comparison facturation.py @ 8:e62e3b548b7e draft default tip

"planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/facturation_ibps commit 07c73df696d6d80e03f03232603d713882131625"

7:b8460b9f4253

# -*- coding: utf-8 -*-


import argparse
import re

import openpyxl

import pandas as pd


def Parser():
    the_parser = argparse.ArgumentParser()
    the_parser.add_argument('--input', '-i', action='store', type=str,

def main(template, input_file, output_file, reduction):
    """Script de parsing des fichiers de facturation de l'IBPS"""

    # ouverture fichier input
    with open(input_file, 'r') as file_object:
        facture_html = file_object.read()
    # convert to unicode utf-8, remove &nbsp and €
    facture_html = facture_html.decode('utf-8')
    facture_html = facture_html.replace(r' ', r' ')
    facture_html = facture_html.replace(r' €', '')
    facture_html = facture_html.replace(u' \u20ac', '')
    # parsing de la référence, de la date et de la période de facturation
    date = re.search(r'Paris le (.*?)</p>'.decode('utf-8'),
                     facture_html).group(1)
    periode = re.search(r'de la prestation (.*?)</p>'.decode('utf-8'),
                        facture_html).group(1)
    ref = re.search(r'rence interne d.*? :\s*(.*?)<'.decode('utf-8'),
                    facture_html).group(1)

    # parsing des tableaux html avec pandas
    facture_parsed = pd.read_html(
        facture_html,

    elements[u'nombre(s)'] = pd.to_numeric(elements[u'nombre(s)'])
    elements[cout_col] = pd.to_numeric(elements[cout_col])

    # ouverture fichier output
    facture_output = openpyxl.load_workbook(
        template, data_only=False, keep_vba=False)
    ws = facture_output.worksheets[0]

    # rajout de l'image de SU qui ne survit pas à la conversion
    img = openpyxl.drawing.image.Image('template_SU.jpg')
    img.anchor = "A1"

8:e62e3b548b7e

# -*- coding: utf-8 -*-


import argparse
import re
import warnings

import openpyxl

import pandas as pd


warnings.filterwarnings("ignore")


def Parser():
    the_parser = argparse.ArgumentParser()
    the_parser.add_argument('--input', '-i', action='store', type=str,

def main(template, input_file, output_file, reduction):
    """Script de parsing des fichiers de facturation de l'IBPS"""

    # ouverture fichier input
    with open(input_file, 'rb') as file_object:
        facture_html = file_object.read()
    # convert to unicode utf-8, remove &nbsp and €
    facture_html = facture_html.decode('utf-8')
    facture_html = facture_html.replace(r' ', r' ')
    facture_html = facture_html.replace(r' €', '')
    facture_html = facture_html.replace(u' \u20ac', '')
    # parsing de la référence, de la date et de la période de facturation
    date = re.search(r'Paris le (.*?)</p>',
                     facture_html).group(1)
    periode = re.search(r'de la prestation (.*?)</p>',
                        facture_html).group(1)
    ref = re.search(r'rence interne d.*? :\s*(.*?)<',
                    facture_html).group(1)

    # parsing des tableaux html avec pandas
    facture_parsed = pd.read_html(
        facture_html,

    elements[u'nombre(s)'] = pd.to_numeric(elements[u'nombre(s)'])
    elements[cout_col] = pd.to_numeric(elements[cout_col])

    # ouverture fichier output
    facture_output = openpyxl.load_workbook(
        template, data_only='True', keep_vba=False)
    ws = facture_output.worksheets[0]

    # rajout de l'image de SU qui ne survit pas à la conversion
    img = openpyxl.drawing.image.Image('template_SU.jpg')
    img.anchor = "A1"