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

cleaner way to get rid of BOM for CsvPage

Browse source
This commit is contained in:
smurail 2014-10-20 17:08:18 +02:00
commit 977f5a9f02
1 changed files with 4 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

5
weboob/browser/pages.py
View file

@ -345,9 +345,12 @@ class CsvPage(Page):
""" """
def build_doc(self, content): def build_doc(self, content):
# We may need to temporarily convert content to utf-8 because csv
# does not support Unicode.
encoding = self.encoding encoding = self.encoding
if encoding == 'utf-16le': if encoding == 'utf-16le':
content = content.decode('utf-16le')[1:].encode('utf-8') # If there is a BOM, decode('utf-16') will get rid of it
content = content.decode('utf-16').encode('utf-8')
encoding = 'utf-8' encoding = 'utf-8'
if self.NEWLINES_HACK: if self.NEWLINES_HACK:
content = content.replace('\r\n', '\n').replace('\r', '\n') content = content.replace('\r\n', '\n').replace('\r', '\n')