一、shutil模块(了解):高级的文件、文件夹、压缩包处理模块。
import shutil # shutil.copyfileobj(fsrc, fdst[, length]),将文件内容拷贝到另一个文件中 shutil.copyfileobj(open('old.xml', 'r'), open('new.xml', 'w')) # shutil.copyfile(src, dst),拷贝文件 shutil.copyfile('f1.log', 'f2.log') # 目标文件无需存在 # shutil.copymode(src, dst),仅拷贝权限。内容、组、用户均不变 shutil.copymode('f1.log', 'f2.log') # 目标文件必须存在 # shutil.copystat(src, dst),仅拷贝状态的信息,包括:mode bits, atime, mtime, flags shutil.copystat('f1.log', 'f2.log') # 目标文件必须存在 # shutil.copy(src, dst),拷贝文件和权限 shutil.copy('f1.log', 'f2.log') # shutil.copy2(src, dst),拷贝文件和状态信息 shutil.copy2('f1.log', 'f2.log') # shutil.ignore_patterns(*patterns) # shutil.copytree(src, dst, symlinks=False, ignore=None),递归的去拷贝文件夹 # 目标目录不能存在,注意对folder2目录父级目录要有可写权限,ignore的意思是排除 shutil.copytree('folder1', 'folder2', ignore=shutil.ignore_patterns('*.pyc', 'tmp*')) # shutil.rmtree(path[, ignore_errors[, onerror]]),递归的去删除文件 shutil.rmtree('folder1') # shutil.move(src, dst),递归的去移动文件,它类似mv命令,其实就是重命名 shutil.move('folder1', 'folder3') # shutil.make_archive(base_name, format, ...),创建压缩包并返回文件路径,例如:zip、tar ''' base_name: 压缩包的文件名,也可以是压缩包的路径。只是文件名时,则保存至当前目录,否则保存至指定路径,如 data_bak = >保存至当前路径;/ tmp/data_bak = >保存至/tmp/ format:压缩包种类,“zip”, “tar”, “bztar”,“gztar” root_dir:要压缩的文件夹路径(默认当前目录) owner:用户,默认当前用户 group:组,默认当前组 logger:用于记录日志,通常是logging.Logger对象 ''' # 将 /data 下的文件打包放置当前程序目录 ret = shutil.make_archive("data_bak", 'gztar', root_dir='/data') # 将 /data下的文件打包放置 /tmp/目录 ret = shutil.make_archive("/tmp/data_bak", 'gztar', root_dir='/data')
shutil 对压缩包的处理是调用 ZipFile 和 TarFile 两个模块来进行的,详细:
1.1 zipfile压缩解压缩
import zipfile # 压缩 z = zipfile.ZipFile('laxi.zip', 'w') z.write('a.log') z.write('data.data') z.close() # 解压 z = zipfile.ZipFile('laxi.zip', 'r') z.extractall(path='.') z.close()
1.2 tarfile压缩解压缩
import tarfile # 压缩 t=tarfile.open('/tmp/egon.tar','w') t.add('/test1/a.py',arcname='a.bak') t.add('/test1/b.py',arcname='b.bak') t.close() # 解压 t=tarfile.open('/tmp/egon.tar','r') t.extractall('/egon') t.close()
二、xml模块(了解)
xml version="1.0"?> <data> <country name="Liechtenstein"> <rank updated="yes">2rank> <year>2008year> <gdppc>141100gdppc> <neighbor name="Austria" direction="E"/> <neighbor name="Switzerland" direction="W"/> country> <country name="Singapore"> <rank updated="yes">5rank> <year>2011year> <gdppc>59900gdppc> <neighbor name="Malaysia" direction="N"/> country> <country name="Panama"> <rank updated="yes">69rank> <year>2011year> <gdppc>13600gdppc> <neighbor name="Costa Rica" direction="W"/> <neighbor name="Colombia" direction="E"/> country> data>
1、遍历和查找xml
xml协议在各个语言里的都是支持的,在python中可以用以下模块操作xml:
# print(root.iter('year')) #全文搜索 # print(root.find('country')) #在root的子节点找,只找一个 # print(root.findall('country')) #在root的子节点找,找所有 import xml.etree.ElementTree as ET tree = ET.parse("xmltest.xml") root = tree.getroot() print(root.tag) # 遍历xml文档 for child in root: print('========>', child.tag, child.attrib, child.attrib['name']) for i in child: print(i.tag, i.attrib, i.text) # 只遍历year 节点 for node in root.iter('year'): print(node.tag, node.text)
2、修改和删除节点
import xml.etree.ElementTree as ET tree = ET.parse("xmltest.xml") root = tree.getroot() # 修改 for node in root.iter('year'): new_year = int(node.text) + 1 node.text = str(new_year) node.set('updated', 'yes') node.set('version', '1.0') tree.write('test.xml') # 删除node for country in root.findall('country'): rank = int(country.find('rank').text) if rank > 50: root.remove(country) tree.write('output.xml')
3、添加节点
# 在country内添加(append)节点year2 import xml.etree.ElementTree as ET tree = ET.parse("a.xml") root = tree.getroot() for country in root.findall('country'): for year in country.findall('year'): if int(year.text) > 2000: year2 = ET.Element('year2') year2.text = '新年' year2.attrib = {'update': 'yes'} country.append(year2) # 往country节点下添加子节点 tree.write('a.xml.swap')
4、自己创建xml文档
import xml.etree.ElementTree as ET new_xml = ET.Element("namelist") name = ET.SubElement(new_xml, "name", attrib={"enrolled": "yes"}) age = ET.SubElement(name, "age", attrib={"checked": "no"}) sex = ET.SubElement(name, "sex") sex.text = '33' name2 = ET.SubElement(new_xml, "name", attrib={"enrolled": "no"}) age = ET.SubElement(name2, "age") age.text = '19' et = ET.ElementTree(new_xml) # 生成文档对象 et.write("test.xml", encoding="utf-8", xml_declaration=True) ET.dump(new_xml) # 打印生成的格式
三、subprocess模块(了解):运行子程序
subprocess模块允许你去创建一个新的进程让其执行另外的程序,并与它进行通信,获取标准的输入、标准输出、标准错误以及返回码等。
更多查看官网:https://docs.python.org/2/library/subprocess.html?highlight=subprocess#frequently-used-arguments
import subprocess ''' sh-3.2# ls /Users/nick/Desktop |grep txt$ mysql.txt tt.txt 事物.txt ''' res1 = subprocess.Popen('ls /Users/jieli/Desktop',shell=True, stdout=subprocess.PIPE) res = subprocess.Popen('grep txt$', shell=True,stdin=res1.stdout, stdout=subprocess.PIPE) print(res.stdout.read().decode('utf-8')) # 下面这段等同于上面,但是上面的优势在于,一个数据流可以和另外一个数据流交互,可以通过爬虫得到结果然后交给grep。 res1 = subprocess.Popen('ls /Users/jieli/Desktop |grep txt$',shell=True, stdout=subprocess.PIPE) print(res1.stdout.read().decode('utf-8')) # windows下: # dir | findstr 'test*' # dir | findstr 'txt$' res1 = subprocess.Popen(r'dir “C:\Users\Administrator\PycharmProjects\test\函数备课”', shell=True, stdout=subprocess.PIPE) res = subprocess.Popen('findstr test*', shell=True, stdin=res1.stdout, stdout=subprocess.PIPE) # subprocess使用当前系统默认编码,得到结果为bytes类型,在windows下需要用gbk解码 print(res.stdout.read().decode('gbk') )