13 Commits

Author SHA1 Message Date
6e0ffe9085 core: change pandas version 2024-10-16 06:47:55 +02:00
ab2fdb0541 Feat: make from_pdf importable and move plumber in it 2024-10-16 06:47:25 +02:00
0fc39ed317 Merge pull request 'Update dependency MarkupSafe to v2.1.5' (#17) from renovate/markupsafe-2.x into main
Reviewed-on: #17
2024-02-17 05:08:19 +00:00
a6d6681756 Merge branch 'main' into renovate/markupsafe-2.x 2024-02-17 05:08:08 +00:00
4eecb3a44c Merge pull request 'Update dependency Jinja2 to v3.1.3' (#16) from renovate/jinja2-3.x into main
Reviewed-on: #16
2024-02-17 05:07:48 +00:00
60da623323 Update dependency MarkupSafe to v2.1.5 2024-02-17 05:04:52 +00:00
1f1e3e2741 Update dependency Jinja2 to v3.1.3 2024-02-17 05:04:48 +00:00
2b3e935f39 Merge pull request 'Update dependency Send2Trash to v1.8.2' (#15) from renovate/send2trash-1.x into main
Reviewed-on: #15
2024-02-17 04:56:16 +00:00
ef63f22d44 Merge pull request 'Update dependency MarkupSafe to v2.1.3' (#14) from renovate/markupsafe-2.x into main
Reviewed-on: #14
2024-02-17 04:55:55 +00:00
1020ef9257 Update dependency Send2Trash to v1.8.2 2024-01-10 11:04:32 +00:00
39084ceebd Update dependency MarkupSafe to v2.1.3 2024-01-10 11:04:30 +00:00
7de6c8dd9c clean renovate.json 2024-01-10 10:46:45 +00:00
da3815eea6 activate renovate 2024-01-09 06:53:09 +00:00
6 changed files with 1859 additions and 1158 deletions

View File

@@ -0,0 +1 @@
from .extract import from_pdf

View File

@@ -38,8 +38,9 @@ def catch_malformed_table(tables):
return tables[0] return tables[0]
def from_pdf(pdf): def from_pdf(pdf_file):
"""Build dataframes one about charges and another on loc""" """Build dataframes one about charges and another on loc"""
pdf = pdfplumber.open(pdf_file)
recapitulatif_tables = [] recapitulatif_tables = []
loc_tables = [] loc_tables = []
charge_tables = [] charge_tables = []
@@ -90,8 +91,7 @@ def extract_save(pdf_file, dest):
xls_charge = Path(dest) / f"{pdf_file.stem.replace(' ', '_')}_charge.xlsx" xls_charge = Path(dest) / f"{pdf_file.stem.replace(' ', '_')}_charge.xlsx"
xls_locataire = Path(dest) / f"{pdf_file.stem.replace(' ', '_')}_locataire.xlsx" xls_locataire = Path(dest) / f"{pdf_file.stem.replace(' ', '_')}_locataire.xlsx"
pdf = pdfplumber.open(pdf_file) df_charge, df_loc = from_pdf(pdf_file)
df_charge, df_loc = from_pdf(pdf)
df_charge.to_excel(xls_charge, sheet_name="Charges", index=False) df_charge.to_excel(xls_charge, sheet_name="Charges", index=False)
logging.info(f"{xls_charge} saved") logging.info(f"{xls_charge} saved")

2927
poetry.lock generated

File diff suppressed because it is too large Load Diff

View File

@@ -13,7 +13,7 @@ pdf-oralia = "pdf_oralia.scripts:main"
python = "^3.10" python = "^3.10"
click = "^8.1.3" click = "^8.1.3"
pdfplumber = "^0.7.4" pdfplumber = "^0.7.4"
pandas = "^1.5.0" pandas = "^2.2.3"
openpyxl = "^3.0.10" openpyxl = "^3.0.10"

2
renovate.json Normal file
View File

@@ -0,0 +1,2 @@
{
}

View File

@@ -1,76 +1,3 @@
argon2-cffi==21.3.0 pdfplumber
argon2-cffi-bindings==21.2.0 numpy
asttokens==2.0.8 pandas
attrs==22.1.0
backcall==0.2.0
beautifulsoup4==4.11.1
bleach==5.0.1
cffi==1.15.1
charset-normalizer==2.1.1
cryptography==38.0.1
debugpy==1.6.3
decorator==5.1.1
defusedxml==0.7.1
entrypoints==0.4
et-xmlfile==1.1.0
executing==1.1.0
fastjsonschema==2.16.2
ipykernel==6.16.0
ipython==8.5.0
ipython-genutils==0.2.0
ipywidgets==8.0.2
jedi==0.18.1
Jinja2==3.1.2
jsonschema==4.16.0
jupyter==1.0.0
jupyter-console==6.4.4
jupyter-core==4.11.1
jupyter_client==7.3.5
jupyterlab-pygments==0.2.2
jupyterlab-widgets==3.0.3
lxml==4.9.1
MarkupSafe==2.1.1
matplotlib-inline==0.1.6
mistune==2.0.4
nbclient==0.6.8
nbconvert==7.0.0
nbformat==5.6.1
nest-asyncio==1.5.5
notebook==6.4.12
numpy==1.23.3
openpyxl==3.0.10
packaging==21.3
pandas==1.5.0
pandocfilters==1.5.0
parso==0.8.3
pdfminer.six==20220524
pdfplumber==0.7.4
pexpect==4.8.0
pickleshare==0.7.5
Pillow==9.2.0
prometheus-client==0.14.1
prompt-toolkit==3.0.31
psutil==5.9.2
ptyprocess==0.7.0
pure-eval==0.2.2
pycparser==2.21
Pygments==2.13.0
pyparsing==3.0.9
pyrsistent==0.18.1
python-dateutil==2.8.2
pytz==2022.2.1
pyzmq==24.0.1
qtconsole==5.3.2
QtPy==2.2.0
Send2Trash==1.8.0
six==1.16.0
soupsieve==2.3.2.post1
stack-data==0.5.1
terminado==0.15.0
tinycss2==1.1.1
tornado==6.2
traitlets==5.4.0
Wand==0.6.10
wcwidth==0.2.5
webencodings==0.5.1
widgetsnbextension==4.0.3