mySpindel/LittleBock/extract.py
2022-05-06 20:13:22 +02:00

49 lines
1.4 KiB
Python
Executable File

#!/usr/bin/python3
"""
extracteur de données iSpindel JSON entreposées par Little Bock en HTML
"""
import json
try:
import lxml.html as LX
except ModuleNotFoundError:
import sys
sys.exit("Le module 'lxml' est nécessaire.\n\thttp://pypi.org/lxml")
import pathlib
def jsproc(data):
"""nettoie des données récursivement"""
unwanted = ["color","opacity","yAxis","dashStyle"]
for u in unwanted:
if u in data.keys():
del(data[u])
for k,v in data.items():
if isinstance(v,dict):
jsproc(v)
return data
def hproc(path_in):
"""traite un document HTML"""
data1, data2 = None, []
h = LX.parse(str(path_in))
x = h.xpath("//*[@id='fermentation_log_chart']")
if x: data1 = x[0].get('data-chart-options')
if data1:
for i in json.loads(data1).pop('series'):
data2.append(jsproc(i))
if len(data2) > 0:
path_out = path_in.with_suffix('.json')
with open(path_out,'w') as f:
f.write(json.dumps(data2, indent=2, sort_keys=False))
print(f"INFO: {path_in.name} >> {path_out.name}")
if __name__ == "__main__":
here = pathlib.Path.cwd()
hdocs = tuple(here.rglob("*.html"))
if len(hdocs) == 0:
print("Aucun fichier HTML ('.html') trouvé.")
for i in hdocs:
if i.exists() and i.stat().st_size > 0:
hproc(i)