yemekhanejson/yemekhanejson.py

#!/bin/python3


import subprocess, json
import urllib.request

days = ["Pazartesi","Salı","Çarşamba","Perşembe","Cuma","Cumartesi","Pazar"]

def main():

    urllib.request.urlretrieve('http://www.boun.edu.tr/Assets/Documents/Content/Public/kampus_hayati/yemek_listesi.pdf','yemek_listesi.pdf')

    pdfdata = subprocess.run(['pdftotext', '-layout', 'yemek_listesi.pdf', '-'],stdout=subprocess.PIPE)

    pdftext = pdfdata.stdout.decode('utf-8')
    
    
    pdftext = pdftext.splitlines()
    
    
    days_list = []
    
    for line in pdftext:
        for day in days:
            if day in line:

                day_index = pdftext.index(line)
                date_index = day_index - 2
                corba_index = date_index - 1
                line = line.strip().split()
                
                

                m_date = pdftext[date_index].strip().split()[0]
                m_day = pdftext[day_index].strip().split()[0]
               



                m_corba = list(filter(None, pdftext[corba_index].strip().split('        ')))
                m_corba = [x.strip() for x in m_corba]
                
                m_o_corba = None
                m_a_corba = None

                if not len(m_corba) == 0:
                    m_o_corba = m_corba[0]
                    if not len(m_corba) == 1:
                        m_a_corba = m_corba[1]



                m_ana = list(filter(None, pdftext[date_index].strip().split('  ')))
                m_ana = [x.strip() for x in m_ana]
              
                
                m_o_ana = None
                m_a_ana = None

                if not len(m_ana) == 1:
                    m_o_ana = m_ana[1]
                    if not len(m_ana) ==2:
                        m_a_ana = m_ana[2]


                m_vegan = list(filter(None, pdftext[date_index+1].strip().split('        ')))
                m_vegan = [x.strip() for x in m_vegan]
                
                m_o_vegan = None
                m_a_vegan = None

                if not len(m_vegan) == 0:
                    m_o_vegan = m_vegan[0]
                    if not len(m_vegan) == 1:
                        m_a_vegan = m_vegan[1]




                m_kar = list(filter(None, pdftext[day_index].strip().split('  ')))
                m_kar = [x.strip() for x in m_kar]
              
                
                m_o_kar = None
                m_a_kar = None

                if not len(m_kar) == 1:
                    m_o_kar = m_kar[1]
                    if not len(m_kar) ==2:
                        m_a_kar = m_kar[2]


                m_tat = list(filter(None, pdftext[day_index+1].strip().split('        ')))
                m_tat = [x.strip() for x in m_tat]
                
                m_o_tat = None
                m_a_tat = None

                if not len(m_tat) == 0:
                    m_o_tat = m_tat[0]
                    if not len(m_tat) == 1:
                        m_a_tat = m_tat[1]

                
                
                item = {
                        "date" : m_date,
                        "day" : m_day,
                        "o_corba" : m_o_corba,
                        "a_corba" : m_a_corba,
                        "o_ana" : m_o_ana,
                        "a_ana" : m_a_ana,
                        "o_kar" : m_o_kar,
                        "a_kar" : m_a_kar,
                        "o_tat" : m_o_tat,
                        "a_tat" : m_a_tat
                        

                        }
                
                days_list.append(item) 
                
                break


    json_string = json.dumps(days_list, ensure_ascii=False)
    

    f = open('yemek_listesi.json', 'wt', encoding='utf-8')
    f.write(json_string)
    print(json_string)


   

if __name__ == '__main__':
    main()