python gzip

通常用gzip压缩过的云端数据需要做解压处理，以下代码主要用python3实现对获取到的云端gzip压缩数据进行还原。

# -*- coding: utf-8 -*-
"""
Spyder Editor
This is a temporary script file.
"""
 
#! /usr/bin/env python3.6
 
import requests
import gzip
 
 
def main():
    url = 'http://127.0.0.1:801/health/index.php/mobile/test/getBanners'    
    data = {'test': 'data'}
    headers ={"User-agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.10; rv:36.0) Gecko/20100101 Firefox/36.0",
              "Accept":"text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
              #"Accept-Language":"en-US,en;q=0.5",
              "Accept-Encoding":"gzip, deflate",
              #"Connection":"keep-alive",
              "Content-Type":"application/x-www-form-urlencoded",
              }
 
    resp = requests.get(url, headers=headers, params=data) 
    #resp = requests.post(url, data=data, headers=headers)
    
    if resp.status_code == 200:
        
        print('gzip data: ',resp.content)
        data = gzip.decompress(resp.content).decode("utf-8")
        print("ungzip data: ",data)
    else:
        print("error")
 
if __name__ == '__main__':
    main()  

 

<pre name="code" class="python">解压gzip文件示例:
import gzip
f = gzip.open('file.txt.gz', 'rb')
file_content = f.read()
f.close()
 
 
创建gzip文件:
import gzip
content = "Lots of content here"
f = gzip.open('file.txt.gz', 'wb')
f.write(content)
f.close()
 
 
gzip压缩现有文件:
import gzip
f_in = open('file.txt', 'rb')
f_out = gzip.open('file.txt.gz', 'wb')
f_out.writelines(f_in)
f_out.close()
f_in.close()

从/opt/mat/*.gz文件中读取每一行，找到包含'GET~#~ ~#~'或者'POST~#~ ~#~'的输出该行

#!/usr/bin/python
#!encoding:utf8
 
import shutil
import os
import sys
import glob
import re
import gzip
 
#扫描目录文件
def parseFile(filename):
    #打开文件，遍历其中的每一行遇到有'GET~#~ ~#~'或者'POST~#~ ~#~'的输出该行
    file = gzip.open(filename, 'rb')
    #eachline = file.readlines()
    for eachline in file:
        #str = eachline
        #if eachline == "*GET~#~ ~#~*" or eachline == "*POST~#~ ~#~*":
        if eachline.find("GET~#~ ~#~") or eachline.find("*POST~#~ ~#~*"):
            print(eachline)
    file.close()
if __name__ == '__main__':
    scandir = '/opt/mat/'
    fileform = '*.gz'
    flist = glob.glob(os.path.join(scandir, fileform))
    for item in flist:
        print(item)
        parseFile(item)