diff --git a/README.md b/README.md
index 94e4df9..b484275 100644
--- a/README.md
+++ b/README.md
@@ -1,4 +1,18 @@
 APC-bills
 ===============
 
-Automatic processing of APC bills (from department "Négociations et Acquisitions")
\ No newline at end of file
+Automatic processing of APC bills (from department "Négociations et Acquisitions")
+
+## Description
+
+Ce repo contient l'essentiel du code pour extraire les informations des factures. Les informations à récupérer dépendent du fournisseur. Elles sont détaillées pour ce code dans le fichier __to_do.xlsx__.
+
+## Utilisation
+Toutes les factures sont initialement mélangées dans le même dossier.
+
+0. (facultatif) metric-data permet d'afficher la répartition des différents codes éditeurs pour cibler les plus importants à traiter.
+1. Lancer le code tri factures en modifiant les paramètres `path_bills`, qui correspond au nom du dossier d'entrée et éventuellement `path_bills_output`, correspondant au nom du dossier de sortie.
+2. Renseigner son adresse mail comme chaîne de caractère en modifiant le paramètre `mail_adress` dans le fichier __editors-processing/global_function.py__  
+2. Lancer un par un les programmes dans editors processing : ils traitent les éditeurs un par un en utilisant de la recherhce de chaîne de caractère. A l'exception de `global_functions.py`qui contient des fonctions utilisées dans chacun des programmes.
+3. Les fichiers sont à présents traités dans un dossier __results__. Dans chaque programme, les paramètres `path` et `path_res` doivent être modifiés en conséquent (_path_ : dossier contenant les factures triées + num éditeur) (_path_res_ : results par défaut)
+4. On aura en résultat autant de csv que d'éditeurs traités. Les non traités seront dans le fichier "autres".
diff --git a/dictionaries/code_fournisseur2fournisseur.json b/dictionaries/code_fournisseur2fournisseur.json
new file mode 100644
index 0000000..4275f25
--- /dev/null
+++ b/dictionaries/code_fournisseur2fournisseur.json
@@ -0,0 +1,18 @@
+{
+    "0001021938":1,
+    "0001197861":2,
+    "0001200930":3,
+    "0001079074":4,
+    "0001021664":5,
+    "0001024808":6,
+    "0001097617":7,
+    "0001091455":8,
+    "0001217181":9,
+    "0001090050":10,
+    "0001157725":11,
+    "0001062310":12,
+    "0001021888":13,
+    "0001222959":14,
+    "0001234181":15,
+    "0001226137":16
+}
diff --git a/editors-processing/0001021664.py b/editors-processing/0001021664.py
new file mode 100644
index 0000000..bc3f41c
--- /dev/null
+++ b/editors-processing/0001021664.py
@@ -0,0 +1,50 @@
+from global_functions import *
+import os
+import PyPDF2
+import pandas as pd
+
+num_editor = "0001021664"
+
+path = './factures-2021-2022-triees/%s' %num_editor
+
+path_res='./results'
+
+
+df_res = pd.DataFrame(columns=["nom_complet","doi","unverified_doi","item_editor","full_text"])
+
+res = []
+for filename in os.listdir(path):
+    file = os.path.join(path, filename)
+    # Read PDF as text
+    try:
+        reader = PyPDF2.PdfReader(file, strict=False)
+        full_text = read_all_page(reader)
+    except:
+        full_text= ""
+    
+    ## Extract infos
+    # DOI
+    unverified_doi = find_doi(full_text)
+    doi = ""
+    #only if a doi is found
+    if unverified_doi:
+        if verify_doi(unverified_doi):
+            #If DOI is found, write it in "doi" column instead of 'unverified_doi' column.
+            doi=unverified_doi
+            unverified_doi=""
+
+    # Article
+    item_editor =  get_caracs_between(full_text,"Description","Product ").replace("\n"," ").replace("Total Due","")
+    if item_editor != "":
+        item_editor = "Product ID + Description: " + item_editor
+    
+    else:
+        item_editor =  get_caracs_between(full_text,"Description","Total Units").replace("\n"," ").replace("Total Due","")
+        if item_editor != "":
+            item_editor = "Product ID + Description: " + item_editor
+
+
+    new_row = {'nom_complet': filename, 'doi': doi, 'unverified_doi':unverified_doi ,"item_editor":item_editor,'full_text': full_text}
+    df_res = pd.concat([df_res,pd.DataFrame([new_row])],ignore_index=True)
+
+df_res.to_csv(path_or_buf="%s/%s.csv"%(path_res,num_editor),index=False,header=True,encoding='utf-8',escapechar='\\')
diff --git a/editors-processing/0001021888.py b/editors-processing/0001021888.py
new file mode 100644
index 0000000..6f0f056
--- /dev/null
+++ b/editors-processing/0001021888.py
@@ -0,0 +1,44 @@
+from global_functions import *
+import os
+import PyPDF2
+import pandas as pd
+
+num_editor = "0001021888"
+
+path = './factures-2021-2022-triees/%s' %num_editor
+
+path_res='./results'
+
+
+df_res = pd.DataFrame(columns=["nom_complet","doi","unverified_doi","item_editor","full_text"])
+
+res = []
+for filename in os.listdir(path):
+    file = os.path.join(path, filename)
+    # Read PDF as text
+    try:
+        reader = PyPDF2.PdfReader(file, strict=False)
+        full_text = read_all_page(reader)
+    except:
+        full_text= ""
+    
+    ## Extract infos
+    # DOI
+    unverified_doi = find_doi(full_text)
+    doi = ""
+    #only if a doi is found
+    if unverified_doi:
+        if verify_doi(unverified_doi):
+            #If DOI is found, write it in "doi" column instead of 'unverified_doi' column.
