filelists.append(os.path.join(parent,filename)) #统计一个的行数 def countLine(fname): count = 0
把文件做二进制看待,read.
for file_line in open(fname, ‘rb’).readlines(): if file_line != ‘’ and file_line != ‘\n’: #过滤掉空行 count += 1 print (fname + ‘----’ , count) return count if name == ‘main’ : startTime = time.clock() getFile(basedir) totalline = 0 for filelist in filelists: totalline = totalline + countLine(filelist) print (‘total lines:’,totalline) print (‘Done! Cost Time: %0.2f second’ % (time.clock() - startTime))
3.扫描当前目录和所有子目录并显示大小。
‘’’ 遇到问题没人解答?小编创建了一个Python学习交流QQ群:579817333 寻找有志同道合的小伙伴,互帮互助,群里还有不错的视频学习教程和PDF电子书! ‘’’ import os import sys try: directory = sys.argv[1] except IndexError: sys.exit(“Must provide an argument.”) dir_size = 0 fsizedicr = {‘Bytes’: 1, ‘Kilobytes’: float(1) / 1024, ‘Megabytes’: float(1) / (1024 * 1024), ‘Gigabytes’: float(1) / (1024 * 1024 * 1024)} for (path, dirs, files) in os.walk(directory): for file in files: filename = os.path.join(path, file) dir_size += os.path.getsize(filename) fsizeList = [str(round(fsizedicr[key] * dir_size, 2)) + " " + key for key in fsizedicr] if dir_size == 0: print (“File Empty”) else: for units in sorted(fsizeList)[::-1]: print ("Folder Size: " + units)
4.将源目录240天以上的所有文件移动到目标目录。
import shutil import sys import time import os import argparse usage = ‘python move_files_over_x_days.py -src [SRC] -dst [DST] -days [DAYS]’ description = ‘Move files from src to dst if they are older than a certain number of days. Default is 240 days’ args_parser = argparse.ArgumentParser(usage=usage, description=description) args_parser.add_argument(‘-src’, ‘–src’, type=str, nargs=‘?’, default=‘.’, help=‘(OPTIONAL) Directory where files will be moved from. Defaults to current directory’) args_parser.add_argument(‘-dst’, ‘–dst’, type=str, nargs=‘?’, required=True, help=‘(REQUIRED) Directory where files will be moved to.’) args_parser.add_argument(‘-days’, ‘–days’, type=int, nargs=‘?’, default=240, help=‘(OPTIONAL) Days value specifies the minimum age of files to be moved. Default is 240.’) args = args_parser.parse_args() if args.days < 0: args.days = 0 src = args.src # 设置源目录 dst = args.dst # 设置目标目录 days = args.days # 设置天数 now = time.time() # 获得当前时间 if not os.path.exists(dst): os.mkdir(dst) for f in os.listdir(src): # 遍历源目录所有文件 if os.stat(f).st_mtime < now - days * 86400: # 判断是否超过240天 if os.path.isfile(f): # 检查是否是文件 shutil.move(f, dst) # 移动文件
5.扫描脚本目录,并给出不同类型脚本的计数。
import os import shutil from time import strftime logsdir=“c:\logs\puttylogs” zipdir=“c:\logs\puttylogs\zipped_logs” zip_program=“zip.exe” for files in os.listdir(logsdir): if files.endswith(“.log”): files1=files+“.”+strftime(“%Y-%m-%d”)+“.zip” os.chdir(logsdir) os.system(zip_program + " " + files1 +" "+ files) shutil.move(files1, zipdir) os.remove(files)
6.下载Leetcode的算法题。
‘’’ 遇到问题没人解答?小编创建了一个Python学习交流QQ群:579817333 寻找有志同道合的小伙伴,互帮互助,群里还有不错的视频学习教程和PDF电子书! ‘’’ import sys import re import os import argparse import requests from lxml import html as lxml_html try: import html except ImportError: import HTMLParser html = HTMLParser.HTMLParser() try: import cPickle as pk except ImportError: import pickle as pk class LeetcodeProblems(object): def get_problems_info(self): leetcode_url = ‘https://leetcode.com/problemset/algorithms’ res = requests.get(leetcode_url) if not res.ok: print(‘request error’) sys.exit() cm = res.text cmt = cm.split(‘tbody>’)[-2] indexs = re.findall(r’(\d+)', cmt) problem_urls = [‘https://leetcode.com’ + url \ for url in re.findall( r’ levels = re.findall(r"(.+?)", cmt) tinfos = zip(indexs, levels, problem_urls) assert (len(indexs) == len(problem_urls) == len(levels)) infos = [] for info in tinfos: res = requests.get(info[-1]) if not res.ok: print(‘request error’) sys.exit() tree = lxml_html.fromstring(res.text) title = tree.xpath(‘//meta[@property=“og:title”]/@content’)[0] description = tree.xpath(‘//meta[@property=“description”]/@content’) if not description: description = tree.xpath(‘//meta[@property=“og:description”]/@content’)[0] else: description = description[0] description = html.unescape(description.strip()) tags = tree.xpath(‘//div[@id=“tags”]/following::a[@class=“btn btn-xs btn-primary”]/text()’) infos.append( { ‘title’: title, ‘level’: info[1], ‘index’: int(info[0]), ‘description’: description, ‘tags’: tags } ) with open(‘leecode_problems.pk’, ‘wb’) as g: pk.dump(infos, g) return infos def to_text(self, pm_infos): if self.args.index: key = ‘index’ elif self.args.title: key = ‘title’ elif self.args.tag: key = ‘tags’ elif self.args.level: key = ‘level’ else: key = ‘index’ infos = sorted(pm_infos, key=lambda i: i[key]) text_template = ‘## {index} - {title}\n’ \ ‘{level} {tags}\n’ \ ‘{description}\n’ + ‘\n’ * self.args.line text = ‘’ for info in infos: if self.args.rm_blank: info[‘description’] = re.sub(r’[\n\r]+‘, r’\n’, info[‘description’]) text += text_template.format(**info) with open(‘leecode problems.txt’, ‘w’) as g: g.write(text) def run(self): if os.path.exists(‘leecode_problems.pk’) and not self.args.redownload: with open(‘leecode_problems.pk’, ‘rb’) as f: pm_infos = pk.load(f) else: pm_infos = self.get_problems_info() print(‘find %s problems.’ % len(pm_infos)) self.to_text(pm_infos) def handle_args(argv): p = argparse.ArgumentParser(description=‘extract all leecode problems to location’) p.add_argument(‘–index’, action=‘store_true’, help=‘sort by index’) p.add_argument(‘–level’, action=‘store_true’, help=‘sort by level’) p.add_argument(‘–tag’, action=‘store_true’, help=‘sort by tag’) p.add_argument(‘–title’, action=‘store_true’, help=‘sort by title’) p.add_argument(‘–rm_blank’, action=‘store_true’, help=‘remove blank’) p.add_argument(‘–line’, action=‘store’, type=int, default=10, help=‘blank of two problems’) p.add_argument(‘-r’, ‘–redownload’, action=‘store_true’, help=‘redownload data’) args = p.parse_args(argv[1:]) return args def main(argv): args = handle_args(argv) x = LeetcodeProblems() x.args = args x.run() if name == ‘main’: argv = sys.argv main(argv)
import sys import os from bs4 import BeautifulSoup import markdown class MarkdownToHtml: headTag = ‘’ def init(self,cssFilePath = None): if cssFilePath != None: self.genStyle(cssFilePath) def genStyle(self,cssFilePath): with open(cssFilePath,‘r’) as f: cssString = f.read() self.headTag = self.headTag[:-7] + ‘’.format(cssString) + self.headTag[-7:] def markdownToHtml(self, sourceFilePath, destinationDirectory = None, outputFileName = None): if not destinationDirectory:
未定义输出目录则将源文件目录(注意要转换为绝对路径)作为输出目录
destinationDirectory = os.path.dirname(os.path.abspath(sourceFilePath)) if not outputFileName:
未定义输出文件名则沿用输入文件名
outputFileName = os.path.splitext(os.path.basename(sourceFilePath))[0] + ‘.html’ if destinationDirectory[-1] != ‘/’: destinationDirectory += ‘/’ with open(sourceFilePath,‘r’, encoding=‘utf8’) as f: markdownText = f.read()
编译出原始 HTML 文本
rawHtml = self.headTag + markdown.markdown(markdownText,output_format=‘html5’)
格式化 HTML 文本为可读性更强的格式
beautifyHtml = BeautifulSoup(rawHtml,‘html5lib’).prettify() with open(destinationDirectory + outputFileName, ‘w’, encoding=‘utf8’) as f: f.write(beautifyHtml) if name == “main”: mth = MarkdownToHtml()
做一个命令行参数列表的浅拷贝,不包含脚本文件名
argv = sys.argv[1:]
目前列表 argv 可能包含源文件路径之外的元素(即选项信息)
程序最后遍历列表 argv 进行编译 markdown 时,列表中的元素必须全部是源文件路径
outputDirectory = None if ‘-s’ in argv:
最后
🍅 硬核资料:关注即可领取PPT模板、简历模板、行业经典书籍PDF。
🍅 技术互助:技术群大佬指点迷津,你的问题可能不是问题,求资源在群里喊一声。
🍅 面试题库:由技术群里的小伙伴们共同投稿,热乎的大厂面试真题,持续更新中。
🍅 知识体系:含编程语言、算法、大数据生态圈组件(Mysql、Hive、Spark、Flink)、数据仓库、Python、前端等等。