Question

我正在尝试使用以下代码在python中使用Bing api：

#!/usr/bin/python
from bingapi import bingapi  
import re
import json
import urllib
import cgi
import cgitb
from HTMLParser import HTMLParser

class MLStripper(HTMLParser):
    def __init__(self):
            self.reset()
            self.fed = []
    def handle_data(self, d):
            self.fed.append(d)
    def get_data(self):
            return ''.join(self.fed)

def strip_tags(html):
    s = MLStripper()
    s.feed(html)
    return s.get_data()

def strip_tags2(data):
    p = re.compile(r'<[^<]*?>')
    q = re.compile(r'[&;!@#$%^*()]*')
    data = p.sub('', data)
    return q.sub('', data)

def getUrl(item):
    return item['Url']

def getContent(item):
    return item['Description']

def getTitle(item):
    return item['Title']

def getInfo(qry, siteStr):
    qryStr = qry + "+" + siteStr
    #qryStr = u"%s" % qryStr.encode('UTF-8')
    query = urllib.urlencode({'q' : qryStr})
    url = 'http://api.bing.net/json.aspx?Appid=<myappid>&Version=2.2&Market=en-US&Query=%s&Sources=web&Web.Count=10&JsonType=raw' % (query)
    search_results = urllib.urlopen(url)
    j = json.loads(search_results.read())
    results = j['SearchResponse']['Web']['Results']
    return results

def updateRecent(qry):
    f = open("recent.txt", "r")
    lines = f.readlines()
    f.close()
    lines = lines[1:]

    if len(qry) > 50: #truncate if string too long
            qry = (qry[:50] + '...')
    qry = strip_tags2(qry) #strip out the html if injection try

    lines.append("\n%s" % qry)
    f = open("recent.txt", "w")
    f.writelines(lines)
    f.close()

if __name__ == '__main__':
    form = cgi.FieldStorage()
    qry = form["qry"].value
    qry = r'%s' % qry

    updateRecent(qry)

    siteStr = "(site:answers.yahoo.com OR site:chacha.com OR site:blurtit.com OR site:answers.com OR site:question.com OR site:answerbag.com OR site:stackexchange.com)"

    print "Content-type: text/html"
    print

    header = open("header.html", "r")
    contents = header.readlines()
    header.close()
    for item in contents:
            print item

    print """
    <div id="results">
    <center><h1>Results:</h1></center>
    """
    for item in getInfo(siteStr, qry):
            print "<h3>%s</h3>" % getTitle(item)
            print "<br />"
            print "%s" % getUrl(item)
            print "<br />"
            print "<p style=\"color:gray\">%s</p>" % getContent(item)
            print "<br />"
    print "</div>"

    footer = open("footer.html", "r")
    contents = footer.readlines()
    footer.close()
    for thing in contents:
            print thing

我打印了一些结果，然后给出了以下错误：

UnicodeEncodeError: 'ascii' codec can't encode character u'\\u2026' in position 72:    ordinal not in range(128)

有人可以解释为什么会这样吗？它显然与url如何编码有关，但究竟是什么错？提前谢谢！

Answer 1

特定的Unicode字符是“HORIZONTAL ELLIPSIS”。一个或多个getXXXXX（）函数返回Unicode字符串，其中一个字符串包含非ASCII字符。我建议声明输出的编码，例如：

Content-Type: text/html; charset=utf-8

并以该编码显式编码输出。

Answer 2

我们需要知道抛出异常的行号，它将在回溯中。无论如何，问题是您正在从文件/ URL读取unicode，然后隐式地将它们转换为US-ASCII，可能是在其中一个串联操作中。你应该在所有常量字符串前加上u来表示它们是unicode字符串，比如

u"\n%s" % qry

Python：'ascii'编解码器不能编码字符u'\\ u2026'

2 个答案: