python学习笔记14 （正则表达式2） 2018-05-03

今天主要是以2道习题的为主，加强对正则表达式的理解：

一，获取json中的skuid和skuimgurl的值：

"errCode":"0",
    "retCode":"",
    "msg":"success",
    "size":"20",
    "sku":[
        {
            "skuid":"26878432382",
            "spuid":"26878432382",
            "skuurl":"[https://qitem.jd.com/fcgi-bin/view?sku=26878432382&shopid=0&enc=jn6CsRbAaCZmUGvwesX4UtzRM1_Urt4t3rrpcBqQFCaOb20E9H_1lIDZrnjpTnQxpDyV61PjwLJntzDdBK6Ws0stJnT97ZXn5YoMHMfdHIXg551U4dquFQ%3D%3D&tk=b532cffc1b0581ce0b3da372aacc8c1d&share=1&fs=1>=1525352327&spu=26878432382&v=1](https://qitem.jd.com/fcgi-bin/view?sku=26878432382&shopid=0&enc=jn6CsRbAaCZmUGvwesX4UtzRM1_Urt4t3rrpcBqQFCaOb20E9H_1lIDZrnjpTnQxpDyV61PjwLJntzDdBK6Ws0stJnT97ZXn5YoMHMfdHIXg551U4dquFQ%3D%3D&tk=b532cffc1b0581ce0b3da372aacc8c1d&share=1&fs=1%3E=1525352327&spu=26878432382&v=1)",
            "skuimgurl":"[https://img12.360buyimg.com/n7/jfs/t18226/169/1318243724/390477/5b0718ff/5ac44edcNa350dbd9.jpg](https://img12.360buyimg.com/n7/jfs/t18226/169/1318243724/390477/5b0718ff/5ac44edcNa350dbd9.jpg)",
            "title":"丹龙（DanLong）声波电动牙刷成人家用非充电式智能防水情侣牙刷 牛奶白-标配",
            "price":"129.00",
            "commissionprice":"25.80",
            "salecount":"6551",
            "goodCom":"3031",
            "comRate":"0.2000"
        },
       ...

image.png

首先，我们在线https://regex101.com/对正则表达式检测：如图

image.png

获取我们需要的正则表达式\"skuid\S{3}(\d+)\S.*?skuimgurl\S{3}(.*?jpg)\"

image.png

然后使用findall()方法得到匹配成功的list；

二，对文件内容匹配并相对应的生成文件：

有一个ga10.wms5.jd.com.txt 文件：内容一下

upstream orderCenter.ga10.wms5.jd.local {
    server 10.46.0.161:8023 weight=10 max_fails=2 fail_timeout=30s;
    server 10.46.0.162:8023 weight=10 max_fails=2 fail_timeout=30s;
}

upstream opperftrace.ga10.wms5.jd.local {
    server 10.46.0.164:8060 weight=10 max_fails=2 fail_timeout=30s;
}

upstream taskassign-c.ga10.wms5.jd.local {
    server 10.46.0.162:8005 weight=10 max_fails=2 fail_timeout=30s;
}

upstream smartQuery.ga10.wms5.jd.local {
    server 10.46.0.164:8013 weight=10 max_fails=2 fail_timeout=30s;
}