+            doi=unverified_doi
+            unverified_doi=""
+
+    # Article
+    item_editor =  get_caracs_between(full_text,"Description","Payment terms").replace("\n"," ")
+    if item_editor != "":
+        item_editor = "Title: " + item_editor
+
+    new_row = {'nom_complet': filename, 'doi': doi, 'unverified_doi':unverified_doi ,"item_editor":item_editor,'full_text': full_text}
+    df_res = pd.concat([df_res,pd.DataFrame([new_row])],ignore_index=True)
+
+df_res.to_csv(path_or_buf="%s/%s.csv"%(path_res,num_editor),index=False,header=True,encoding='utf-8',escapechar='\\')
diff --git a/editors-processing/0001021938.py b/editors-processing/0001021938.py
new file mode 100644
index 0000000..76e7a1e
--- /dev/null
+++ b/editors-processing/0001021938.py
@@ -0,0 +1,52 @@
+from global_functions import *
+import os
+import PyPDF2
+import pandas as pd
+
+num_editor = "0001021938"
+
+path = './factures-2021-2022-triees/%s' %num_editor
+
+path_res='./results'
+
+
+df_res = pd.DataFrame(columns=["nom_complet","doi","unverified_doi","item_editor","full_text"])
+
+res = []
+for filename in os.listdir(path):
+    file = os.path.join(path, filename)
+    # Read PDF as text
+    try:
+        reader = PyPDF2.PdfReader(file, strict=False)
+        full_text = read_all_page(reader)
+    except:
+        full_text= ""
+    
+    ## Extract infos
+    # DOI
+    unverified_doi = find_doi(full_text)
+    doi = ""
+    #only if a doi is found
+    if unverified_doi:
+        if verify_doi(unverified_doi):
+            #If DOI is found, write it in "doi" column instead of 'unverified_doi' column.
+            doi=unverified_doi
+            unverified_doi=""
+
+    # Article
+    if "Author/Article:" in full_text:
+        item_editor =  get_caracs_between(full_text,"Author/Article:","Manuscript").replace("\n"," ")
+        
+        if item_editor != "":
+            item_editor = "Author/Article: " + item_editor
+
+    else:
+        item_editor =  get_caracs_between(full_text,"Author","Manuscript ID:").replace("\n"," ")
+        
+        if item_editor != "":
+            item_editor = "Author" + item_editor
+
+    new_row = {'nom_complet': filename, 'doi': doi, 'unverified_doi':unverified_doi ,"item_editor":item_editor,'full_text': full_text}
+    df_res = pd.concat([df_res,pd.DataFrame([new_row])],ignore_index=True)
+
+df_res.to_csv(path_or_buf="%s/%s.csv"%(path_res,num_editor),index=False,header=True,encoding='utf-8',escapechar='\\')
diff --git a/editors-processing/0001024808.py b/editors-processing/0001024808.py
new file mode 100644
index 0000000..b18290e
--- /dev/null
+++ b/editors-processing/0001024808.py
@@ -0,0 +1,50 @@
+from global_functions import *
+import os
+import PyPDF2
+import pandas as pd
+
+num_editor = "0001024808"
+
+path = './factures-2021-2022-triees/%s' %num_editor
+
+path_res='./results'
+
+
+df_res = pd.DataFrame(columns=["nom_complet","doi","unverified_doi","item_editor","full_text"])
+
+res = []
+for filename in os.listdir(path):
+    file = os.path.join(path, filename)
+    # Read PDF as text
+    try:
+        reader = PyPDF2.PdfReader(file, strict=False)
+        full_text = read_all_page(reader)
+    except:
+        full_text= ""
+    
+    ## Extract infos
+    # DOI
+    unverified_doi = find_doi(full_text)
+    doi = ""
+    #only if a doi is found
+    if unverified_doi:
+        if verify_doi(unverified_doi):
+            #If DOI is found, write it in "doi" column instead of 'unverified_doi' column.
