{"id":106450,"date":"2020-05-28T18:42:33","date_gmt":"2020-05-28T10:42:33","guid":{"rendered":"http:\/\/4563.org\/?p=106450"},"modified":"2020-05-28T18:42:33","modified_gmt":"2020-05-28T10:42:33","slug":"python-b-%e6%96%87%e4%bb%b6%e9%87%8c%e7%9a%84%e6%af%8f%e8%a1%8c%e6%95%b0%e6%8d%ae%e5%8c%b9%e9%85%8d-a-%e6%96%87%e4%bb%b6%e9%87%8c%e7%9a%84%e5%86%85%e5%ae%b9-%e9%80%bb%e8%be%91%e9%97%ae%e9%a2%98","status":"publish","type":"post","link":"http:\/\/4563.org\/?p=106450","title":{"rendered":"Python B \u6587\u4ef6\u91cc\u7684\u6bcf\u884c\u6570\u636e\u5339\u914d A \u6587\u4ef6\u91cc\u7684\u5185\u5bb9 \u903b\u8f91\u95ee\u9898"},"content":{"rendered":"
\n
\n
\n

Python B \u6587\u4ef6\u91cc\u7684\u6bcf\u884c\u6570\u636e\u5339\u914d A \u6587\u4ef6\u91cc\u7684\u5185\u5bb9 \u903b\u8f91\u95ee\u9898 <\/h1>\n

<\/p>\n

\n
\u8cc7\u6df1\u5927\u4f6c : aaa5838769 <\/span> <\/i> 1<\/span> <\/div>\n
<\/div>\n<\/p><\/div>\n<\/p><\/div>\n<\/p><\/div>\n
<\/p>\n

A \u6587\u4ef6\u662f\u4e2a json \u6587\u4ef6\uff1a a.txt<\/p>\n

{  \"_id\": \"113.254.82.124\",  \"_index\": \"fofapro_subdomain\",  \"header\": \"HTTP\/1.1 401 UnauthorizedrnConnection: closernContent-Length: 195rnCache-Control: no-cachernContent-Type: text\/htmlrnDate: Sat, 20 Oct 2018 15:59:44 GMTrnEtag: \"0-29d-b90\"rnServer: Embedthis-Appweb\/3.3.1rnWww-Authenticate: Basic realm=\"DCS-2530L\"rnX-Frame-Options: SAMEORIGINrn\", } {  \"_id\": \"http:\/\/10.254.82.12\",  \"_index\": \"fofapro_subdomain\",  \"header\": \"HTTP\/1.1 401 UnauthorizedrnConnection: closernContent-Length: 195rnCache-Control: no-cachernContent-Type: text\/htmlrnDate: Sat, 20 Oct 2018 15:59:44 GMTrnEtag: \"0-29d-b90\"rnServer: Embedthis-Appweb\/3.3.1rnWww-Authenticate: Basic realm=\"DCS-2530L\"rnX-Frame-Options: SAMEORIGINrn\", } {  \"_id\": \"https:\/\/192.168.1.10:9090\",  \"_index\": \"fofapro_subdomain\",  \"header\": \"HTTP\/1.1 401 UnauthorizedrnConnection: closernContent-Length: 195rnCache-Control: no-cachernContent-Type: text\/htmlrnDate: Sat, 20 Oct 2018 15:59:44 GMTrnEtag: \"0-29d-b90\"rnServer: Embedthis-Appweb\/3.3.1rnWww-Authenticate: Basic realm=\"DCS-2530L\"rnX-Frame-Options: SAMEORIGINrn\", } {  \"_id\": \"127.0.0.1:8343\",  \"_index\": \"fofapro_subdomain\",  \"header\": \"HTTP\/1.1 401 UnauthorizedrnConnection: closernContent-Length: 195rnCache-Control: no-cachernContent-Type: text\/htmlrnDate: Sat, 20 Oct 2018 15:59:44 GMTrnEtag: \"0-29d-b90\"rnServer: Embedthis-Appweb\/3.3.1rnWww-Authenticate: Basic realm=\"DCS-2530L\"rnX-Frame-Options: SAMEORIGINrn\", } <\/code><\/pre>\n
B \u6587\u4ef6\uff1a b.txt<\/p>\n
127.0.01 192.168.1.10 192.168.88.88 <\/code><\/pre>\n
\u4ee3\u7801<\/p>\n
import re import json  def filesJson(filepath,dstpaths):     datas = set()     #\u6b63\u5219\u5339\u914d     rule = re.compile('^[a-zA-z]{1}.*$')     with open(filepath, 'r', encoding='UTF-8') as a, open(dstpaths, 'r', encoding='UTF-8') as b:         b.seek(0)         for realine_a in a:             json_datas = json.loads(realine_a)             ips = json_datas['_id']             if rule.findall(ips):                 ips = ips.strip(\"http[s]?:\/\/\")                 ips = ips.split(\":\")[0]                 datas.add(ips)         for realine_b in b:             if realine_b in datas:                 print(realine_b)             else:                 break  if __name__ == '__main__':     file_paths = \"a.txt\"     dstpaths = 'b.txt'     filesJson(file_paths, dstpaths) <\/code><\/pre>\n
