mySpindel/LittleBock/extract.py

#!/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  http://pypi.org/lxml")
import pathlib

def proc(path_in):
    s, js = None, None
    h = LX.parse(str(path_in))
    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:
        path_out = path_in.with_suffix('.json')
        with open(path_out,'w') as f:
            f.write(js)
            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:
            proc(i)