c语言有些字符已用unicode替换字符替换,UnicodeWarning:某些字符无法解码，已替换为替换字符...

我在代码中使用的是python&＃43;bs4&＃43;pyside&＃xff0c;请看下面部分代码&＃xff1a;enter code here

#coding:gb2312

import urllib2

import sys

import urllib

import urlparse

import random

import time

from datetime import datetime, timedelta

import socket

from bs4 import BeautifulSoup

import lxml.html

from PySide.QtGui import *

from PySide.QtCore import *

from PySide.QtWebKit import *

def download(self, url, headers, proxy, num_retries, data&＃61;None):

print &＃39;Downloading:&＃39;, url

request &＃61; urllib2.Request(url, data, headers or {})

opener &＃61; self.opener or urllib2.build_opener()

if proxy:

proxy_params &＃61; {urlparse.urlparse(url).scheme: proxy}

opener.add_handler(urllib2.ProxyHandler(proxy_params))

try:

response &＃61; opener.open(request)

html &＃61; response.read()

code &＃61; response.code

except Exception as e:

print &＃39;Download error:&＃39;, str(e)

html &＃61; &＃39;&＃39;

if hasattr(e, &＃39;code&＃39;):

code &＃61; e.code

if num_retries > 0 and 500 <&＃61; code <600:

# retry 5XX HTTP errors

return self._get(url, headers, proxy, num_retries-1, data)

else:

code &＃61; None

return {&＃39;html&＃39;: html, &＃39;code&＃39;: code}

def crawling_hdf(openfile):

filename &＃61; open(openfile,&＃39;r&＃39;)

namelist &＃61; filename.readlines()

app &＃61; QApplication(sys.argv)

for name in namelist:

url &＃61; "http://so.haodf.com/index/search?type&＃61;doctor&kw&＃61;"&＃43; urllib.quote(name)

#get doctor&＃39;s home page

D &＃61; Downloader(delay&＃61;DEFAULT_DELAY, user_agent&＃61;DEFAULT_AGENT, proxies&＃61;None, num_retries&＃61;DEFAULT_RETRIES, cache&＃61;None)

html &＃61; D(url)

soup &＃61; BeautifulSoup(html)

tr &＃61; soup.find(attrs&＃61;{&＃39;class&＃39;:&＃39;docInfo&＃39;})

td &＃61; tr.find(attrs&＃61;{&＃39;class&＃39;:&＃39;docName font_16&＃39;}).get(&＃39;href&＃39;)

print td

#get doctor&＃39;s detail information page

loadPage_bs4(td)

filename.close()

if __name__ &＃61;&＃61; &＃39;__main__&＃39;:

crawling_hdf("name_list.txt")

运行程序后&＃xff0c;会显示警告信息&＃xff1a;

警告(来自警告模块)&＃xff1a;

文件“C:\Python27\lib\site packages\bs4\该死的.py“&＃xff0c;第231行

无法解码某些字符&＃xff0c;并且

UnicodeWarning:某些字符无法解码&＃xff0c;已替换为替换字符。

我用过print str(html)发现所有标签中的中文都是乱码。在

我尝试过使用“解码或编码”和“gzip”解决方案&＃xff0c;这是在这个网站上搜索&＃xff0c;但它不适用于我的情况。在

非常感谢你的帮助