\u6211\u7684\u60f3\u6cd5\u662f\u628a A \u6587\u4ef6\u91cc\u7684 IP\uff0c\u53bb\u9664\u534f\u8bae\u548c\u7aef\u53e3\uff0c\u53ea\u4fdd\u7559 IP \u5199\u5165\u5230\u4e00\u4e2a\u96c6\u5408\u4e2d\uff0c\u7136\u540e\u5728\u901a\u8fc7 B \u6587\u4ef6\u7684\u6570\u636e\u53bb\u5339\u914d\u8fd9\u4e2a\u96c6\u5408\uff0c\u6709\u6ca1\u6709\u8fd9\u4e2a IP\uff0c\u5982\u679c\u6709\u8fd9\u4e2a IP\uff0c\u628a A \u6587\u4ef6\u8fd9\u884c\u6570\u636e\u5199\u5165\u5230 C \u6587\u4ef6\u4e2d\uff0c\u73b0\u5728\u95ee\u9898\u662f B \u6587\u4ef6\u65e0\u6cd5\u5339\u914d A \u6587\u4ef6\u7684\u6570\u636e\uff0c\u800c\u4e14\u5982\u679c A \u6587\u4ef6\u5185\u5bb9\u662f\u51e0\u767e\u4e07\u884c\u6570\u636e\uff0cB \u6587\u4ef6\u5185\u5bb9\u662f\u51e0\u4e07\u884c\u6570\u636e\uff0c\u8fd9\u79cd\u903b\u8f91\u662f\u4e0d\u662f\u6709\u5f88\u5927\u7684\u95ee\u9898\u3002<\/p>\n<\/p><\/div>\n
 \u5927\u4f6c\u6709\u8a71\u8aaa<\/b> (20<\/span>)        <\/div>\n
 <\/div>\n<\/p><\/div>\n<\/p><\/div>\n
    \n
  • \n
    \n
    \n
     \u8cc7\u6df1\u5927\u4f6c : liprais <\/span>  <\/div>\n
     <\/i>            <\/span> <\/div>\n<\/p><\/div>\n
                                                                 pyspark \u5b89\u6392\u4e86                                                            <\/div>\n<\/p><\/div>\n<\/li>\n
  • \n
    \n
    \n
     \u4e3b<\/span> \u8cc7\u6df1\u5927\u4f6c : aaa5838769 <\/span>  <\/div>\n
     <\/i>            <\/span> <\/div>\n<\/p><\/div>\n
                                                                 @liprais \u611f\u8c22\u56de\u590d\uff0c\u4f46\u662f\u6211\u73b0\u5728\u7684\u4ee3\u7801\u903b\u8f91\u662f\u65e0\u6cd5\u5339\u914d\u5230\u6570\u636e\u3002                                                            <\/div>\n<\/p><\/div>\n<\/li>\n
  • \n
    \n
    \n
     \u8cc7\u6df1\u5927\u4f6c : telnetning <\/span>  <\/div>\n
     <\/i>            <\/span> <\/div>\n<\/p><\/div>\n
                                                                 \u786e\u8ba4\u4e00\u4e0b\u6bcf\u4e2a Json \u662f\u5728\u4e00\u884c\u5417\uff1b rule \u7684\u6b63\u5219\u53ef\u4ee5\u518d\u770b\u4e00\u770b\uff1f\uff1b\u53ef\u4ee5\u76f4\u63a5\u65ad\u70b9\u8c03\u8bd5\u4e00\u4e0b\uff5e                                                            <\/div>\n<\/p><\/div>\n<\/li>\n
  • \n
    \n
    \n
     \u8cc7\u6df1\u5927\u4f6c : noqwerty <\/span>  <\/div>\n
     <\/i>            <\/span> <\/div>\n<\/p><\/div>\n
                                                                 \u522b\u7684\u4e0d\u8bf4\uff0c\u4f60\u73b0\u5728\u6bcf\u63d2\u5165\u4e00\u6761\u6570\u636e\u5c31\u8981\u904d\u5386\u4e00\u6b21 b \u5b8c\u5168\u6ca1\u610f\u4e49\u554a\uff0c\u62ff\u5230\u4e24\u4e2a set \u4e4b\u540e\u76f4\u63a5\u53d6\u4ea4\u96c6\u4e0d\u5c31\u884c\u4e86\u5417                                                            <\/div>\n<\/p><\/div>\n<\/li>\n
  • \n
    \n
    \n
     \u4e3b<\/span> \u8cc7\u6df1\u5927\u4f6c : aaa5838769 <\/span>  <\/div>\n
     <\/i>            <\/span> <\/div>\n<\/p><\/div>\n
                                                                 @noqwerty \u6211\u8bd5\u8fc7\u4ea4\u96c6\uff0c\u53d1\u73b0\u8fd8\u662f\u6ca1\u6709\u6570\u636e\u3002                                                            <\/div>\n<\/p><\/div>\n<\/li>\n
  • \n
    \n
    \n
     \u4e3b<\/span> \u8cc7\u6df1\u5927\u4f6c : aaa5838769 <\/span>  <\/div>\n
     <\/i>            <\/span> <\/div>\n<\/p><\/div>\n
                                                                 @telnetning \u6bcf\u4e2a json \u4e0d\u5728\u4e00\u884c\uff0c\u4e00\u4e2a json \u6709\u5f88\u591a\u6570\u636e\uff0c\u6211\u53ea\u662f\u63d0\u53d6\u51fa\u6765\u51e0\u4e2a\u5b57\u6bb5\uff0c\u6211\u7684\u6b63\u5219\u4e3b\u8981\u662f\u4e3a\u4e86\u5339\u914d\u5230 http \u5f00\u5934\u7684\uff0c\u7136\u540e\u5220\u9664\u534f\u8bae\uff0c\u5982\u679c\u6709\u7aef\u53e3\uff0c\u8fdb\u884c\u622a\u53d6\uff0c\u518d\u5b58\u5230\u96c6\u5408\u4e2d\u3002                                                            <\/div>\n<\/p><\/div>\n<\/li>\n
  • \n
    \n
    \n
     \u8cc7\u6df1\u5927\u4f6c : AFlash <\/span>  <\/div>\n
     <\/i>            <\/span> <\/div>\n<\/p><\/div>\n
                                                                 \u8bd5\u8bd5\u628a\u201celse\uff1abreak\u201d\u53bb\u6389\uff0c                                                            <\/div>\n<\/p><\/div>\n<\/li>\n
  • \n
    \n
    \n
     \u8cc7\u6df1\u5927\u4f6c : noqwerty <\/span>  <\/div>\n
     <\/i>            <\/span> <\/div>\n<\/p><\/div>\n
                                                                 @aaa5838769 #6 \u4e0d\u5728\u4e00\u884c\u7684\u8bdd\u4f60\u7684 json.loads(realine_a) \u4e0d\u4f1a\u62a5\u9519\u5417\uff1f                                                            <\/div>\n<\/p><\/div>\n<\/li>\n
  • \n
    \n
    \n
     \u8cc7\u6df1\u5927\u4f6c : ipwx <\/span>  <\/div>\n
     <\/i>            <\/span> <\/div>\n<\/p><\/div>\n
                                                                 @aaa5838769 \u3002\u3002\u3002<\/p>\n
    b_set = set(filter(lambda s: s, (l.strip() for l in open(‘b.txt’, ‘r’, encoding=’utf-8′))))
    with open(‘a.txt’, ‘r’, encoding=’utf-8′) as a_file, open(‘c.txt’, ‘r’, encoding=’utf-8′) as c_file:
    ….for s in a:
    ……..do what you have do to get s_ip
    ……..if s_ip in b_set:
    …………c_file.write(s_ip + ‘n’)                                                            <\/div>\n<\/p><\/div>\n<\/li>\n
  • \n
    \n
    \n
     \u8cc7\u6df1\u5927\u4f6c : ipwx <\/span>  <\/div>\n
     <\/i>            <\/span> <\/div>\n<\/p><\/div>\n
                                                                 open(‘c.txt’, ‘r’, encoding=’utf-8′) as c_file => open(‘c.txt’, ‘w’, encoding=’utf-8′) as c_file:                                                            <\/div>\n<\/p><\/div>\n<\/li>\n
  • \n
    \n
    \n
     \u8cc7\u6df1\u5927\u4f6c : ipwx <\/span>  <\/div>\n
     <\/i>            <\/span> <\/div>\n<\/p><\/div>\n
                                                                 \u4e3b\u4f60\u8fd9\u9700\u6c42\uff0c\u50cf\u6211\u4e0a\u9762\u8fd9\u6837\uff0c\u628a b \u505a\u6210 set \u8fc7\u4e00\u904d a \u5c31\u884c\u4e86\u3002\u4e0d\u7406\u89e3\u4f60\u5728\u7ea0\u7ed3\u5565\u3002                                                            <\/div>\n<\/p><\/div>\n<\/li>\n
  • \n
    \n
    \n
     \u8cc7\u6df1\u5927\u4f6c : xujunfu <\/span>  <\/div>\n
     <\/i>            <\/span> <\/div>\n<\/p><\/div>\n
                                                                 \u53d6\u51fa b \u6587\u4ef6\u6240\u4ee5 ips\uff0c\u518d\u628a\u6bcf\u4e2a ip \u8f6c\u6210 long \u6570\u503c\uff0c\u5c06\u6570\u7ec4\u6392\u5e8f;\u904d\u5386 a \u6587\u4ef6\u53d6\u51fa ip \u5e76\u8f6c long \u6570\u503c\uff0c\u4e8c\u5206\u67e5\u627e\u5728\u4e0d\u5728 long_ips \u6570\u7ec4\u4e2d                                                            <\/div>\n<\/p><\/div>\n<\/li>\n
  • \n
    \n
    \n
     \u4e3b<\/span> \u8cc7\u6df1\u5927\u4f6c : aaa5838769 <\/span>  <\/div>\n
     <\/i>            <\/span> <\/div>\n<\/p><\/div>\n
                                                                 @noqwerty \u4e0d\u597d\u610f\u601d\uff0c\u5728\u4e00\u884c\u4e0a\uff0c\u6211\u8111\u5b50\u77ed\u8def\u554a\uff0c\u6211\u4e13\u95e8\u683c\u5f0f\u5316\u4e00\u4e0b\uff0c\u7136\u540e\u590d\u5236\u5230\u8bba\u575b\u91cc\u3002                                                            <\/div>\n<\/p><\/div>\n<\/li>\n
  • \n
    \n
    \n
     \u4e3b<\/span> \u8cc7\u6df1\u5927\u4f6c : aaa5838769 <\/span>  <\/div>\n
     <\/i>            <\/span> <\/div>\n<\/p><\/div>\n
                                                                 @ipwx \u6211\u4e4b\u524d\u7528\u8fc7\u4e24\u4e2a set \u505a\u4ea4\u96c6\uff0c\u4e5f\u6ca1\u6709\u5339\u914d\u5230\u6570\u636e\uff0c\u6240\u4ee5\u6362\u4e86\u53e6\u4e00\u79cd\u903b\u8f91\u3002                                                            <\/div>\n<\/p><\/div>\n<\/li>\n
  • \n
    \n
    \n
     \u8cc7\u6df1\u5927\u4f6c : wuwukai007 <\/span>  <\/div>\n
     <\/i>            <\/span> <\/div>\n<\/p><\/div>\n
                                                                 a \u6587\u4ef6\u683c\u5f0f\u662f\u8fd9\u6837\uff1f
    {\u2018_id\u2019:xxx}\u4e0b\u4e00\u884c
    {\u2018_id\u2019:xxx}\u4e0b\u4e00\u884c                                                            <\/div>\n<\/p><\/div>\n<\/li>\n
  • \n
    \n
    \n
     \u4e3b<\/span> \u8cc7\u6df1\u5927\u4f6c : aaa5838769 <\/span>  <\/div>\n
     <\/i>            <\/span> <\/div>\n<\/p><\/div>\n
                                                                 @wuwukai007 \u662f\u7684                                                            <\/div>\n<\/p><\/div>\n<\/li>\n
  • \n
    \n
    \n
     \u8cc7\u6df1\u5927\u4f6c : rrfeng <\/span>  <\/div>\n
     <\/i>            <\/span> <\/div>\n<\/p><\/div>\n
                                                                 \u8fd9\u4e2a\u6700\u4f73\u5b9e\u8df5\u662f\uff1a<\/p>\n
    b \u9884\u8bfb\u5b8c\uff0c\u505a\u6210 hash \uff08 dict \uff09\uff0cip \u5f53 key\uff0c\u653e\u5728\u5185\u5b58\u91cc\u3002<\/p>\n
    \u7136\u540e a \u7528\u6d41\u5f0f json \u5904\u7406\u89e3\u6790\u5b8c\u76f4\u63a5\u67e5\u627e hash \u8868\u3002                                                            <\/p><\/div>\n<\/p><\/div>\n<\/li>\n
  • \n
    \n
    \n
     \u8cc7\u6df1\u5927\u4f6c : wuwukai007 <\/span>  <\/div>\n
     <\/i>            <\/span> <\/div>\n<\/p><\/div>\n
