BYR Achieve · 镜像论坛

各位大神帮忙查查错

2014/7/13镜像同步4 回复

附件(4.1KB) __geturlinfo.py 各位大神在执行如上的python程序时为啥会报如图的错？错在哪？谢谢各位了代码直接贴吧 # -*- coding: utf-8 -*- import os import glob from imp import reload import sys import _thread import threading import time inputdir='''indir''' outputdir='''hugeoutput''' logdir='''errlog''' useragent='''\"User-Agent:Mozilla/5.0 (iPhone; CPU iPhone OS 7_0 like Mac OS X; en-us) AppleWebKit/534+ (KHTML, like Gecko) Version/7.0 Mobile/11A465 Safari/9537.53 MsnBot-Media /1.0b\"''' class urlprocessor(threading.Thread): def __init__(self,infile,outfile): threading.Thread.__init__(self) self.inputfile=infile self.number=outfile self.outputfile=outputdir+'''\\'''+outfile+".txt" self.logfile=logdir+'''\\'''+outfile+".txt" self.outstream=open(self.outputfile,'a',encoding= 'utf-8') self.logstream=open(self.logfile,'a',encoding= 'utf-8') self.cmd='''curl ''' self.servernotfound=0 self.http=0 self.location=0 self.redirected=0 self.normal=0 self.outputline='''''' def run(self): with open(self.inputfile,'r',encoding= 'utf-8') as f0: f1=f0.readlines() print(len(f1)) out = open("hugeoutput\\"+self.number+".txt",encoding= 'utf-8') outcont=out.readlines() outsize=len(outcont) out.close() err = open("errlog\\"+self.number+".txt",encoding= 'utf-8') errcont=err.readlines() outsize+=len(errcont) err.close() ff=f1[outsize:-1] print(outsize) time.sleep(10) for i in ff: tmp=i.split() url=tmp[0] self.cmd="curl -H "+useragent+" "+url+" -I" self.outputline=url+' ' print("it work ok\n") try: results=os.popen(self.cmd).readlines() except: try: self.logstream.write(url+'\n') self.logstream.flush() print("decode error\n") except: print("log write error!\n") for item in results: http=item.find('HTTP') if http>=0: self.http=1 self.outputline+=item[:-1] break if self.http==0: self.outputline+=' '+"HTTP/servernotfound" self.servernotfound+=1 else: self.http=0 for item in results: location=item.find('Location') if location>=0: self.redirected+=1 self.location=1 substr=item.split(':') self.outputline+=' '+item break if self.location==0: self.outputline+=' '+url+'\n' self.normal+=1 else: self.location=0 try: self.outstream.write(self.outputline) self.outstream.flush() except Exception: print("output err\n") self.logstream.write('\n') self.logstream.write("redirected:"+str(self.redirected)+" normal:"+\ str(self.normal)+" servernotfound:"+\ str(self.servernotfound)) self.outstream.close() self.logstream.close() print("be at the end\n") def stop(self): self.thread_stop=1 def caller(): files=glob.glob(inputdir+'\\*.txt') threadlist=[] for file in files: filename=file.split("\\")[1] filenum=filename.split(".")[0] thread=urlprocessor(file,filenum) thread.start() threadlist.append(thread) for threads in threadlist: threads.stop() print("A thread finished\n") if __name__=='__main__': caller()

订阅后，新回复会通过你的通知中心匿名送达。