upstream center.ga10.wms5.jd.local {
    server 10.46.0.164:9020 weight=10 max_fails=2 fail_timeout=30s;
    server 10.46.0.163:9020 weight=10 max_fails=2 fail_timeout=30s;
}
upstream aps.wms5.jd.local {
  server 10.46.0.161:8001 weight=10 max_fails=2 fail_timeout=10s;
  server 10.46.0.162:8001 weight=10 max_fails=2 fail_timeout=10s;
}
upstream inbound.wms5.jd.local {
  server 10.46.0.161:8002 weight=10 max_fails=2 fail_timeout=10s;
  server 10.46.0.162:8002 weight=10 max_fails=2 fail_timeout=10s;
}
upstream invop.wms5.jd.local {
  server 10.46.0.161:8003 weight=10 max_fails=2 fail_timeout=10s;
  server 10.46.0.162:8003 weight=10 max_fails=2 fail_timeout=10s;
}
upstream mcs.wms5.jd.local {
  server 10.46.0.161:8004 weight=10 max_fails=2 fail_timeout=10s;
  server 10.46.0.162:8004 weight=10 max_fails=2 fail_timeout=10s;
}
upstream pickingplan.wms5.jd.local {
  server 10.46.0.161:8005 weight=10 max_fails=2 fail_timeout=10s;
  server 10.46.0.162:8005 weight=10 max_fails=2 fail_timeout=10s;
}
upstream picking.wms5.jd.local {
  server 10.46.0.161:8006 weight=10 max_fails=2 fail_timeout=10s;
  server 10.46.0.162:8006 weight=10 max_fails=2 fail_timeout=10s;
}
upstream power.wms5.jd.local {
  server 10.46.0.161:8007 weight=10 max_fails=2 fail_timeout=10s;
  server 10.46.0.162:8007 weight=10 max_fails=2 fail_timeout=10s;
}
upstream shipment.wms5.jd.local {
  server 10.46.0.161:8008 weight=10 max_fails=2 fail_timeout=10s;
  server 10.46.0.162:8008 weight=10 max_fails=2 fail_timeout=10s;
}
upstream stock.wms5.jd.local {
  server 10.46.0.161:8009 weight=10 max_fails=2 fail_timeout=10s;
  server 10.46.0.162:8009 weight=10 max_fails=2 fail_timeout=10s;
}
upstream inner.wms5.jd.local {
  server 10.46.0.161:8011 weight=10 max_fails=2 fail_timeout=10s;
  server 10.46.0.162:8010 weight=10 max_fails=2 fail_timeout=10s;
}
upstream task.wms5.jd.local {
  server 10.46.0.163:8001 weight=10 max_fails=2 fail_timeout=10s;
  server 10.46.0.164:8001 weight=10 max_fails=2 fail_timeout=10s;
}
upstream taskmg.wms5.jd.local {
  server 10.46.0.163:8002 weight=10 max_fails=2 fail_timeout=10s;
  server 10.46.0.164:8002 weight=10 max_fails=2 fail_timeout=10s;
}
upstream report.wms5.jd.local {
  server 10.46.0.163:8003 weight=10 max_fails=2 fail_timeout=10s;
  server 10.46.0.164:8003 weight=10 max_fails=2 fail_timeout=10s;
}
upstream master.wms5.jd.local {
  server 10.46.0.163:8004 weight=10 max_fails=2 fail_timeout=10s;
  server 10.46.0.164:8004 weight=10 max_fails=2 fail_timeout=10s;
}
upstream clover.jd.local {
  server 10.46.0.163:1601 weight=10 max_fails=2 fail_timeout=10s;
  server 10.46.0.164:1601 weight=10 max_fails=2 fail_timeout=10s;
}

upstream backbone.web.wms5.jd.local {
  server 10.46.0.163:8006 weight=10 max_fails=2 fail_timeout=10s;
}
upstream wump-heartbeat.wms5.jd.local {
    server 10.46.0.130:8001 weight=10 max_fails=2 fail_timeout=10s;
}
upstream dec.wms5.jd.local {
        server 10.46.0.161:8012 weight=10 max_fails=2 fail_timeout=10s;
        server 10.46.0.162:8011 weight=10 max_fails=2 fail_timeout=10s;
}


# ##############################################################################

server
{
    listen                   80;
    server_name              ga10.wms5.jd.com 10.46.0.217 10.46.0.161;
    access_log               /export/servers/nginx/logs/ga10.wms5.jd.com/ga10.wms5.jd.com_access.log main;
    error_log                /export/servers/nginx/logs/ga10.wms5.jd.com/ga10.wms5.jd.com_error.log warn;
    #chunkin on;
    error_page 411 = @my_error;
    location @my_error {
        #chunkin_resume;
    }


        location /logs/ {
                autoindex       off;
                deny all;
        }

