UnicodeEncodeError: 'ascii' codec ne peut pas encoder les caractères u'\xc7' à la position 0: quand écrire à .csv

Faites défiler vers le bas: http://docs.python.org/library/csv.html

plus précisément, l'utilisation de cet écrivain:

class UnicodeWriter:
"""
A CSV writer which will write rows to CSV file "f",
which is encoded in the given encoding.
"""
def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
# Redirect output to a queue
self.queue = cStringIO.StringIO()
self.writer = csv.writer(self.queue, dialect=dialect, **kwds)
self.stream = f
self.encoder = codecs.getincrementalencoder(encoding)()
def writerow(self, row):
self.writer.writerow([s.encode("utf-8") for s in row])
# Fetch UTF-8 output from the queue ...
data = self.queue.getvalue()
data = data.decode("utf-8")
# ... and reencode it into the target encoding
data = self.encoder.encode(data)
# write to the target stream
self.stream.write(data)
# empty queue
self.queue.truncate(0)
def writerows(self, rows):
for row in rows:
self.writerow(row)

Alors, au lieu de

c = csv.writer(open("MYFILE.csv", "wb"))

utilisation

c = UnicodeWriter(open("MYFILE.csv", "wb"))

le problème était que je n'étais pas à l'aide de l'unicode correctement, voici le dernier code

#!/usr/local/bin/python
# -*- coding: utf-8 -*-
import urllib2
import BeautifulSoup
import csv
origin_site = 'http://typo3.nimes.fr/index.php?id=annuaire_assos&theme=0&rech=&num_page='
pages = range(1,21)
assoc_table = []
for page_no in pages:
print page_no
req = ('%s%s' % (origin_site, page_no))
user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
headers = { 'User-Agent' : user_agent }
try:
doc = urllib2.urlopen(req)
except urllib2.URLError, e:
pass 
else:
# do something with the page    
soup = BeautifulSoup.BeautifulSoup(doc)
for row in soup.findAll('tr', { "class" : "menu2" }):
assoc_data = []
item = row.renderContents()
soup = BeautifulSoup.BeautifulSoup(item)
# we get the Thème
for assoc_theme in soup.findAll('u'):
assoc_data.append(assoc_theme.renderContents())
# we get the Nom de l'association
for assoc_name in soup.findAll('td', { "width": "70%"}):
assoc_data.append(assoc_name.renderContents())
# we list all the links to the indivudual pages
for i in soup.findAll('a', {'href':'#'}):
if 'associations' in i.attrMap['onclick']:
req = i.attrMap['onclick'].split('\'')[1]
try:
doc = urllib2.urlopen(req)
except urllib2.URLError, e:
pass
else:
soup = BeautifulSoup.BeautifulSoup(doc)
emails = []
web_sites = []
for tag in soup.recursiveChildGenerator():
if isinstance(tag,BeautifulSoup.Tag) and tag.name in ('a'):
assoc_link = (tag.string)
if '@' in str(assoc_link):
print assoc_link
emails.append(assoc_link)
if emails != []:
assoc_data.append(emails[0])
else:
assoc_data.append('pas du email')
for tag in soup.recursiveChildGenerator():
if isinstance(tag,BeautifulSoup.Tag) and tag.name in ('a'):
assoc_link = (tag.string)
if 'http' in str(assoc_link):
web_sites.append(assoc_link)
#
if web_sites != []:
assoc_data.append(web_sites[0])
else:
assoc_data.append('pas du site web')
assoc_addr = [] 
assoc_cont = soup.findAll('td', { "width" : "49%", "class": "menu2" })
for i in assoc_cont:
assoc_addr.append(i.renderContents())
assoc_tels = []
for addr in assoc_addr:
assoc_data.append(addr)
assoc_tel = soup.findAll('td', { "width" : "45%", "class": "menu2" })
for i in assoc_tel:
assoc_tels.append(i.renderContents())
assoc_data.append(assoc_tels[0])
print assoc_tels[0]
assoc_table.append(assoc_data)
print assoc_data
print assoc_table
c = csv.writer(open("nimes_assoc.csv", "wb"))
for item in assoc_table:
#print item
c.writerow(item)

merci à tous pour votre aide et de [email protected] liste de diffusion