+            doi=unverified_doi
+            unverified_doi=""
+
+    # Article
+    item_editor =  get_caracs_between(full_text,"Description","Total Units").replace("\n"," ")
+    if item_editor != "":
+        item_editor = "Description: " + item_editor
+    
+    else:
+        item_editor =  get_caracs_between(full_text,"Description","Product ").replace("\n"," ")
+        if item_editor != "":
+            item_editor = "Description: " + item_editor
+
+
+    new_row = {'nom_complet': filename, 'doi': doi, 'unverified_doi':unverified_doi ,"item_editor":item_editor,'full_text': full_text}
+    df_res = pd.concat([df_res,pd.DataFrame([new_row])],ignore_index=True)
+
+df_res.to_csv(path_or_buf="%s/%s.csv"%(path_res,num_editor),index=False,header=True,encoding='utf-8',escapechar='\\')
diff --git a/editors-processing/0001062310.py b/editors-processing/0001062310.py
new file mode 100644
index 0000000..bb39759
--- /dev/null
+++ b/editors-processing/0001062310.py
@@ -0,0 +1,44 @@
+from global_functions import *
+import os
+import PyPDF2
+import pandas as pd
+
+num_editor = "0001062310"
+
+path = './factures-2021-2022-triees/%s' %num_editor
+
+path_res='./results'
+
+
+df_res = pd.DataFrame(columns=["nom_complet","doi","unverified_doi","item_editor","full_text"])
+
+res = []
+for filename in os.listdir(path):
+    file = os.path.join(path, filename)
+    # Read PDF as text
+    try:
+        reader = PyPDF2.PdfReader(file, strict=False)
+        full_text = read_all_page(reader)
+    except:
+        full_text= ""
+    
+    ## Extract infos
+    # DOI
+    unverified_doi = find_doi(full_text)
+    doi = ""
+    #only if a doi is found
+    if unverified_doi:
+        if verify_doi(unverified_doi):
+            #If DOI is found, write it in "doi" column instead of 'unverified_doi' column.
+            doi=unverified_doi
+            unverified_doi=""
+
+    # Article
+    item_editor =  get_caracs_between(full_text,"Amount","Processing Charge").replace("\n"," ")
+    if item_editor != "":
+        item_editor = "Article Number + Title of Manuscript: " + item_editor
+
+    new_row = {'nom_complet': filename, 'doi': doi, 'unverified_doi':unverified_doi ,"item_editor":item_editor,'full_text': full_text}
+    df_res = pd.concat([df_res,pd.DataFrame([new_row])],ignore_index=True)
+
+df_res.to_csv(path_or_buf="%s/%s.csv"%(path_res,num_editor),index=False,header=True,encoding='utf-8',escapechar='\\')
diff --git a/editors-processing/0001079074.py b/editors-processing/0001079074.py
new file mode 100644
index 0000000..7470402
--- /dev/null
+++ b/editors-processing/0001079074.py
@@ -0,0 +1,42 @@
+from global_functions import *
+import os
+import PyPDF2
+import pandas as pd
+
+num_editor = "0001079074"
+path = './factures-2021-2022-triees/%s' %num_editor
+path_res='./results'
+df_res = pd.DataFrame(columns=["nom_complet","doi","unverified_doi","item_editor","full_text"])
+
+res = []
+for filename in os.listdir(path):
+    file = os.path.join(path, filename)
+    # Read PDF as text
+    try:
+        reader = PyPDF2.PdfReader(file, strict=False)
+        full_text = read_all_page(reader)
+    except:
+        full_text= ""
+    
+    #Extract infos
+    # DOI
+    unverified_doi = find_doi(full_text)
+    doi = ""
+    #only if a doi is found
+    if unverified_doi:
+        if verify_doi(unverified_doi):
+            #If DOI is found, write it in "doi" column instead of 'unverified_doi' column.
+            doi=unverified_doi
+            unverified_doi=""
+
+
+    # propre à l'éditeur
+    item_editor = get_caracs_between(full_text,"Article:","Tax").replace("\n"," ")   
+    if item_editor != "":
+        item_editor = "Article: " + item_editor
+    
+    
+    new_row = {'nom_complet': filename, 'doi': doi, 'unverified_doi':unverified_doi ,'item_editor':item_editor,'full_text': full_text} #HERE ADD
+    df_res = pd.concat([df_res,pd.DataFrame([new_row])],ignore_index=True)
+
+df_res.to_csv(path_or_buf="%s/%s.csv"%(path_res,num_editor),index=False,header=True,encoding='utf-8',escapechar='\\')
diff --git a/editors-processing/0001090050.py b/editors-processing/0001090050.py
new file mode 100644
index 0000000..4c122d7
--- /dev/null
+++ b/editors-processing/0001090050.py
@@ -0,0 +1,44 @@
+from global_functions import *
+import os
+import PyPDF2
+import pandas as pd
+
+num_editor = "0001090050"
+
+path = './factures-2021-2022-triees/%s' %num_editor
+
+path_res='./results'
+
+
+df_res = pd.DataFrame(columns=["nom_complet","doi","unverified_doi","item_editor","full_text"])
+
+res = []
+for filename in os.listdir(path):
+    file = os.path.join(path, filename)
+    # Read PDF as text
+    try:
+        reader = PyPDF2.PdfReader(file, strict=False)
+        full_text = read_all_page(reader)
+    except:
+        full_text= ""
+    
+    ## Extract infos
+    # DOI
+    unverified_doi = find_doi(full_text)
+    doi = ""
+    #only if a doi is found
+    if unverified_doi:
+        if verify_doi(unverified_doi):
+            #If DOI is found, write it in "doi" column instead of 'unverified_doi' column.
