38 lines
1011 B
Python
38 lines
1011 B
Python
|
#!/usr/bin/python3
|
||
|
"""
|
||
|
extracteur de données iSpindel JSON entreposées par Little Bock en HTML
|
||
|
"""
|
||
|
import json
|
||
|
try:
|
||
|
import lxml.html as LX
|
||
|
except ModuleNotFoundError as e:
|
||
|
import sys
|
||
|
print("Le module 'lxml' est nécessaire.\n http://pypi.org/lxml")
|
||
|
sys.exit()
|
||
|
import pathlib
|
||
|
|
||
|
def proc(path):
|
||
|
s, js = None, None
|
||
|
h = LX.parse(path.name)
|
||
|
x = h.xpath("//*[@id='fermentation_log_chart']")
|
||
|
if x: s = x[0].get('data-chart-options')
|
||
|
if s:
|
||
|
js = json.dumps(
|
||
|
json.loads(s).pop('series'), indent=4, sort_keys=True) or None
|
||
|
if js:
|
||
|
p = path.with_suffix('.json')
|
||
|
with open(p,'w') as f:
|
||
|
f.write(js)
|
||
|
print(f"INFO: extraction des données dans {p.name}.")
|
||
|
|
||
|
if __name__ == "__main__":
|
||
|
here = pathlib.Path.cwd()
|
||
|
hdocs = tuple(here.glob("*.html"))
|
||
|
if len(hdocs) == 0:
|
||
|
print("Aucun fichier HTML ('.html') trouvé.")
|
||
|
for i in hdocs:
|
||
|
if i.exists() and i.stat().st_size > 0:
|
||
|
proc(i)
|
||
|
|
||
|
|