depot == True :
- print ("bool_depot_prod ",bool_depot_prod )
- result = createXml_sendHal(numero, listauthors, language, title, conf, nb_pages, year, listdomains, type_publi, town, country, country_acr,doi_value, editor_book, volume, name_user, labo_auth_final, id_hal_user, login_user, login_depot, passwd_depot, bool_depot_preprod, bool_depot_prod)
-
- # methode createXml_sendHal renvoie true -> depot HAL ou preprod OK
- if result == True :
- depots = depots + "num. "+numero+" au titre "+title.decode("utf-8")+" deposee dans HAL<br/>"
- # methode createXml_sendHal renvoie true -> pb depot HAL ou preprod ou pas de depot demande
- if result == False :
- problemes_depot = problemes_depot + "num. "+numero+" au titre "+title.decode("utf-8")+" a un probleme de depot<br/>"
+ authors= authors.replace(", et al.","")
+ x = authors.find(";")
+ authors = authors[:x]
+ listauthors = []
+ list_authors_mix = authors.split(",")
+ for auth in list_authors_mix :
+ auth = auth.strip()
+ lab_struct = ""
+ #print ("TEST form_author "+form_author+" - auth "+auth)
+
+ if form_author in auth :
+ print ("Script_csv Match form_author keynote")
+ auth = name_user+" "+firstname_user
+ lab_struct = labo_auth_final
+
+ auth_full = auth.split(" ")
+ prenom = auth_full[1]
+ prenom = prenom.encode('utf-8')
+ nom = auth_full[0]
+ nom = nom.encode('utf-8')
+ #print ("author "+str(nom)+ " - prenom "+str(prenom)+" - labo"+str(lab_struct))
+ #print ("Script_dblp "+"author "+auth.encode('utf-8')+ " - prenom "+ prenom.encode('utf-8')+ " - nom "+nom.encode('utf-8')+ str(type(auth.encode('utf-8'))))
+ listauthors.append((nom,prenom,lab_struct))
+ except IndexError :
+ print ('listauthors pb')
+ #listauthors = []
+
+ ## CONF JOURNAL YEAR
+ x = confjournalyear.find(".")
+ confjournal = confjournalyear[:x]
+ year = confjournalyear[x+1:]
+ year = year.strip()
+
+ print ("confjournal "+str(confjournal))
+ print ("year "+str(year))
+
+ ## VOL PAGES
+ # split details
+ x = details.find("pii: ")
+ if x == -1 : # get vol and pages
+ y = details.find(";")
+ if y == -1 :
+ volume =""
+ nb_pages = ""
+ else :
+ volpages = details[y+1:]
+ z = volpages.find(":")
+ volume = volpages[:z]
+ nb_pages = volpages[z+1:]
+ w = nb_pages.find(".")
+ nb_pages = nb_pages[:w]
+
+ else :
+ volume=""
+ nb_pages = ""
+
+ print ("vol "+str(volume)+ " - pages "+str(nb_pages))
+
+ ## DOI
+ x = details.find("doi: ")
+ if x == -1 : # no doi
+ doi_value = ""
+ else :
+ doi_value = details[x+5:]
+ y = doi_value.find(" ")
+ if y > -1 :
+ doi_value = doi_value[:y-1]
else :
+ doi_value = doi_value[:-1] #suppression point final
+
+
+ print ("doi "+str(doi_value))
+ ########################
+ ### ENDIF PUBMED
+
+
+ # Test value "single"
+ # if false -> call createXml_sendHal (create XML and deposit)
+ # if true -> call create_single_xml (build XML without creation, no deposit)
+ if (type_publi == "ART") or (type_publi == "COMM") or (type_publi == "OUV") :
+ if single == False :
+
+ action_todo=""
+
+ # Verification que la publi n'existe pas deja dans HAL
+ # pour un meilleur matching, titre en minuscule et recherche par le champ title_t (sans casse ni accent)
+ title_low = title.lower()
+ url_request = "https://api.archives-ouvertes.fr/search/?q=title_t:\"{0}\"&fl=uri_s,halId_s,authFullName_s,authIdHal_s,title_s&wt=json".format(title_low)
+
+ req = requests.get(url_request)
+ json = ""
+ try :
+ json = req.json()
+ except ValueError :
+ print ("PROBLEME VALUEERROR")
+ try :
+ if json is not "" :
+ result = json['response']['docs']
+
+ # si un resultat est trouve, recup authors et URI pour affichage dans 'resultat', action_todo = "E"
+ if (len(result) == 1 ) :
+ all_auth = ""
+ try :
+ tous_authors = result[0]["authFullName_s"]
+ for auth in tous_authors:
+ all_auth = all_auth + auth+"-"
+ except KeyError, e :
+ print ("error print authors existing publi")
+ resultat = resultat + "num. "+numero+" - "+result[0]["uri_s"]+" - auteurs:"+all_auth+"<br/>"
+ action_todo = "E"
+
+ # si plusieurs resultats trouves, recup URI pour affichage dans 'problemes_doublon', action_todo = "2"
+ if (len(result) >1 ) :
+ problemes_doublon = problemes_doublon + "num. "+numero+" - URLS "+result[0]["uri_s"]+" "+result[1]["uri_s"]+"<br/>"
+ action_todo = "2"
+
+ # Si aucun resultat on peut deposer, action_todo = "D"
+ if (len(result) == 0 ) :
+ action_todo = "D"
+ result = False
+ accept_depot = True
+
+ # Si caracteres incoherents (issus de DBLP) dans le titre -> pas de depot -> problemes_depot
+ if ("\\(^\\mbox" in title) :
+ print("-----------------> MBOX")
+ accept_depot = False
+ result = False
+
+ title = title.encode("utf-8")
+ confjournal = confjournal.encode("utf-8")
+ town = town.encode("utf-8")
+ editor_book = editor_book.encode("utf-8")
+
+ if accept_depot == True :
+ print ("bool_depot_prod ",bool_depot_prod )
+ result = createXml_sendHal(numero, listauthors, language, title, confjournal, nb_pages, year, listdomains, type_publi, town, country, country_acr,doi_value, editor_book, volume, pubmed, name_user, labo_auth_final, id_hal_user, login_user, login_depot, passwd_depot, bool_depot_preprod, bool_depot_prod)
+
+ # methode createXml_sendHal renvoie true -> depot HAL ou preprod OK
+ if result == True :
+ depots = depots + "num. "+numero+" au titre "+title.decode("utf-8")+" deposee dans HAL<br/>"
+ # methode createXml_sendHal renvoie true -> pb depot HAL ou preprod ou pas de depot demande
+ if result == False :
+ problemes_depot = problemes_depot + "num. "+numero+" au titre "+title.decode("utf-8")+" a un probleme de depot<br/>"
+ else :
+ # pb de lecture json, pas depot -> problemes_url
+ action_todo = "P"
+ problemes_url = problemes_url + "num. "+numero+" au titre "+title.decode("utf-8")+"<br/>"
+ except KeyError :
# pb de lecture json, pas depot -> problemes_url
action_todo = "P"
- problemes_url = problemes_url + "num. "+numero+" au titre "+title.decode("utf-8")+"<br/>"
- except KeyError :
- # pb de lecture json, pas depot -> problemes_url
- action_todo = "P"
- problemes_url = problemes_url + "num. "+numero+" au titre "+title.decode("utf-8")+"<br/>"
-
- # Creation du CSV qui sera renvoye et affiche
- authors = authors.replace(" and",", ")
- list_pub_csv.append((numero,authors,title,conf,nb_pages, volume,year, type_publi, action_todo, town, country, country_acr, language))
-
+ problemes_url = problemes_url + "num. "+numero+" au titre "+title.decode("utf-8")+"<br/>"
+
+ # Creation du CSV qui sera renvoye et affiche
+ authors = authors.replace(" and",", ")
+ list_pub_csv.append((numero,authors,title,confjournal,nb_pages, volume,year, type_publi, action_todo, town, country, country_acr, language))
+
+
+ elif single == True :
+ title = title.encode("utf-8")
+ confjournal = confjournal.encode("utf-8")
+ town = town.encode("utf-8")
+ editor_book = editor_book.encode("utf-8")
+ login_user = login_depot
+ reponse_single_xml = create_single_xml(listauthors, language, title, confjournal, nb_pages, year, listdomains, type_publi, town, country, country_acr, doi_value, editor_book, volume, name_user, labo_auth_final, id_hal_user, login_user)
+ else :
+ print("empty line")
+ # ------------------END LOOP -----------------
+
- elif single == True :
- title = title.encode("utf-8")
- conf = conf.encode("utf-8")
- town = town.encode("utf-8")
- editor_book = editor_book.encode("utf-8")
- login_user = login_depot
- reponse_single_xml = create_single_xml(listauthors, language, title, conf, nb_pages, year, listdomains, type_publi, town, country, country_acr, doi_value, editor_book, volume, name_user, labo_auth_final, id_hal_user, login_user)
- # ------------------END LOOP -----------------
- cnt_total+=1
########################
####### ECRITURE RESULTATS -> list_resultats
@@ -360,12 +345,12 @@ def script_csv_2_hal (csv_file, bib_name_user, name_user, firstname_user, labo_a
allauth = pub[1]
allauth = allauth.replace("\n","")
title = pub[2]#.decode("utf-8")
- conf = pub[3]#.decode("utf-8")
+ confjournal = pub[3]#.decode("utf-8")
ville = pub[9]#.decode("utf-8")
- list_resultats.append((str(pub[0]),allauth,title,conf,str(pub[4]),str(pub[5]),str(pub[6]),str(pub[7]),str(pub[8]),ville,str(pub[10]),str(pub[11]),str(pub[12])))
-
- cnt_nb_publis = cnt_article + cnt_inproceeding + cnt_book + cnt_incollection + cnt_phdthesis
+ list_resultats.append((str(pub[0]),allauth,title,confjournal,str(pub[4]),str(pub[5]),str(pub[6]),str(pub[7]),str(pub[8]),ville,str(pub[10]),str(pub[11]),str(pub[12])))
+
+ cnt_nb_publis = cnt_article + cnt_conf + cnt_book + cnt_phdthesis
list_resultats.append(("RESULTATS","nombre de publis",str(cnt_nb_publis),"","","","","","","","","",""))
list_resultats.append(("RESULTATS","publis deja presentes dans HAL",resultat,"","","","","","","","","",""))
@@ -376,16 +361,16 @@ def script_csv_2_hal (csv_file, bib_name_user, name_user, firstname_user, labo_a
print ("####### RESULTATS PARSING BIBTEX ########")
print ("cnt_article ", cnt_article)
- print ("cnt_inproceeding ", cnt_inproceeding)
- print ("cnt_proceeding ", cnt_proceeding)
- print ("cnt_incollection ", cnt_incollection)
+ print ("cnt_conf ", cnt_conf)
print ("cnt_book ", cnt_book)
print ("cnt_phdthesis ", cnt_phdthesis)
+ print ("cnt_reel ", cnt_reel)
print ("cnt_total ", cnt_total)
print ("ERROR Author", cnt_error_auth)
print ("ERROR Title", cnt_error_title)
+ """
print ("-------ERRORS ARTICLE------")
print ("cnt_error_jrn",cnt_error_jrn)
print ("cnt_error_vol",cnt_error_vol)
@@ -406,7 +391,7 @@ def script_csv_2_hal (csv_file, bib_name_user, name_user, firstname_user, labo_a
print ("cnt_error_idcrossref:",cnt_error_idcrossref)
print ("#########################################")
-
+ """
print ("######## RESULTATS XML + DEPOTS ##########")
print ("RESULTATS existants")
print (resultat.encode("utf-8"))
@@ -423,8 +408,10 @@ def script_csv_2_hal (csv_file, bib_name_user, name_user, firstname_user, labo_a
print ("PROBLEMES URL")
print (problemes_url.encode("utf-8"))
+ #print ("special_cnt"+str(special_cnt))
if single == False :
return list_resultats
if single == True :
return reponse_single_xml
+
\ No newline at end of file
diff --git a/hal/scripts_text.py b/hal/scripts_text.py
index 965ed781e287adb1d0bfefcccfcc47c4f0200374..5c04a761e2a403dd6aa3e586b5ff6f4e0c02825d 100644
--- a/hal/scripts_text.py
+++ b/hal/scripts_text.py
@@ -127,6 +127,8 @@ def script_text_2_hal (text_file, form_author, name_user, firstname_user, labo_a
list_publis = text_file.splitlines()
for publi in list_publis:
+
+ pubmed = ""
language = "en"
# recup numero avant le -
@@ -323,7 +325,7 @@ def script_text_2_hal (text_file, form_author, name_user, firstname_user, labo_a
action_todo = "D"
result = False
if (type_publi=="ART") or (type_publi=="COMM") or (type_publi=="POSTER") or (type_publi=="OUV") or (type_publi=="COUV"):
- result = createXml_sendHal(numero, listauthors, language, title, conf, nb_pages, year, listdomains, type_publi, town, country, country_acr,doi_value, editor_book, volume, name_user, labo_auth_final, id_hal_user, login_user, login_depot, passwd_depot, bool_depot_preprod, bool_depot_prod)
+ result = createXml_sendHal(numero, listauthors, language, title, conf, nb_pages, year, listdomains, type_publi, town, country, country_acr,doi_value, editor_book, volume, pubmed, name_user, labo_auth_final, id_hal_user, login_user, login_depot, passwd_depot, bool_depot_preprod, bool_depot_prod)
if result == True :
depots = depots + "num. "+numero+" au titre "+title.decode('utf-8')+" deposee dans HAL<br/>"
if result == False :
@@ -338,7 +340,7 @@ def script_text_2_hal (text_file, form_author, name_user, firstname_user, labo_a
list_pub_csv.append((numero,authors,title,conf,nb_pages, volume,year, type_publi, action_todo, town, country, country_acr, language))
elif single == True :
- reponse_single_xml = create_single_xml(listauthors, language, title, conf, nb_pages, year, listdomains, type_publi, town, country, country_acr, doi_value, editor_book, volume, name_user, labo_auth_final, id_hal_user, login_user)
+ reponse_single_xml = create_single_xml(listauthors, language, title, conf, nb_pages, year, listdomains, type_publi, town, country, country_acr, doi_value, editor_book, volume, pubmed, name_user, labo_auth_final, id_hal_user, login_user)
#print "REPONSE_SINGLE_XML : "+ reponse_single_xml
diff --git a/hal/templates/hal/aide.html b/hal/templates/hal/aide.html
index 04bea03f9b485eba73e7046a07719c6b93d354b1..01979b8fddd261bce0a8404a4403cd74d127bff9 100644
--- a/hal/templates/hal/aide.html
+++ b/hal/templates/hal/aide.html
@@ -232,7 +232,7 @@ Pour récupérer ce contenu dans DBLP, rechercher l'auteur et cliquez sur le lie
<img src="{% static 'img/dblp_hal_help1.png' %}" > </p>
<br/>
<p align="justify">
-Une page présentant le contenu des publis au format bibtex s'ouvre et vous pouvez cliqu6333333er sur le lien <u>download as .bib file</u> pour télécharger ce fichier.