+            doi=unverified_doi
+            unverified_doi=""
+
+    # Article
+    item_editor =  get_caracs_between(full_text,"Manuscript","\n").replace("\n"," ")
+    if item_editor != "":
+        item_editor = "Manuscript: " + item_editor
+
+    new_row = {'nom_complet': filename, 'doi': doi, 'unverified_doi':unverified_doi ,"item_editor":item_editor,'full_text': full_text}
+    df_res = pd.concat([df_res,pd.DataFrame([new_row])],ignore_index=True)
+
+df_res.to_csv(path_or_buf="%s/%s.csv"%(path_res,num_editor),index=False,header=True,encoding='utf-8',escapechar='\\')
diff --git a/editors-processing/0001091455.py b/editors-processing/0001091455.py
new file mode 100644
index 0000000..f5c834b
--- /dev/null
+++ b/editors-processing/0001091455.py
@@ -0,0 +1,44 @@
+from global_functions import *
+import os
+import PyPDF2
+import pandas as pd
+
+num_editor = "0001091455"
+
+path = './factures-2021-2022-triees/%s' %num_editor
+
+path_res='./results'
+
+
+df_res = pd.DataFrame(columns=["nom_complet","doi","unverified_doi","item_editor","full_text"])
+
+res = []
+for filename in os.listdir(path):
+    file = os.path.join(path, filename)
+    # Read PDF as text
+    try:
+        reader = PyPDF2.PdfReader(file, strict=False)
+        full_text = read_all_page(reader)
+    except:
+        full_text= ""
+    
+    ## Extract infos
+    # DOI
+    unverified_doi = find_doi(full_text)
+    doi = ""
+    #only if a doi is found
+    if unverified_doi:
+        if verify_doi(unverified_doi):
+            #If DOI is found, write it in "doi" column instead of 'unverified_doi' column.
+            doi=unverified_doi
+            unverified_doi=""
+
+    # Article
+    item_editor =  get_caracs_between(full_text,"Item","Total").replace("\n"," ")
+    if item_editor != "":
+        item_editor = "Item: " + item_editor
+
+    new_row = {'nom_complet': filename, 'doi': doi, 'unverified_doi':unverified_doi ,"item_editor":item_editor,'full_text': full_text}
+    df_res = pd.concat([df_res,pd.DataFrame([new_row])],ignore_index=True)
+
+df_res.to_csv(path_or_buf="%s/%s.csv"%(path_res,num_editor),index=False,header=True,encoding='utf-8',escapechar='\\')
diff --git a/editors-processing/0001097617.py b/editors-processing/0001097617.py
new file mode 100644
index 0000000..6500aeb
--- /dev/null
+++ b/editors-processing/0001097617.py
@@ -0,0 +1,44 @@
+from global_functions import *
+import os
+import PyPDF2
+import pandas as pd
+
+num_editor = "0001097617"
+
+path = './factures-2021-2022-triees/%s' %num_editor
+
+path_res='./results'
+
+
+df_res = pd.DataFrame(columns=["nom_complet","doi","unverified_doi","item_editor","full_text"])
+
+res = []
+for filename in os.listdir(path):
+    file = os.path.join(path, filename)
+    # Read PDF as text
+    try:
+        reader = PyPDF2.PdfReader(file, strict=False)
+        full_text = read_all_page(reader)
+    except:
+        full_text= ""
+    
+    ## Extract infos
+    # DOI
+    unverified_doi = find_doi(full_text)
+    doi = ""
+    #only if a doi is found
+    if unverified_doi:
+        if verify_doi(unverified_doi):
+            #If DOI is found, write it in "doi" column instead of 'unverified_doi' column.
