Question

我看到类似的问题，但我认为我的有点不同。试图解决方案所说的几乎是什么。我尝试从此页面创建rss Feed＆＃34; http://www.taraf.com.tr/author/hayko-bagdat＆＃34; 我得到了run.py：

import tar
import PyRSS2Gen
import locale
from datetime import datetime
locale.setlocale(locale.LC_ALL,'')
rss = PyRSS2Gen.RSS2(title='ff',link='',description='',lastBuildDate='',items = [])
sonit=[]
sonit+=tar.parse('http://www.taraf.com.tr/author/hayko-bagdat')
print "************************"
for k in sonit:
        print k.zaman
        rss.items.append(PyRSS2Gen.RSSItem(
         title = k.baslik,
         link = k.link,               
         description = k.aciklama,
         guid = PyRSS2Gen.Guid(k.link),

         pubDate = datetime.strptime(str(k.time),u'%d %B %Y %H:%M'),))
rss.write_xml(open("pyrss2gen.xml", "w"))

和tar.py

from bs4 import BeautifulSoup
import urllib2
import codecs
from datetime import datetime
import locale
import lxml.html
from BeautifulSoup import UnicodeDammit
import PyRSS2Gen
locale.setlocale(locale.LC_ALL, '')
import requests
import sys    
class yenitem:
        baslik= ""
        link=""
        aciklama=""
        time=""

def parse(url):    
     request=urllib2.Request(url)
     request.add_header('Accept-Encoding','utf-8')
     response=urllib2.urlopen(request)   

     soup = BeautifulSoup(response.read().decode('utf-8', 'ignore'))    
     items=[]    
     for link in soup.find_all('article',{'class':'item-list'}):             
         item=yenitem()    
         item.baslik=link.find_all('h2')[0].get_text()
         item.link= link.find_all('a')[0].get('href')
         item.aciklama= link.find_all('div')[1].get_text()
         item.time= link.find_all('span')[0].get_text()
         print item.time




         items.append(item)
     return items

这很奇怪，因为它会打印＆＃34; time＆＃34;首先正确使用项目，但在向pubDate添加datetime时会出现问题。这是控制台输出：

24 Ocak 2015 00:00
21 Ocak 2015 00:00
17 Ocak 2015 00:00
14 Ocak 2015 00:00
10 Ocak 2015 00:00
07 Ocak 2015 00:00
03 Ocak 2015 00:00
31 Aralık 2014 00:00
27 Aralık 2014 00:00
24 Aralık 2014 00:00
************************
24 Ocak 2015 00:00
21 Ocak 2015 00:00
17 Ocak 2015 00:00
14 Ocak 2015 00:00
10 Ocak 2015 00:00
07 Ocak 2015 00:00
03 Ocak 2015 00:00
31 Aralık 2014 00:00

    Traceback (most recent call last):
      File "C:\Users\bigM\Desktop\yeni\runk.py", line 18, in <module>
        pubDate = datetime.strptime(str(k.time),u'%d %B %Y %H:%M'),))
    UnicodeEncodeError: 'ascii' codec can't encode character u'\u0131' in position 7: ordinal not in range(128)

Beautifulsoup：'ascii'编解码器不能编码字符u'\ u0131'

0 个答案: