Python中数据解压缩的技巧分享

import zipfile
import os

# 定义Zip文件路径和解压目录
zip_file = 'data.zip'
extract_dir = 'extracted_data'

# 解压Zip文件
with zipfile.ZipFile(zip_file, 'r') as zip_ref:
    zip_ref.extractall(extract_dir)

# 列出解压后的文件列表
print(os.listdir(extract_dir))

import gzip
import shutil

# 定义gzip文件路径和解压文件路径
gzip_file = 'data.gz'
extracted_file = 'extracted_data.txt'

# 解压gzip文件
with gzip.open(gzip_file, 'rb') as f_in:
    with open(extracted_file, 'wb') as f_out:
        shutil.copyfileobj(f_in, f_out)

# 打印解压后的文件内容
with open(extracted_file, 'r') as f:
    print(f.read())

import tarfile

# 定义tar文件路径和解压目录
tar_file = 'data.tar'
extract_dir = 'extracted_data'

# 解压tar文件
with tarfile.open(tar_file, 'r') as tar_ref:
    tar_ref.extractall(extract_dir)

# 列出解压后的文件列表
print(os.listdir(extract_dir))

import bz2

# 定义bz2文件路径和解压文件路径
bz2_file = 'data.bz2'
extracted_file = 'extracted_data.txt'

# 解压bz2文件
with bz2.open(bz2_file, 'rb') as f_in:
    with open(extracted_file, 'wb') as f_out:
        shutil.copyfileobj(f_in, f_out)

# 打印解压后的文件内容
with open(extracted_file, 'r') as f:
    print(f.read())

import shutil

# 定义压缩文件路径和解压目录
archive_file = 'data.gz'
extract_dir = 'extracted_data'

# 解压文件
shutil.unpack_archive(archive_file, extract_dir)

# 列出解压后的文件列表
print(os.listdir(extract_dir))

import rarfile

# 定义RAR文件路径和解压目录
rar_file = 'data.rar'
extract_dir = 'extracted_data'

# 解压RAR文件
with rarfile.RarFile(rar_file, 'r') as rar_ref:
    rar_ref.extractall(extract_dir)

# 列出解压后的文件列表
print(os.listdir(extract_dir))

extracted_file = 'extracted_data.txt'

with open(extracted_file, 'r') as f:
    content = f.read()

print(content)

import pandas as pd

csv_file = 'data.csv.gz'

df = pd.read_csv(csv_file)
print(df)

binary_file = 'binary_data.bin'

with open(binary_file, 'rb') as f:
    data = f.read()

print(data)

import xml.etree.ElementTree as ET

xml_file = 'data.xml.gz'

with gzip.open(xml_file, 'rb') as f:
    tree = ET.parse(f)
    root = tree.getroot()

# 处理 XML 数据
for child in root:
    print(child.tag, child.attrib)

import json

json_file = 'data.json.gz'

with gzip.open(json_file, 'rb') as f:
    data = json.load(f)

# 处理 JSON 数据
print(data)