                                                                 a.txt \u683c\u5f0f
    {xxxxxxxx}n
    {xxxxxxxx}n
    b.txt \u683c\u5f0f
    192.168.1.10
    192.168.1.10<\/p>\n
    import pandas as pd
    import re
    df = pd.read_csv(r’a.txt’,header=None)
    df.rename(columns={0:’ip’},inplace=True)
    regex = ‘(([01]{0,1}d{0,1}d|2[0-4]d|25[0-5]).){3}([01]{0,1}d{0,1}d|2[0-4]d|25[0-5])’
    df[‘ip_host’] = df.ip.str.replace(rf’^((?!{regex}).)*’,”).str.replace(‘(:d+)|”‘,”)
    df2 = pd.read_csv(r”b.txt”,sep=’n’,header=None)
    df2.columns = [‘ip_host’]
    df3 = df2.merge(df,on=’ip_host’,how=’inner’)
    df3.drop(‘ip_host’,axis=1,inplace=True)
    df3.to_csv(r”c.txt”,index=None,header=None,quoting=None,quotechar=”‘”)                                                            <\/div>\n<\/p><\/div>\n<\/li>\n
  • \n
    \n
    \n
     \u8cc7\u6df1\u5927\u4f6c : wuwukai007 <\/span>  <\/div>\n
     <\/i>            <\/span> <\/div>\n<\/p><\/div>\n
                                                                 a.txt \u683c\u5f0f
    {xxxxxxxx}\u6362\u884c\u7b26
    {xxxxxxxx}\u6362\u884c\u7b26
    b.txt \u683c\u5f0f
    192.168.1.10 \u6362\u884c\u7b26
    192.168.1.10 \u6362\u884c\u7b26<\/p>\n
    import pandas as pd
    import re
    df = pd.read_csv(r’a.txt’,header=None)
    df.rename(columns={0:’ip’},inplace=True)
    regex = ‘(([01]{0,1}d{0,1}d|2[0-4]d|25[0-5]).){3}([01]{0,1}d{0,1}d|2[0-4]d|25[0-5])’
    df[‘ip_host’] = df.ip.str.replace(rf’^((?!{regex}).)*’,”).str.replace(‘(:d+)|”‘,”)
    df2 = pd.read_csv(r”b.txt”,sep=’n’,header=None)
    df2.columns = [‘ip_host’]
    df3 = df2.merge(df,on=’ip_host’,how=’inner’)
    df3.drop(‘ip_host’,axis=1,inplace=True)
    df3.to_csv(r”c.txt”,index=None,header=None,quoting=None,quotechar=”‘”)<\/p>\n
    \u8f93\u51fa c.txt
    {xxxxxxxx}\u6362\u884c\u7b26
    {xxxxxxxx}\u6362\u884c\u7b26                                                            <\/div>\n<\/p><\/div>\n<\/li>\n
  • \n
    \n
    \n
     \u4e3b<\/span> \u8cc7\u6df1\u5927\u4f6c : aaa5838769 <\/span>  <\/div>\n
     <\/i>            <\/span> <\/div>\n<\/p><\/div>\n
                                                                 @rrfeng value \u4e3a\u7a7a\u4e48\uff1f                                                            <\/div>\n<\/p><\/div>\n<\/li>\n
  • \n","protected":false},"excerpt":{"rendered":"
    Python B \u6587\u4ef6\u91cc\u7684\u6bcf\u884c\u6570\u636e…<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[],"tags":[],"_links":{"self":[{"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/posts\/106450"}],"collection":[{"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/4563.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=106450"}],"version-history":[{"count":0,"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/posts\/106450\/revisions"}],"wp:attachment":[{"href":"http:\/\/4563.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=106450"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/4563.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=106450"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/4563.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=106450"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}