    # frontend  ########################################
    rewrite_log on;
    #more_set_headers "Foo: bar";
location /dec/ {
                proxy_next_upstream     http_500 http_502 http_503 http_504 error timeout invalid_header;
                proxy_set_header        Host  $host;
                proxy_set_header        X-Forwarded-For $proxy_add_x_forwarded_for;
                expires                 0;
                proxy_pass http://dec.wms5.jd.local/;
        }
location ~ /pickingplan/((?:services/)?taskassign_.+) {
    proxy_next_upstream     http_500 http_502 http_503 http_504 error timeout invalid_header;
    proxy_set_header        Host  $host;
    proxy_set_header        X-Forwarded-For $proxy_add_x_forwarded_for;
    expires                 0;
    rewrite /pickingplan/((?:services/)?taskassign_.+) /$1 break;
    proxy_pass http://taskassign-c.ga10.wms5.jd.local;
}

location /wump-heartbeat/ {
        proxy_next_upstream     http_500 http_502 http_503 http_504 error timeout invalid_header;
        proxy_set_header        Host  $host;
        proxy_set_header        X-Forwarded-For $proxy_add_x_forwarded_for;
        expires                 0;
        proxy_pass http://wump-heartbeat.wms5.jd.local/;
}
location /master/ {
    proxy_next_upstream     http_500 http_502 http_503 http_504 error timeout invalid_header;
    proxy_set_header        Host  $host;
    proxy_set_header        X-Forwarded-For $proxy_add_x_forwarded_for;
    expires                 0;
    proxy_pass http://master.wms5.jd.local/;
}
location /mcs/ {
    proxy_next_upstream     http_500 http_502 http_503 http_504 error timeout invalid_header;
    proxy_set_header        Host  $host;
    proxy_set_header        X-Forwarded-For $proxy_add_x_forwarded_for;
    expires                 0;
    proxy_pass http://mcs.wms5.jd.local/;
}
location /power/ {
    proxy_next_upstream     http_500 http_502 http_503 http_504 error timeout invalid_header;
    proxy_set_header        Host  $host;
    proxy_set_header        X-Forwarded-For $proxy_add_x_forwarded_for;
    expires                 0;
    proxy_pass http://power.wms5.jd.local/;
}
location /cluster1/ {
        proxy_next_upstream     http_500 http_502 http_503 http_504 error timeout invalid_header;
        proxy_set_header        Host  $host;
        proxy_set_header        X-Forwarded-For $proxy_add_x_forwarded_for;
        expires                 0;
        proxy_pass http://clover.jd.local;
}
location /aps/ {
    proxy_next_upstream     http_500 http_502 http_503 http_504 error timeout invalid_header;
    proxy_set_header        Host  $host;
    proxy_set_header        X-Forwarded-For $proxy_add_x_forwarded_for;
    expires                 0;
    proxy_pass http://aps.wms5.jd.local/;
}
location /task/ {
    proxy_next_upstream     http_500 http_502 http_503 http_504 error timeout invalid_header;
    proxy_set_header        Host  $host;
    proxy_set_header        X-Forwarded-For $proxy_add_x_forwarded_for;
    expires                 0;
    proxy_pass http://task.wms5.jd.local/;
}
location /taskmg/ {
    proxy_next_upstream     http_500 http_502 http_503 http_504 error timeout invalid_header;
    proxy_set_header        Host  $host;
    proxy_set_header        X-Forwarded-For $proxy_add_x_forwarded_for;
    expires                 0;
    proxy_pass http://taskmg.wms5.jd.local/;
}
location /stock/ {
    proxy_next_upstream     http_500 http_502 http_503 http_504 error timeout invalid_header;
    proxy_set_header        Host  $host;
    proxy_set_header        X-Forwarded-For $proxy_add_x_forwarded_for;
    expires                 0;
    proxy_pass http://stock.wms5.jd.local/;
}
location /invop/ {
    proxy_next_upstream     http_500 http_502 http_503 http_504 error timeout invalid_header;
    proxy_set_header        Host  $host;
    proxy_set_header        X-Forwarded-For $proxy_add_x_forwarded_for;
    expires                 0;
    proxy_pass http://invop.wms5.jd.local/;
}
location /picking/ {
    proxy_next_upstream     http_500 http_502 http_503 http_504 error timeout invalid_header;
    proxy_set_header        Host  $host;
    proxy_set_header        X-Forwarded-For $proxy_add_x_forwarded_for;
    expires                 0;
    proxy_pass http://picking.wms5.jd.local/;
}
location /pickingplan/ {
    proxy_next_upstream     http_500 http_502 http_503 http_504 error timeout invalid_header;
    proxy_set_header        Host  $host;
    proxy_set_header        X-Forwarded-For $proxy_add_x_forwarded_for;
    expires                 0;
    proxy_pass http://pickingplan.wms5.jd.local/;
}
location /shipment/ {
    proxy_next_upstream     http_500 http_502 http_503 http_504 error timeout invalid_header;
    proxy_set_header        Host  $host;
    proxy_set_header        X-Forwarded-For $proxy_add_x_forwarded_for;
    expires                 0;
    proxy_pass http://shipment.wms5.jd.local/;
}
location /inbound/ {
    proxy_next_upstream     http_500 http_502 http_503 http_504 error timeout invalid_header;
    proxy_set_header        Host  $host;
    proxy_set_header        X-Forwarded-For $proxy_add_x_forwarded_for;
    expires                 0;
    proxy_pass http://inbound.wms5.jd.local/;
}
location /winapp/ {
    root /export/App/app.wms5.jd.local/;
    index ReleaseList.xml;
}   
location /rfapp/ {
    root /export/App/app.wms5.jd.local/;
    index ReleaseList.xml;  
}   
location /report/ {
    proxy_next_upstream     http_500 http_502 http_503 http_504 error timeout invalid_header;
    proxy_set_header        Host  $host;
    proxy_set_header        X-Forwarded-For $proxy_add_x_forwarded_for;
    expires                 0;
    proxy_pass http://report.wms5.jd.local/;
}
location /inner/ {
    proxy_next_upstream     http_500 http_502 http_503 http_504 error timeout invalid_header;
    proxy_set_header        Host  $host;
    proxy_set_header        X-Forwarded-For $proxy_add_x_forwarded_for;
    expires                 0;
    proxy_pass http://inner.wms5.jd.local/;
}
location /backbone/ {
        proxy_next_upstream     http_500 http_502 http_503 http_504 error timeout invalid_header;
        proxy_set_header        Host  $host;
        proxy_set_header        X-Forwarded-For $proxy_add_x_forwarded_for;
        expires                 0;
        proxy_pass http://backbone.web.wms5.jd.local/;
}

