我觉得我的Python脚本有内存泄漏
这是我的代码:
from xgoogle.search import GoogleSearch, SearchError
import urllib, urllib2, sys, argparse
global stringArr
stringArr = ["string 1",
"string 2",
"string 3",
"string etc"]
def searchIt(url):
try:
if(args.verbose>='1'): print "[INFO] Opening URL: "+url
response = urllib.urlopen(url)
except urllib2.URLError, e:
print "[ERROR] "+e.reason
return False
except KeyboardInterrupt:
print "Suspended by user..."
sys.exit()
if(checkForStr(response.read())):
if(args.verbose=='0'): print "[INFO] String found in URL: "+url
else:
if(args.verbose>='1'): print "[INFO] No string found in URL: "+url
def checkForStr(html):
global stringArr
try:
if any(checkStr in html for checkStr in stringArr):
return True
else:
return False
except KeyboardInterrupt:
print "Suspended by user..."
sys.exit()
def main():
try:
i=0
gs = GoogleSearch(args.keyword)
gs.results_per_page = 100
results = []
while True:
tmp = gs.get_results()
i = i+1 # page number
if not tmp: # no more results (pages) were found
break
results.extend(tmp)
for r in results: # process results for page
searchIt(r.url) # check for string
del results[:] # clean results
# finished
except SearchError, e:
print "[ERROR] Search failed: %s" % e
except KeyboardInterrupt:
print "Suspended by user..."
sys.exit()
if __name__ == '__main__':
try:
parser = argparse.ArgumentParser()
parser.add_argument('-v', dest='verbose', default='0', help='Verbosity level', choices='012')
group = parser.add_argument_group('required arguments')
group.add_argument('-k', dest='keyword', help='Keyword to use on google query', required=True)
args = parser.parse_args()
main()
except KeyboardInterrupt:
print "Suspended by user..."
sys.exit()
我把代码简化了一些,以便更容易阅读,但它仍然可以正常工作。这段代码将是一个更大脚本的一部分。
我使用了这个库:XGOOGLE,用来从谷歌抓取搜索结果,然后我会访问每个结果,查看网站是否包含字符串数组中的任何字符串。
我第一次测试的时候没有遇到任何问题(我在不到10个结果后就按了Ctrl+C),但第一次让我让它运行的时候,测试了大约100个网址后,我遇到了这个错误:
File "./StringScan.py", line 99, in <module>
main()
File "./StringScan.py", line 83, in main
checkForStr(r.url)
File "./StringScan.py", line 39, in checkForStr
response = urllib.urlopen(url)
File "/usr/lib/python2.6/urllib.py", line 86, in urlopen
return opener.open(url)
File "/usr/lib/python2.6/urllib.py", line 205, in open
return getattr(self, name)(url)
File "/usr/lib/python2.6/urllib.py", line 344, in open_http
h.endheaders()
File "/usr/lib/python2.6/httplib.py", line 904, in endheaders
self._send_output()
File "/usr/lib/python2.6/httplib.py", line 776, in _send_output
self.send(msg)
File "/usr/lib/python2.6/httplib.py", line 735, in send
self.connect()
File "/usr/lib/python2.6/httplib.py", line 716, in connect
self.timeout)
File "/usr/lib/python2.6/socket.py", line 500, in create_connection
for res in getaddrinfo(host, port, 0, SOCK_STREAM):
IOError: [Errno socket error] [Errno -2] Name or service not known
(行号不一样是因为我修改了代码以便在这里发布)
之后,我的Linux终端恢复了,就好像脚本已经结束了。但我注意到我的电脑运行得不太正常,我查看了系统监视器,发现Python进程占用了1.3GB的内存,我不得不结束这个进程才能让我的电脑恢复正常。
是我的代码导致了这个问题,还是说可能是什么原因呢?
我知道我的代码可能有一些错误,但现在我主要关心的是可能导致内存问题的错误。任何帮助都将不胜感激。
2 个回答
0
这可能是用到 urllib.urlopen()。可以查看这个链接了解更多信息:http://bugs.python.org/issue1208304
0
我对你的代码做了一些小改动,让我更容易理解。不过,我没有发现这里有任何可能导致内存泄漏的问题。
from itertools import count
import urllib, urllib2, sys, argparse
from xgoogle.search import GoogleSearch, SearchError
stringArr = ["string 1",
"string 2",
"string 3",
"string etc"]
def searchIt(url):
try:
if(args.verbose>='1'):
print "[INFO] Opening URL: "+url
response = urllib.urlopen(url)
except urllib2.URLError, e:
print "[ERROR] "+e.reason
return False
if checkForStr(response.read()):
if(args.verbose=='0'):
print "[INFO] String found in URL: "+url
else:
if(args.verbose>='1'):
print "[INFO] No string found in URL: "+url
def checkForStr(html):
return any(checkStr in html for checkStr in stringArr)
def main():
try:
gs = GoogleSearch(args.keyword)
gs.results_per_page = 100
for i in count():
results = gs.get_results()
if not results: # no more results (pages) were found
break
for r in results: # process results for page
searchIt(r.url) # check for string
# finished
except SearchError, e:
print "[ERROR] Search failed: %s" % e
if __name__ == '__main__':
try:
parser = argparse.ArgumentParser()
parser.add_argument('-v', dest='verbose', default='0', help='Verbosity level', choices='012')
group = parser.add_argument_group('required arguments')
group.add_argument('-k', dest='keyword', help='Keyword to use on google query', required=True)
args = parser.parse_args()
main()
except KeyboardInterrupt:
print "Suspended by user..."
sys.exit()