+Une page présentant le contenu des publis au format bibtex s'ouvre et vous pouvez cliquer sur le lien <u>download as .bib file</u> pour télécharger ce fichier.
<br/><br/>
Copiez-collez le contenu de ce fichier dans l'emplacement prévu nommé <b>contenu bibtex</b>
<br/>
diff --git a/hal/templates/hal/index.html b/hal/templates/hal/index.html
index d5fa2ca4eda6a9b98c3db28f4a86dfd4c5e7952a..d27b76a6e907e26db214399dc5bea10f257fefef 100644
--- a/hal/templates/hal/index.html
+++ b/hal/templates/hal/index.html
@@ -31,11 +31,13 @@
<br/>
- <a href="https://dblp.uni-trier.de/" target="_blank">DBLP</a>.
<br/>
- - <a href="https://dblp.uni-trier.de/" target="_blank">ENDNOTE</a>.
+ - <a href="https://endnote.com/" target="_blank">ENDNOTE</a>.
<br/><br/>
<b>CSV_2_Hal</b> permet de faire des imports massifs dans HAL à partir de fichiers au format CSV provenant de différentes sources.
<br/>
- - <a href="https://dblp.uni-trier.de/" target="_blank">KEYNOTE</a>.
+ - <a href="https://www.ncbi.nlm.nih.gov/pubmed/" target="_blank">PUBMED</a>.
+ <!-- <br/>
+ - <a href="https://www.scopus.com/home.uri" target="_blank">SCOPUS</a>.-->
<br/><br/>
<b>Text_2_Hal</b> permet de faire des imports massifs dans HAL à partir d'une liste texte, de formater une liste texte ou de formater du texte issu de différentes sources telles que :
<br/>
diff --git a/hal/views.py b/hal/views.py
index 8b9e02721139263a7d58b965dea1175daf6b0f0e..55e800f40e850cf7aeb4a556e93be131fbe75c04 100644
--- a/hal/views.py
+++ b/hal/views.py
@@ -12,6 +12,7 @@ from forms import ConnexionForm, Bibtex2halForm, Text2halForm, BibtexXmlForm, Cs
from scripts_bibtex import script_bibtex_2_hal
from scripts_text import script_text_2_hal
+from scripts_csv import script_csv_2_hal
import httplib
@@ -253,6 +254,8 @@ def csv2hal(request):
domain3 = form.cleaned_data['domain3']
domain4 = form.cleaned_data['domain4']
domain5 = form.cleaned_data['domain5']
+
+ choice_source = form.cleaned_data['choice_source']
login_depot = form.cleaned_data['login_depot']
passwd_depot = form.cleaned_data['passwd_depot']
@@ -289,8 +292,9 @@ def csv2hal(request):
single = False
- print ("begin script")
- reponse = script_csv_2_hal (csv_file, bib_name_user, name_user, firstname_user, labo_auth_final, id_hal_user, login_user, listdomains, login_depot, passwd_depot, bool_depot_preprod, bool_depot_prod, single, source_csv)
+ #print ("begin script")
+ print ("form_author "+form_author)
+ reponse = script_csv_2_hal (csv_file, form_author, name_user, firstname_user, labo_auth_final, id_hal_user, login_user, listdomains, login_depot, passwd_depot, bool_depot_preprod, bool_depot_prod, single, choice_source)
reponse_to_post = ""
list_to_post = []