seitenabruf ok, regex fail

This commit is contained in:
Frederik Jaeckel 2022-11-21 09:32:57 +01:00
parent 2b80f22897
commit 4b9c25ec46

View file

@ -61,7 +61,13 @@ class OnlineSource(ModelSQL, ModelView):
"""
OSourc = Pool().get('investment.source')
result = OSourc.read_from_website(self, debug=False)
result = OSourc.read_from_website(
self,
isin = self.isin,
nsin = self.nsin,
symbol = self.symbol,
debug=True,
)
self.text = result.get('text', None)
@fields.depends('nsin', 'isin', 'symbol', 'text')
@ -155,25 +161,30 @@ class OnlineSource(ModelSQL, ModelView):
print('\n## get_regex_result:', rgxcode, type(rgxcode))
rgxcode = rgxcode or ''
if len(rgxcode) == 0:
print('-- get_regex_result: stop 1')
return None
result = re.compile(rgxcode).match(html_text)
if result is None:
print('-- get_regex_result: stop 2')
return None
print('-- result:', result, result.group())
print('-- get_regex_result - result:', result, result.group())
return result
@classmethod
def read_from_website(cls, updtsource, debug=False):
def read_from_website(cls, updtsource, isin=None, nsin=None, symbol=None, debug=True):
""" read from url, extract values
"""
result = {}
res1 = requests.get(
updtsource.url,
updtsource.get_url_with_parameter(
isin = isin,
nsin = nsin,
symbol = symbol,
),
allow_redirects=True,
timeout=5.0)
print('-- res1:', res1.history)
if res1.status_code in [200, 204, 404]:
html = cls.cleanup_spaces(res1.text)
@ -195,7 +206,7 @@ class OnlineSource(ModelSQL, ModelView):
print('\n## result:', result)
else :
#logger.error('read_from_website: %s' % res1.text)
logger.error('read_from_website: %s' % res1.text)
if debug:
result['text'] = res1.text
return result