增补：python3.x

1.用BS采集页面内容
2.写入CSV
3.运行的时候发现能够写入，但是写入内容如下图，全英文的OK，有中文的乱码

代码如下：

import io
import sys
import re
import csv
from urllib.request import Request
from urllib.request import urlopen
from bs4 import BeautifulSoup
from bs4 import UnicodeDammit
from datetime import datetime

sys.stdout = io.TextIOWrapper(sys.stdout.buffer,encoding='utf-8')

page = 2
url = 'http://www.qiushibaike.com/hot/page/' + str(page)
user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
headers = {'User-Agent':user_agent}
request = Request(url,headers=headers)
response = urlopen(request)
doc = response.read()
soup = BeautifulSoup(doc)
needdivs = soup.findAll("div",{"class":"article block untagged mb15"})

csvFile = open("test.csv",'w+')
try:
    writer = csv.writer(csvFile)
    writer.writerow(('author','content','datetime'))
    for div in needdivs:
        author = div.findAll("h2")[0].get_text().encode('utf-8')
        contentDiv = div.find("div",{"class":"content"})
        content = contentDiv.get_text().encode('utf-8')
        m = re.findall(r'<!--(.*?)-->',str(contentDiv))
        strTime = str(m[0])
        intTime = int(strTime)
        dt = datetime.fromtimestamp(intTime)
        strdt = str(dt).encode('utf-8')
        writer.writerow((author,content,strdt))
        print(author)
        print(dt)
        print(content)
finally:
    csvFile.close()

我估计错误行在于 content = contentDiv.get_text().encode('utf-8')
但是我一旦去掉encode('utf-8') 那么会报下面错误
UnicodeEncodeError: 'ascii' codec can't encode characters in position 0-5:

请各位大神帮忙看看，写手写PY

====================================================
根据网上的一些，建议增加import codecs
其中 csvFile = codecs.open("test.csv",'wb+','utf-8')
里面为了比较差异
author = div.findAll("h2")[0].get_text().encode('utf-8')
另外存储的去掉了encode('utf-8')
sublime 结果为

那么得到的cvs内容为

=============参考代码如下===================

import io
import sys
import re
import csv
import codecs
from urllib.request import Request
from urllib.request import urlopen
from bs4 import BeautifulSoup
from bs4 import UnicodeDammit
from datetime import datetime

sys.stdout = io.TextIOWrapper(sys.stdout.buffer,encoding='utf-8')

page = 2
url = 'http://www.qiushibaike.com/hot/page/' + str(page)
user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
headers = {'User-Agent':user_agent}
request = Request(url,headers=headers)
response = urlopen(request)
doc = response.read()
soup = BeautifulSoup(doc)
needdivs = soup.findAll("div",{"class":"article block untagged mb15"})

# csvFile = open("test.csv",'wb+'，encoding ='utf-8')
csvFile = codecs.open("test.csv",'wb+','utf-8')
try:
    writer = csv.writer(csvFile)
    writer.writerow((u'苏州','content','datetime'))
    for div in needdivs:
        author = div.findAll("h2")[0].get_text().encode('utf-8')
        contentDiv = div.find("div",{"class":"content"})
        content = contentDiv.get_text()
        m = re.findall(r'<!--(.*?)-->',str(contentDiv))
        strTime = str(m[0])
        intTime = int(strTime)
        dt = datetime.fromtimestamp(intTime)
        strdt = str(dt)
        writer.writerow((author,content,strdt))
        print(author)
        print(dt)
        print(content)
finally:
    csvFile.close()

如果按照这个帖子参考Python 编码转换与中文处理 那么我这里的strdt = str(dt).encode('utf-8') 是不能从str encode只能为decode但是又没有报错。见鬼了。