    location /center/ {
        proxy_next_upstream     http_500 http_502 http_503 http_504 error timeout invalid_header;
        proxy_set_header        Host  $host;
        proxy_set_header        X-Forwarded-For $proxy_add_x_forwarded_for;
        expires                 0;
        proxy_pass http://center.ga10.wms5.jd.local/;
    }

    location /smartQuery/ {
        proxy_next_upstream     http_500 http_502 http_503 http_504 error timeout invalid_header;
        proxy_set_header        Host  $host;
        proxy_set_header        X-Forwarded-For $proxy_add_x_forwarded_for;
        expires                 0;
        proxy_pass http://smartQuery.ga10.wms5.jd.local/;
    }

    location /opperftrace/ {
        proxy_next_upstream     http_500 http_502 http_503 http_504 error timeout invalid_header;
        proxy_set_header        Host  $host;
        proxy_set_header        X-Forwarded-For $proxy_add_x_forwarded_for;
        expires                 0;
        proxy_pass http://opperftrace.ga10.wms5.jd.local/;
    }

    location /orderCenter/ {
        proxy_next_upstream     http_500 http_502 http_503 http_504 error timeout invalid_header;
        proxy_set_header        Host  $host;
        proxy_set_header        X-Forwarded-For $proxy_add_x_forwarded_for;
        expires                 0;
        proxy_pass http://orderCenter.ga10.wms5.jd.local/;
    }
}

（1） 获取upstream后面的内容 相对应的生成文件，将其包含的内容写入文件中：

import codecs
import re
import os

# 匹配出文件名的正则表达式  
'''
第一个()匹配出upstream的所有内容：upstream aps.wms5.jd.local {
  server 10.46.0.161:8001 weight=10 max_fails=2 fail_timeout=10s;
  server 10.46.0.162:8001 weight=10 max_fails=2 fail_timeout=10s;
}
第二个()匹配出upstream后面的文件名aps.wms5.jd.local
'''
regUpstream = re.compile(r"\s*(upstream\s+(\S+)\s+{[^}]+})")

# 打开文件
with codecs.open("ga10.wms5.jd.com.txt") as fu:
    # 正则匹配获取文件名
    textList = regUpstream.findall(fu.read())

    # 创建文件
    if not os.path.exists("upstream"):
        os.mkdir("upstream")  # 不存在就创建upstreamwen文件夹

    os.chdir("upstream")  # 切换到新建文件夹下
    for item in textList:
        with codecs.open(item[1],"w") as fw:
            fw.write(item[0])
    os.chdir("..")

运行结果：

image.png