Compare commits

...

3 Commits

Author SHA1 Message Date
frabad 3eea3854dc ignore les JSON de test 2022-05-06 20:15:43 +02:00
frabad 496e95f191 nettoyage récursif des données JSON 2022-05-06 20:13:22 +02:00
frabad 09209b3b3e recherche récursive des sources de données 2022-05-06 18:23:36 +02:00
2 changed files with 29 additions and 17 deletions

1
.gitignore vendored
View File

@ -1,3 +1,4 @@
local/ local/
*.tar.gz *.tar.gz
*.json

View File

@ -5,33 +5,44 @@ extracteur de données iSpindel JSON entreposées par Little Bock en HTML
import json import json
try: try:
import lxml.html as LX import lxml.html as LX
except ModuleNotFoundError as e: except ModuleNotFoundError:
import sys import sys
print("Le module 'lxml' est nécessaire.\n http://pypi.org/lxml") sys.exit("Le module 'lxml' est nécessaire.\n\thttp://pypi.org/lxml")
sys.exit()
import pathlib import pathlib
def proc(path): def jsproc(data):
s, js = None, None """nettoie des données récursivement"""
h = LX.parse(path.name) 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']") x = h.xpath("//*[@id='fermentation_log_chart']")
if x: s = x[0].get('data-chart-options') if x: data1 = x[0].get('data-chart-options')
if s: if data1:
js = json.dumps( for i in json.loads(data1).pop('series'):
json.loads(s).pop('series'), indent=4, sort_keys=True) or None data2.append(jsproc(i))
if js: if len(data2) > 0:
p = path.with_suffix('.json') path_out = path_in.with_suffix('.json')
with open(p,'w') as f: with open(path_out,'w') as f:
f.write(js) f.write(json.dumps(data2, indent=2, sort_keys=False))
print(f"INFO: extraction des données dans {p.name}.") print(f"INFO: {path_in.name} >> {path_out.name}")
if __name__ == "__main__": if __name__ == "__main__":
here = pathlib.Path.cwd() here = pathlib.Path.cwd()
hdocs = tuple(here.glob("*.html")) hdocs = tuple(here.rglob("*.html"))
if len(hdocs) == 0: if len(hdocs) == 0:
print("Aucun fichier HTML ('.html') trouvé.") print("Aucun fichier HTML ('.html') trouvé.")
for i in hdocs: for i in hdocs:
if i.exists() and i.stat().st_size > 0: if i.exists() and i.stat().st_size > 0:
proc(i) hproc(i)