Last active
February 8, 2020 04:57
-
-
Save kabir0st/f8158ef935999c01ff619ae1c30659df to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import xml.etree.ElementTree as et | |
import json | |
json_format = { | |
'amud':'','daf':'','perek_id':1,'text_eng':[], 'text_heb':[], 'type':0 | |
} | |
output_json = [] | |
data = et.parse('xm.xml') | |
stories = data.findall('Story') | |
for story in stories: | |
engs = story.findall('Talmud_eng') | |
for eng in engs: | |
# for amud | |
try: | |
daf_text = eng[0][0][1][1].text | |
daf_texts = daf_text.split() | |
json_format['daf'] = str(daf_texts[1]) | |
json_format['amud'] = str(daf_texts[3]) | |
print(json_format) | |
except: | |
pass | |
#for perek_id | |
try: | |
perek_id_text = eng[0][1][1][1].text | |
json_format['perek_id'] = str(perek_id_text.split()[1]) | |
except: | |
pass | |
# for heb in a tablmud_eng | |
heb = eng.findall(".//Talmud_Heb") | |
print(heb) | |
for x in heb: | |
json_format['text_heb'].append(x.text) | |
#for text_eng | |
tag_names = {t.tag for t in eng.findall('.//*')} | |
for tag_name in tag_names: | |
if tag_name.__contains__('Talmud_') and tag_name != 'Talmud_Heb': | |
for tag in eng.findall(tag_name): | |
if (tag.text): | |
json_format['text_eng'].append(tag.text) | |
output_json.append(json_format) | |
#resetting | |
json_format['text_eng'] = [] | |
json_format['text_heb'] = [] | |
with open('output.json', 'w') as output_file: | |
json.dump(output_json, output_file) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment