recherche récursive des sources de données

This commit is contained in:
frabad 2022-05-06 18:23:36 +02:00
parent 009b60b8db
commit 09209b3b3e
1 changed files with 10 additions and 11 deletions

View File

@ -5,29 +5,28 @@ extracteur de données iSpindel JSON entreposées par Little Bock en HTML
import json
try:
import lxml.html as LX
except ModuleNotFoundError as e:
except ModuleNotFoundError:
import sys
print("Le module 'lxml' est nécessaire.\n http://pypi.org/lxml")
sys.exit()
sys.exit("Le module 'lxml' est nécessaire.\n http://pypi.org/lxml")
import pathlib
def proc(path):
def proc(path_in):
s, js = None, None
h = LX.parse(path.name)
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
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:
path_out = path_in.with_suffix('.json')
with open(path_out,'w') as f:
f.write(js)
print(f"INFO: extraction des données dans {p.name}.")
print(f"INFO: {path_in.name} >> {path_out.name}")
if __name__ == "__main__":
here = pathlib.Path.cwd()
hdocs = tuple(here.glob("*.html"))
hdocs = tuple(here.rglob("*.html"))
if len(hdocs) == 0:
print("Aucun fichier HTML ('.html') trouvé.")
for i in hdocs: