Question

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()

我缩短了一点以使其更容易阅读，但它应该仍然有效。此代码将成为更大脚本的一部分。

我正在使用此lib：XGOOGLE来搜索google的结果，然后我访问每个结果以搜索该网站是否包含来自stringArr的任何字符串。

我做了第一次测试没有任何问题（我在不到10个结果后ctrl + C），但是第一次让它运行，经过大约100个urls测试后我得到了这个错误：

  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，因为我修改了代码以便在此处发布）

之后我恢复了我的linux终端，就像脚本已经完成一样。但是我注意到我的电脑工作效果不好，我检查了系统监视器，我看到了使用1.3gb内存的Python进程，我不得不杀死进程让我的电脑恢复正常。

我的代码中是否存在导致此问题的原因或为什么会发生？

我知道我的代码可能有一些错误，但是现在我主要对可能导致内存问题的任何错误感兴趣。任何帮助将不胜感激。

Answer 1

我重新编写了一些代码，让我更容易阅读。我在这里看不到任何会泄漏记忆的东西

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()

Answer 2

可能是urllib.urlopen（）。见http://bugs.python.org/issue1208304

我想我的python脚本中有内存泄漏

2 个答案: