nojhan/weboob-devel
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

fix parsing on special cases

Browse source
This commit is contained in:
Romain Bignon 2013-07-25 15:26:53 +02:00
commit f9f6049019
2 changed files with 13 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

10
modules/boursorama/pages/account_history.py
View file

@ -47,11 +47,15 @@ class AccountHistory(BasePage):
def get_operations(self): def get_operations(self):
for form in self.document.xpath('//form[@name="marques"]'): for form in self.document.xpath('//form[@name="marques"]'):
for tr in form.xpath('.//tbody/tr'): for tr in form.xpath('.//tbody/tr'):
if tr.attrib.get('class', '') == 'total': if tr.attrib.get('class', '') == 'total' or 'style' in tr.attrib:
continue continue
date = self.parser.tocleanstring(tr.cssselect('td.label span.DateOperation')[0]) date = self.parser.tocleanstring(tr.cssselect('td.operation span.DateOperation')[0])
label = self.parser.tocleanstring(tr.cssselect('td.label span')[-1]) span = tr.cssselect('td.operation span, td.operation a')[-1]
# remove links
for font in span.xpath('./font'):
font.drop_tree()
label = self.parser.tocleanstring(span)
amount = self.parser.tocleanstring(tr.cssselect('td.amount')[0]) amount = self.parser.tocleanstring(tr.cssselect('td.amount')[0])
try: try:

7
modules/boursorama/pages/accounts_list.py
View file

@ -42,7 +42,12 @@ class AccountsList(BasePage):
break break
elif td.attrib.get('class', '') == 'account-name': elif td.attrib.get('class', '') == 'account-name':
account.label = self.parser.tocleanstring(td.xpath('./span[@class="label"]')[0]) try:
span = td.xpath('./span[@class="label"]')[0]
except IndexError:
# ignore account
break
account.label = self.parser.tocleanstring(span)
account._link_id = td.xpath('.//a')[0].attrib['href'] account._link_id = td.xpath('.//a')[0].attrib['href']
elif td.attrib.get('class', '') == 'account-more-actions': elif td.attrib.get('class', '') == 'account-more-actions':