lafrite/pdf_auralia
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects 1 Releases Wiki Activity

I9_juillet23 #10

Merged
lafrite merged 2 commits from I9_juillet23 into main 2023-09-20 07:32:01 +00:00
Conversation 0 Commits 2 Files Changed 2 +6 -3
2 changed files with 6 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
pdf_oralia/extract.py
View File

@ -45,7 +45,7 @@ def from_pdf(pdf):
charge_tables = [] charge_tables = []
patrimoie_tables = [] patrimoie_tables = []
for page in pdf.pages: for page_number, page in enumerate(pdf.pages):
page_text = page.extract_text() page_text = page.extract_text()
date = extract_date(page_text) date = extract_date(page_text)
additionnal_fields = { additionnal_fields = {
@ -76,7 +76,7 @@ def from_pdf(pdf):
pass pass
else: else:
raise ValueError("Page non reconnu") logging.warning(f"Page {page_number+1} non reconnu. Page ignorée.")
df_charge = charge.table2df(recapitulatif_tables + charge_tables) df_charge = charge.table2df(recapitulatif_tables + charge_tables)
df_loc = locataire.table2df(loc_tables) df_loc = locataire.table2df(loc_tables)

3
pdf_oralia/pages/charge.py
View File

@ -32,7 +32,10 @@ def is_it(page_text):
def get_lot(txt): def get_lot(txt):
"""Return lot number from "RECAPITULATIF DES OPERATIONS" """ """Return lot number from "RECAPITULATIF DES OPERATIONS" """
regex = r"[BSM](\d+)(?=\s*-)" regex = r"[BSM](\d+)(?=\s*-)"
try:
result = re.findall(regex, txt) result = re.findall(regex, txt)
except TypeError:
return "*"
if result: if result:
return "{:02d}".format(int(result[0])) return "{:02d}".format(int(result[0]))
return "*" return "*"