+            doi=unverified_doi
+            unverified_doi=""
+
+    # Article
+    item_editor =  get_caracs_between(full_text,"","").replace("\n"," ")
+    if item_editor != "":
+        item_editor = "Title: " + item_editor
+
+    new_row = {'nom_complet': filename, 'doi': doi, 'unverified_doi':unverified_doi ,"item_editor":item_editor,'full_text': full_text}
+    df_res = pd.concat([df_res,pd.DataFrame([new_row])],ignore_index=True)
+
+df_res.to_csv(path_or_buf="%s/%s.csv"%(path_res,num_editor),index=False,header=True,encoding='utf-8',escapechar='\\')
diff --git a/editors-processing/0001157725.py b/editors-processing/0001157725.py
new file mode 100644
index 0000000..7e6c8f7
--- /dev/null
+++ b/editors-processing/0001157725.py
@@ -0,0 +1,44 @@
+from global_functions import *
+import os
+import PyPDF2
+import pandas as pd
+
+num_editor = "0001157725"
+
+path = './factures-2021-2022-triees/%s' %num_editor
+
+path_res='./results'
+
+
+df_res = pd.DataFrame(columns=["nom_complet","doi","unverified_doi","item_editor","full_text"])
+
+res = []
+for filename in os.listdir(path):
+    file = os.path.join(path, filename)
+    # Read PDF as text
+    try:
+        reader = PyPDF2.PdfReader(file, strict=False)
+        full_text = read_all_page(reader)
+    except:
+        full_text= ""
+    
+    ## Extract infos
+    # DOI
+    unverified_doi = find_doi(full_text)
+    doi = ""
+    #only if a doi is found
+    if unverified_doi:
+        if verify_doi(unverified_doi):
+            #If DOI is found, write it in "doi" column instead of 'unverified_doi' column.
+            doi=unverified_doi
+            unverified_doi=""
+
+    # Article
+    item_editor =  get_caracs_between(full_text,"Journal Name","DOI").replace("\n"," ")
+    if item_editor != "":
+        item_editor = "Description: " + item_editor
+
+    new_row = {'nom_complet': filename, 'doi': doi, 'unverified_doi':unverified_doi ,"item_editor":item_editor,'full_text': full_text}
+    df_res = pd.concat([df_res,pd.DataFrame([new_row])],ignore_index=True)
+
+df_res.to_csv(path_or_buf="%s/%s.csv"%(path_res,num_editor),index=False,header=True,encoding='utf-8',escapechar='\\')
diff --git a/editors-processing/0001197861.py b/editors-processing/0001197861.py
new file mode 100644
index 0000000..93bd46d
--- /dev/null
+++ b/editors-processing/0001197861.py
@@ -0,0 +1,44 @@
+from global_functions import *
+import os
+import PyPDF2
+import pandas as pd
+
+num_editor = "0001197861"
+
+path = './factures-2021-2022-triees/%s' %num_editor
+
+path_res='./results'
+
+
+df_res = pd.DataFrame(columns=["nom_complet","doi","unverified_doi","item_editor","full_text"])
+
+res = []
+for filename in os.listdir(path):
+    file = os.path.join(path, filename)
+    # Read PDF as text
+    try:
+        reader = PyPDF2.PdfReader(file, strict=False)
+        full_text = read_all_page(reader)
+    except:
+        full_text= ""
+    
+    ## Extract infos
+    # DOI
+    unverified_doi = find_doi(full_text)
+    doi = ""
+    #only if a doi is found
+    if unverified_doi:
+        if verify_doi(unverified_doi):
+            #If DOI is found, write it in "doi" column instead of 'unverified_doi' column.
+            doi=unverified_doi
+            unverified_doi=""
+
+    # Article
+    item_editor =  get_caracs_between(full_text,"Description","Net Value")
+    if item_editor != "":
+        item_editor = "Description: " + item_editor
+
+    new_row = {'nom_complet': filename, 'doi': doi, 'unverified_doi':unverified_doi ,"item_editor":item_editor,'full_text': full_text}
+    df_res = pd.concat([df_res,pd.DataFrame([new_row])],ignore_index=True)
+
+df_res.to_csv(path_or_buf="%s/%s.csv"%(path_res,num_editor),index=False,header=True,encoding='utf-8',escapechar='\\')
diff --git a/editors-processing/0001200930.py b/editors-processing/0001200930.py
new file mode 100644
index 0000000..1d06086
--- /dev/null
+++ b/editors-processing/0001200930.py
@@ -0,0 +1,48 @@
+from global_functions import *
+import os
+import PyPDF2
+import pandas as pd
+
+num_editor = "0001200930"
+
+# path = './test/%s' %num_editor
+path = './factures-2021-2022-triees/%s' %num_editor
+
+# path_res='./test-results'
+path_res='./results'
+
+
+df_res = pd.DataFrame(columns=["nom_complet","doi","unverified_doi","item_editor","full_text"])
+
+res = []
+for filename in os.listdir(path):
+    file = os.path.join(path, filename)
+    # Read PDF as text
+    try:
+        reader = PyPDF2.PdfReader(file, strict=False)
+        full_text = read_all_page(reader)
+    except:
+        full_text= ""
+    
+    ## Extract infos
+    # DOI
+    unverified_doi = find_doi(full_text)
+    doi = ""
+    #only if a doi is found
+    if unverified_doi:
+        if verify_doi(unverified_doi):
+            #If DOI is found, write it in "doi" column instead of 'unverified_doi' column.
+            doi=unverified_doi
+            unverified_doi=""
+
+
+    # Article
+    item_editor =  get_caracs_between(full_text,'"','"').replace("\n"," ")
+    if item_editor != "":
+        item_editor = "Article Title: " + item_editor
+        
+        
+    new_row = {'nom_complet': filename, 'doi': doi, 'unverified_doi':unverified_doi ,"item_editor":item_editor,'full_text': full_text}
+    df_res = pd.concat([df_res,pd.DataFrame([new_row])],ignore_index=True)
+
+df_res.to_csv(path_or_buf="%s/%s.csv"%(path_res,num_editor),index=False,header=True,encoding='utf-8',escapechar='\\')
diff --git a/editors-processing/0001217181.py b/editors-processing/0001217181.py
new file mode 100644
index 0000000..ab91666
--- /dev/null
+++ b/editors-processing/0001217181.py
@@ -0,0 +1,42 @@
+from global_functions import *
+import os
+import PyPDF2
+import pandas as pd
+
+num_editor = "0001217181"
+path = './factures-2021-2022-triees/%s' %num_editor
+path_res='./results'
+df_res = pd.DataFrame(columns=["nom_complet","doi","unverified_doi","item_editor","full_text"])
+
+res = []
+for filename in os.listdir(path):
+    file = os.path.join(path, filename)
+    # Read PDF as text
+    try:
+        reader = PyPDF2.PdfReader(file, strict=False)
+        full_text = read_all_page(reader)
+    except:
+        full_text= ""
+    
+    ## Extract infos
+    # DOI
+    unverified_doi = find_doi(full_text)
+    doi = ""
+    #only if a doi is found
+    if unverified_doi:
+        if verify_doi(unverified_doi):
+            #If DOI is found, write it in "doi" column instead of 'unverified_doi' column.
+            doi=unverified_doi
+            unverified_doi=""
+
+
+    # Article
+    item_editor =  get_caracs_between(full_text,"Title","published in").replace("\n"," ")
+    if item_editor != "":
+        item_editor = "Title: " + item_editor
+
+
+    new_row = {'nom_complet': filename, 'doi': doi, 'unverified_doi':unverified_doi,"item_editor":item_editor,'full_text': full_text}
+    df_res = pd.concat([df_res,pd.DataFrame([new_row])],ignore_index=True)
+
+df_res.to_csv(path_or_buf="%s/%s.csv"%(path_res,num_editor),index=False,header=True,encoding='utf-8',escapechar='\\')
diff --git a/editors-processing/0001222959.py b/editors-processing/0001222959.py
new file mode 100644
index 0000000..a51d561
--- /dev/null
+++ b/editors-processing/0001222959.py
@@ -0,0 +1,44 @@
+from global_functions import *
+import os
+import PyPDF2
+import pandas as pd
+
+num_editor = "0001222959"
+
+path = './factures-2021-2022-triees/%s' %num_editor
+
+path_res='./results'
+
+
+df_res = pd.DataFrame(columns=["nom_complet","doi","unverified_doi","item_editor","full_text"])
+
+res = []
+for filename in os.listdir(path):
+    file = os.path.join(path, filename)
+    # Read PDF as text
+    try:
+        reader = PyPDF2.PdfReader(file, strict=False)
+        full_text = read_all_page(reader)
+    except:
+        full_text= ""
+    
+    ## Extract infos
+    # DOI
+    unverified_doi = find_doi(full_text)
+    doi = ""
+    #only if a doi is found
+    if unverified_doi:
+        if verify_doi(unverified_doi):
+            #If DOI is found, write it in "doi" column instead of 'unverified_doi' column.
+            doi=unverified_doi
+            unverified_doi=""
+
+    # Article
+    item_editor =  get_caracs_between(full_text,"Manuscript ID","Net Value").replace("\n"," ")
+    if item_editor != "":
+        item_editor = "Manuscript ID: " + item_editor
+
+    new_row = {'nom_complet': filename, 'doi': doi, 'unverified_doi':unverified_doi ,"item_editor":item_editor,'full_text': full_text}
+    df_res = pd.concat([df_res,pd.DataFrame([new_row])],ignore_index=True)
+
+df_res.to_csv(path_or_buf="%s/%s.csv"%(path_res,num_editor),index=False,header=True,encoding='utf-8',escapechar='\\')
diff --git a/editors-processing/0001226137.py b/editors-processing/0001226137.py
new file mode 100644
index 0000000..75c2cdc
--- /dev/null
+++ b/editors-processing/0001226137.py
@@ -0,0 +1,47 @@
+from global_functions import *
+import os
+import PyPDF2
+import pandas as pd
+
+num_editor = "0001226137"
+
+path = './factures-2021-2022-triees/%s' %num_editor
+
+path_res='./results'
+
+
+df_res = pd.DataFrame(columns=["nom_complet","doi","unverified_doi","item_editor","full_text"])
+
+res = []
+for filename in os.listdir(path):
+    file = os.path.join(path, filename)
+    # Read PDF as text
+    try:
+        reader = PyPDF2.PdfReader(file, strict=False)
+        full_text = read_all_page(reader)
+    except:
+        full_text= ""
+    
+    ## Extract infos
+    # DOI
+    unverified_doi = find_doi(full_text)
+    doi = ""
+    #only if a doi is found
+    if unverified_doi:
+        if verify_doi(unverified_doi):
+            #If DOI is found, write it in "doi" column instead of 'unverified_doi' column.
+            doi=unverified_doi
+            unverified_doi=""
+
+    # Article
+    item_editor =  get_caracs_between(full_text,"Title","Author").replace("\n"," ")
+    if item_editor != "":
+        item_editor = "Article Title: " + item_editor
+    
+    is_oa = get_caracs_between(full_text,"Item Description","Total Amount").replace("\n"," ")
+    item_editor = item_editor + "\nItem Description :" + is_oa
+
+    new_row = {'nom_complet': filename, 'doi': doi, 'unverified_doi':unverified_doi ,"item_editor":item_editor,'full_text': full_text}
+    df_res = pd.concat([df_res,pd.DataFrame([new_row])],ignore_index=True)
+
+df_res.to_csv(path_or_buf="%s/%s.csv"%(path_res,num_editor),index=False,header=True,encoding='utf-8',escapechar='\\')
diff --git a/editors-processing/0001234181.py b/editors-processing/0001234181.py
new file mode 100644
index 0000000..7a0943a
--- /dev/null
+++ b/editors-processing/0001234181.py
@@ -0,0 +1,44 @@
+from global_functions import *
+import os
+import PyPDF2
+import pandas as pd
+
+num_editor = "0001234181"
+
+path = './factures-2021-2022-triees/%s' %num_editor
+
+path_res='./results'
+
+
+df_res = pd.DataFrame(columns=["nom_complet","doi","unverified_doi","item_editor","full_text"])
+
+res = []
+for filename in os.listdir(path):
+    file = os.path.join(path, filename)
+    # Read PDF as text
+    try:
+        reader = PyPDF2.PdfReader(file, strict=False)
+        full_text = read_all_page(reader)
+    except:
+        full_text= ""
+    
+    ## Extract infos
+    # DOI
+    unverified_doi = find_doi(full_text)
+    doi = ""
+    #only if a doi is found
+    if unverified_doi:
+        if verify_doi(unverified_doi):
+            #If DOI is found, write it in "doi" column instead of 'unverified_doi' column.
+            doi=unverified_doi
+            unverified_doi=""
+
+    # Article
+    item_editor =  get_caracs_between(full_text,"","").replace("\n"," ")
+    if item_editor != "":
+        item_editor = "Title: " + item_editor
+
+    new_row = {'nom_complet': filename, 'doi': doi, 'unverified_doi':unverified_doi ,"item_editor":item_editor,'full_text': full_text}
+    df_res = pd.concat([df_res,pd.DataFrame([new_row])],ignore_index=True)
+
+df_res.to_csv(path_or_buf="%s/%s.csv"%(path_res,num_editor),index=False,header=True,encoding='utf-8',escapechar='\\')
diff --git a/editors-processing/autres.py b/editors-processing/autres.py
new file mode 100644
index 0000000..8dbd11c
--- /dev/null
+++ b/editors-processing/autres.py
@@ -0,0 +1,34 @@
+from global_functions import *
+import os
+import PyPDF2
+import pandas as pd
+
+path = './factures-2021-2022-triees/autres'
+path_res='./results'
+df_res = pd.DataFrame(columns=["nom_complet","doi","unverified_doi","full_text"])
+
+res = []
+for filename in os.listdir(path):
+    file = os.path.join(path, filename)
+    # Read PDF as text
+    try:
+        reader = PyPDF2.PdfReader(file, strict=False)
+        full_text = read_all_page(reader)
+    except:
+        full_text= ""
+    
+    #Extract infos
+    unverified_doi = find_doi(full_text)
+    doi = ""
+    #only if a doi is found
+    if unverified_doi:
+        if verify_doi(unverified_doi):
+            #If DOI is found, write it in "doi" column instead of 'unverified_doi' column.
+            doi=unverified_doi
+            unverified_doi=""
+
+
+    new_row = {'nom_complet': filename, 'doi': doi, 'unverified_doi':unverified_doi ,'full_text': full_text}
+    df_res = pd.concat([df_res,pd.DataFrame([new_row])],ignore_index=True)
+
+df_res.to_csv(path_or_buf="%s/autres-sorted.csv"%path_res,index=False,header=True,encoding='utf-8',escapechar='\\')
\ No newline at end of file
diff --git a/editors-processing/global_functions.py b/editors-processing/global_functions.py
new file mode 100644
index 0000000..de6cb82
--- /dev/null
+++ b/editors-processing/global_functions.py
@@ -0,0 +1,90 @@
+import re
+from requests_ratelimiter import LimiterSession
+
+mail_adress = "[prefix_mail]@[domaine].[fr|com]"
+session = LimiterSession(per_second=5)
+
+def find_doi(text):
+    """
+    return the first doi found in a text (input)
+    """
+    doiRegex = r'\b10.\d{4,}\/[^\s]+\b'
+    doi = re.search(doiRegex, text)
+    if doi == None:
+        return ""
+    try:
+        doiStr = doi.group()
+        return doiStr
+    except:
+        return ""
+    
+def verify_doi(doi,mail=mail_adress):
+    """
+    check with crossref api if doi is correct.
+    """
+    url = f"https://api.crossref.org/works/{doi}/agency?mailto={mail}"
+
+    # Return True if DOI exists in crossref api
+    code_response = session.get(url).status_code
+    return code_response == 200
+
+
+def read_all_page(reader):
+    """
+    for a reader, return all his page separate with "\n" in str format
+    """
+    text= ""
+    lenPages = len(reader.pages)
+    for i in range(lenPages):
+        #transform page into text
+        text+= reader.pages[i].extract_text()
+        text+= "\n"
+    return text
+
+
+def get_caracs_between(chaine, debut, fin):
+    """return a string between to string "debut" "fin"
+
+    Args:
+        chaine (str): search in
+        debut (str): beginning of the string
+        fin (str): ending
+
+    Returns:
+        str: string
+    """
+    # Use regex
+    motif = re.escape(debut) + "(.*?)" + re.escape(fin)
+    resultat = re.search(motif, chaine,re.DOTALL)
+
+    if resultat:
+        contenu_entre_chaines = resultat.group(1)
+        return contenu_entre_chaines
+    else:
+        return ""
+    
+import re
+
+def get_caracs_between_multiple(chaine, debuts, fins):
+    """return a string between uncertenly beginning or ending
+
+    Args:
+        chaine (_str_): input text
+        debuts (_list_): list of possibles begins
+        fins (_list_): list of possibles endings
+
+    Returns:
+        _str_: caracters between begins,ends. Can take multiple ends/begins !
+    """
+    motifs = [re.escape(debut) + "(.*?)" + re.escape(fin) for debut, fin in zip(debuts, fins)]
+
+    global_regex = "|".join(motifs)
+
+    resultat = re.search(global_regex, chaine,re.DOTALL)
+
+    # Vérifier si la correspondance a été trouvée
+    if resultat:
+        contenu_entre_chaines = resultat.group(1)
+        return contenu_entre_chaines
+    else:
+        return ""
diff --git a/metric-data.py b/metric-data.py
new file mode 100644
index 0000000..4337425
--- /dev/null
+++ b/metric-data.py
@@ -0,0 +1,18 @@
+from pathlib import Path
+
+path_bills = "factures-2021-2022"
+
+#fonction qui classe les PDFs par editeur
+def metrics_editors(path):
+    dic_stats = {}
+    files = Path('./%s/' %path).glob('*')
+    for file in files:
+        code_editor=str(file).split("_")[1]
+        if code_editor not in dic_stats:
+            dic_stats[code_editor]=1
+        else :
+            dic_stats[code_editor]+=1
+    return dict(sorted(dic_stats.items(), key=lambda item:item[1]))
+
+
+print(metrics_editors(path=path_bills))
\ No newline at end of file
diff --git a/to_do.xlsx b/to_do.xlsx
new file mode 100644
index 0000000..4016360
--- /dev/null
+++ b/to_do.xlsx
Binary files differ
diff --git a/tri-factures.py b/tri-factures.py
new file mode 100644
index 0000000..894ad64
--- /dev/null
+++ b/tri-factures.py
@@ -0,0 +1,35 @@
+import shutil
+from pathlib import Path
+import os
+import json
+
+path_bills = "factures-2021-2022"
+path_bills_output = "factures-2021-2022-triees"
+"""
+Notice d'utilisation
+ATTENTION : Les dossier d'entrée et de sortie ne doivent PAS CONTENIR de "_" : c'est réservé pour les noms de fichier pdf des factures.
+
+Ce programme permet de trier un dossier de facture par code fournisseur
+Si le code fournisseur n'est pas dans la liste id_editor2editor, ne peut être traité de manière automatique.
+"""
+#address path to datas (pdf only)
+with open('./dictionaries/code_fournisseur2fournisseur.json','r') as f_in:
+    id_editor2editor = json.load(f_in)
+
+#fonction utilitaire pour classEditors qui copie le fichier PDF dans un repository dans son code editeur.
+def copyItIn(file,repository,global_path='./%s' %path_bills_output):
+    if not os.path.exists('%s/%s' % (global_path,repository) ):
+        os.makedirs('%s/%s' % (global_path,repository) )
+    shutil.copy(file, '%s/%s' % (global_path,repository) )
+
+
+# classe les PDFs par editeur
+
+files = Path('./%s/' %path_bills).glob('*')
+for file in files:
+    code_editor=str(file).split("_")[1]
+    if code_editor in id_editor2editor.keys():
+        copyItIn(file,code_editor)
+    else:
+        copyItIn(file,'autres')
+